A Railway Fastener Inspection Method Based on Abnormal Sample Generation

Regular fastener detection is necessary to ensure the safety of railways.However,the number of abnormal fasteners is significantly lower than the number of normal fasteners in real railways.Existing supervised inspectionmethods have insufficient detection ability in cases of imbalanced samples.To solve this problem,we propose an approach based on deep convolutional neural networks(DCNNs),which consists of three stages:fastener localization,abnormal fastener sample generation based on saliency detection,and fastener state inspection.First,a lightweight YOLOv5s is designed to achieve fast and precise localization of fastener regions.Then,the foreground clip region of a fastener image is extracted by the designed fastener saliency detection network(F-SDNet),combined with data augmentation to generate a large number of abnormal fastener samples and balance the number of abnormal and normal samples.Finally,a fastener inspection model called Fastener ResNet-8 is constructed by being trained with the augmented fastener dataset.Results show the effectiveness of our proposed method in solving the problem of sample imbalance in fastener detection.Qualitative and quantitative comparisons show that the proposed F-SDNet outperforms other state-of-the-art methods in clip region extraction,reaching MAE and max F-measure of 0.0215 and 0.9635,respectively.In addition,the FPS of the fastener state inspection model reached 86.2,and the average accuracy reached 98.7%on 614 augmented fastener test sets and 99.9%on 7505 real fastener datasets.

High-order harmonic generation of ZnO crystals in chirped and static electric fields

High harmonic generation in ZnO crystals under chirped single-color field and static electric field are investigated by solving the semiconductor Bloch equation(SBE). It is found that when the chirp pulse is introduced, the interference structure becomes obvious while the harmonic cutoff is not extended. Furthermore, the harmonic efficiency is improved when the static electric field is included. These phenomena are demonstrated by the classical recollision model in real space affected by the waveform of laser field and inversion symmetry. Specifically, the electron motion in k-space shows that the change of waveform and the destruction of the symmetry of the laser field lead to the incomplete X-structure of the crystal-momentum-resolved(k-resolved) inter-band harmonic spectrum. Furthermore, a pre-acceleration process in the solid four-step model is confirmed.

A Multi-Task Motion Generation Model that Fuses a Discriminator and a Generator

The human motion generation model can extract structural features from existing human motion capture data,and the generated data makes animated characters move.The 3D human motion capture sequences contain complex spatial-temporal structures,and the deep learning model can fully describe the potential semantic structure of human motion.To improve the authenticity of the generated human motion sequences,we propose a multi-task motion generation model that consists of a discriminator and a generator.The discriminator classifies motion sequences into different styles according to their similarity to the mean spatial-temporal templates from motion sequences of 17 crucial human joints in three-freedom degrees.And target motion sequences are created with these styles by the generator.Unlike traditional related works,our model can handle multiple tasks,such as identifying styles and generating data.In addition,by extracting 17 crucial joints from 29 human joints,our model avoids data redundancy and improves the accuracy of model recognition.The experimental results show that the discriminator of the model can effectively recognize diversified movements,and the generated data can correctly fit the actual data.The combination of discriminator and generator solves the problem of low reuse rate of motion data,and the generated motion sequences are more suitable for actual movement.

Calibration of quantitative rescattering model for simulating vortex high-order harmonic generation driven by Laguerre–Gaussian beam with nonzero orbital angular momentum

We calibrate the macroscopic vortex high-order harmonic generation(HHG)obtained by the quantitative rescattering(QRS)model to compute single-atom induced dipoles against that by solving the time-dependent Schr?dinger equation(TDSE).We show that the QRS perfectly agrees with the TDSE under the favorable phase-matching condition,and the QRS can accurately predict the main features in the spatial profiles of vortex HHG if the phase-matching condition is not good.We uncover that harmonic emissions from short and long trajectories are adjusted by the phase-matching condition through the time-frequency analysis and the QRS can simulate the vortex HHG accurately only when the interference between two trajectories is absent.This work confirms that it is an efficient way to employ the QRS model in the single-atom response for precisely simulating the macroscopic vortex HHG.

Research on Equivalent Modeling Method of AC-DC Power Networks Integrating with Renewable Energy Generation

Along with the increasing integration of renewable energy generation in AC-DC power networks,investigating the dynamic behaviors of this complex system with a proper equivalent model is significant.This paper presents an equivalent modeling method for the AC-DC power networks with doubly-fed induction generator(DFIG)based wind farms to decrease the simulation scale and computational burden.For the AC-DC power networks,the equivalent modeling strategy in accordance with the physical structure simplification is stated.Regarding the DFIG-based wind farms,the equivalent modeling based on the sequential identification of multi-machine parameters using the improved chaotic cuckoo search algorithm(ICCSA)is conducted.In light of the MATLAB simulation platform,a two-zone four-DC interconnected power grid with wind farms is built to check the efficacy of the proposed equivalentmodelingmethod.Fromthe simulation analyses and comparative validation in different algorithms and cases,the proposed method can precisely reflect the steady and dynamic performance of the demonstrated system under N-1 and N-2 fault scenarios,and it can efficiently achieve the parameter identification of the wind farms and fulfill the equivalent modeling.Consequently,the proposed approach’s effectiveness and suitability are confirmed.

Physics-informed neural network approach for heat generation rate estimation of lithium-ion battery under various driving conditions

Accurate insight into the heat generation rate(HGR) of lithium-ion batteries(LIBs) is one of key issues for battery management systems to formulate thermal safety warning strategies in advance.For this reason,this paper proposes a novel physics-informed neural network(PINN) approach for HGR estimation of LIBs under various driving conditions.Specifically,a single particle model with thermodynamics(SPMT) is first constructed for extracting the critical physical knowledge related with battery HGR.Subsequently,the surface concentrations of positive and negative electrodes in battery SPMT model are integrated into the bidirectional long short-term memory(BiLSTM) networks as physical information.And combined with other feature variables,a novel PINN approach to achieve HGR estimation of LIBs with higher accuracy is constituted.Additionally,some critical hyperparameters of BiLSTM used in PINN approach are determined through Bayesian optimization algorithm(BOA) and the results of BOA-based BiLSTM are compared with other traditional BiLSTM/LSTM networks.Eventually,combined with the HGR data generated from the validated virtual battery,it is proved that the proposed approach can well predict the battery HGR under the dynamic stress test(DST) and worldwide light vehicles test procedure(WLTP),the mean absolute error under DST is 0.542 kW/m^(3),and the root mean square error under WLTP is1.428 kW/m^(3)at 25℃.Lastly,the investigation results of this paper also show a new perspective in the application of the PINN approach in battery HGR estimation.

Kinetics and model of gas generation of source rocks in the deepwater area, Qiongdongnan Basin

In order to investigate the hydrocarbon generation process and gas potentials of source rocks in deepwater area of the Qiongdongnan Basin, kinetic parameters of gas generation （activation energy distribution and frequency factor） of the Yacheng Formation source rocks （coal and neritic mudstones） was determined by thermal simulation experiments in the closed system and the specific KINETICS Software. The results show that the activation energy （Ea） distribution of C1–C5 generation ranges from 50 to 74 kcal/mol with a frequency factor of 2.4×1015 s–1 for the neritic mudstone and the Ea distribution of C1–C5 generation ranges from 49 to 73 kcal/mol with a frequency factor of 8.92×1013 s–1 for the coal. On the basis of these kinetic parameters and combined with the data of sedimentary burial and paleothermal histories, the gas generation model of the Yacheng Formation source rocks closer to geological condition was worked out, indicating its main gas generation stage at Ro （vitrinite reflectance） of 1.25%–2.8%. Meanwhile, the gas generation process of the source rocks of different structural locations （central part, southern slope and south low uplift） in the Lingshui Sag was simulated. Among them, the gas generation of the Yacheng Formation source rocks in the central part and the southern slope of the sag entered the main gas window at 10 and 5 Ma respectively and the peak gas generation in the southern slope occurred at 3 Ma. The very late peak gas generation and the relatively large gas potential indices （GPI：20×10^8–60×10^8 m^3/km^2） would provide favorable conditions for the accumulation of large natural gas reserves in the deepwater area.

Construction of a Computational Scheme for the Fuzzy HIV/AIDS Epidemic Model with a Nonlinear Saturated Incidence Rate

This work aimed to construct an epidemic model with fuzzy parameters.Since the classical epidemic model doesnot elaborate on the successful interaction of susceptible and infective people,the constructed fuzzy epidemicmodel discusses the more detailed versions of the interactions between infective and susceptible people.Thenext-generation matrix approach is employed to find the reproduction number of a deterministic model.Thesensitivity analysis and local stability analysis of the systemare also provided.For solving the fuzzy epidemic model,a numerical scheme is constructed which consists of three time levels.The numerical scheme has an advantage overthe existing forward Euler scheme for determining the conditions of getting the positive solution.The establishedscheme also has an advantage over existing non-standard finite difference methods in terms of order of accuracy.The stability of the scheme for the considered fuzzy model is also provided.From the plotted results,it can beobserved that susceptible people decay by rising interaction parameters.

Mathematical Model and Geometrical Model of Double Pitch ZN-type Worm Gear Set Based on Generation Mechanism

The current researches on the tooth surface mathematical equations and the theory of gearing mainly pay attention to the ordinary type worm gear set（e.g., ZN, ZA, or ZK）. The research of forming mechanism and three-dimensional modeling method for the double pitch worm gear set is not enough. So there are some difficulties in mathematical model deducing and geometry modeling of double pitch ZN-type worm gear set based on generation mechanism. In order to establish the mathematical model and the precise geometric model of double pitch ZN-type worm gear set, the structural characteristics and generation mechanism of the double pitch ZN-type worm gear set are investigated. Mathematical model of the ZN-type worm gear set is derived based on its generation mechanism and the theory of gearing. According to the mathematical model of the worm gear set which has been developed, a geometry modeling method of the double pitch ZN-type worm and worm gear is presented. Furthermore, a geometrical precision calculate method is proposed to evaluate the geometrical quality of the double pitch worm gear set. As a result, the maximum error is less than 6′10–4 mm in magnitude, thus the model of the double pitch ZN-type worm gear set is available to meet the requirements of finite element analysis and engineering application. The derived mathematical model and the proposed geometrical modeling method are helpful to guiding the design, manufacture and contact analysis of the worm gear set.

Forecasting method of monthly wind power generation based on climate model and long short-term memory neural network

Predicting wind power gen eration over the medium and long term is helpful for dispatchi ng departme nts,as it aids in constructing generation plans and electricity market transactions.This study presents a monthly wind power gen eration forecast!ng method based on a climate model and long short-term memory(LSTM)n eural n etwork.A non linear mappi ng model is established between the meteorological elements and wind power monthly utilization hours.After considering the meteorological data(as predicted for the future)and new installed capacity planning,the monthly wind power gen eration forecast results are output.A case study shows the effectiveness of the prediction method.

Uncertain Multidisciplinary Design Optimization on Next Generation Subsea Production System by Using Surrogate Model and Interval Method

The innovative Next Generation Subsea Production System(NextGen SPS)concept is a newly proposed petroleum development solution in ultra-deep water areas.The definition of NextGen SPS involves several disciplines,which makes the design process difficult.In this paper,the definition of NextGen SPS is modeled as an uncertain multidisciplinary design optimization(MDO)problem.The deterministic optimization model is formulated,and three concerning disciplines—cost calculation,hydrodynamic analysis and global performance analysis are presented.Surrogate model technique is applied in the latter two disciplines.Collaborative optimization(CO)architecture is utilized to organize the concerning disciplines.A deterministic CO framework with two disciplinelevel optimizations is proposed firstly.Then the uncertainties of design parameters and surrogate models are incorporated by using interval method,and uncertain CO frameworks with triple loop and double loop optimization structure are established respectively.The optimization results illustrate that,although the deterministic MDO result achieves higher reduction in objective function than the uncertain MDO result,the latter is more reliable than the former.

A Simplified Model for SO_(2) Generation during Spontaneous Combustion of Coal Gangue

A simplified model for SO_(2) generation during spontaneous combustion of coal gangue was put forward and validated using the measured data.Using the proposed model,the effects of initial temperature inside the gangue and fresh air supply on SO_(2) generation were discussed.The results showed that,higher initial temperature inside the gangue could accelerate the oxidation rate of FeS_(2) and increase the maximum concentration of SO_(2).If initial temperature inside the gangue increased by about 37%,the total SO_(2) generation increased by 166%.Fresh air supply had less significant effect on the oxidation rate of FeS_(2).However,the higher the fresh air supply was,the more FeS_(2) could be oxidized,which ultimately produced more SO_(2).Although the computed results and the measured data concerning the inner locations inside the gangue had a certain degree of error,the proposed model can provide a relatively precise total release of SO_(2) within acceptable accuracy.Besides,this method provides a useful prototype to predict the generation of hazardous materials,such as CO,NO_(x),and chlorine during the spontaneous combustion of coal gangue.

Low organic matter abundance and highly efficient hydrocarbon generation of saline source rock in the Qaidam Basin,NW China

The geochemical analysis and experimental simulation are comprehensively used to systematically study the hydrocarbon generation material,organic matter enrichment and hydrocarbon generation model of Paleogene source rock in the Western Qaidam Depression,Qaidam Basin,NW China.Three main factors result in low TOC values of saline lacustrine source rock of the Qaidam Basin:relatively poor nutrient supply inhibits the algal bloom,too fast deposition rate causes the dilution of organic matter,and high organic matter conversion efficiency causes the low residual organic carbon.For this type of hydrogen-rich organic matter,due to the reduction of organic carbon during hydrocarbon generation,TOC needs to be restored based on maturity before evaluating organic matter abundance.The hydrocarbon generation of saline lacustrine source rocks of the Qaidam Basin is from two parts:soluble organic matter and insoluble organic matter.The soluble organic matter is inherited from organisms and preserved in saline lacustrine basins.It generates hydrocarbons during low-maturity stage,and the formed hydrocarbons are rich in complex compounds such as NOS,and undergo secondary cracking to form light components in the later stage;the hydrocarbon generation model of insoluble organic matter conforms to the traditional“Tissot”model,with an oil generation peak corresponding to Ro of 1.0%.

Identification of Type of a Fault in Distribution System Using Shallow Neural Network with Distributed Generation

A distributed generation system(DG)has several benefits over a traditional centralized power system.However,the protection area in the case of the distributed generator requires special attention as it encounters stability loss,failure re-closure,fluctuations in voltage,etc.And thereby,it demands immediate attention in identifying the location&type of a fault without delay especially when occurred in a small,distributed generation system,as it would adversely affect the overall system and its operation.In the past,several methods were proposed for classification and localisation of a fault in a distributed generation system.Many of those methods were accurate in identifying location,but the accuracy in identifying the type of fault was not up to the acceptable mark.The proposed work here uses a shallow artificial neural network(sANN)model for identifying a particular type of fault that could happen in a specific distribution network when used in conjunction with distributed generators.Firstly,a distribution network consisting of two similar distributed generators(DG1 and DG2),one grid,and a 100 Km distribution line is modeled.Thereafter,different voltages and currents corresponding to various faults(line to line,line to ground)at different locations are tabulated,resulting in a matrix of 500×18 inputs.Secondly,the sANN is formulated for identifying the types of faults in the system in which the above-obtained data is used to train,validate,and test the neural network.The overall result shows an unprecedented almost zero percent error in identifying the type of the faults.

Low-order harmonic generation of hydrogen molecular ion in laser field studied by the two-state model

The low-order harmonic generation of hydrogen molecular ion interacting with a linearly polarized laser field has been investigated theoretically by using a simple two-state model. The validity of the two-state model is carefully examined by comparing the harmonic spectra of hydrogen molecular ion obtained from this model with those from the three-dimensional time-dependent Schr¨odinger equation. When combined with the Morlet transform of quantum time-frequency spectrum,the two-state model can be used to study the dynamical origin of the low-order harmonic generation of hydrogen molecular ion driven by low-frequency pulses. In addition, some interesting structures of the time profiles for low order harmonics are obtained.

Automatic Generation Method of Geological Cross-Sections in Dredging Engineering Based on 3D Solid NURBS Models

An automatic generation method of geological cross-sections in dredging engineering based on 3D geological solid models is presented.The 3D geological models are built applying the non-uniform rational B-splines(NURBS) technique,and a 2D profile can be calculated and generated automatically through Boolean operation to meet the demands of dredging projects.Moreover,an automatic marking method for geological attributes is put forward based on database technology,and the geological attributes include the profile name,scale,horizontal and vertical relative coordinates,geological lithology,and 2D standard lithology legend.At the same time,the automatic marking method can also provide an interactive mode for geological engineers to edit and modify the profile in the modeling system.Practical engineering applications show that the automatic generation method is a simple,flexible,fast and precise visual graphics rendering process that can create 2D standard profiles automatically and efficiently.This method also provides a convenient support tool for geological engineering digital analysis.

Weis-Fogh Mechanism Mathematic Model of Wave Power Generation Device

A Weis-Fogh mechanism wave power generation system is designed, its physical model and mathematical model are discussed, and the component expressions of fluid dynamic expression are derived. Adopting numerical integral algorithm, the work done by fluid force acting on wing is calculated.

Generation Model of Particle Physics with Excited Rishon States

It is proposed that the Generation Model (GM) of particle physics, which describes the elementary particles, the six leptons, the six quarks and the three weak bosons, of the Standard Model (SM) as composite particles in terms of three kinds of rishons and their antiparticles may be mimicking a simpler model, employing only two kinds of rishons and their antiparticles.

AI-infused Semantic Model to Enrich and Expand Programming Question Generation

Creating practice questions for programming learning is not easy.It requires the instructor to diligently organize heterogeneous learning resources,that is,conceptual programming concepts and procedural programming rules.Today’s programming question generation(PQG)is still largely relying on the demanding creation task performed by the instructors without advanced technological support.In this work,we propose a semantic PQG model that aims to help the instructor generate new programming questions and expand the assessment items.The PQG model is designed to transform conceptual and procedural programming knowledge from textbooks into a semantic network by the Local Knowledge Graph(LKG)and Abstract Syntax Tree(AST).For any given question,the model queries the established network to find related code examples and generates a set of questions by the associated LKG/AST semantic structures.We conduct analysis to compare instructor-made questions from 9 undergraduate introductory programming courses and textbook questions.The results show that the instructormade questions had much simpler complexity than the textbook ones.The disparity of topic distribution intrigued us to further research the breadth and depth of question quality and also to investigate the complexity of the questions in relation to the student performances.Finally,we report a user study results on the proposed Artificial Intelligent-infused semantic PQG model in examining the machine-generated questions’quality.

Understanding Credit Risk in Internet Consumer Finance:An Empirical Analysis with a Focus on the Young Generation

In recent years,internet finance has garnered increasing attention from the public.Online lending,emerging within the framework of Internet finance as a pivotal component,has witnessed substantial growth.While online credit,within the realm of Internet finance,presents numerous advantages over traditional lending,it concurrently exposes a plethora of credit risk issues.This study aims to facilitate the effective utilization of online credit tools by the young generation within the context of Internet finance.Additionally,it seeks to ensure the overall stability of the Internet finance environment and mitigate risks for the youth.Given the significance of understanding credit risk management for college students in the age of internet finance,this paper adopts the logistic model to evaluate credit risk in internet consumer finance and provides pertinent recommendations from the perspective of the young generation.