Pub Date : 2023-05-01DOI: 10.1109/IDITR57726.2023.10145939
Wenqiang Yin, Ran An, Zhengyan He, W. Zhang
As joint warfare and network-centric warfare become the main styles of modern warfare, a single test environment and test equipment can no longer meet the verification requirements of cross-platform joint tests, and the construction of an LVC (Live-Virtual-Constructive) cross-domain simulation test platform through testing, modeling and simulation technology is a necessary means to realize joint warfare tests. This paper addresses the problems of high cost of real environment construction, low test efficiency and high test flight risk when conducting manned and unmanned multi-aircraft collaborative tests, based on the virtual-real hybrid technology, a set of virtual-real hybrid integrated verification and simulation environment is built by integrating the real-assembly validator, simulation simulator and virtual digital system together, and the manned and unmanned multi-aircraft collaborative mission projection technology research is carried out based on typical collaborative scenarios. This method can provide technical support for the capability verification of equipment in real complex environments.
{"title":"The virtual-real hybrid verification technology of manned and unmanned multi-aircraft cooperative base on LVC","authors":"Wenqiang Yin, Ran An, Zhengyan He, W. Zhang","doi":"10.1109/IDITR57726.2023.10145939","DOIUrl":"https://doi.org/10.1109/IDITR57726.2023.10145939","url":null,"abstract":"As joint warfare and network-centric warfare become the main styles of modern warfare, a single test environment and test equipment can no longer meet the verification requirements of cross-platform joint tests, and the construction of an LVC (Live-Virtual-Constructive) cross-domain simulation test platform through testing, modeling and simulation technology is a necessary means to realize joint warfare tests. This paper addresses the problems of high cost of real environment construction, low test efficiency and high test flight risk when conducting manned and unmanned multi-aircraft collaborative tests, based on the virtual-real hybrid technology, a set of virtual-real hybrid integrated verification and simulation environment is built by integrating the real-assembly validator, simulation simulator and virtual digital system together, and the manned and unmanned multi-aircraft collaborative mission projection technology research is carried out based on typical collaborative scenarios. This method can provide technical support for the capability verification of equipment in real complex environments.","PeriodicalId":272880,"journal":{"name":"2023 2nd International Conference on Innovations and Development of Information Technologies and Robotics (IDITR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117175022","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 : 2023-05-01DOI: 10.1109/IDITR57726.2023.10145826
He Liao, Jing Yang, Hao Li, J. Tuo, Yarong Ma, Yuxin Feng, Changshun Fei
Use artificial intelligence semantic extraction and knowledge calculation to create professional knowledge base, covering professional field standards, key indicators, and evaluation experience, and form a knowledge map and store it in the graph database, and the formed professional key knowledge base can be used as a standard library and algorithm library for professional applications. This paper extracts knowledge from the feasibility study documents in the power grid field to form a knowledge base of key points for grid feasibility study review: Use artificial intelligence OCR recognition technology to structure useful information from feasibility study documents, use artificial intelligence NLP components to extract knowledge from information, and use artificial intelligence knowledge graphs to store knowledge.
{"title":"Analysis of New Distribution Network Planning Using Artificial Intelligence Semantic Recognition","authors":"He Liao, Jing Yang, Hao Li, J. Tuo, Yarong Ma, Yuxin Feng, Changshun Fei","doi":"10.1109/IDITR57726.2023.10145826","DOIUrl":"https://doi.org/10.1109/IDITR57726.2023.10145826","url":null,"abstract":"Use artificial intelligence semantic extraction and knowledge calculation to create professional knowledge base, covering professional field standards, key indicators, and evaluation experience, and form a knowledge map and store it in the graph database, and the formed professional key knowledge base can be used as a standard library and algorithm library for professional applications. This paper extracts knowledge from the feasibility study documents in the power grid field to form a knowledge base of key points for grid feasibility study review: Use artificial intelligence OCR recognition technology to structure useful information from feasibility study documents, use artificial intelligence NLP components to extract knowledge from information, and use artificial intelligence knowledge graphs to store knowledge.","PeriodicalId":272880,"journal":{"name":"2023 2nd International Conference on Innovations and Development of Information Technologies and Robotics (IDITR)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116438627","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 : 2023-05-01DOI: 10.1109/iditr57726.2023.10145935
{"title":"Conference Speakers","authors":"","doi":"10.1109/iditr57726.2023.10145935","DOIUrl":"https://doi.org/10.1109/iditr57726.2023.10145935","url":null,"abstract":"","PeriodicalId":272880,"journal":{"name":"2023 2nd International Conference on Innovations and Development of Information Technologies and Robotics (IDITR)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116539631","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 : 2023-05-01DOI: 10.1109/IDITR57726.2023.10145948
Liu Nan, Shao Weiguang, Yan Xiaohao, Tao Jia, Yang Changhui, Wang Yi, Yang Ming
In order to realize the automatic operation of the refueling robot, the identification and positioning system of the refueling robot is designed for the rotary piston refueling port of a special vehicle. RealSense D435i RGB-D camera and ring light source were used to build a visual system, and Hoff gradient method and Shi-Tomasi method were used to extract the features of the refueling port. Then, 3D positioning of the refueling port was realized through the registration of color image and depth image, and visual guidance was realized through hand-eye calibration. The experimental verification is carried out on the built experimental platform. The experimental results show that the positioning error of the refueling port is within ±1mm and the angle error of the slot is within 1° through the RGB-D camera method of identification and positioning of the refueling port proposed in this paper.
{"title":"Refueling Port Identification and Positioning of Refueling Robot Based on RGB-D Camera","authors":"Liu Nan, Shao Weiguang, Yan Xiaohao, Tao Jia, Yang Changhui, Wang Yi, Yang Ming","doi":"10.1109/IDITR57726.2023.10145948","DOIUrl":"https://doi.org/10.1109/IDITR57726.2023.10145948","url":null,"abstract":"In order to realize the automatic operation of the refueling robot, the identification and positioning system of the refueling robot is designed for the rotary piston refueling port of a special vehicle. RealSense D435i RGB-D camera and ring light source were used to build a visual system, and Hoff gradient method and Shi-Tomasi method were used to extract the features of the refueling port. Then, 3D positioning of the refueling port was realized through the registration of color image and depth image, and visual guidance was realized through hand-eye calibration. The experimental verification is carried out on the built experimental platform. The experimental results show that the positioning error of the refueling port is within ±1mm and the angle error of the slot is within 1° through the RGB-D camera method of identification and positioning of the refueling port proposed in this paper.","PeriodicalId":272880,"journal":{"name":"2023 2nd International Conference on Innovations and Development of Information Technologies and Robotics (IDITR)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122468029","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 : 2023-05-01DOI: 10.1109/IDITR57726.2023.10145979
Yi Chang, Qiuqing Yang, Huawei Liang, Zhiyuan Li, Hanqi Wang, Jian Wang
This paper's major objective is to rapidly and precisely plan the optimal trajectory in a complex environment. Because collisions must be avoided to ensure driving safety and compliance with kinematic constraints to enable precise tracking, this task can be characterized as an optimal control problem(OCP). The outcome of the optimal control problem is determined by the initial solution. A good first solution can reduce the time needed to solve the problem and enhance the effectiveness of the planning process. Hybrid A* is a well-known heuristic method that has a short planning time and satisfies vehicle but it is not complete. It offers a good initial solution for following optimal control problems. In order to achieve the ideal balance between optimality and solvability, we therefore suggest that, in the event that Hybrid A* planning fails, the complete two-dimensional A* planning result be employed as the initial solution of the optimal control problem. It is difficult and time-consuming to avoid contact with any obstacles when the initial solution indicates the homotopy path. The collision avoidance constraint is changed into a linear constraint by the addition of a space corridor, making it independent of the overall quantity of obstacles and solely related to obstacles that are approaching the trajectory. Soft constraints are utilized to further simplify the optimal control problem and guarantee its solvability. We conduct simulation experiments in multiple scenes to prove the feasibility of the algorithm.
{"title":"Trajectory Planning Method Based on Optimization in Complex Environment","authors":"Yi Chang, Qiuqing Yang, Huawei Liang, Zhiyuan Li, Hanqi Wang, Jian Wang","doi":"10.1109/IDITR57726.2023.10145979","DOIUrl":"https://doi.org/10.1109/IDITR57726.2023.10145979","url":null,"abstract":"This paper's major objective is to rapidly and precisely plan the optimal trajectory in a complex environment. Because collisions must be avoided to ensure driving safety and compliance with kinematic constraints to enable precise tracking, this task can be characterized as an optimal control problem(OCP). The outcome of the optimal control problem is determined by the initial solution. A good first solution can reduce the time needed to solve the problem and enhance the effectiveness of the planning process. Hybrid A* is a well-known heuristic method that has a short planning time and satisfies vehicle but it is not complete. It offers a good initial solution for following optimal control problems. In order to achieve the ideal balance between optimality and solvability, we therefore suggest that, in the event that Hybrid A* planning fails, the complete two-dimensional A* planning result be employed as the initial solution of the optimal control problem. It is difficult and time-consuming to avoid contact with any obstacles when the initial solution indicates the homotopy path. The collision avoidance constraint is changed into a linear constraint by the addition of a space corridor, making it independent of the overall quantity of obstacles and solely related to obstacles that are approaching the trajectory. Soft constraints are utilized to further simplify the optimal control problem and guarantee its solvability. We conduct simulation experiments in multiple scenes to prove the feasibility of the algorithm.","PeriodicalId":272880,"journal":{"name":"2023 2nd International Conference on Innovations and Development of Information Technologies and Robotics (IDITR)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133760548","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}
As one of the most popular sports, football has been a subject to growth and advancements in technology. The combination of football and artificial intelligence is expected to be used for intelligent football analysis. Image semantic segmentation is an important basis for image analysis and understanding. This paper proposes a deep learning-based image segmentation model for pixel-level classification of the video recordings frames of football matches. Every pixel of football video frame is classified into one of the 10 classes, e.g., players, ball, goal bar and several background scenes. In this paper, we first test a variety of CNN architectures and pre-trained models and select the MobileNet-UNet architecture as our baseline. We note the severe unbalanced data distribution in football scene segmentation. To solve this problem, the weighted multi-class cross-entropy loss is adopted in training of MobileNet-UNet to redistribute the weights of classification loss, focusing on smaller foreground object classes and improving segmentation accuracy. We also propose to use image transformations and a random mixture sampling technique for training data augmentation to reduce model overfitting. The model is trained and validated in the well-annotated Football Semantic Segmentation Open Dataset. The proposed best model achieves 0.96 frequency weighted IoU and 0.90 mean IoU segmentation accuracy on validation set.
{"title":"Deep Learning for Semantic Segmentation of Football Match Image","authors":"Yutian Wu, Wuqi Zhao, Chen-Chun Huang, Yaming Xi, Qing Li, Heng Wang","doi":"10.1109/IDITR57726.2023.10145987","DOIUrl":"https://doi.org/10.1109/IDITR57726.2023.10145987","url":null,"abstract":"As one of the most popular sports, football has been a subject to growth and advancements in technology. The combination of football and artificial intelligence is expected to be used for intelligent football analysis. Image semantic segmentation is an important basis for image analysis and understanding. This paper proposes a deep learning-based image segmentation model for pixel-level classification of the video recordings frames of football matches. Every pixel of football video frame is classified into one of the 10 classes, e.g., players, ball, goal bar and several background scenes. In this paper, we first test a variety of CNN architectures and pre-trained models and select the MobileNet-UNet architecture as our baseline. We note the severe unbalanced data distribution in football scene segmentation. To solve this problem, the weighted multi-class cross-entropy loss is adopted in training of MobileNet-UNet to redistribute the weights of classification loss, focusing on smaller foreground object classes and improving segmentation accuracy. We also propose to use image transformations and a random mixture sampling technique for training data augmentation to reduce model overfitting. The model is trained and validated in the well-annotated Football Semantic Segmentation Open Dataset. The proposed best model achieves 0.96 frequency weighted IoU and 0.90 mean IoU segmentation accuracy on validation set.","PeriodicalId":272880,"journal":{"name":"2023 2nd International Conference on Innovations and Development of Information Technologies and Robotics (IDITR)","volume":"593 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115105350","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 : 2023-05-01DOI: 10.1109/IDITR57726.2023.10145985
Jinhao Liu, Z. Lv, Jiahui Xu, Yiting Hu
In order to explore the reasons for the insufficient positioning accuracy of the crane, to ensure the personal safety of the staff, and to improve the reliability of production operations and work efficiency. Focus on building a set of practical, easy-to-operate, concise and efficient real-time positioning system based on TOF wireless ranging technology and laser radar technology measurement principle. Analyze the principle of the TOF wireless ranging data error, and use the extended Kalman filter method to perform error analysis and noise reduction processing on the distance data collected by the TOF wireless ranging sensor on site. After the extended Kalman filtering data, the average error is less than 0.1 cm, to improve the reliability and robustness of real-time positioning systems for on-site operations in steel mills. The Moore voting method is used to locate the smelting crane laterally, combined with the distance data of the laser radar sensor to determine the longitudinal positioning of the wireless smelting crane, and realize the all-round real-time positioning function of the smelting crane during operation.
{"title":"Wireless Ranging and Smelting Driving Location based on Moore Voting Method","authors":"Jinhao Liu, Z. Lv, Jiahui Xu, Yiting Hu","doi":"10.1109/IDITR57726.2023.10145985","DOIUrl":"https://doi.org/10.1109/IDITR57726.2023.10145985","url":null,"abstract":"In order to explore the reasons for the insufficient positioning accuracy of the crane, to ensure the personal safety of the staff, and to improve the reliability of production operations and work efficiency. Focus on building a set of practical, easy-to-operate, concise and efficient real-time positioning system based on TOF wireless ranging technology and laser radar technology measurement principle. Analyze the principle of the TOF wireless ranging data error, and use the extended Kalman filter method to perform error analysis and noise reduction processing on the distance data collected by the TOF wireless ranging sensor on site. After the extended Kalman filtering data, the average error is less than 0.1 cm, to improve the reliability and robustness of real-time positioning systems for on-site operations in steel mills. The Moore voting method is used to locate the smelting crane laterally, combined with the distance data of the laser radar sensor to determine the longitudinal positioning of the wireless smelting crane, and realize the all-round real-time positioning function of the smelting crane during operation.","PeriodicalId":272880,"journal":{"name":"2023 2nd International Conference on Innovations and Development of Information Technologies and Robotics (IDITR)","volume":"2441 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130913922","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 : 2023-05-01DOI: 10.1109/IDITR57726.2023.10145995
Changrong Xie, Hui Li, Kebin Chen, Yuxiao Li
The research on robustness optimization of large- scale heterogeneous combat network(HCN) is of great significance to improve the ability of combat system-of-systems(CSOS) to work in complex battlefield environment. However, there are still some shortcomings in the existing research, including the single setting attack strategy and the high computational cost in the search process of the optimization algorithm. In this article, we address aforementioned problems by using an computationally efficient evolutionary algorithm SP-RV-MOEANet to optimize the robustness of HCN. More specifically, two robust network parameters for node attack and link attack are first determined, then multi-objective optimization of HCN is carried out for these two parameters. Last, we analyze the results population and the optimal individual topology. Results show that the SP-RV-MOEANet has a satisfactory optimization effect for large-scale HCN, especially the optimization effect of robustness parameter for node attack is significantly better than that for link attack. On the other hand, by comparing the network topology before and after optimization, we find that the link from Sensor entities to Influential entities is more important. This finding provides useful insights for design of more robust combat system-of-systems.
{"title":"Research on Large-Scale Heterogeneous Combat Network Optimization based on SP-RV-Moeanet Algorithm","authors":"Changrong Xie, Hui Li, Kebin Chen, Yuxiao Li","doi":"10.1109/IDITR57726.2023.10145995","DOIUrl":"https://doi.org/10.1109/IDITR57726.2023.10145995","url":null,"abstract":"The research on robustness optimization of large- scale heterogeneous combat network(HCN) is of great significance to improve the ability of combat system-of-systems(CSOS) to work in complex battlefield environment. However, there are still some shortcomings in the existing research, including the single setting attack strategy and the high computational cost in the search process of the optimization algorithm. In this article, we address aforementioned problems by using an computationally efficient evolutionary algorithm SP-RV-MOEANet to optimize the robustness of HCN. More specifically, two robust network parameters for node attack and link attack are first determined, then multi-objective optimization of HCN is carried out for these two parameters. Last, we analyze the results population and the optimal individual topology. Results show that the SP-RV-MOEANet has a satisfactory optimization effect for large-scale HCN, especially the optimization effect of robustness parameter for node attack is significantly better than that for link attack. On the other hand, by comparing the network topology before and after optimization, we find that the link from Sensor entities to Influential entities is more important. This finding provides useful insights for design of more robust combat system-of-systems.","PeriodicalId":272880,"journal":{"name":"2023 2nd International Conference on Innovations and Development of Information Technologies and Robotics (IDITR)","volume":"2 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120999315","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 : 2023-05-01DOI: 10.1109/IDITR57726.2023.10145981
Suyang Wu, Hongmei Chu, Cong Cheng
For the problem of deep learning-based steel surface defect classification with a small dataset, most of the defects are small-scale defects in the actual operation process, which leads to the unsatisfactory effect of convolutional neural network for defect classification. This paper proposes a convolutional neural network with an attention mechanism to categorize steel surface defects. In the proposed detection network, we use ResNet34 network as the backbone network, and introduce squeeze and excitation networks into the network to adaptively correct features. In addition, during the experiment, the data augmentation method of changing the contrast and saturation of the image and the data augmentation method of random rotation of the image were used to extend the dataset. Experiments demonstrate that the proposed method's classification accuracy on NEU-DET dataset is 98.3%, which is 7.8% higher than that of only using ResNet34 network.
{"title":"Deep Network for Steel Surface Defect Detection Based on Attention Mechanism","authors":"Suyang Wu, Hongmei Chu, Cong Cheng","doi":"10.1109/IDITR57726.2023.10145981","DOIUrl":"https://doi.org/10.1109/IDITR57726.2023.10145981","url":null,"abstract":"For the problem of deep learning-based steel surface defect classification with a small dataset, most of the defects are small-scale defects in the actual operation process, which leads to the unsatisfactory effect of convolutional neural network for defect classification. This paper proposes a convolutional neural network with an attention mechanism to categorize steel surface defects. In the proposed detection network, we use ResNet34 network as the backbone network, and introduce squeeze and excitation networks into the network to adaptively correct features. In addition, during the experiment, the data augmentation method of changing the contrast and saturation of the image and the data augmentation method of random rotation of the image were used to extend the dataset. Experiments demonstrate that the proposed method's classification accuracy on NEU-DET dataset is 98.3%, which is 7.8% higher than that of only using ResNet34 network.","PeriodicalId":272880,"journal":{"name":"2023 2nd International Conference on Innovations and Development of Information Technologies and Robotics (IDITR)","volume":"123 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125553920","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 : 2023-05-01DOI: 10.1109/IDITR57726.2023.10145965
Maoxin Yao, Xiangyun Li, Kang Li
Shape memory alloy(SMA) actuators have the characteristics of high force-to-mass ratio, high energy density, and lightweight, leading to broad perspective applications in electromechanical systems. Due to the hysteretic nonlinear characteristic of SMA during phase transition, the traditional linear control method can not achieve the precise trajectory tracking control of SMA actuators. In this paper, we propose a backstepping dynamic surface control method based on an adaptive neural network. First, we establish a third-order nonlinear model with the internal dynamics of the SMA actuator. Secondly, we design the nonlinear controller using the backstepping dynamic surface method. Finally, the nonlinear function and parameter of the system are estimated using the designed radial basis function neural network(RBFNN) and adaptive law. This paper solves the problem that the controller depends on the SMA mathematical model. The controller has the characteristics of model-free, fast response, high precision, strong robustness, and low complexity. Compared with PID control and iterative learning control(ILC), the proposed control strategy has the advantages of high precision, rapid response, and fast anti-disturbance performance.
{"title":"Backstepping Dynamic Surface Control of an SMA Actuator Based on Adaptive Neural Network","authors":"Maoxin Yao, Xiangyun Li, Kang Li","doi":"10.1109/IDITR57726.2023.10145965","DOIUrl":"https://doi.org/10.1109/IDITR57726.2023.10145965","url":null,"abstract":"Shape memory alloy(SMA) actuators have the characteristics of high force-to-mass ratio, high energy density, and lightweight, leading to broad perspective applications in electromechanical systems. Due to the hysteretic nonlinear characteristic of SMA during phase transition, the traditional linear control method can not achieve the precise trajectory tracking control of SMA actuators. In this paper, we propose a backstepping dynamic surface control method based on an adaptive neural network. First, we establish a third-order nonlinear model with the internal dynamics of the SMA actuator. Secondly, we design the nonlinear controller using the backstepping dynamic surface method. Finally, the nonlinear function and parameter of the system are estimated using the designed radial basis function neural network(RBFNN) and adaptive law. This paper solves the problem that the controller depends on the SMA mathematical model. The controller has the characteristics of model-free, fast response, high precision, strong robustness, and low complexity. Compared with PID control and iterative learning control(ILC), the proposed control strategy has the advantages of high precision, rapid response, and fast anti-disturbance performance.","PeriodicalId":272880,"journal":{"name":"2023 2nd International Conference on Innovations and Development of Information Technologies and Robotics (IDITR)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122710916","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：