Pub Date : 2021-11-08DOI: 10.1109/IAI53119.2021.9619329
Wanying Zhu, Yupeng Li, Liangliang Sun, T. Hou, Song Bai, Baolong Yuan, Languang Zhao
The batch plan of the tundish takes over the charge plan, distributes the charges to obtain the result of the tundish preparation, and then starts the casting plan. It has played a transitional role in the steelmaking-continuous casting batch plan, and formulating a reasonable tundish plan is of great significance to the steel manufacturing industry. This paper establishes a mathematical model from the perspective of reducing energy consumption, improving the efficiency of the tundish and meeting the capacity of production equipment. The optimization goals of this mathematical model are “minimize the number of charges not incorporated into the tundish”, “minimize the remaining service life of the tundish” and “minimize the difference between the total number of charges, the weight of each flow direction, the weight of ironing roller materials, the total number of RH-refining charges and the target value”. Then an augmented Lagrangian relaxation algorithm based on linearized tundish decomposition strategy is used to solve the tundish batch planning problem. Finally, based on the MATLAB simulation platform, a simulation experiment was carried out on the actual production data of a large domestic steel enterprise, and the effectiveness of the mathematical model established in this paper and the solution strategy adopted by the comparison experiment was verified, and then the feasibility of this research for the tundish planning problem was demonstrated.
{"title":"Research on Batch Planning Method of Steelmaking-Continuous Casting Tundish","authors":"Wanying Zhu, Yupeng Li, Liangliang Sun, T. Hou, Song Bai, Baolong Yuan, Languang Zhao","doi":"10.1109/IAI53119.2021.9619329","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619329","url":null,"abstract":"The batch plan of the tundish takes over the charge plan, distributes the charges to obtain the result of the tundish preparation, and then starts the casting plan. It has played a transitional role in the steelmaking-continuous casting batch plan, and formulating a reasonable tundish plan is of great significance to the steel manufacturing industry. This paper establishes a mathematical model from the perspective of reducing energy consumption, improving the efficiency of the tundish and meeting the capacity of production equipment. The optimization goals of this mathematical model are “minimize the number of charges not incorporated into the tundish”, “minimize the remaining service life of the tundish” and “minimize the difference between the total number of charges, the weight of each flow direction, the weight of ironing roller materials, the total number of RH-refining charges and the target value”. Then an augmented Lagrangian relaxation algorithm based on linearized tundish decomposition strategy is used to solve the tundish batch planning problem. Finally, based on the MATLAB simulation platform, a simulation experiment was carried out on the actual production data of a large domestic steel enterprise, and the effectiveness of the mathematical model established in this paper and the solution strategy adopted by the comparison experiment was verified, and then the feasibility of this research for the tundish planning problem was demonstrated.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132166205","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 : 2021-11-08DOI: 10.1109/IAI53119.2021.9619209
Xujia Hou, Feihu Zhang
Recently, deep learning for object detection has been widely used in face recognition, traffic detection, and other fields. However, due to the dataset limitation and the target scale variation issues, ship detection is not as perfect as in other fields. To address such issues, in this paper, an anchor-free detection method is proposed in framework of CenterNet. By improving the network structure and using the unique activation function, the detection issues are successfully solved. Experimental results show that the improved CenterNet method is 5.6% higher in mAP in contrast to the state-of-the-art, and the FPS is increased by 4, respectively.
{"title":"The Improved CenterNet for Ship Detection in Scale-Varying Images","authors":"Xujia Hou, Feihu Zhang","doi":"10.1109/IAI53119.2021.9619209","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619209","url":null,"abstract":"Recently, deep learning for object detection has been widely used in face recognition, traffic detection, and other fields. However, due to the dataset limitation and the target scale variation issues, ship detection is not as perfect as in other fields. To address such issues, in this paper, an anchor-free detection method is proposed in framework of CenterNet. By improving the network structure and using the unique activation function, the detection issues are successfully solved. Experimental results show that the improved CenterNet method is 5.6% higher in mAP in contrast to the state-of-the-art, and the FPS is increased by 4, respectively.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132303273","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}
This paper investigates the image guidance control of flexible tip-steerable needles subject to random time delay of control input. The aim of the bevel-tip needle guidance in this paper is to steer the needle tip to a planar plane. Therefore, the 6-degree-of-freedom (DOF) model is reduced to a 3-DOF one. Furthermore, the reduced order model is transformed to a linear system by feedback linearization. In the setup of the needle guidance task, the states of the needle tip are estimated from the captured image. As the processing of the image and estimation of needle states are time consuming and the feedback controller using the estimated states. These delays are modeled as random delays and considered in a closed loop system. To address the random time delay, a robust $mathcal{H}_{infty}$ is proposed for the needle tip guidance task, which is novel in the bevel-tip needle guidance problem. Moreover, simulation results are provided to verify the effectiveness of the proposed time-delayed robust controller by comparing with the commonly used $mathcal{H}_{infty}$ controller without considering time delay.
{"title":"Robust H∞ Image-Based Control of Flexible Tip-Steerable Needles with Time-Varying Delays","authors":"Xiang Li, Zhiyang Ju, Zhi Qi, Xiangyang Xu, Hui Zhang","doi":"10.1109/IAI53119.2021.9619366","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619366","url":null,"abstract":"This paper investigates the image guidance control of flexible tip-steerable needles subject to random time delay of control input. The aim of the bevel-tip needle guidance in this paper is to steer the needle tip to a planar plane. Therefore, the 6-degree-of-freedom (DOF) model is reduced to a 3-DOF one. Furthermore, the reduced order model is transformed to a linear system by feedback linearization. In the setup of the needle guidance task, the states of the needle tip are estimated from the captured image. As the processing of the image and estimation of needle states are time consuming and the feedback controller using the estimated states. These delays are modeled as random delays and considered in a closed loop system. To address the random time delay, a robust $mathcal{H}_{infty}$ is proposed for the needle tip guidance task, which is novel in the bevel-tip needle guidance problem. Moreover, simulation results are provided to verify the effectiveness of the proposed time-delayed robust controller by comparing with the commonly used $mathcal{H}_{infty}$ controller without considering time delay.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133249533","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}
Unmanned aerial vehicles (UAVs) have great potential in the field of information technology due to their flexible deployment, low energy consumption and high adaptability. However, incidents about negative use of UAVs have gradually increased. Therefore, it is urgent to disable malicious UAVs. In this paper, a UAVs security experiment platform has been built to simulate various attacks suffered by UAVs. On this platform, UAVs use the MAVLink protocol and communicate with the ground control station through a wireless network. We analyze and compare the two versions of the MAVLink protocol, which is one of the most widely used protocols for wireless network communication systems. We explore vulnerabilities in the MAVLink protocol and design the strategies of the DoS attack and the hijacking attack. Empirical researches are provided to demonstrate the effectiveness of these attacks.
{"title":"Experimental Analysis of MAVLink Protocol Vulnerability on UAVs Security Experiment Platform","authors":"Haisong Xu, Heng Zhang, Jianwei Sun, Weiwei Xu, Wenshuo Wang, Hongran Li, Jian Zhang","doi":"10.1109/IAI53119.2021.9619330","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619330","url":null,"abstract":"Unmanned aerial vehicles (UAVs) have great potential in the field of information technology due to their flexible deployment, low energy consumption and high adaptability. However, incidents about negative use of UAVs have gradually increased. Therefore, it is urgent to disable malicious UAVs. In this paper, a UAVs security experiment platform has been built to simulate various attacks suffered by UAVs. On this platform, UAVs use the MAVLink protocol and communicate with the ground control station through a wireless network. We analyze and compare the two versions of the MAVLink protocol, which is one of the most widely used protocols for wireless network communication systems. We explore vulnerabilities in the MAVLink protocol and design the strategies of the DoS attack and the hijacking attack. Empirical researches are provided to demonstrate the effectiveness of these attacks.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116617397","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 : 2021-11-08DOI: 10.1109/IAI53119.2021.9619260
Jing Han, Guici Chen, Guodong Zhang
This paper discusses the problem of exponential stabilization for a class of fuzzy inertial neural networks(FINNs) with mixed delays. By using Lyapunov stability theory and some inequality techniques, several new criteria are derived to get global exponential stability of the investigated FINNs. Compared with the previous works on inertial neural networks(INNs) without fuzzy terms or only consider common time delays, our systems considered here are more general and meaningful. Furthermore, we get the exponential stabilization criteria directly from the FINNs themselves without the reduced-order method. At last, illustrative examples are given to show the correctness of the results.
{"title":"Exponential stabilization of fuzzy inertial neural networks with mixed delays","authors":"Jing Han, Guici Chen, Guodong Zhang","doi":"10.1109/IAI53119.2021.9619260","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619260","url":null,"abstract":"This paper discusses the problem of exponential stabilization for a class of fuzzy inertial neural networks(FINNs) with mixed delays. By using Lyapunov stability theory and some inequality techniques, several new criteria are derived to get global exponential stability of the investigated FINNs. Compared with the previous works on inertial neural networks(INNs) without fuzzy terms or only consider common time delays, our systems considered here are more general and meaningful. Furthermore, we get the exponential stabilization criteria directly from the FINNs themselves without the reduced-order method. At last, illustrative examples are given to show the correctness of the results.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124787330","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}
In this paper, the parafoil-rocket first stage booster system is used as the research object. Aiming at the problem of accurate fall area recovery in the first-stage booster system, a threat avoidance method of parafoil-rocket system combining genetic algorithm (GA) and sequential quadratic programming (SQP) is designed by using optimal control homing method. This method takes advantage of GA’s strong robustness and global optimization as well as SQP’s fast convergence rate and high efficiency to solve the problem of optimal control. The result of GA’s global optimization is taken as the initial value of SQP algorithm, then the local optimal solution is further obtained to solve the problem of obstacle avoidance in the complex terrain of the target landing area. The simulation results from Matlab/Simulink show that the method adopted in this paper meets the requirements of fall zone control, and compared with the path planned by the traditional GA, The path is smoother and less detour, the deviation of landing point and the error of headwind are smaller. This method has the feasibility of implementation.
{"title":"Optimal Control Homing of Rocket First-Stage Booster Recovery Based on Improved Genetic Algorithm with SQP","authors":"Mengping Chen, Xiaojun Xing, Yichen Han, Guozheng Fan, Yiming Guo","doi":"10.1109/IAI53119.2021.9619428","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619428","url":null,"abstract":"In this paper, the parafoil-rocket first stage booster system is used as the research object. Aiming at the problem of accurate fall area recovery in the first-stage booster system, a threat avoidance method of parafoil-rocket system combining genetic algorithm (GA) and sequential quadratic programming (SQP) is designed by using optimal control homing method. This method takes advantage of GA’s strong robustness and global optimization as well as SQP’s fast convergence rate and high efficiency to solve the problem of optimal control. The result of GA’s global optimization is taken as the initial value of SQP algorithm, then the local optimal solution is further obtained to solve the problem of obstacle avoidance in the complex terrain of the target landing area. The simulation results from Matlab/Simulink show that the method adopted in this paper meets the requirements of fall zone control, and compared with the path planned by the traditional GA, The path is smoother and less detour, the deviation of landing point and the error of headwind are smaller. This method has the feasibility of implementation.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125123348","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 : 2021-11-08DOI: 10.1109/iai53119.2021.9619370
{"title":"[IAI 2021 Front cover]","authors":"","doi":"10.1109/iai53119.2021.9619370","DOIUrl":"https://doi.org/10.1109/iai53119.2021.9619370","url":null,"abstract":"","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130111050","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 : 2021-11-08DOI: 10.1109/IAI53119.2021.9619418
Jingyang Wang, Ying Liu, Haojie Sun, Yutong Zou
With the rapid development and urbanization of the economy, Municipal Domestic Waste (MDW) pollution is getting worse, the total amount of MDW is increasing year by year. As the basis of the effective use, the study of MDW classified collection has drawn more and more attention. In this paper, through the comprehensive analysis of impact factors of MDW classified collection, we established the indication system which can affect the MDW classified collection with the ISM - ANP method. We find the most important factor by index assignment. Furthermore, we put forward countermeasures to promote MDW classified collection.
{"title":"Research on Analyzing Factors and Countermeasures of MDW Classified Collection","authors":"Jingyang Wang, Ying Liu, Haojie Sun, Yutong Zou","doi":"10.1109/IAI53119.2021.9619418","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619418","url":null,"abstract":"With the rapid development and urbanization of the economy, Municipal Domestic Waste (MDW) pollution is getting worse, the total amount of MDW is increasing year by year. As the basis of the effective use, the study of MDW classified collection has drawn more and more attention. In this paper, through the comprehensive analysis of impact factors of MDW classified collection, we established the indication system which can affect the MDW classified collection with the ISM - ANP method. We find the most important factor by index assignment. Furthermore, we put forward countermeasures to promote MDW classified collection.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129528719","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 : 2021-11-08DOI: 10.1109/IAI53119.2021.9619378
Xin Wang, C. Zang, Shuqing Xu, Peng Zeng
A mobile sensing robot team (MSRT) is a typical application of multiagent system, which faces the huge challenge of environment dynamism that the change of action selection of one robot may influence behaviors of the other robots. In this paper, we investigate reinforcement learning methods for MSRT problem. A target-coupled multiagent reinforcement learning approach is proposed to solve the MSRT problem by taking advantage of both the knowledge of each agent and the local environment information sensed by the agent for achieving a shared goal in a common environment. We show the strength of our approach compared to the existed decentralized Q-learning in MSRT problem, where sensing robots are able to meet targets coverage requirement by discovering a coordinated strategy.
{"title":"A Target-coupled Multiagent Reinforcement Learning Approach for Teams of Mobile Sensing Robots","authors":"Xin Wang, C. Zang, Shuqing Xu, Peng Zeng","doi":"10.1109/IAI53119.2021.9619378","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619378","url":null,"abstract":"A mobile sensing robot team (MSRT) is a typical application of multiagent system, which faces the huge challenge of environment dynamism that the change of action selection of one robot may influence behaviors of the other robots. In this paper, we investigate reinforcement learning methods for MSRT problem. A target-coupled multiagent reinforcement learning approach is proposed to solve the MSRT problem by taking advantage of both the knowledge of each agent and the local environment information sensed by the agent for achieving a shared goal in a common environment. We show the strength of our approach compared to the existed decentralized Q-learning in MSRT problem, where sensing robots are able to meet targets coverage requirement by discovering a coordinated strategy.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124344331","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：