Pub Date : 2020-10-23DOI: 10.1109/IAI50351.2020.9262217
Mai Peng, Changhe Li
The multi-population method is a common method for solving dynamic optimization problems. However, to design an efficient multi-population method, one of the challenging issues is how to allocate computational resources between populations given a limited computing buget in dynamic environments. This paper designs a contribution-based resource allocation mechanism. In this mechanism, a contribution degree of a population is defined according to the performance of the population, which determines the probability of the population to obtain the computing resource. This mechanism is implemented in an adaptive multi-population method. Experimental results on the moving peaks benchmark show that the algorithm equipped with the resource allocation mechanism outperforms the original algorithms.
{"title":"A Contribution-based Resource Allocation Scheme for Multi-population Methods in Dynamic Environments","authors":"Mai Peng, Changhe Li","doi":"10.1109/IAI50351.2020.9262217","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262217","url":null,"abstract":"The multi-population method is a common method for solving dynamic optimization problems. However, to design an efficient multi-population method, one of the challenging issues is how to allocate computational resources between populations given a limited computing buget in dynamic environments. This paper designs a contribution-based resource allocation mechanism. In this mechanism, a contribution degree of a population is defined according to the performance of the population, which determines the probability of the population to obtain the computing resource. This mechanism is implemented in an adaptive multi-population method. Experimental results on the moving peaks benchmark show that the algorithm equipped with the resource allocation mechanism outperforms the original algorithms.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115804188","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 : 2020-10-23DOI: 10.1109/IAI50351.2020.9262225
Ziquan Yu, H. Badihi, Youmin Zhang, Yajie Ma, B. Jiang, C. Su
In this paper, a fractional-order sliding-mode fault-tolerant tracking control scheme is proposed for a fixed-wing UAV with prescribed performance. The outer-loop position dynamics is first transformed to the second-order nonlinear model. By using neural networks, the unknown nonlinear functions containing actuator faults are identified. Moreover, the minimum learning parameter of neural networks is constructed to reduce the computational burden. Fractional-order calculus is further utilized in the sliding-mode control for improving the fault-tolerant tracking performance. Simulation results are presented to show the effectiveness.
{"title":"Fractional-Order Sliding-Mode Fault-Tolerant Neural Adaptive Control of Fixed-Wing UAV With Prescribed Tracking Performance","authors":"Ziquan Yu, H. Badihi, Youmin Zhang, Yajie Ma, B. Jiang, C. Su","doi":"10.1109/IAI50351.2020.9262225","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262225","url":null,"abstract":"In this paper, a fractional-order sliding-mode fault-tolerant tracking control scheme is proposed for a fixed-wing UAV with prescribed performance. The outer-loop position dynamics is first transformed to the second-order nonlinear model. By using neural networks, the unknown nonlinear functions containing actuator faults are identified. Moreover, the minimum learning parameter of neural networks is constructed to reduce the computational burden. Fractional-order calculus is further utilized in the sliding-mode control for improving the fault-tolerant tracking performance. Simulation results are presented to show the effectiveness.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133143460","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 : 2020-10-23DOI: 10.1109/IAI50351.2020.9262233
Ni Da-peng, Zhang Guo-jin, Jia Ming-xing
A method of operation performance assessment based on the combination of fuzzy classification and Gaussian mixture model is proposed to assess the operation performance for the smelting process of electrofused magnesium furnace. And a method of non-optimal cause tracing based on the combination of contribution diagram and case-based reasoning is used to trace the non-optimal causes. For the qualitative data, the fuzzy classification method is used to transform the qualitative division into the quantitative division. Then, the posterior probability of the Gaussian mixture model of each running state of the online data is calculated to get the evaluation results. When the evaluation result is not optimal, the contribution rate of each variable is compared to obtain the non-optimal variable, and the non-optimal reason is found by case search. Finally, the effectiveness of the proposed method is verified by the simulation platform of electrofused magnesium furnace.
{"title":"Operation Performance Assessment and Non-optimal Reasons Traceability for Melting Process of Fused Magnesium Furnace","authors":"Ni Da-peng, Zhang Guo-jin, Jia Ming-xing","doi":"10.1109/IAI50351.2020.9262233","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262233","url":null,"abstract":"A method of operation performance assessment based on the combination of fuzzy classification and Gaussian mixture model is proposed to assess the operation performance for the smelting process of electrofused magnesium furnace. And a method of non-optimal cause tracing based on the combination of contribution diagram and case-based reasoning is used to trace the non-optimal causes. For the qualitative data, the fuzzy classification method is used to transform the qualitative division into the quantitative division. Then, the posterior probability of the Gaussian mixture model of each running state of the online data is calculated to get the evaluation results. When the evaluation result is not optimal, the contribution rate of each variable is compared to obtain the non-optimal variable, and the non-optimal reason is found by case search. Finally, the effectiveness of the proposed method is verified by the simulation platform of electrofused magnesium furnace.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125922324","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 : 2020-10-23DOI: 10.1109/IAI50351.2020.9262218
Xuejiao Wang, Hao Luo, Kuan Li, Shen Yin, O. Kaynak
Thanks to rapid development of artificial intelligence (AI), a new branch of computer science, modern industry system becomes increasingly intelligent. What's more, mountains of data in industrial process can be saved for data-driven intelligent fault detection and classification. A method of intelligent data-driven fault classification based on stability margin is proposed in this paper, which gives a data-driven stability margin solution. As an important feature, the stability margin, together with the input and output (I/O) data, is input into the LM-BP neural network multi-classifier for fault classification. Moreover, the proposed method is demonstrated to be effective with high accuracy through a DC motor benchmark.
{"title":"An Intelligent Fault Classification Method Based on Data-Driven Stability Margin","authors":"Xuejiao Wang, Hao Luo, Kuan Li, Shen Yin, O. Kaynak","doi":"10.1109/IAI50351.2020.9262218","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262218","url":null,"abstract":"Thanks to rapid development of artificial intelligence (AI), a new branch of computer science, modern industry system becomes increasingly intelligent. What's more, mountains of data in industrial process can be saved for data-driven intelligent fault detection and classification. A method of intelligent data-driven fault classification based on stability margin is proposed in this paper, which gives a data-driven stability margin solution. As an important feature, the stability margin, together with the input and output (I/O) data, is input into the LM-BP neural network multi-classifier for fault classification. Moreover, the proposed method is demonstrated to be effective with high accuracy through a DC motor benchmark.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114251072","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 : 2020-10-23DOI: 10.1109/IAI50351.2020.9262208
First A. Jing Wang, Second B. Miao Li, Third C. Yue Qiu, Fourth D. Heng Wang
This paper has presented an idea of using substation and monitoring data to locate the key operations and difficulties in operations of staff working in substation. The analysis also make it possible for related department of majors find out the training needs of staff and technique development needs in power grid. With the help of field data, the conclusion of above analysis will be more clear and objective.
{"title":"In-depth Analysis and Application of Power Grid Data for Location of Task Difficultie","authors":"First A. Jing Wang, Second B. Miao Li, Third C. Yue Qiu, Fourth D. Heng Wang","doi":"10.1109/IAI50351.2020.9262208","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262208","url":null,"abstract":"This paper has presented an idea of using substation and monitoring data to locate the key operations and difficulties in operations of staff working in substation. The analysis also make it possible for related department of majors find out the training needs of staff and technique development needs in power grid. With the help of field data, the conclusion of above analysis will be more clear and objective.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116587142","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 : 2020-10-23DOI: 10.1109/IAI50351.2020.9262228
Weiguo Xia, Hong Liang
This paper studies the evolution of an expressed and private opinion dynamics model with asynchronous updating. It is shown that under some mild connectivity and individual activation conditions, the expressed and private opinions of all individuals in the network converge to a common value exponentially fast when the susceptibility to influence of all individuals is equal to one. A numerical example verifies the theoretical result.
{"title":"An Expressed and Private Opinion Model on Influence Networks","authors":"Weiguo Xia, Hong Liang","doi":"10.1109/IAI50351.2020.9262228","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262228","url":null,"abstract":"This paper studies the evolution of an expressed and private opinion dynamics model with asynchronous updating. It is shown that under some mild connectivity and individual activation conditions, the expressed and private opinions of all individuals in the network converge to a common value exponentially fast when the susceptibility to influence of all individuals is equal to one. A numerical example verifies the theoretical result.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116508048","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 : 2020-10-23DOI: 10.1109/IAI50351.2020.9262190
Zhenyao Zhao, Guangbin Zhang, Min Jiang, Liang Feng, K. Tan
Neural architecture search (NAS) is the process of automatically searching for the best performing neural model on a given task. Designing a neural model requires a lot of time for experts, NAS's automated process effectively solves this problem and makes neural networks easier to promote. Although NAS has achieved excellent performance, its search process is still very time consuming. In this paper, we propose a neural architecture design method based on distribution estimation method called EDNAS, a fast and economical solution to design neural architecture automatically. In EDNAS, we assume that the best performing architecture obeys a certain probability distribution in search space. Therefore, NAS can be transformed to learning this probability distribution. We construct a probability model on the search space, and search for this probability distribution by iterating the probability model. Finally, an architecture that maximizes the performance on a validation set is generated from this probability distribution. Experiment shows the efficiency of our method. On CIFAR-10 dataset, EDNAS discovers a novel architecture in just 4 hours with 2.89% test error, which shows efficent and strong performance.
{"title":"EDNAS: An Efficient Neural Architecture Design based on Distribution Estimation","authors":"Zhenyao Zhao, Guangbin Zhang, Min Jiang, Liang Feng, K. Tan","doi":"10.1109/IAI50351.2020.9262190","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262190","url":null,"abstract":"Neural architecture search (NAS) is the process of automatically searching for the best performing neural model on a given task. Designing a neural model requires a lot of time for experts, NAS's automated process effectively solves this problem and makes neural networks easier to promote. Although NAS has achieved excellent performance, its search process is still very time consuming. In this paper, we propose a neural architecture design method based on distribution estimation method called EDNAS, a fast and economical solution to design neural architecture automatically. In EDNAS, we assume that the best performing architecture obeys a certain probability distribution in search space. Therefore, NAS can be transformed to learning this probability distribution. We construct a probability model on the search space, and search for this probability distribution by iterating the probability model. Finally, an architecture that maximizes the performance on a validation set is generated from this probability distribution. Experiment shows the efficiency of our method. On CIFAR-10 dataset, EDNAS discovers a novel architecture in just 4 hours with 2.89% test error, which shows efficent and strong performance.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132345661","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 : 2020-10-23DOI: 10.1109/IAI50351.2020.9262168
Yining Wu, Suogui Dang, Huajin Tang, Rui Yan
This paper addresses the problem of improving the fly hashing [1] that is a high-dimensional hash function based on the fruit fly olfactory circuit. The encoding of fly hashing only uses sparsely addition operations instead of the usual costly dense multiplications, and thus results in efficient computations which is important for near duplicate detection tasks in large-scale search system. However, the firing rate based winner-take-all (WTA) circuit of it is neither biologically plausible nor energy saving, and if this circuit is taken into consideration, theoretical results of locality-sensitive are no longer strong. To improve the fly hashing, we proposed a locality-sensitive hash function based on random projection and threshold based spike-threshold-surface (STS) circuit, and both of them are biologically plausible and can be computed very efficiently in hardware. We also presented a strong theoretical analysis of the proposed hash function, and the experimental result supports our proofs. In addition, we performed experiments on datasets SIFT, GloVe and MNIST, and obtained high search precisions as well as fly hashing with less time to consume.
{"title":"An improved hash function inspired by the fly hashing for near duplicate detections","authors":"Yining Wu, Suogui Dang, Huajin Tang, Rui Yan","doi":"10.1109/IAI50351.2020.9262168","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262168","url":null,"abstract":"This paper addresses the problem of improving the fly hashing [1] that is a high-dimensional hash function based on the fruit fly olfactory circuit. The encoding of fly hashing only uses sparsely addition operations instead of the usual costly dense multiplications, and thus results in efficient computations which is important for near duplicate detection tasks in large-scale search system. However, the firing rate based winner-take-all (WTA) circuit of it is neither biologically plausible nor energy saving, and if this circuit is taken into consideration, theoretical results of locality-sensitive are no longer strong. To improve the fly hashing, we proposed a locality-sensitive hash function based on random projection and threshold based spike-threshold-surface (STS) circuit, and both of them are biologically plausible and can be computed very efficiently in hardware. We also presented a strong theoretical analysis of the proposed hash function, and the experimental result supports our proofs. In addition, we performed experiments on datasets SIFT, GloVe and MNIST, and obtained high search precisions as well as fly hashing with less time to consume.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114416468","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 : 2020-10-23DOI: 10.1109/IAI50351.2020.9262206
Guang Yang, Shuoyu Wang, Junyou Yang, Peng Shi
A risk-aware motion control system is presented so that care robots can conduct human-like behaviors by changing the behavior patterns concerning environmental risk. First, a method of evaluating the environmental risk of possible collision is introduced, by measuring the narrowness of the robot-centered space. Then a way of defining and achieving robot behavior patterns through the limitation of velocity and acceleration in the motion controller is presented. Finally, a system integrating the risk evaluation module and behavior adjust module is introduced which allows human-like behaviors upon traditional indoor navigation. Experiments were conducted in a real household environment with our care robot, KUT-PCR, in which the effectiveness of the proposed approach was verified.
{"title":"Risk-Aware Motion Control for Care Robots","authors":"Guang Yang, Shuoyu Wang, Junyou Yang, Peng Shi","doi":"10.1109/IAI50351.2020.9262206","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262206","url":null,"abstract":"A risk-aware motion control system is presented so that care robots can conduct human-like behaviors by changing the behavior patterns concerning environmental risk. First, a method of evaluating the environmental risk of possible collision is introduced, by measuring the narrowness of the robot-centered space. Then a way of defining and achieving robot behavior patterns through the limitation of velocity and acceleration in the motion controller is presented. Finally, a system integrating the risk evaluation module and behavior adjust module is introduced which allows human-like behaviors upon traditional indoor navigation. Experiments were conducted in a real household environment with our care robot, KUT-PCR, in which the effectiveness of the proposed approach was verified.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130095082","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 : 2020-10-23DOI: 10.1109/IAI50351.2020.9262166
Chenjing Meng, Huiping Li
This paper studies the model predictive control problem (MPC) of linear systems with unknown parameters both in system models and measurement models. The method that combines the estimation of system parameters and states with MPC is proposed, where the reinforcement learning (RL) is used to learn the optimal control strategies. Its characteristics are that the control and estimate can proceed simultaneously. Simulation studies verify that the designed algorithm can converge to the optimal linear feedback and the parameters converge as well.
{"title":"Model Predictive Control of Linear Systems with Unknown Parameters","authors":"Chenjing Meng, Huiping Li","doi":"10.1109/IAI50351.2020.9262166","DOIUrl":"https://doi.org/10.1109/IAI50351.2020.9262166","url":null,"abstract":"This paper studies the model predictive control problem (MPC) of linear systems with unknown parameters both in system models and measurement models. The method that combines the estimation of system parameters and states with MPC is proposed, where the reinforcement learning (RL) is used to learn the optimal control strategies. Its characteristics are that the control and estimate can proceed simultaneously. Simulation studies verify that the designed algorithm can converge to the optimal linear feedback and the parameters converge as well.","PeriodicalId":137183,"journal":{"name":"2020 2nd International Conference on Industrial Artificial Intelligence (IAI)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128281072","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：