Pub Date : 1900-01-01DOI: 10.5220/0008849700260031
Qianqian Zhu, Hang Li, Weiming Guo
With the increase of vehicle ownership in China, the number of auto insurance cases is also increasing. The detection and direction determination of vehicles involved in auto insurance cases have important applications in the field of intelligent loss assessment. In this paper, a model of vehicle detection and direction determination based on ResNet-101+FPN backbone network and RetinaNet is built by using convolutional neural network in deep learning. Then, the model is trained and tested on the labelled data set. The model has a relatively high accuracy of prediction, in which the accuracy of vehicle detection reaches 98.7%, and the accuracy of the five directions determination of frontal, lateral-frontal, lateral, lateral-back and back reaches 97.2%.
{"title":"Research on Vehicle Detection and Direction Determination based on Deep Learning","authors":"Qianqian Zhu, Hang Li, Weiming Guo","doi":"10.5220/0008849700260031","DOIUrl":"https://doi.org/10.5220/0008849700260031","url":null,"abstract":"With the increase of vehicle ownership in China, the number of auto insurance cases is also increasing. The detection and direction determination of vehicles involved in auto insurance cases have important applications in the field of intelligent loss assessment. In this paper, a model of vehicle detection and direction determination based on ResNet-101+FPN backbone network and RetinaNet is built by using convolutional neural network in deep learning. Then, the model is trained and tested on the labelled data set. The model has a relatively high accuracy of prediction, in which the accuracy of vehicle detection reaches 98.7%, and the accuracy of the five directions determination of frontal, lateral-frontal, lateral, lateral-back and back reaches 97.2%.","PeriodicalId":186406,"journal":{"name":"Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117113054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.5220/0008480803290335
Jiman Luo, L. Dai
In order to control the new pipe dredging robot more accurately and ensure the stable operation of the robot in the harsh environment, the motion control system of the robot is designed and the PI algorithm based on double closed-loop speed control system for walking unit of wheeled mechanism is studied. According to the Simulations by Simulink and experimentations of the above control methods, it was indicated that the motor speed can be stabilized at the set speed value under the disturbance of load change, and the dynamic performance is also stable. Finally, a double closed-loop speed control system with strong anti-load fluctuation capability is adopted. The control method satisfied the requirements of the working condition of the robot in a complex environment and realized that the precise control of the motion state of the robot.
{"title":"The Research on Control System of Pipeline Dredging Robot based on Simulink","authors":"Jiman Luo, L. Dai","doi":"10.5220/0008480803290335","DOIUrl":"https://doi.org/10.5220/0008480803290335","url":null,"abstract":"In order to control the new pipe dredging robot more accurately and ensure the stable operation of the robot in the harsh environment, the motion control system of the robot is designed and the PI algorithm based on double closed-loop speed control system for walking unit of wheeled mechanism is studied. According to the Simulations by Simulink and experimentations of the above control methods, it was indicated that the motor speed can be stabilized at the set speed value under the disturbance of load change, and the dynamic performance is also stable. Finally, a double closed-loop speed control system with strong anti-load fluctuation capability is adopted. The control method satisfied the requirements of the working condition of the robot in a complex environment and realized that the precise control of the motion state of the robot.","PeriodicalId":186406,"journal":{"name":"Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130020386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.5220/0008848801550164
Chao Chen, Ziji’an Wang, Mei Han
Permitted height of combined center of gravity for railroad cars in China is studied. This study establishes a MBS model of the railroad freight car, and then validates the model. Orthogonal experiment method is used to find the worst operating condition. The factors’ levels are determined and used for designing orthogonal experiment schemes. Extensive simulations are performed for the schemes. Statistics analysis is applied to simulation results. The worst operating conditions for Grade I and III railroad are derived from objective analysis. Based on the worst operating conditions, the permitted height of combined center of gravity for railroad cars can be increased to 2500mm. The influence degree of each factor is derived by variance analysis. Factor B is a significant factor for derailment coefficient, factor A and factor C have little effect on derailment coefficient. But the three factors are significant factors for wheel unloading rate.
{"title":"Research on the Permitted Height of Combined Center of Gravity for Railroad Cars","authors":"Chao Chen, Ziji’an Wang, Mei Han","doi":"10.5220/0008848801550164","DOIUrl":"https://doi.org/10.5220/0008848801550164","url":null,"abstract":"Permitted height of combined center of gravity for railroad cars in China is studied. This study establishes a MBS model of the railroad freight car, and then validates the model. Orthogonal experiment method is used to find the worst operating condition. The factors’ levels are determined and used for designing orthogonal experiment schemes. Extensive simulations are performed for the schemes. Statistics analysis is applied to simulation results. The worst operating conditions for Grade I and III railroad are derived from objective analysis. Based on the worst operating conditions, the permitted height of combined center of gravity for railroad cars can be increased to 2500mm. The influence degree of each factor is derived by variance analysis. Factor B is a significant factor for derailment coefficient, factor A and factor C have little effect on derailment coefficient. But the three factors are significant factors for wheel unloading rate.","PeriodicalId":186406,"journal":{"name":"Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering","volume":"305 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132943178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.5220/0008870401020107
Ziyu Zheng
The noise caused by the vibration of the car body will reduce the comfort of the car. In order to reduce the indoor noise, through the experimental modal analysis of the cab, the change of natural frequency and basic mode of vibration is obtained. It is found that when the frequency is 120.44 Hz, the cab noise has the greatest impact. Through symplectic geometric analysis and panel acoustic contribution analysis, it is found that the cab panel has the greatest influence on the sound pressure near the ear of the roof driver. In order to solve the above problems, the noise reduction method of the cab roof using stiffened panels and the sound radiation theory is used to simulate the noise reduction effect of the improved cab. It is found that the sound pressure of the improved cab is significantly reduced, the low-frequency noise is effectively suppressed, and the comfort of the car is improved.
{"title":"Design and Simulation of Vehicle Cab Noise Reduction based on Symplectic Geometry Method","authors":"Ziyu Zheng","doi":"10.5220/0008870401020107","DOIUrl":"https://doi.org/10.5220/0008870401020107","url":null,"abstract":"The noise caused by the vibration of the car body will reduce the comfort of the car. In order to reduce the indoor noise, through the experimental modal analysis of the cab, the change of natural frequency and basic mode of vibration is obtained. It is found that when the frequency is 120.44 Hz, the cab noise has the greatest impact. Through symplectic geometric analysis and panel acoustic contribution analysis, it is found that the cab panel has the greatest influence on the sound pressure near the ear of the roof driver. In order to solve the above problems, the noise reduction method of the cab roof using stiffened panels and the sound radiation theory is used to simulate the noise reduction effect of the improved cab. It is found that the sound pressure of the improved cab is significantly reduced, the low-frequency noise is effectively suppressed, and the comfort of the car is improved.","PeriodicalId":186406,"journal":{"name":"Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126361960","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.5220/0008868300700077
Huilai Sun, Liu Pengbo, Yong Wang, Song Yuanyuan, Li Zeying, Yao Guoming
: Aiming at the special structure and steering characteristic of wheeled electric-driven articulated underground mining truck, a differential control strategy which takes the equal slip rate as control target was given. The kinematic and dynamic model of electric-driven mining ADT was established and the movement relationship and stress condition of the driving wheels were analyzed during steering. Acceleration sensors in the sample ADT were used to test the actual speed of the vehicle. Results show that the filtered signal has small delay and fast response and can be directly used to estimate the speed. Equal slip rate control strategy is superior to equal torque control strategy because it can make full use of the ground adhesion coefficient and reach reasonable distribution of drive power. Two sides wheel slip rate can be stable -0.08 and sliping situation is avoided in experimental turning. This control strategy has practical effect for reducing tire wear and improving driving power utilization.
{"title":"Differential Control Strategy Research of Wheeled Electric Drive ADT Mining Truck","authors":"Huilai Sun, Liu Pengbo, Yong Wang, Song Yuanyuan, Li Zeying, Yao Guoming","doi":"10.5220/0008868300700077","DOIUrl":"https://doi.org/10.5220/0008868300700077","url":null,"abstract":": Aiming at the special structure and steering characteristic of wheeled electric-driven articulated underground mining truck, a differential control strategy which takes the equal slip rate as control target was given. The kinematic and dynamic model of electric-driven mining ADT was established and the movement relationship and stress condition of the driving wheels were analyzed during steering. Acceleration sensors in the sample ADT were used to test the actual speed of the vehicle. Results show that the filtered signal has small delay and fast response and can be directly used to estimate the speed. Equal slip rate control strategy is superior to equal torque control strategy because it can make full use of the ground adhesion coefficient and reach reasonable distribution of drive power. Two sides wheel slip rate can be stable -0.08 and sliping situation is avoided in experimental turning. This control strategy has practical effect for reducing tire wear and improving driving power utilization.","PeriodicalId":186406,"journal":{"name":"Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121448329","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.5220/0008387703230328
Hesong Xia, Jie Ma
: Stable platform has been widely used in modern weapons and civil equipment due to its ability to isolate carrier interference, and research on key technologies for stable platforms has very important practical significance and application value. In this paper, the three-axis stabilized platform is taken as the research object. A control system based on multi-loop control structure is designed around the mathematical model of DC torque motor. The design and implementation of servo control system are carried out by using classical PID and BP neural network PID control algorithm respectively. The BP neural network PID control algorithm is verified by MATLAB simulation. Compared with classical PID control algorithm, it has higher control precision and anti-interference ability.
{"title":"BP Neural Network PID Control of Stable Platform","authors":"Hesong Xia, Jie Ma","doi":"10.5220/0008387703230328","DOIUrl":"https://doi.org/10.5220/0008387703230328","url":null,"abstract":": Stable platform has been widely used in modern weapons and civil equipment due to its ability to isolate carrier interference, and research on key technologies for stable platforms has very important practical significance and application value. In this paper, the three-axis stabilized platform is taken as the research object. A control system based on multi-loop control structure is designed around the mathematical model of DC torque motor. The design and implementation of servo control system are carried out by using classical PID and BP neural network PID control algorithm respectively. The BP neural network PID control algorithm is verified by MATLAB simulation. Compared with classical PID control algorithm, it has higher control precision and anti-interference ability.","PeriodicalId":186406,"journal":{"name":"Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering","volume":"38 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121013450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.5220/0008868704160420
Hanghang Qu, Jie Zeng, Ranran Sheng, Yongwei Guo
Abstract: Relative to traditional methods of back-EMF zero crossing points (ZCPs) delay detect, a new method to detect the rotor position of BLDCM is proposed by constructing a state observer to estimate line back-EMF based on line voltage and line current in this paper.And improve the observer, the linear error function is added to the original nonlinear error feedback coefficient of the observer. The combination of the two functions helps accelerate the convergence of the observer and improve the stability of the observer.In order to make its rotate speed more stable, the fuzzy PID is used to replace the traditional PID for the outer ring of the rotate speed.Finally, the simulation results show that this method can accurately estimate the position information of the rotor. With the help of the fuzzy PID control method, the precise control of BLDCM can be realized in a wide speed range.
{"title":"Research on Sensorless Fuzzy PID Control of BDCM based on Improved State Observer","authors":"Hanghang Qu, Jie Zeng, Ranran Sheng, Yongwei Guo","doi":"10.5220/0008868704160420","DOIUrl":"https://doi.org/10.5220/0008868704160420","url":null,"abstract":"Abstract: Relative to traditional methods of back-EMF zero crossing points (ZCPs) delay detect, a new method to detect the rotor position of BLDCM is proposed by constructing a state observer to estimate line back-EMF based on line voltage and line current in this paper.And improve the observer, the linear error function is added to the original nonlinear error feedback coefficient of the observer. The combination of the two functions helps accelerate the convergence of the observer and improve the stability of the observer.In order to make its rotate speed more stable, the fuzzy PID is used to replace the traditional PID for the outer ring of the rotate speed.Finally, the simulation results show that this method can accurately estimate the position information of the rotor. With the help of the fuzzy PID control method, the precise control of BLDCM can be realized in a wide speed range.","PeriodicalId":186406,"journal":{"name":"Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116733837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.5220/0008872201080113
Zhenzheng Yan, Jihui Zhuang, Xiaoming Cheng, Ying Yan
Driving cycles are an important means for new vehicle technology development and emission prediction and evaluation. To establish a representative driving cycle for urban buses in Haikou city, in this paper, the principal component analysis (PCA) and DBSCAN cluster algorithm are applied to develop the driving cycle. Firstly, a large number of vehicle driving data are collected, which comprised of 12 characteristic parameters. Next, the PCA is employed to extract main components from the characteristic parameters of driving data and the DBSCAN cluster is used to select representative micro trips. Subsequently, several most representative micro-trips were picked out to form the driving cycle. The effectiveness and uniqueness of the developed driving cycle are verified via comparing the parameters with the real-world driving data and the existing driving cycles, respectively.
{"title":"Driving Cycle Development for Urban Bus using Principal Component Analysis and DBSCAN Clustering: With the Case of Haikou, China","authors":"Zhenzheng Yan, Jihui Zhuang, Xiaoming Cheng, Ying Yan","doi":"10.5220/0008872201080113","DOIUrl":"https://doi.org/10.5220/0008872201080113","url":null,"abstract":"Driving cycles are an important means for new vehicle technology development and emission prediction and evaluation. To establish a representative driving cycle for urban buses in Haikou city, in this paper, the principal component analysis (PCA) and DBSCAN cluster algorithm are applied to develop the driving cycle. Firstly, a large number of vehicle driving data are collected, which comprised of 12 characteristic parameters. Next, the PCA is employed to extract main components from the characteristic parameters of driving data and the DBSCAN cluster is used to select representative micro trips. Subsequently, several most representative micro-trips were picked out to form the driving cycle. The effectiveness and uniqueness of the developed driving cycle are verified via comparing the parameters with the real-world driving data and the existing driving cycles, respectively.","PeriodicalId":186406,"journal":{"name":"Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123856204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.5220/0008386103060309
Xiao-bing Han, S. Huang, Xiaohong Wang, Y. Ma
: This paper uses Altera's 5CSEMA5F31C6N chip to realize the hardware circuit description of the traffic light system controller through VHDL language. It is compiled, simulated and downloaded to the FPGA device for programming in Altera's EDA software platform Quartusii environment. The control process of the traffic light system.
{"title":"Design of Traffic Light based on FPGA","authors":"Xiao-bing Han, S. Huang, Xiaohong Wang, Y. Ma","doi":"10.5220/0008386103060309","DOIUrl":"https://doi.org/10.5220/0008386103060309","url":null,"abstract":": This paper uses Altera's 5CSEMA5F31C6N chip to realize the hardware circuit description of the traffic light system controller through VHDL language. It is compiled, simulated and downloaded to the FPGA device for programming in Altera's EDA software platform Quartusii environment. The control process of the traffic light system.","PeriodicalId":186406,"journal":{"name":"Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131137436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.5220/0008874204610466
Ruifang Wang, Xiaoyu Lan
Tracking a moving speech source in non-Gaussian noise environments is a challenging problem. A speech source tracking method based on the particle filter (PF) and the generalized correntropy function (GCTF) in non-Gaussian noise and reverberant environments is proposed in the paper. Multiple TDOAs are estimated by the GCTF and the multiple-hypothesis likelihood is calculated as weights for the PF. Next, predict the particles from the Langevin model for the PF. Finally, the global position of moving speech source is estimated in term of representation of weighted particles. Simulation results demonstrate the vadility of the proposed method.
{"title":"Speech Source Tracking based on Particle Filter under non-Gaussian Noise and Reverberant Environments","authors":"Ruifang Wang, Xiaoyu Lan","doi":"10.5220/0008874204610466","DOIUrl":"https://doi.org/10.5220/0008874204610466","url":null,"abstract":"Tracking a moving speech source in non-Gaussian noise environments is a challenging problem. A speech source tracking method based on the particle filter (PF) and the generalized correntropy function (GCTF) in non-Gaussian noise and reverberant environments is proposed in the paper. Multiple TDOAs are estimated by the GCTF and the multiple-hypothesis likelihood is calculated as weights for the PF. Next, predict the particles from the Langevin model for the PF. Finally, the global position of moving speech source is estimated in term of representation of weighted particles. Simulation results demonstrate the vadility of the proposed method.","PeriodicalId":186406,"journal":{"name":"Proceedings of 5th International Conference on Vehicle, Mechanical and Electrical Engineering","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133147979","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：