Pub Date : 2022-06-23DOI: 10.1109/wsai55384.2022.9836349
Tingting Sun, Kai Yan, Tingwei Li, Xiaoqian Lu, Oian Dona
E-learning is an important part of the library service and a direction of transformation for libraries. How to ensure the security of e-learning platforms is a key point that cannot be ignored in the construction. Although machine learning has been widely used in network anomaly detection, traditional machine learning methods have problems such as over-reliance on manual feature extraction, dimension disaster, etc., and it is difficult to achieve effective prediction of potential threats in practical applications. To solve these problems, this paper proposes a network anomaly intrusion detection method based on ensemble learning to effectively ensure the network security of the e-learning platform. Combined with the concept of ensemble learning, simple decision tree is used as the base class learner, and by combining multiple models into a stronger model, the random forest method is used to improve the ability to identify anomaly network attacks. After experimental verification, various performance evaluation indicators and ROC curves of the experimental results show that the algorithm can effectively identify both normal network access and abnormal network access. Therefore, this method can be applied to the library e-learning platform, which can provide learners with rich and convenient online learning services, and at the same time effectively ensure the network security of the platform.
{"title":"A Network Anomaly Intrusion Detection Method Based on Ensemble Learning for Library e-Learning Platform","authors":"Tingting Sun, Kai Yan, Tingwei Li, Xiaoqian Lu, Oian Dona","doi":"10.1109/wsai55384.2022.9836349","DOIUrl":"https://doi.org/10.1109/wsai55384.2022.9836349","url":null,"abstract":"E-learning is an important part of the library service and a direction of transformation for libraries. How to ensure the security of e-learning platforms is a key point that cannot be ignored in the construction. Although machine learning has been widely used in network anomaly detection, traditional machine learning methods have problems such as over-reliance on manual feature extraction, dimension disaster, etc., and it is difficult to achieve effective prediction of potential threats in practical applications. To solve these problems, this paper proposes a network anomaly intrusion detection method based on ensemble learning to effectively ensure the network security of the e-learning platform. Combined with the concept of ensemble learning, simple decision tree is used as the base class learner, and by combining multiple models into a stronger model, the random forest method is used to improve the ability to identify anomaly network attacks. After experimental verification, various performance evaluation indicators and ROC curves of the experimental results show that the algorithm can effectively identify both normal network access and abnormal network access. Therefore, this method can be applied to the library e-learning platform, which can provide learners with rich and convenient online learning services, and at the same time effectively ensure the network security of the platform.","PeriodicalId":402449,"journal":{"name":"2022 4th World Symposium on Artificial Intelligence (WSAI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129363445","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 : 2022-06-23DOI: 10.1109/wsai55384.2022.9836368
Ying H. Cao
The improvement of teaching quality is an essential part of modernization of Chinese education, and the scientific, rational and timely improvement of teaching effectiveness assessment plays a key role. The improvement of scientific and timely teaching effectiveness evaluation plays a key role. This paper takes artificial intelligence technology as the leading to address the problem of low accuracy of university English teaching effectiveness evaluation, a evaluation method based on IGA-WNN is proposed. Firstly, an English course teaching evaluation system was established according to the actual teaching situation, and the entropy method (EM) was used to assign weights to the original teaching evaluation effect data, then an English course teaching evaluation model was designed based on wavelet neural network, and an improved genetic algorithm was studied to optimize the wavelet neural network parameters. The experimental results show that the method can evaluate the quality of English teaching more accurately and has a good educational support function.
{"title":"A Neural Network Optimization Model-Based Approach to Evaluate the Teaching Effectiveness of English Courses","authors":"Ying H. Cao","doi":"10.1109/wsai55384.2022.9836368","DOIUrl":"https://doi.org/10.1109/wsai55384.2022.9836368","url":null,"abstract":"The improvement of teaching quality is an essential part of modernization of Chinese education, and the scientific, rational and timely improvement of teaching effectiveness assessment plays a key role. The improvement of scientific and timely teaching effectiveness evaluation plays a key role. This paper takes artificial intelligence technology as the leading to address the problem of low accuracy of university English teaching effectiveness evaluation, a evaluation method based on IGA-WNN is proposed. Firstly, an English course teaching evaluation system was established according to the actual teaching situation, and the entropy method (EM) was used to assign weights to the original teaching evaluation effect data, then an English course teaching evaluation model was designed based on wavelet neural network, and an improved genetic algorithm was studied to optimize the wavelet neural network parameters. The experimental results show that the method can evaluate the quality of English teaching more accurately and has a good educational support function.","PeriodicalId":402449,"journal":{"name":"2022 4th World Symposium on Artificial Intelligence (WSAI)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126544571","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 : 2022-06-23DOI: 10.1109/wsai55384.2022.9836396
Wang Yuxiang, Maogen Fu
Self-driving technology has been studied and developed for a long time and gradually tends to mature. However, we want to complete the fully self-driving under the smart city, whether in self-driving cars or uncrewed express vehicles and other vehicles. However, there are still many problems with traffic command and vehicle interworking during the car's driving. In this article, based on the two problems mentioned above, the authors improve the existing self-driving algorithm from these two aspects. On the one hand, the authors use the OpenPose to deal with 3-D motion and gestures and experiment on static images and static video of traffic gestures, the model can accurately segment various traffic information including traffic indication gestures in the target, and give feedback based on the set priority. On the other hand, by simulating vehicle information experiments, the algorithm can process nearby information and makes corresponding pre-processing according to the processing results. These two improvements not only make the existing self-driving algorithm more perfect but also make the surrounding road condition information predictable, which means that the self-driving technology becomes more flexible and safer.
{"title":"Improvement of Self-Driving Algorithm with Traffic Command Recognition and Vehicle Information Interaction","authors":"Wang Yuxiang, Maogen Fu","doi":"10.1109/wsai55384.2022.9836396","DOIUrl":"https://doi.org/10.1109/wsai55384.2022.9836396","url":null,"abstract":"Self-driving technology has been studied and developed for a long time and gradually tends to mature. However, we want to complete the fully self-driving under the smart city, whether in self-driving cars or uncrewed express vehicles and other vehicles. However, there are still many problems with traffic command and vehicle interworking during the car's driving. In this article, based on the two problems mentioned above, the authors improve the existing self-driving algorithm from these two aspects. On the one hand, the authors use the OpenPose to deal with 3-D motion and gestures and experiment on static images and static video of traffic gestures, the model can accurately segment various traffic information including traffic indication gestures in the target, and give feedback based on the set priority. On the other hand, by simulating vehicle information experiments, the algorithm can process nearby information and makes corresponding pre-processing according to the processing results. These two improvements not only make the existing self-driving algorithm more perfect but also make the surrounding road condition information predictable, which means that the self-driving technology becomes more flexible and safer.","PeriodicalId":402449,"journal":{"name":"2022 4th World Symposium on Artificial Intelligence (WSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129912888","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 : 2022-06-23DOI: 10.1109/wsai55384.2022.9836403
Chunan Luo, Yong Wu, Shaofang Li, Chu-guang Liang
Artificial intelligence is one of the most disruptive science and technologies at present, with strong processing capabilities in computational intelligence, perceptual intelligence and cognitive intelligence. This paper expounds two applications of artificial intelligence in the mechanized construction of power grid engineering, namely the application of BIM building model and BP neural network in emergency rescue of mechanized construction, and the application of artificial intelligence in the positioning and sway prevention of tower cranes. The application of artificial intelligence in the mechanized construction of power grid projects improves the rescue work of rescuers, ensures the personal safety of construction workers, and enables tower cranes to quickly locate and eliminate swings. The corresponding links of its application are described in detail in this paper.
{"title":"Application of Artificial Intelligence in Mechanized Construction of Power Grid Engineering","authors":"Chunan Luo, Yong Wu, Shaofang Li, Chu-guang Liang","doi":"10.1109/wsai55384.2022.9836403","DOIUrl":"https://doi.org/10.1109/wsai55384.2022.9836403","url":null,"abstract":"Artificial intelligence is one of the most disruptive science and technologies at present, with strong processing capabilities in computational intelligence, perceptual intelligence and cognitive intelligence. This paper expounds two applications of artificial intelligence in the mechanized construction of power grid engineering, namely the application of BIM building model and BP neural network in emergency rescue of mechanized construction, and the application of artificial intelligence in the positioning and sway prevention of tower cranes. The application of artificial intelligence in the mechanized construction of power grid projects improves the rescue work of rescuers, ensures the personal safety of construction workers, and enables tower cranes to quickly locate and eliminate swings. The corresponding links of its application are described in detail in this paper.","PeriodicalId":402449,"journal":{"name":"2022 4th World Symposium on Artificial Intelligence (WSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125444376","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}
During the acceleration of the vehicle, the oil sensor will generate violent vibration, which will affect its measurement accuracy. For the vibration problem of the oil sensor, a vibration isolation device is proposed to achieve the purpose of vibration isolation. To this end, this paper takes the oil-liquid sensor vibration isolation device as the research object, establishes a two-dimensional CFD simulation model with the help of Fluent software, and studies the influence of different damping media and spring stiffness on the oil-liquid sensor integration device. The results show that the use of a spring with a stiffness coefficient of 1500N/m in the horizontal direction, a spring with a stiffness coefficient of 3000N/m in the vertical direction and diesel oil or kerosene as the damping medium can effectively improve the vibration isolation effect of the vibration isolation system for the oil-hydraulic sensor, reduce the data acquisition error caused by severe vibration, and provide a theoretical basis for the optimal design of the vibration isolation system for the oil-hydraulic sensor.
{"title":"Vehicle Oil Sensor Vibration Isolation Technology Research","authors":"Hua Yang, M. Wang, Jing Tian, Hanqing Huang, Yunti Liu, Jibin Zhao, Lunming Huang","doi":"10.1109/wsai55384.2022.9836550","DOIUrl":"https://doi.org/10.1109/wsai55384.2022.9836550","url":null,"abstract":"During the acceleration of the vehicle, the oil sensor will generate violent vibration, which will affect its measurement accuracy. For the vibration problem of the oil sensor, a vibration isolation device is proposed to achieve the purpose of vibration isolation. To this end, this paper takes the oil-liquid sensor vibration isolation device as the research object, establishes a two-dimensional CFD simulation model with the help of Fluent software, and studies the influence of different damping media and spring stiffness on the oil-liquid sensor integration device. The results show that the use of a spring with a stiffness coefficient of 1500N/m in the horizontal direction, a spring with a stiffness coefficient of 3000N/m in the vertical direction and diesel oil or kerosene as the damping medium can effectively improve the vibration isolation effect of the vibration isolation system for the oil-hydraulic sensor, reduce the data acquisition error caused by severe vibration, and provide a theoretical basis for the optimal design of the vibration isolation system for the oil-hydraulic sensor.","PeriodicalId":402449,"journal":{"name":"2022 4th World Symposium on Artificial Intelligence (WSAI)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129522236","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 : 2022-06-23DOI: 10.1109/wsai55384.2022.9836376
Xiaoxiong Lu, J. Zhang, Kai Chen, Di Ma, Yingmei Zhang, Y. Wan
In order to solve the common problems such as low efficiency, heavy labor consumption, incomplete inspection existing in the operation and maintenance of traditional power equipment and improve the overall operation and application efficiency, this work presents a kind of wearable metering device based inspection method of the augmented reality system consists of wearable smart augmented reality glasses, used for taking pictures, recording, scanning the bar code for data information acquisition, and selectively through gestures or voice operation real-time display the required information. The collected data is sent to the intelligent mobile terminal through wireless transmission. Eventually, the system can realize the display of login interface and function menu interface, voice recognition and gesture recognition function, and work order acquisition and feedback. We provide experiments to show the superiority of the system designed in this work in meter reading and accounting tasks and real-time response.
{"title":"Efficiency and Safety Improvement of Power Equipment Smart Inspection and Operation via Augmented Reality Glasses based on AI Technology","authors":"Xiaoxiong Lu, J. Zhang, Kai Chen, Di Ma, Yingmei Zhang, Y. Wan","doi":"10.1109/wsai55384.2022.9836376","DOIUrl":"https://doi.org/10.1109/wsai55384.2022.9836376","url":null,"abstract":"In order to solve the common problems such as low efficiency, heavy labor consumption, incomplete inspection existing in the operation and maintenance of traditional power equipment and improve the overall operation and application efficiency, this work presents a kind of wearable metering device based inspection method of the augmented reality system consists of wearable smart augmented reality glasses, used for taking pictures, recording, scanning the bar code for data information acquisition, and selectively through gestures or voice operation real-time display the required information. The collected data is sent to the intelligent mobile terminal through wireless transmission. Eventually, the system can realize the display of login interface and function menu interface, voice recognition and gesture recognition function, and work order acquisition and feedback. We provide experiments to show the superiority of the system designed in this work in meter reading and accounting tasks and real-time response.","PeriodicalId":402449,"journal":{"name":"2022 4th World Symposium on Artificial Intelligence (WSAI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129754527","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 : 2022-06-23DOI: 10.1109/wsai55384.2022.9836345
{"title":"2022 the 4th World Symposium on Artificial Intelligence (WSAI)","authors":"","doi":"10.1109/wsai55384.2022.9836345","DOIUrl":"https://doi.org/10.1109/wsai55384.2022.9836345","url":null,"abstract":"","PeriodicalId":402449,"journal":{"name":"2022 4th World Symposium on Artificial Intelligence (WSAI)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125349429","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 : 2022-06-23DOI: 10.1109/wsai55384.2022.9836406
Jimin Liu, Jianye Zhuo, Huiqi Zhao, Xueyu Dong, Xin Ge
At present, there are a lot of algorithms about Intrusion Detection System (IDS) of the Wireless Sensor Network (WSN). However, based on the complexity of the environment and its own characteristics, the traditional intrusion detection technology has some problems, such as low detection rate and slow detection rate for different kinds of intruders. In order to enhance the accuracy of the model, this paper introduces Random Forest (RF) and Arithmetic Optimization Algorithm (AOA) to solve the intrusion detection problem when WSN receives DDoS attack, with higher accuracy and lower error rate. The improved tent chaotic map is used to increase the diversity of individuals; The parallel strategy enhances the communication between populations and adjusts the optimization. Firstly, the PT -AOA algorithm proposed has excellent performance in the evaluation of test function, and effectively ensures the improvement of RF classifier. On this basis, the optimized RF intrusion detection model has better performance than the traditional machine learning method in the simulation experiments on WSN-DS and CICDDoS2019 data sets.
{"title":"An Improved Random Forest Intrusion Detection Model Based on Tent Mapping","authors":"Jimin Liu, Jianye Zhuo, Huiqi Zhao, Xueyu Dong, Xin Ge","doi":"10.1109/wsai55384.2022.9836406","DOIUrl":"https://doi.org/10.1109/wsai55384.2022.9836406","url":null,"abstract":"At present, there are a lot of algorithms about Intrusion Detection System (IDS) of the Wireless Sensor Network (WSN). However, based on the complexity of the environment and its own characteristics, the traditional intrusion detection technology has some problems, such as low detection rate and slow detection rate for different kinds of intruders. In order to enhance the accuracy of the model, this paper introduces Random Forest (RF) and Arithmetic Optimization Algorithm (AOA) to solve the intrusion detection problem when WSN receives DDoS attack, with higher accuracy and lower error rate. The improved tent chaotic map is used to increase the diversity of individuals; The parallel strategy enhances the communication between populations and adjusts the optimization. Firstly, the PT -AOA algorithm proposed has excellent performance in the evaluation of test function, and effectively ensures the improvement of RF classifier. On this basis, the optimized RF intrusion detection model has better performance than the traditional machine learning method in the simulation experiments on WSN-DS and CICDDoS2019 data sets.","PeriodicalId":402449,"journal":{"name":"2022 4th World Symposium on Artificial Intelligence (WSAI)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126980877","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 : 2022-06-23DOI: 10.1109/wsai55384.2022.9836437
Guanqun Li, He Zhu, Peng Yuan, Yu Zheng, Hongdan Zhao, F. Gao, Haoran Zhu, Jun He
In order to realize the reliable climbing of the climbing transformer robot on the transformer wall and solve the problems of unstable center of gravity and easy sliding of the current wall climbing robot, this paper studies the kinematics of the four-wheel climbing transformer robot according to the actual working situation, and establishes the two-wheel differential driving motion equation of the four-wheel robot and the steering radius equation of the four-wheel robot, The model of the climbing transformer robot is established by SolidWorks. After importing the model into ADAMS, the kinematics simulation analysis is carried out in ADAMS / view, and finally the motion characteristics of the four-wheel climbing transformer robot are obtained to ensure the wall climbing reliability of the wall robot.
{"title":"Motion Simulation and Analysis of Four Wheeled Climbing Transformer Robot","authors":"Guanqun Li, He Zhu, Peng Yuan, Yu Zheng, Hongdan Zhao, F. Gao, Haoran Zhu, Jun He","doi":"10.1109/wsai55384.2022.9836437","DOIUrl":"https://doi.org/10.1109/wsai55384.2022.9836437","url":null,"abstract":"In order to realize the reliable climbing of the climbing transformer robot on the transformer wall and solve the problems of unstable center of gravity and easy sliding of the current wall climbing robot, this paper studies the kinematics of the four-wheel climbing transformer robot according to the actual working situation, and establishes the two-wheel differential driving motion equation of the four-wheel robot and the steering radius equation of the four-wheel robot, The model of the climbing transformer robot is established by SolidWorks. After importing the model into ADAMS, the kinematics simulation analysis is carried out in ADAMS / view, and finally the motion characteristics of the four-wheel climbing transformer robot are obtained to ensure the wall climbing reliability of the wall robot.","PeriodicalId":402449,"journal":{"name":"2022 4th World Symposium on Artificial Intelligence (WSAI)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134064265","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 : 2022-06-23DOI: 10.1109/wsai55384.2022.9836413
H. Yang, Haoyue Wu, Ruisheng Wan, Wenkai Wu, Jin Wang, Rui Tian
Crawler vehicles always slipped during the steering process. To address this problem, this paper uses particle swarm algorithm (PSO) to optimize the initial weights and thresholds of the BP neural network and establishes a turning radius prediction model based on the PSO-BP neural network. The model takes the turning angle as the input and the turning radius as the output. Kalman filter is used for data processing to eliminate random errors during the test process. The law between the physical parameters and algorithm parameters in the model is discussed by changing the range of turning angle and the number of hidden layers and initialization populations, and the reliability of the model is verified by a real vehicle test. The results show that it is feasible to predict the turning radius in the presence of slip by using the PSO- BP neural network algorithm, and the accuracy of the prediction model can reach 99% after Kalman filtering. The prediction model of the turning radius proposed in this paper provides a certain reference for the prediction of the turning radius of tracked vehicles under actual conditions.
{"title":"Turning Radius Prediction Method for Tracked Vehicles Based on PSO-BP Algorithm","authors":"H. Yang, Haoyue Wu, Ruisheng Wan, Wenkai Wu, Jin Wang, Rui Tian","doi":"10.1109/wsai55384.2022.9836413","DOIUrl":"https://doi.org/10.1109/wsai55384.2022.9836413","url":null,"abstract":"Crawler vehicles always slipped during the steering process. To address this problem, this paper uses particle swarm algorithm (PSO) to optimize the initial weights and thresholds of the BP neural network and establishes a turning radius prediction model based on the PSO-BP neural network. The model takes the turning angle as the input and the turning radius as the output. Kalman filter is used for data processing to eliminate random errors during the test process. The law between the physical parameters and algorithm parameters in the model is discussed by changing the range of turning angle and the number of hidden layers and initialization populations, and the reliability of the model is verified by a real vehicle test. The results show that it is feasible to predict the turning radius in the presence of slip by using the PSO- BP neural network algorithm, and the accuracy of the prediction model can reach 99% after Kalman filtering. The prediction model of the turning radius proposed in this paper provides a certain reference for the prediction of the turning radius of tracked vehicles under actual conditions.","PeriodicalId":402449,"journal":{"name":"2022 4th World Symposium on Artificial Intelligence (WSAI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132964341","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：