A novel fault diagnosis method for sensors in air handling unit（AHU） using wavelet energy entropy was presented. Instead of directly comparing the numerous data under noise conditiom, the wavelet energy entropy resi...A novel fault diagnosis method for sensors in air handling unit（AHU） using wavelet energy entropy was presented. Instead of directly comparing the numerous data under noise conditiom, the wavelet energy entropy residual was compared in the proposed method. Three.level wavelet analysis was used to decompose the measurement data under both fault-free and faulty operation conditions. The concept of Shannon entropy was referred to define wavelet energy entropy of the wavelet coefficients. The sensor faults were diagnosed by comparing the deviation of the wavelet energy entropy of the measured signal and the estimated one with the preset threshold. Testing results showed that the wavelet energy entropy was sensitive to diagnose the biased faults. The wavelet energy entropy residuals exceed the threshold significantly when faults occur. In addition, the severer the faults were, the larger the residuals would be. The results prove that the proposed method is feasible and effective for the fault detection and diagnosis of the sensors.展开更多
A sensor graph network is a sensor network model organized according to graph network structure.Structural unit and signal propagation of core nodes are the basic characteristics of sensor graph networks.In sensor net...A sensor graph network is a sensor network model organized according to graph network structure.Structural unit and signal propagation of core nodes are the basic characteristics of sensor graph networks.In sensor networks,network structure recognition is the basis for accurate identification and effective prediction and control of node states.Aiming at the problems of difficult global structure identification and poor interpretability in complex sensor graph networks,based on the characteristics of sensor networks,a method is proposed to firstly unitize the graph network structure and then expand the unit based on the signal transmission path of the core node.This method which builds on unit patulousness and core node signal propagation(called p-law)can rapidly and effectively achieve the global structure identification of a sensor graph network.Different from the traditional graph network structure recognition algorithms such as modularity maximization and spectral clustering,the proposed method reveals the natural evolution process and law of graph network subgroup generation.Experimental results confirm the effectiveness,accuracy and rationality of the proposed method and suggest that our method can be a new approach for graph network global structure recognition.展开更多
The condition of bolted connections significantly affects the structural safety.However,conventional bolt tension sensors fail to provide precise measurements due to their bulky size or inadequate stability.This study...The condition of bolted connections significantly affects the structural safety.However,conventional bolt tension sensors fail to provide precise measurements due to their bulky size or inadequate stability.This study employs the piezoresistive effect of crystalline silicon material to fabricate an ultrathin sensor.The sensor exhibits a linear relationship between pressure and voltage,an exceptional stability at varying temperatures,and a superior resistance to corrosion,making it adaptable and user-friendly for applications of high-strength bolt tension monitoring.A monitoring system,incorporating the proposed sensor,has also been developed.This system provides real-time display of bolt tension and enables the assessment of sensor and structural conditions,including bolt loosening or component failure.The efficacy of the proposed sensor and monitoring system was validated through a project carried out at the Xiluodu Hydropower Plant.According to the results,the sensor and online monitoring system effectively gauged and proficiently conveyed and stored bolt tension data.In addition,correlations were created between bolt tensions and essential unit parameters,such as water head,active power,and pressures at vital points,facilitating anomaly detection and early warning.展开更多
In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant attention.Previously developed HAR models use hand-crafted features to recognize human activities,leading to the e...In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant attention.Previously developed HAR models use hand-crafted features to recognize human activities,leading to the extraction of basic features.The images captured by wearable sensors contain advanced features,allowing them to be analyzed by deep learning algorithms to enhance the detection and recognition of human actions.Poor lighting and limited sensor capabilities can impact data quality,making the recognition of human actions a challenging task.The unimodal-based HAR approaches are not suitable in a real-time environment.Therefore,an updated HAR model is developed using multiple types of data and an advanced deep-learning approach.Firstly,the required signals and sensor data are accumulated from the standard databases.From these signals,the wave features are retrieved.Then the extracted wave features and sensor data are given as the input to recognize the human activity.An Adaptive Hybrid Deep Attentive Network(AHDAN)is developed by incorporating a“1D Convolutional Neural Network(1DCNN)”with a“Gated Recurrent Unit(GRU)”for the human activity recognition process.Additionally,the Enhanced Archerfish Hunting Optimizer(EAHO)is suggested to fine-tune the network parameters for enhancing the recognition process.An experimental evaluation is performed on various deep learning networks and heuristic algorithms to confirm the effectiveness of the proposed HAR model.The EAHO-based HAR model outperforms traditional deep learning networks with an accuracy of 95.36,95.25 for recall,95.48 for specificity,and 95.47 for precision,respectively.The result proved that the developed model is effective in recognizing human action by taking less time.Additionally,it reduces the computation complexity and overfitting issue through using an optimization approach.展开更多
The evaporative cooling,which assists the refrigeration machinery air-conditioning systems test-rig,has been designed.Its structure and working principle were described,and the performance test was conducted and analy...The evaporative cooling,which assists the refrigeration machinery air-conditioning systems test-rig,has been designed.Its structure and working principle were described,and the performance test was conducted and analyzed.The test shows that making full use of the evaporative cooling "free cooling" in Spring and Autumn seasons can fully meet the requirements of air-conditioned comfort through the switch of the function in different seasons.Taking into account the evaporative cooling fan and pump energy consumption,compared with the traditional mechanical refrigeration system,more than 80 percent of energy can be saved,and the energy efficiency ratio of the Unit(EER)is as high as 7.63.Using the two stages of indirect evaporative cooling to pre-cool the new wind in summer,under the conditions of the same air supply temperature requirements,0.83 kg/s chilled water saved can be equivalent to the traditional mechanical refrigeration system,and when the new wind ratio up to 50 percent,more than 10 percent load was reduced in mechanical refrigeration system.The overall EER increased about 35 percent.展开更多
基金National Natural Science Foundation of China(No.31101085)
文摘A novel fault diagnosis method for sensors in air handling unit（AHU） using wavelet energy entropy was presented. Instead of directly comparing the numerous data under noise conditiom, the wavelet energy entropy residual was compared in the proposed method. Three.level wavelet analysis was used to decompose the measurement data under both fault-free and faulty operation conditions. The concept of Shannon entropy was referred to define wavelet energy entropy of the wavelet coefficients. The sensor faults were diagnosed by comparing the deviation of the wavelet energy entropy of the measured signal and the estimated one with the preset threshold. Testing results showed that the wavelet energy entropy was sensitive to diagnose the biased faults. The wavelet energy entropy residuals exceed the threshold significantly when faults occur. In addition, the severer the faults were, the larger the residuals would be. The results prove that the proposed method is feasible and effective for the fault detection and diagnosis of the sensors.
基金This research is supported by the Natural Science Foundation Project of Fujian Provincial Department of Science and Technology(Grant No.2020J01385)Digital Fujian Industrial Energy Big Data Research Institute(Grant No.KB180045)Provincial Key Laboratory of Industrial Big Data Analysis and Application(Grant No.KB180029).
文摘A sensor graph network is a sensor network model organized according to graph network structure.Structural unit and signal propagation of core nodes are the basic characteristics of sensor graph networks.In sensor networks,network structure recognition is the basis for accurate identification and effective prediction and control of node states.Aiming at the problems of difficult global structure identification and poor interpretability in complex sensor graph networks,based on the characteristics of sensor networks,a method is proposed to firstly unitize the graph network structure and then expand the unit based on the signal transmission path of the core node.This method which builds on unit patulousness and core node signal propagation(called p-law)can rapidly and effectively achieve the global structure identification of a sensor graph network.Different from the traditional graph network structure recognition algorithms such as modularity maximization and spectral clustering,the proposed method reveals the natural evolution process and law of graph network subgroup generation.Experimental results confirm the effectiveness,accuracy and rationality of the proposed method and suggest that our method can be a new approach for graph network global structure recognition.
文摘The condition of bolted connections significantly affects the structural safety.However,conventional bolt tension sensors fail to provide precise measurements due to their bulky size or inadequate stability.This study employs the piezoresistive effect of crystalline silicon material to fabricate an ultrathin sensor.The sensor exhibits a linear relationship between pressure and voltage,an exceptional stability at varying temperatures,and a superior resistance to corrosion,making it adaptable and user-friendly for applications of high-strength bolt tension monitoring.A monitoring system,incorporating the proposed sensor,has also been developed.This system provides real-time display of bolt tension and enables the assessment of sensor and structural conditions,including bolt loosening or component failure.The efficacy of the proposed sensor and monitoring system was validated through a project carried out at the Xiluodu Hydropower Plant.According to the results,the sensor and online monitoring system effectively gauged and proficiently conveyed and stored bolt tension data.In addition,correlations were created between bolt tensions and essential unit parameters,such as water head,active power,and pressures at vital points,facilitating anomaly detection and early warning.
文摘In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant attention.Previously developed HAR models use hand-crafted features to recognize human activities,leading to the extraction of basic features.The images captured by wearable sensors contain advanced features,allowing them to be analyzed by deep learning algorithms to enhance the detection and recognition of human actions.Poor lighting and limited sensor capabilities can impact data quality,making the recognition of human actions a challenging task.The unimodal-based HAR approaches are not suitable in a real-time environment.Therefore,an updated HAR model is developed using multiple types of data and an advanced deep-learning approach.Firstly,the required signals and sensor data are accumulated from the standard databases.From these signals,the wave features are retrieved.Then the extracted wave features and sensor data are given as the input to recognize the human activity.An Adaptive Hybrid Deep Attentive Network(AHDAN)is developed by incorporating a“1D Convolutional Neural Network(1DCNN)”with a“Gated Recurrent Unit(GRU)”for the human activity recognition process.Additionally,the Enhanced Archerfish Hunting Optimizer(EAHO)is suggested to fine-tune the network parameters for enhancing the recognition process.An experimental evaluation is performed on various deep learning networks and heuristic algorithms to confirm the effectiveness of the proposed HAR model.The EAHO-based HAR model outperforms traditional deep learning networks with an accuracy of 95.36,95.25 for recall,95.48 for specificity,and 95.47 for precision,respectively.The result proved that the developed model is effective in recognizing human action by taking less time.Additionally,it reduces the computation complexity and overfitting issue through using an optimization approach.
基金Xi'an Polytechnic University Graduate Innovational Foundation(chx080608)
文摘The evaporative cooling,which assists the refrigeration machinery air-conditioning systems test-rig,has been designed.Its structure and working principle were described,and the performance test was conducted and analyzed.The test shows that making full use of the evaporative cooling "free cooling" in Spring and Autumn seasons can fully meet the requirements of air-conditioned comfort through the switch of the function in different seasons.Taking into account the evaporative cooling fan and pump energy consumption,compared with the traditional mechanical refrigeration system,more than 80 percent of energy can be saved,and the energy efficiency ratio of the Unit(EER)is as high as 7.63.Using the two stages of indirect evaporative cooling to pre-cool the new wind in summer,under the conditions of the same air supply temperature requirements,0.83 kg/s chilled water saved can be equivalent to the traditional mechanical refrigeration system,and when the new wind ratio up to 50 percent,more than 10 percent load was reduced in mechanical refrigeration system.The overall EER increased about 35 percent.
