Identifying workers’construction activities or behaviors can enable managers to better monitor labor efficiency and construction progress.However,current activity analysis methods for construction workers rely solely...Identifying workers’construction activities or behaviors can enable managers to better monitor labor efficiency and construction progress.However,current activity analysis methods for construction workers rely solely on manual observations and recordings,which consumes considerable time and has high labor costs.Researchers have focused on monitoring on-site construction activities of workers.However,when multiple workers are working together,current research cannot accu rately and automatically identify the construction activity.This research proposes a deep learning framework for the automated analysis of the construction activities of multiple workers.In this framework,multiple deep neural network models are designed and used to complete worker key point extraction,worker tracking,and worker construction activity analysis.The designed framework was tested at an actual construction site,and activity recognition for multiple workers was performed,indicating the feasibility of the framework for the automated monitoring of work efficiency.展开更多
The optimization of the rule base of a fuzzy logic system (FLS) based on evolutionary algorithm has achievednotable results. However, due to the diversity of the deep structure in the hierarchical fuzzy system (HFS) a...The optimization of the rule base of a fuzzy logic system (FLS) based on evolutionary algorithm has achievednotable results. However, due to the diversity of the deep structure in the hierarchical fuzzy system (HFS) and thecorrelation of each sub fuzzy system, the uncertainty of the HFS’s deep structure increases. For the HFS, a largenumber of studies mainly use fixed structures, which cannot be selected automatically. To solve this problem, thispaper proposes a novel approach for constructing the incremental HFS. During system design, the deep structureand the rule base of the HFS are encoded separately. Subsequently, the deep structure is adaptively mutated basedon the fitness value, so as to realize the diversity of deep structures while ensuring reasonable competition amongthe structures. Finally, the differential evolution (DE) is used to optimize the deep structure of HFS and theparameters of antecedent and consequent simultaneously. The simulation results confirm the effectiveness of themodel. Specifically, the root mean square errors in the Laser dataset and Friedman dataset are 0.0395 and 0.0725,respectively with rule counts of rules is 8 and 12, respectively.When compared to alternative methods, the resultsindicate that the proposed method offers improvements in accuracy and rule counts.展开更多
Automatic modulation recognition(AMR)of radiation source signals is a research focus in the field of cognitive radio.However,the AMR of radiation source signals at low SNRs still faces a great challenge.Therefore,the ...Automatic modulation recognition(AMR)of radiation source signals is a research focus in the field of cognitive radio.However,the AMR of radiation source signals at low SNRs still faces a great challenge.Therefore,the AMR method of radiation source signals based on two-dimensional data matrix and improved residual neural network is proposed in this paper.First,the time series of the radiation source signals are reconstructed into two-dimensional data matrix,which greatly simplifies the signal preprocessing process.Second,the depthwise convolution and large-size convolutional kernels based residual neural network(DLRNet)is proposed to improve the feature extraction capability of the AMR model.Finally,the model performs feature extraction and classification on the two-dimensional data matrix to obtain the recognition vector that represents the signal modulation type.Theoretical analysis and simulation results show that the AMR method based on two-dimensional data matrix and improved residual network can significantly improve the accuracy of the AMR method.The recognition accuracy of the proposed method maintains a high level greater than 90% even at -14 dB SNR.展开更多
Parking in a small parking lot within limited space poses a difficult task. It often leads to deviations between the final parking posture and the target posture. These deviations can lead to partial occupancy of adja...Parking in a small parking lot within limited space poses a difficult task. It often leads to deviations between the final parking posture and the target posture. These deviations can lead to partial occupancy of adjacent parking lots, which poses a safety threat to vehicles parked in these parking lots. However, previous studies have not addressed this issue. In this paper, we aim to evaluate the impact of parking deviation of existing vehicles next to the target parking lot(PDEVNTPL) on the automatic ego vehicle(AEV) parking, in terms of safety, comfort, accuracy, and efficiency of parking. A segmented parking training framework(SPTF) based on soft actor-critic(SAC) is proposed to improve parking performance. In the proposed method, the SAC algorithm incorporates strategy entropy into the objective function, to enable the AEV to learn parking strategies based on a more comprehensive understanding of the environment. Additionally, the SPTF simplifies complex parking tasks to maintain the high performance of deep reinforcement learning(DRL). The experimental results reveal that the PDEVNTPL has a detrimental influence on the AEV parking in terms of safety, accuracy, and comfort, leading to reductions of more than 27%, 54%, and 26%respectively. However, the SAC-based SPTF effectively mitigates this impact, resulting in a considerable increase in the parking success rate from 71% to 93%. Furthermore, the heading angle deviation is significantly reduced from 2.25 degrees to 0.43degrees.展开更多
In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a p...In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling paradigm for semantics-aware speech recognition in air traffic control communications, which could contribute to the advancement of intelligent and efficient aviation safety management.展开更多
This study presents a method for the inverse analysis of fluid flow problems.The focus is put on accurately determining boundary conditions and characterizing the physical properties of granular media,such as permeabi...This study presents a method for the inverse analysis of fluid flow problems.The focus is put on accurately determining boundary conditions and characterizing the physical properties of granular media,such as permeability,and fluid components,like viscosity.The primary aim is to deduce either constant pressure head or pressure profiles,given the known velocity field at a steady-state flow through a conduit containing obstacles,including walls,spheres,and grains.The lattice Boltzmann method(LBM)combined with automatic differentiation(AD)(AD-LBM)is employed,with the help of the GPU-capable Taichi programming language.A lightweight tape is used to generate gradients for the entire LBM simulation,enabling end-to-end backpropagation.Our AD-LBM approach accurately estimates the boundary conditions for complex flow paths in porous media,leading to observed steady-state velocity fields and deriving macro-scale permeability and fluid viscosity.The method demonstrates significant advantages in terms of prediction accuracy and computational efficiency,making it a powerful tool for solving inverse fluid flow problems in various applications.展开更多
In order to enhance the accuracy of Air Traffic Control(ATC)cybersecurity attack detection,in this paper,a new clustering detection method is designed for air traffic control network security attacks.The feature set f...In order to enhance the accuracy of Air Traffic Control(ATC)cybersecurity attack detection,in this paper,a new clustering detection method is designed for air traffic control network security attacks.The feature set for ATC cybersecurity attacks is constructed by setting the feature states,adding recursive features,and determining the feature criticality.The expected information gain and entropy of the feature data are computed to determine the information gain of the feature data and reduce the interference of similar feature data.An autoencoder is introduced into the AI(artificial intelligence)algorithm to encode and decode the characteristics of ATC network security attack behavior to reduce the dimensionality of the ATC network security attack behavior data.Based on the above processing,an unsupervised learning algorithm for clustering detection of ATC network security attacks is designed.First,determine the distance between the clustering clusters of ATC network security attack behavior characteristics,calculate the clustering threshold,and construct the initial clustering center.Then,the new average value of all feature objects in each cluster is recalculated as the new cluster center.Second,it traverses all objects in a cluster of ATC network security attack behavior feature data.Finally,the cluster detection of ATC network security attack behavior is completed by the computation of objective functions.The experiment took three groups of experimental attack behavior data sets as the test object,and took the detection rate,false detection rate and recall rate as the test indicators,and selected three similar methods for comparative test.The experimental results show that the detection rate of this method is about 98%,the false positive rate is below 1%,and the recall rate is above 97%.Research shows that this method can improve the detection performance of security attacks in air traffic control network.展开更多
In view of low recognition rate of complex radar intra-pulse modulation signal type by traditional methods under low signal-to-noise ratio(SNR),the paper proposes an automatic recog-nition method of complex radar intr...In view of low recognition rate of complex radar intra-pulse modulation signal type by traditional methods under low signal-to-noise ratio(SNR),the paper proposes an automatic recog-nition method of complex radar intra-pulse modulation signal type based on deep residual network.The basic principle of the recognition method is to obtain the transformation relationship between the time and frequency of complex radar intra-pulse modulation signal through short-time Fourier transform(STFT),and then design an appropriate deep residual network to extract the features of the time-frequency map and complete a variety of complex intra-pulse modulation signal type recognition.In addition,in order to improve the generalization ability of the proposed method,label smoothing and L2 regularization are introduced.The simulation results show that the proposed method has a recognition accuracy of more than 95%for complex radar intra-pulse modulation sig-nal types under low SNR(2 dB).展开更多
Aiming at the problem that the data-driven automatic correlation methods which are difficult to adapt to the automatic correlation of oil-bearing strata with large changes in lateral sedimentary facies and strata thic...Aiming at the problem that the data-driven automatic correlation methods which are difficult to adapt to the automatic correlation of oil-bearing strata with large changes in lateral sedimentary facies and strata thickness,an intelligent automatic correlation method of oil-bearing strata based on pattern constraints is formed.We propose to introduce knowledge-driven in automatic correlation of oil-bearing strata,constraining the correlation process by stratigraphic sedimentary patterns and improving the similarity measuring machine and conditional constraint dynamic time warping algorithm to automate the correlation of marker layers and the interfaces of each stratum.The application in Shishen 100 block in the Shinan Oilfield of the Bohai Bay Basin shows that the coincidence rate of the marker layers identified by this method is over 95.00%,and the average coincidence rate of identified oil-bearing strata reaches 90.02% compared to artificial correlation results,which is about 17 percentage points higher than that of the existing automatic correlation methods.The accuracy of the automatic correlation of oil-bearing strata has been effectively improved.展开更多
The identification of intercepted radio fuze modulation types is a prerequisite for decision-making in interference systems.However,the electromagnetic environment of modern battlefields is complex,and the signal-to-n...The identification of intercepted radio fuze modulation types is a prerequisite for decision-making in interference systems.However,the electromagnetic environment of modern battlefields is complex,and the signal-to-noise ratio(SNR)of such environments is usually low,which makes it difficult to implement accurate recognition of radio fuzes.To solve the above problem,a radio fuze automatic modulation recognition(AMR)method for low-SNR environments is proposed.First,an adaptive denoising algorithm based on data rearrangement and the two-dimensional(2D)fast Fourier transform(FFT)(DR2D)is used to reduce the noise of the intercepted radio fuze intermediate frequency(IF)signal.Then,the textural features of the denoised IF signal rearranged data matrix are extracted from the statistical indicator vectors of gray-level cooccurrence matrices(GLCMs),and support vector machines(SVMs)are used for classification.The DR2D-based adaptive denoising algorithm achieves an average correlation coefficient of more than 0.76 for ten fuze types under SNRs of-10 d B and above,which is higher than that of other typical algorithms.The trained SVM classification model achieves an average recognition accuracy of more than 96%on seven modulation types and recognition accuracies of more than 94%on each modulation type under SNRs of-12 d B and above,which represents a good AMR performance of radio fuzes under low SNRs.展开更多
The fractured-vuggy carbonate oil resources in the western basin of China are extremely rich.The connectivity of carbonate reservoirs is complex,and there is still a lack of clear understanding of the development and ...The fractured-vuggy carbonate oil resources in the western basin of China are extremely rich.The connectivity of carbonate reservoirs is complex,and there is still a lack of clear understanding of the development and topological structure of the pore space in fractured-vuggy reservoirs.Thus,effective prediction of fractured-vuggy reservoirs is difficult.In view of this,this work employs adaptive point cloud technology to reproduce the shape and capture the characteristics of a fractured-vuggy reservoir.To identify the complex connectivity among pores,fractures,and vugs,a simplified one-dimensional connectivity model is established by using the meshless connection element method(CEM).Considering that different types of connection units have different flow characteristics,a sequential coupling calculation method that can efficiently calculate reservoir pressure and saturation is developed.By automatic history matching,the dynamic production data is fitted in real-time,and the characteristic parameters of the connection unit are inverted.Simulation results show that the three-dimensional connectivity model of the fractured-vuggy reservoir built in this work is as close as 90%of the fine grid model,while the dynamic simulation efficiency is much higher with good accuracy.展开更多
A system for fully automatic selection of welding specifications in resistance welding equipment has been developed to address the problem of workers frequently choosing the wrong specifications during manual welding ...A system for fully automatic selection of welding specifications in resistance welding equipment has been developed to address the problem of workers frequently choosing the wrong specifications during manual welding of multiple parts on a single machine in automobile factories. The system incorporates an automatic recognition system for different workpiece materials using the added machine fixture,visual detection system for nuts and bolts,and secondary graphical confirmation to ensure the correctness of specification calling. This system achieves reliable,fully automatic selection of welding specifications in resistance welding equipment and has shown significant effects in improving welding quality for massproduced workpieces,while solving the problem of specification calling errors that can occur with traditional methods involving process charts and code adjustments. This system is particularly suitable for promoting applications in manual welding of multiple parts on a single machine in automobile factories,ensuring correct specification calling and welding quality.展开更多
Depression is a common mental health disorder.With current depression detection methods,specialized physicians often engage in conversations and physiological examinations based on standardized scales as auxiliary mea...Depression is a common mental health disorder.With current depression detection methods,specialized physicians often engage in conversations and physiological examinations based on standardized scales as auxiliary measures for depression assessment.Non-biological markers-typically classified as verbal or non-verbal and deemed crucial evaluation criteria for depression-have not been effectively utilized.Specialized physicians usually require extensive training and experience to capture changes in these features.Advancements in deep learning technology have provided technical support for capturing non-biological markers.Several researchers have proposed automatic depression estimation(ADE)systems based on sounds and videos to assist physicians in capturing these features and conducting depression screening.This article summarizes commonly used public datasets and recent research on audio-and video-based ADE based on three perspectives:Datasets,deficiencies in existing research,and future development directions.展开更多
In this paper,an improved sag control strategy based on automatic SOC equalization is proposed to solve the problems of slow SOC equalization and excessive bus voltage fluctuation amplitude and offset caused by load a...In this paper,an improved sag control strategy based on automatic SOC equalization is proposed to solve the problems of slow SOC equalization and excessive bus voltage fluctuation amplitude and offset caused by load and PV power variations in a stand-alone DC microgrid.The strategy includes primary and secondary control.Among them,the primary control suppresses the DC microgrid voltage fluctuation through the I and II section control,and the secondary control aims to correct the P-U curve of the energy storage system and the PV system,thus reducing the steady-state bus voltage excursion.The simulation results demonstrate that the proposed control strategy effectively achieves SOC balancing and enhances the immunity of bus voltage.The proposed strategy improves the voltage fluctuation suppression ability by approximately 39.4%and 43.1%under the PV power and load power fluctuation conditions,respectively.Furthermore,the steady-state deviation of the bus voltage,△U_(dc) is only 0.01–0.1 V,ensuring stable operation of the DC microgrid in fluctuating power environments.展开更多
To evaluate the reliability of the Real-time Intelligent Seismic Processing System(RISP)in the operation of the Nei Monggol seismic network,31 earthquake events occurred in the area within 30 days before and after the...To evaluate the reliability of the Real-time Intelligent Seismic Processing System(RISP)in the operation of the Nei Monggol seismic network,31 earthquake events occurred in the area within 30 days before and after the Helinger ML 4.5 earthquake that occurred on March 30,2020,were taken as the research object.The results of manual cataloging and real-time intelligent seismic processing system output(automatic cataloging)were compared and analyzed,and the following conclusions were drawn:The number of events identified by the real-time intelligent seismic processing system(RISP)is about 2.5 times that of manual identification.The automatic catalog matches 30 events from the manual catalog,and the event recall rate is as high as 96.8%.The automatic catalog has a smaller deviation from the manual catalog in terms of the time of earthquake occurrence,epicenter position,magnitude,and P and S phase arrivals.By comparing the results of automatic and manual catalogs,it can be seen that the cataloging results for the same event in both catalogs are consistent,with an epicenter deviation generally within the range of±10 km and an earthquake occurrence time generally within the range of±2 s.The automatic catalog basically meets the requirements of the error range for manual cataloging.Overall,the output results of the Real-time Intelligent Earthquake Processing System(RISP)meet the expected goals and can provide data support for scientific research such as rapid post-earthquake aftershock sequences and earthquake swarm trend judgment.展开更多
The article mainly studies the application strategy of automatic addressable single-lamp control technology in tunnel lighting.It encompasses an introduction to this technology,an analysis of the tunnel lighting syste...The article mainly studies the application strategy of automatic addressable single-lamp control technology in tunnel lighting.It encompasses an introduction to this technology,an analysis of the tunnel lighting system using automatic addressable single-lamp control technology,and outlines the main development direction for this technology in modern tunnel lighting.The aim is to offer insights that can inform the rational deployment of this technology,thereby enhancing the lighting control effectiveness in modern tunnels and meeting their specific lighting requirements more effectively.展开更多
Automatic pavement crack detection is a critical task for maintaining the pavement stability and driving safety.The task is challenging because the shadows on the pavement may have similar intensity with the crack,whi...Automatic pavement crack detection is a critical task for maintaining the pavement stability and driving safety.The task is challenging because the shadows on the pavement may have similar intensity with the crack,which interfere with the crack detection performance.Till to the present,there still lacks efficient algorithm models and training datasets to deal with the interference brought by the shadows.To fill in the gap,we made several contributions as follows.First,we proposed a new pavement shadow and crack dataset,which contains a variety of shadow and pavement pixel size combinations.It also covers all common cracks(linear cracks and network cracks),placing higher demands on crack detection methods.Second,we designed a two-step shadow-removal-oriented crack detection approach:SROCD,which improves the performance of the algorithm by first removing the shadow and then detecting it.In addition to shadows,the method can cope with other noise disturbances.Third,we explored the mechanism of how shadows affect crack detection.Based on this mechanism,we propose a data augmentation method based on the difference in brightness values,which can adapt to brightness changes caused by seasonal and weather changes.Finally,we introduced a residual feature augmentation algorithm to detect small cracks that can predict sudden disasters,and the algorithm improves the performance of the model overall.We compare our method with the state-of-the-art methods on existing pavement crack datasets and the shadow-crack dataset,and the experimental results demonstrate the superiority of our method.展开更多
Electric vehicle charging identification and positioning is critically important to achieving automatic charging.In terms of the problem of automatic charging for electric vehicles,a dual recognition and positioning m...Electric vehicle charging identification and positioning is critically important to achieving automatic charging.In terms of the problem of automatic charging for electric vehicles,a dual recognition and positioning method based on deep learning is proposed.The method is divided into two parts:global recognition and localization and local recognition and localization.In the specific implementation process,the collected pictures of electric vehicle charging attitude are classified and labeled.It is trained with the improved YOLOv4 networkmodel and the corresponding detectionmodel is obtained.The contour of the electric vehicle is extracted by the BiSeNet semantic segmentation algorithm.The minimum external rectangle is used for positioning of the electric vehicle.Based on the location relationship between the charging port and the electric vehicle,the rough location information of the charging port is obtained.The automatic charging equipment moves to the vicinity of the charging port,and the camera near the charging gun collects pictures of the charging port.The model is detected by the Hough circle,the KM algorithmis used for featurematching,and the homography matrix is used to solve the attitude.The results show that the dual identification and location method based on the improved YOLOv4 algorithm proposed in this paper can accurately locate the charging port.The accuracy of the charging connection can reach 80%.It provides an effective way to solve the problems of automatic charging identification and positioning of electric vehicles and has strong engineering practical value.展开更多
Local geometric information and discontinuity features are key aspects of the analysis of the evolution and failure mechanisms of unstable rock blocks in rock tunnels.This study demonstrates the integration of terrest...Local geometric information and discontinuity features are key aspects of the analysis of the evolution and failure mechanisms of unstable rock blocks in rock tunnels.This study demonstrates the integration of terrestrial laser scanning(TLS)with distinct element method for rock mass characterization and stability analysis in tunnels.TLS records detailed geometric information of the surrounding rock mass by scanning and collecting the positions of millions of rock surface points without contact.By conducting a fuzzy K-means method,a discontinuity automatic identification algorithm was developed,and a method for obtaining the geometric parameters of discontinuities was proposed.This method permits the user to visually identify each discontinuity and acquire its spatial distribution features(e.g.occurrences,spac-ings,trace lengths)in great detail.Compared with hand mapping in conventional geotechnical surveys,the geometric information of discontinuities obtained by this approach is more accurate and the iden-tification is more efficient.Then,a discrete fracture network with the same statistical characteristics as the actual discontinuities was generated with the distinct element method,and a representative nu-merical model of the jointed surrounding rock mass was established.By means of numerical simulation,potential unstable rock blocks were assessed,and failure mechanisms were analyzed.This method was applied to detection and assessment of unstable rock blocks in the spillway and sand flushing tunnel of the Hongshiyan hydropower project after a collapse.The results show that the noncontact detection of blocks was more labor-saving with lower safety risks compared with manual surveys,and the stability assessment was more reliable since the numerical model built by this method was more consistent with the distribution characteristics of actual joints.This study can provide a reference for geological survey and unstable rock block hazard mitigation in tunnels subjected to complex geology and active rockfalls.展开更多
基金supported by the National Natural Science Foundation of China(52130801,U20A20312,52178271,and 52077213)the National Key Research and Development Program of China(2021YFF0500903)。
文摘Identifying workers’construction activities or behaviors can enable managers to better monitor labor efficiency and construction progress.However,current activity analysis methods for construction workers rely solely on manual observations and recordings,which consumes considerable time and has high labor costs.Researchers have focused on monitoring on-site construction activities of workers.However,when multiple workers are working together,current research cannot accu rately and automatically identify the construction activity.This research proposes a deep learning framework for the automated analysis of the construction activities of multiple workers.In this framework,multiple deep neural network models are designed and used to complete worker key point extraction,worker tracking,and worker construction activity analysis.The designed framework was tested at an actual construction site,and activity recognition for multiple workers was performed,indicating the feasibility of the framework for the automated monitoring of work efficiency.
基金the Sichuan Science and Technology Program(2021ZYD0016).
文摘The optimization of the rule base of a fuzzy logic system (FLS) based on evolutionary algorithm has achievednotable results. However, due to the diversity of the deep structure in the hierarchical fuzzy system (HFS) and thecorrelation of each sub fuzzy system, the uncertainty of the HFS’s deep structure increases. For the HFS, a largenumber of studies mainly use fixed structures, which cannot be selected automatically. To solve this problem, thispaper proposes a novel approach for constructing the incremental HFS. During system design, the deep structureand the rule base of the HFS are encoded separately. Subsequently, the deep structure is adaptively mutated basedon the fitness value, so as to realize the diversity of deep structures while ensuring reasonable competition amongthe structures. Finally, the differential evolution (DE) is used to optimize the deep structure of HFS and theparameters of antecedent and consequent simultaneously. The simulation results confirm the effectiveness of themodel. Specifically, the root mean square errors in the Laser dataset and Friedman dataset are 0.0395 and 0.0725,respectively with rule counts of rules is 8 and 12, respectively.When compared to alternative methods, the resultsindicate that the proposed method offers improvements in accuracy and rule counts.
基金National Natural Science Foundation of China under Grant No.61973037China Postdoctoral Science Foundation under Grant No.2022M720419。
文摘Automatic modulation recognition(AMR)of radiation source signals is a research focus in the field of cognitive radio.However,the AMR of radiation source signals at low SNRs still faces a great challenge.Therefore,the AMR method of radiation source signals based on two-dimensional data matrix and improved residual neural network is proposed in this paper.First,the time series of the radiation source signals are reconstructed into two-dimensional data matrix,which greatly simplifies the signal preprocessing process.Second,the depthwise convolution and large-size convolutional kernels based residual neural network(DLRNet)is proposed to improve the feature extraction capability of the AMR model.Finally,the model performs feature extraction and classification on the two-dimensional data matrix to obtain the recognition vector that represents the signal modulation type.Theoretical analysis and simulation results show that the AMR method based on two-dimensional data matrix and improved residual network can significantly improve the accuracy of the AMR method.The recognition accuracy of the proposed method maintains a high level greater than 90% even at -14 dB SNR.
基金supported by National Natural Science Foundation of China(52222215, 52272420, 52072051)。
文摘Parking in a small parking lot within limited space poses a difficult task. It often leads to deviations between the final parking posture and the target posture. These deviations can lead to partial occupancy of adjacent parking lots, which poses a safety threat to vehicles parked in these parking lots. However, previous studies have not addressed this issue. In this paper, we aim to evaluate the impact of parking deviation of existing vehicles next to the target parking lot(PDEVNTPL) on the automatic ego vehicle(AEV) parking, in terms of safety, comfort, accuracy, and efficiency of parking. A segmented parking training framework(SPTF) based on soft actor-critic(SAC) is proposed to improve parking performance. In the proposed method, the SAC algorithm incorporates strategy entropy into the objective function, to enable the AEV to learn parking strategies based on a more comprehensive understanding of the environment. Additionally, the SPTF simplifies complex parking tasks to maintain the high performance of deep reinforcement learning(DRL). The experimental results reveal that the PDEVNTPL has a detrimental influence on the AEV parking in terms of safety, accuracy, and comfort, leading to reductions of more than 27%, 54%, and 26%respectively. However, the SAC-based SPTF effectively mitigates this impact, resulting in a considerable increase in the parking success rate from 71% to 93%. Furthermore, the heading angle deviation is significantly reduced from 2.25 degrees to 0.43degrees.
基金This research was funded by Shenzhen Science and Technology Program(Grant No.RCBS20221008093121051)the General Higher Education Project of Guangdong Provincial Education Department(Grant No.2020ZDZX3085)+1 种基金China Postdoctoral Science Foundation(Grant No.2021M703371)the Post-Doctoral Foundation Project of Shenzhen Polytechnic(Grant No.6021330002K).
文摘In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling paradigm for semantics-aware speech recognition in air traffic control communications, which could contribute to the advancement of intelligent and efficient aviation safety management.
文摘This study presents a method for the inverse analysis of fluid flow problems.The focus is put on accurately determining boundary conditions and characterizing the physical properties of granular media,such as permeability,and fluid components,like viscosity.The primary aim is to deduce either constant pressure head or pressure profiles,given the known velocity field at a steady-state flow through a conduit containing obstacles,including walls,spheres,and grains.The lattice Boltzmann method(LBM)combined with automatic differentiation(AD)(AD-LBM)is employed,with the help of the GPU-capable Taichi programming language.A lightweight tape is used to generate gradients for the entire LBM simulation,enabling end-to-end backpropagation.Our AD-LBM approach accurately estimates the boundary conditions for complex flow paths in porous media,leading to observed steady-state velocity fields and deriving macro-scale permeability and fluid viscosity.The method demonstrates significant advantages in terms of prediction accuracy and computational efficiency,making it a powerful tool for solving inverse fluid flow problems in various applications.
基金National Natural Science Foundation of China(U2133208,U20A20161)National Natural Science Foundation of China(No.62273244)Sichuan Science and Technology Program(No.2022YFG0180).
文摘In order to enhance the accuracy of Air Traffic Control(ATC)cybersecurity attack detection,in this paper,a new clustering detection method is designed for air traffic control network security attacks.The feature set for ATC cybersecurity attacks is constructed by setting the feature states,adding recursive features,and determining the feature criticality.The expected information gain and entropy of the feature data are computed to determine the information gain of the feature data and reduce the interference of similar feature data.An autoencoder is introduced into the AI(artificial intelligence)algorithm to encode and decode the characteristics of ATC network security attack behavior to reduce the dimensionality of the ATC network security attack behavior data.Based on the above processing,an unsupervised learning algorithm for clustering detection of ATC network security attacks is designed.First,determine the distance between the clustering clusters of ATC network security attack behavior characteristics,calculate the clustering threshold,and construct the initial clustering center.Then,the new average value of all feature objects in each cluster is recalculated as the new cluster center.Second,it traverses all objects in a cluster of ATC network security attack behavior feature data.Finally,the cluster detection of ATC network security attack behavior is completed by the computation of objective functions.The experiment took three groups of experimental attack behavior data sets as the test object,and took the detection rate,false detection rate and recall rate as the test indicators,and selected three similar methods for comparative test.The experimental results show that the detection rate of this method is about 98%,the false positive rate is below 1%,and the recall rate is above 97%.Research shows that this method can improve the detection performance of security attacks in air traffic control network.
文摘In view of low recognition rate of complex radar intra-pulse modulation signal type by traditional methods under low signal-to-noise ratio(SNR),the paper proposes an automatic recog-nition method of complex radar intra-pulse modulation signal type based on deep residual network.The basic principle of the recognition method is to obtain the transformation relationship between the time and frequency of complex radar intra-pulse modulation signal through short-time Fourier transform(STFT),and then design an appropriate deep residual network to extract the features of the time-frequency map and complete a variety of complex intra-pulse modulation signal type recognition.In addition,in order to improve the generalization ability of the proposed method,label smoothing and L2 regularization are introduced.The simulation results show that the proposed method has a recognition accuracy of more than 95%for complex radar intra-pulse modulation sig-nal types under low SNR(2 dB).
基金Supported by the National Natural Science Foundation of China(42272110)CNPC-China University of Petroleum(Beijing)Strategic Cooperation Project(ZLZX2020-02).
文摘Aiming at the problem that the data-driven automatic correlation methods which are difficult to adapt to the automatic correlation of oil-bearing strata with large changes in lateral sedimentary facies and strata thickness,an intelligent automatic correlation method of oil-bearing strata based on pattern constraints is formed.We propose to introduce knowledge-driven in automatic correlation of oil-bearing strata,constraining the correlation process by stratigraphic sedimentary patterns and improving the similarity measuring machine and conditional constraint dynamic time warping algorithm to automate the correlation of marker layers and the interfaces of each stratum.The application in Shishen 100 block in the Shinan Oilfield of the Bohai Bay Basin shows that the coincidence rate of the marker layers identified by this method is over 95.00%,and the average coincidence rate of identified oil-bearing strata reaches 90.02% compared to artificial correlation results,which is about 17 percentage points higher than that of the existing automatic correlation methods.The accuracy of the automatic correlation of oil-bearing strata has been effectively improved.
基金National Natural Science Foundation of China under Grant No.61973037China Postdoctoral Science Foundation 2022M720419 to provide fund for conducting experiments。
文摘The identification of intercepted radio fuze modulation types is a prerequisite for decision-making in interference systems.However,the electromagnetic environment of modern battlefields is complex,and the signal-to-noise ratio(SNR)of such environments is usually low,which makes it difficult to implement accurate recognition of radio fuzes.To solve the above problem,a radio fuze automatic modulation recognition(AMR)method for low-SNR environments is proposed.First,an adaptive denoising algorithm based on data rearrangement and the two-dimensional(2D)fast Fourier transform(FFT)(DR2D)is used to reduce the noise of the intercepted radio fuze intermediate frequency(IF)signal.Then,the textural features of the denoised IF signal rearranged data matrix are extracted from the statistical indicator vectors of gray-level cooccurrence matrices(GLCMs),and support vector machines(SVMs)are used for classification.The DR2D-based adaptive denoising algorithm achieves an average correlation coefficient of more than 0.76 for ten fuze types under SNRs of-10 d B and above,which is higher than that of other typical algorithms.The trained SVM classification model achieves an average recognition accuracy of more than 96%on seven modulation types and recognition accuracies of more than 94%on each modulation type under SNRs of-12 d B and above,which represents a good AMR performance of radio fuzes under low SNRs.
基金funded by the Natural Science Foundation of Xinjiang Uygur Autonomous Region (No.2022D01A330)the CNPC (China National Petroleum Corporation)Scientific Research and Technology Development Project (Grant No.2021DJ1501)+1 种基金National Natural Science Foundation Project (No.52274030)“Tianchi Talent”Introduction Plan of Xinjiang Uygur Autonomous Region (2022).
文摘The fractured-vuggy carbonate oil resources in the western basin of China are extremely rich.The connectivity of carbonate reservoirs is complex,and there is still a lack of clear understanding of the development and topological structure of the pore space in fractured-vuggy reservoirs.Thus,effective prediction of fractured-vuggy reservoirs is difficult.In view of this,this work employs adaptive point cloud technology to reproduce the shape and capture the characteristics of a fractured-vuggy reservoir.To identify the complex connectivity among pores,fractures,and vugs,a simplified one-dimensional connectivity model is established by using the meshless connection element method(CEM).Considering that different types of connection units have different flow characteristics,a sequential coupling calculation method that can efficiently calculate reservoir pressure and saturation is developed.By automatic history matching,the dynamic production data is fitted in real-time,and the characteristic parameters of the connection unit are inverted.Simulation results show that the three-dimensional connectivity model of the fractured-vuggy reservoir built in this work is as close as 90%of the fine grid model,while the dynamic simulation efficiency is much higher with good accuracy.
文摘A system for fully automatic selection of welding specifications in resistance welding equipment has been developed to address the problem of workers frequently choosing the wrong specifications during manual welding of multiple parts on a single machine in automobile factories. The system incorporates an automatic recognition system for different workpiece materials using the added machine fixture,visual detection system for nuts and bolts,and secondary graphical confirmation to ensure the correctness of specification calling. This system achieves reliable,fully automatic selection of welding specifications in resistance welding equipment and has shown significant effects in improving welding quality for massproduced workpieces,while solving the problem of specification calling errors that can occur with traditional methods involving process charts and code adjustments. This system is particularly suitable for promoting applications in manual welding of multiple parts on a single machine in automobile factories,ensuring correct specification calling and welding quality.
基金Supported by Shandong Province Key R and D Program,No.2021SFGC0504Shandong Provincial Natural Science Foundation,No.ZR2021MF079Science and Technology Development Plan of Jinan(Clinical Medicine Science and Technology Innovation Plan),No.202225054.
文摘Depression is a common mental health disorder.With current depression detection methods,specialized physicians often engage in conversations and physiological examinations based on standardized scales as auxiliary measures for depression assessment.Non-biological markers-typically classified as verbal or non-verbal and deemed crucial evaluation criteria for depression-have not been effectively utilized.Specialized physicians usually require extensive training and experience to capture changes in these features.Advancements in deep learning technology have provided technical support for capturing non-biological markers.Several researchers have proposed automatic depression estimation(ADE)systems based on sounds and videos to assist physicians in capturing these features and conducting depression screening.This article summarizes commonly used public datasets and recent research on audio-and video-based ADE based on three perspectives:Datasets,deficiencies in existing research,and future development directions.
基金supported by the NationalNatural Science Foundation of China(No.52067013)the Natural Science Foundation of Gansu Province(No.20JR5RA395)as well as the Tianyou Innovation Team of Lanzhou Jiaotong University(TY202010).
文摘In this paper,an improved sag control strategy based on automatic SOC equalization is proposed to solve the problems of slow SOC equalization and excessive bus voltage fluctuation amplitude and offset caused by load and PV power variations in a stand-alone DC microgrid.The strategy includes primary and secondary control.Among them,the primary control suppresses the DC microgrid voltage fluctuation through the I and II section control,and the secondary control aims to correct the P-U curve of the energy storage system and the PV system,thus reducing the steady-state bus voltage excursion.The simulation results demonstrate that the proposed control strategy effectively achieves SOC balancing and enhances the immunity of bus voltage.The proposed strategy improves the voltage fluctuation suppression ability by approximately 39.4%and 43.1%under the PV power and load power fluctuation conditions,respectively.Furthermore,the steady-state deviation of the bus voltage,△U_(dc) is only 0.01–0.1 V,ensuring stable operation of the DC microgrid in fluctuating power environments.
文摘To evaluate the reliability of the Real-time Intelligent Seismic Processing System(RISP)in the operation of the Nei Monggol seismic network,31 earthquake events occurred in the area within 30 days before and after the Helinger ML 4.5 earthquake that occurred on March 30,2020,were taken as the research object.The results of manual cataloging and real-time intelligent seismic processing system output(automatic cataloging)were compared and analyzed,and the following conclusions were drawn:The number of events identified by the real-time intelligent seismic processing system(RISP)is about 2.5 times that of manual identification.The automatic catalog matches 30 events from the manual catalog,and the event recall rate is as high as 96.8%.The automatic catalog has a smaller deviation from the manual catalog in terms of the time of earthquake occurrence,epicenter position,magnitude,and P and S phase arrivals.By comparing the results of automatic and manual catalogs,it can be seen that the cataloging results for the same event in both catalogs are consistent,with an epicenter deviation generally within the range of±10 km and an earthquake occurrence time generally within the range of±2 s.The automatic catalog basically meets the requirements of the error range for manual cataloging.Overall,the output results of the Real-time Intelligent Earthquake Processing System(RISP)meet the expected goals and can provide data support for scientific research such as rapid post-earthquake aftershock sequences and earthquake swarm trend judgment.
文摘The article mainly studies the application strategy of automatic addressable single-lamp control technology in tunnel lighting.It encompasses an introduction to this technology,an analysis of the tunnel lighting system using automatic addressable single-lamp control technology,and outlines the main development direction for this technology in modern tunnel lighting.The aim is to offer insights that can inform the rational deployment of this technology,thereby enhancing the lighting control effectiveness in modern tunnels and meeting their specific lighting requirements more effectively.
基金supported in part by the 14th Five-Year Project of Ministry of Science and Technology of China(2021YFD2000304)Fundamental Research Funds for the Central Universities(531118010509)Natural Science Foundation of Hunan Province,China(2021JJ40114)。
文摘Automatic pavement crack detection is a critical task for maintaining the pavement stability and driving safety.The task is challenging because the shadows on the pavement may have similar intensity with the crack,which interfere with the crack detection performance.Till to the present,there still lacks efficient algorithm models and training datasets to deal with the interference brought by the shadows.To fill in the gap,we made several contributions as follows.First,we proposed a new pavement shadow and crack dataset,which contains a variety of shadow and pavement pixel size combinations.It also covers all common cracks(linear cracks and network cracks),placing higher demands on crack detection methods.Second,we designed a two-step shadow-removal-oriented crack detection approach:SROCD,which improves the performance of the algorithm by first removing the shadow and then detecting it.In addition to shadows,the method can cope with other noise disturbances.Third,we explored the mechanism of how shadows affect crack detection.Based on this mechanism,we propose a data augmentation method based on the difference in brightness values,which can adapt to brightness changes caused by seasonal and weather changes.Finally,we introduced a residual feature augmentation algorithm to detect small cracks that can predict sudden disasters,and the algorithm improves the performance of the model overall.We compare our method with the state-of-the-art methods on existing pavement crack datasets and the shadow-crack dataset,and the experimental results demonstrate the superiority of our method.
基金supported by Guangdong Province Key Research and Development Project(2019B090909001)National Natural Science Foundation of China(52175236)+1 种基金the Natural Science Foundation of China(Grant 51705268)China Postdoctoral Science Foundation Funded Project(Grant 2017M612191).
文摘Electric vehicle charging identification and positioning is critically important to achieving automatic charging.In terms of the problem of automatic charging for electric vehicles,a dual recognition and positioning method based on deep learning is proposed.The method is divided into two parts:global recognition and localization and local recognition and localization.In the specific implementation process,the collected pictures of electric vehicle charging attitude are classified and labeled.It is trained with the improved YOLOv4 networkmodel and the corresponding detectionmodel is obtained.The contour of the electric vehicle is extracted by the BiSeNet semantic segmentation algorithm.The minimum external rectangle is used for positioning of the electric vehicle.Based on the location relationship between the charging port and the electric vehicle,the rough location information of the charging port is obtained.The automatic charging equipment moves to the vicinity of the charging port,and the camera near the charging gun collects pictures of the charging port.The model is detected by the Hough circle,the KM algorithmis used for featurematching,and the homography matrix is used to solve the attitude.The results show that the dual identification and location method based on the improved YOLOv4 algorithm proposed in this paper can accurately locate the charging port.The accuracy of the charging connection can reach 80%.It provides an effective way to solve the problems of automatic charging identification and positioning of electric vehicles and has strong engineering practical value.
基金support of the National Natural Science Foundation of China(Grant No.42102316)the Open Project of the Technology Innovation Center for Geological Environment Monitoring of Ministry of Natural Resources of China(Grant No.2022KFK1212005).
文摘Local geometric information and discontinuity features are key aspects of the analysis of the evolution and failure mechanisms of unstable rock blocks in rock tunnels.This study demonstrates the integration of terrestrial laser scanning(TLS)with distinct element method for rock mass characterization and stability analysis in tunnels.TLS records detailed geometric information of the surrounding rock mass by scanning and collecting the positions of millions of rock surface points without contact.By conducting a fuzzy K-means method,a discontinuity automatic identification algorithm was developed,and a method for obtaining the geometric parameters of discontinuities was proposed.This method permits the user to visually identify each discontinuity and acquire its spatial distribution features(e.g.occurrences,spac-ings,trace lengths)in great detail.Compared with hand mapping in conventional geotechnical surveys,the geometric information of discontinuities obtained by this approach is more accurate and the iden-tification is more efficient.Then,a discrete fracture network with the same statistical characteristics as the actual discontinuities was generated with the distinct element method,and a representative nu-merical model of the jointed surrounding rock mass was established.By means of numerical simulation,potential unstable rock blocks were assessed,and failure mechanisms were analyzed.This method was applied to detection and assessment of unstable rock blocks in the spillway and sand flushing tunnel of the Hongshiyan hydropower project after a collapse.The results show that the noncontact detection of blocks was more labor-saving with lower safety risks compared with manual surveys,and the stability assessment was more reliable since the numerical model built by this method was more consistent with the distribution characteristics of actual joints.This study can provide a reference for geological survey and unstable rock block hazard mitigation in tunnels subjected to complex geology and active rockfalls.