Pub Date : 2021-06-01DOI: 10.1109/ICAA53760.2021.00163
Kun Xie, Liaoni Wu, Chengchan He
In order to research the ability of the UAV to correct deviation during the front three-wheel taxiing phase and establish accurate taxi model of the drone, this paper takes a certain UAV with nose-wheel landing gear as the research object. This paper conducts a complete dynamic analysis of its ground model, improves the ground force analysis and aerodynamic analysis, builds a 6-demention model which contains a PID controller and adds a LADRC controller in Matlab for verifying the anti-disturbance ability of LADRC of the UAV in the model. The result shows that compared with PID controller, LADRC can effectively suppress heading deviation caused by the disturbance, and the drone can be more quickly aligned to the heading for the UAV rolling under disturbance.
{"title":"UAV Taxiing Control Based on Linear Active Disturbance Rejection Control","authors":"Kun Xie, Liaoni Wu, Chengchan He","doi":"10.1109/ICAA53760.2021.00163","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00163","url":null,"abstract":"In order to research the ability of the UAV to correct deviation during the front three-wheel taxiing phase and establish accurate taxi model of the drone, this paper takes a certain UAV with nose-wheel landing gear as the research object. This paper conducts a complete dynamic analysis of its ground model, improves the ground force analysis and aerodynamic analysis, builds a 6-demention model which contains a PID controller and adds a LADRC controller in Matlab for verifying the anti-disturbance ability of LADRC of the UAV in the model. The result shows that compared with PID controller, LADRC can effectively suppress heading deviation caused by the disturbance, and the drone can be more quickly aligned to the heading for the UAV rolling under disturbance.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"173 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133435048","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 : 2021-06-01DOI: 10.1109/ICAA53760.2021.00135
Buquan Liu, Chung-Hsiao R. Wu, Hao Guo
Microkernel operating system plays an important role in industrial control system, embedded system and real-time system, etc. From many aspects, this paper studies the microkernel technology, such as its architecture, history, characteristics, and scenarios. In view of the deficiencies of microkernel architecture in the future interconnection of everything, this paper expounds the further research direction of microkernel from interoperation, distributed storage, security and so on. Finally, some experiments, based on seL4 microkernel, are discussed, including virtualization, and performance comparison with Linux.
{"title":"A Survey of Operating System Microkernel","authors":"Buquan Liu, Chung-Hsiao R. Wu, Hao Guo","doi":"10.1109/ICAA53760.2021.00135","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00135","url":null,"abstract":"Microkernel operating system plays an important role in industrial control system, embedded system and real-time system, etc. From many aspects, this paper studies the microkernel technology, such as its architecture, history, characteristics, and scenarios. In view of the deficiencies of microkernel architecture in the future interconnection of everything, this paper expounds the further research direction of microkernel from interoperation, distributed storage, security and so on. Finally, some experiments, based on seL4 microkernel, are discussed, including virtualization, and performance comparison with Linux.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132576784","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 : 2021-06-01DOI: 10.1109/ICAA53760.2021.00165
Xin Wang, Jian Zhang, Tan Zhao, Chen-yang Di
In this study, the buckling analysis and comparative study of toroidal shell with uniform wall thickness and toroidal shell with varying wall thickness were investigated. Through the numerical calculation based on the arc length method, the buckling load, destruction mode and Huber-Mises-Hencky stress under the critical state of the two kinds of shell were obtained, and a comparative analysis was carried out. The numerical results suggested that the buckling loads of the toroidal shell with varying wall thickness optimised by equal strength design was significantly improved, which was 1.304 times that of the toroidal shell with uniform wall thickness. In addition, it was also found that both shells were buckled in a nonlinear elastic plastic mode. The research can provide new ideas for the optimization of toroidal shells.
{"title":"Buckling of a Toroidal Shell with Varying Wall Thickness Under Uniform External Pressure","authors":"Xin Wang, Jian Zhang, Tan Zhao, Chen-yang Di","doi":"10.1109/ICAA53760.2021.00165","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00165","url":null,"abstract":"In this study, the buckling analysis and comparative study of toroidal shell with uniform wall thickness and toroidal shell with varying wall thickness were investigated. Through the numerical calculation based on the arc length method, the buckling load, destruction mode and Huber-Mises-Hencky stress under the critical state of the two kinds of shell were obtained, and a comparative analysis was carried out. The numerical results suggested that the buckling loads of the toroidal shell with varying wall thickness optimised by equal strength design was significantly improved, which was 1.304 times that of the toroidal shell with uniform wall thickness. In addition, it was also found that both shells were buckled in a nonlinear elastic plastic mode. The research can provide new ideas for the optimization of toroidal shells.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115353955","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 : 2021-06-01DOI: 10.1109/ICAA53760.2021.00033
Mengling Zhao, Meng Zhao, Xinlu Yang
In order to improve the drawback that the LBG algorithm is more sensitive to the initial code book, the similarity measure of Euclidean distance only reflects the local consistency characteristics of the clustering results, but not the global consistency of the clusters. The clone selection algorithm is introduced to generate the initial code book using the splitting method. Further, it is proposed to generate the final code book using the flow distance based clone selection clustering method for optimization. The experimental results show that MDCSA achieves relatively high PSNR values for different code book sizes. The design method of clone selection based on manifold distance has better performance and effectiveness.
{"title":"Design of Vector Quantization Code Book Based on Clone Selection Algorithm and its Application","authors":"Mengling Zhao, Meng Zhao, Xinlu Yang","doi":"10.1109/ICAA53760.2021.00033","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00033","url":null,"abstract":"In order to improve the drawback that the LBG algorithm is more sensitive to the initial code book, the similarity measure of Euclidean distance only reflects the local consistency characteristics of the clustering results, but not the global consistency of the clusters. The clone selection algorithm is introduced to generate the initial code book using the splitting method. Further, it is proposed to generate the final code book using the flow distance based clone selection clustering method for optimization. The experimental results show that MDCSA achieves relatively high PSNR values for different code book sizes. The design method of clone selection based on manifold distance has better performance and effectiveness.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115568882","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 : 2021-06-01DOI: 10.1109/ICAA53760.2021.00070
Puning Yu, Yunyi Liu
Question answering is an essential component of the chatbot where it can facilitate users retrieve tremendous information from online websites. Traditional question answering system are built upon the conventional deep learning sequence models, where they are failed to capture sufficient semantic features due to the complexity of the question answering task. To tackle the above challenges, we propose a novel approach, equipped with a Roberta-based encoder-encoder framework, to extract the underlying semantic features more effectively. The experimental results on a well-studied dataset, i.e., SQUAD, show that our proposed method outperforms the baseline models in term of both EM and F1 evaluation metrics, which proves our model effectiveness.
{"title":"Roberta-based Encoder-decoder Model for Question Answering System","authors":"Puning Yu, Yunyi Liu","doi":"10.1109/ICAA53760.2021.00070","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00070","url":null,"abstract":"Question answering is an essential component of the chatbot where it can facilitate users retrieve tremendous information from online websites. Traditional question answering system are built upon the conventional deep learning sequence models, where they are failed to capture sufficient semantic features due to the complexity of the question answering task. To tackle the above challenges, we propose a novel approach, equipped with a Roberta-based encoder-encoder framework, to extract the underlying semantic features more effectively. The experimental results on a well-studied dataset, i.e., SQUAD, show that our proposed method outperforms the baseline models in term of both EM and F1 evaluation metrics, which proves our model effectiveness.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114488656","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 : 2021-06-01DOI: 10.1109/ICAA53760.2021.00153
Yan Ren, B. Liu
In this paper, the model predictive control algorithm based on the kinematics model of unmanned tractor is designed for the problem of precise tracking of unmanned tractor path. The adaptive predictive control algorithm is used to adaptively control the PID parameters [1]. Finally, the method of predicting the path tracking model in the actual road is compared with the traditional PID control result. The results show that compared with the traditional PID control algorithm, the overshoot and oscillation amplitude can be effectively suppressed by the model predictive control algorithm[2], the reference path can be accurately fitted, and the optimization of system dynamic performance and steady-state error performance can be optimized, Unmanned tractors got a more accurate path fit result. Realized to achieve more precise control.
{"title":"Application of Model Predictive Control Algorithm Used in Path Planning of the Unmanned Tractor","authors":"Yan Ren, B. Liu","doi":"10.1109/ICAA53760.2021.00153","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00153","url":null,"abstract":"In this paper, the model predictive control algorithm based on the kinematics model of unmanned tractor is designed for the problem of precise tracking of unmanned tractor path. The adaptive predictive control algorithm is used to adaptively control the PID parameters [1]. Finally, the method of predicting the path tracking model in the actual road is compared with the traditional PID control result. The results show that compared with the traditional PID control algorithm, the overshoot and oscillation amplitude can be effectively suppressed by the model predictive control algorithm[2], the reference path can be accurately fitted, and the optimization of system dynamic performance and steady-state error performance can be optimized, Unmanned tractors got a more accurate path fit result. Realized to achieve more precise control.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114639086","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 : 2021-06-01DOI: 10.1109/ICAA53760.2021.00084
Qingwu Fan, Guanghuang Chen, Kaiqin Yang
For the treatment of environmental complaint information, it is essential to judge the similarity between current report events and historical report cases. However, complaint events are complicated, so it is hard to calculate the similarity between them. In general, the event similarity is usually a comprehensive result based on the similarity of constituent elements. Therefore, an event similarity calculation method based on an improved fruit fly optimization algorithm (IFOA) is proposed in this paper to solve the problem of environmental complaint events similarity computation. Firstly, the fruit fly optimization algorithm (FOA) is modified to solve the issues of fixed search radius and low population diversity. Secondly, the similarity degree set is constructed by calculating the similarity degree of each component between two events, which is taken as the sample data. Then, the generalized regression neural network (GRNN) is applied to establish the similarity calculation model. Finally, the parameter of the model is optimized by IFOA. Experimental results show that this method has high accuracy and can meet the actual demand.
{"title":"Similarity Calculation of Environmental Complaint Events Based on Improved FOA","authors":"Qingwu Fan, Guanghuang Chen, Kaiqin Yang","doi":"10.1109/ICAA53760.2021.00084","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00084","url":null,"abstract":"For the treatment of environmental complaint information, it is essential to judge the similarity between current report events and historical report cases. However, complaint events are complicated, so it is hard to calculate the similarity between them. In general, the event similarity is usually a comprehensive result based on the similarity of constituent elements. Therefore, an event similarity calculation method based on an improved fruit fly optimization algorithm (IFOA) is proposed in this paper to solve the problem of environmental complaint events similarity computation. Firstly, the fruit fly optimization algorithm (FOA) is modified to solve the issues of fixed search radius and low population diversity. Secondly, the similarity degree set is constructed by calculating the similarity degree of each component between two events, which is taken as the sample data. Then, the generalized regression neural network (GRNN) is applied to establish the similarity calculation model. Finally, the parameter of the model is optimized by IFOA. Experimental results show that this method has high accuracy and can meet the actual demand.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116984641","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 : 2021-06-01DOI: 10.1109/ICAA53760.2021.00125
J. Gong, S. Ling
In order to solve the web application security threats of campus network, a log security threat monitoring platform based on elk is designed. Firstly, the data of Web log is analyzed, and the attack patterns of security threats are mined to form a security monitoring model library, which is applied to real-time security monitoring. The system operation results show that the platform can effectively find the security threats in the campus network, visual association analysis is convenient, and can effectively improve the operation and maintenance efficiency and the speed of security attack investigation.
{"title":"Security Analysis of University Web Log Based on Elk","authors":"J. Gong, S. Ling","doi":"10.1109/ICAA53760.2021.00125","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00125","url":null,"abstract":"In order to solve the web application security threats of campus network, a log security threat monitoring platform based on elk is designed. Firstly, the data of Web log is analyzed, and the attack patterns of security threats are mined to form a security monitoring model library, which is applied to real-time security monitoring. The system operation results show that the platform can effectively find the security threats in the campus network, visual association analysis is convenient, and can effectively improve the operation and maintenance efficiency and the speed of security attack investigation.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116458323","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 : 2021-06-01DOI: 10.1109/ICAA53760.2021.00019
Haibin Yao, Xue Shen, Jie Li
In order to meet the needs of increased production capacity, equipment expansion, cigarette brand specification switching, etc., the cigarette factory needs to increase the carton conveyor line. However, the cost of adding a new conveyor line is extremely high, and the construction period is long, making implementation difficult. For this reason, after measuring the carrying capacity of the existing crawler carton conveyor line, this paper uses the servo motor speed control technology based on Parker's theoretical analysis and uses the conjugate combined conveyin2g technology of different passes to fully explore the carrying capacity of the carton conveyor, Designed a “two-in-one” device for carton delivery. It satisfies the function of alternately merging the cartons conveyed by two packaging machines into one conveyor line. After the improvement, the single-line conveying capacity has increased from 55 per minute to 75 per minute, breaking the industry bottleneck of single-line conveying capacity., Reaching the current domestic fastest speed, effectively reducing the cost of equipment upgrades.
{"title":"Design andApplication of Two-in-one Device for Carton Deliver","authors":"Haibin Yao, Xue Shen, Jie Li","doi":"10.1109/ICAA53760.2021.00019","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00019","url":null,"abstract":"In order to meet the needs of increased production capacity, equipment expansion, cigarette brand specification switching, etc., the cigarette factory needs to increase the carton conveyor line. However, the cost of adding a new conveyor line is extremely high, and the construction period is long, making implementation difficult. For this reason, after measuring the carrying capacity of the existing crawler carton conveyor line, this paper uses the servo motor speed control technology based on Parker's theoretical analysis and uses the conjugate combined conveyin2g technology of different passes to fully explore the carrying capacity of the carton conveyor, Designed a “two-in-one” device for carton delivery. It satisfies the function of alternately merging the cartons conveyed by two packaging machines into one conveyor line. After the improvement, the single-line conveying capacity has increased from 55 per minute to 75 per minute, breaking the industry bottleneck of single-line conveying capacity., Reaching the current domestic fastest speed, effectively reducing the cost of equipment upgrades.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128635088","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 : 2021-06-01DOI: 10.1109/ICAA53760.2021.00169
Haifeng Feng, Wei Zeng
The makespan of support operations of carrier-borne aircraft is a key factor affecting the sortie generation rate. The support operation process involves multiple support resources and operational tasks should satisfy serial and parallel constraint relationships. The effective coordination of these processes can be considered as a multi-resource constrained multi-project scheduling problem (MRCMPSP), which is a complex NP-hard problem. In this paper, a deep reinforcement learning (RL) method is designed to solve the problem, including the image representation of the state, the definition of action mapping, and reward function. Deep convolution neural network and advantage actor-critic algorithm (A2C) are utilized to provide a new solution to the scheduling problem, and experimental results show that the effectiveness of the proposed algorithm.
{"title":"Deep Reinforcement Learning for Carrier-borne Aircraft Support Operation Scheduling","authors":"Haifeng Feng, Wei Zeng","doi":"10.1109/ICAA53760.2021.00169","DOIUrl":"https://doi.org/10.1109/ICAA53760.2021.00169","url":null,"abstract":"The makespan of support operations of carrier-borne aircraft is a key factor affecting the sortie generation rate. The support operation process involves multiple support resources and operational tasks should satisfy serial and parallel constraint relationships. The effective coordination of these processes can be considered as a multi-resource constrained multi-project scheduling problem (MRCMPSP), which is a complex NP-hard problem. In this paper, a deep reinforcement learning (RL) method is designed to solve the problem, including the image representation of the state, the definition of action mapping, and reward function. Deep convolution neural network and advantage actor-critic algorithm (A2C) are utilized to provide a new solution to the scheduling problem, and experimental results show that the effectiveness of the proposed algorithm.","PeriodicalId":121879,"journal":{"name":"2021 International Conference on Intelligent Computing, Automation and Applications (ICAA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129551800","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：