Pub Date : 2021-11-08DOI: 10.1109/IAI53119.2021.9619245
Wei Liu, Yuan Zhang, Le Zhou, Yuting Lyu
Pulsed thermography (PT) is a well-established non-destructive testing technique for the subsurface defect detection in Carbon Fiber Reinforced Polymer (CFRP). Among the analysis methods for the thermographic data, principal component thermography (PCT) and sparse principal component thermography (SPCT) are recommended for visualization enhancement of defect signals. However, since the methods of PCT and SPCT are performed directly based on the characteristic matrix model of the original thermal images, their results are heavily affected by the noise and uneven background signals inside the images. To solve the problem above, a new method known as difference of Gaussian convolutional sparse principal component thermography (DoG-SPCT) is proposed in this paper. The method first separates defect signals from the interference with a DoG filter, and then extracts features for defective areas by SPCT to enhance visualization of defects. In the experimental part, one CFRP specimen with subsurface defects is detected by PT and the proposed DoG-SPCT is evaluated for the defect visualization enhancing purpose. The result of the experiment shows that the DoG filter can separate the defect components from the noise and uneven background signals, so that the features for defective regions can be effectively extracted in the following SPCT.
{"title":"Difference of Gaussian Convolutional Sparse Principal Component Thermography for Defect Signal Enhance in Composite Materials","authors":"Wei Liu, Yuan Zhang, Le Zhou, Yuting Lyu","doi":"10.1109/IAI53119.2021.9619245","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619245","url":null,"abstract":"Pulsed thermography (PT) is a well-established non-destructive testing technique for the subsurface defect detection in Carbon Fiber Reinforced Polymer (CFRP). Among the analysis methods for the thermographic data, principal component thermography (PCT) and sparse principal component thermography (SPCT) are recommended for visualization enhancement of defect signals. However, since the methods of PCT and SPCT are performed directly based on the characteristic matrix model of the original thermal images, their results are heavily affected by the noise and uneven background signals inside the images. To solve the problem above, a new method known as difference of Gaussian convolutional sparse principal component thermography (DoG-SPCT) is proposed in this paper. The method first separates defect signals from the interference with a DoG filter, and then extracts features for defective areas by SPCT to enhance visualization of defects. In the experimental part, one CFRP specimen with subsurface defects is detected by PT and the proposed DoG-SPCT is evaluated for the defect visualization enhancing purpose. The result of the experiment shows that the DoG filter can separate the defect components from the noise and uneven background signals, so that the features for defective regions can be effectively extracted in the following SPCT.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"7 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":"133483611","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/IAI53119.2021.9619381
Qiang Deng, Hang Wang, Xiaokun Wang
Ensuring the safe operation of nuclear facilities has always been an important research topic in the development of nuclear energy. Therefore, a variety of methods have been proposed in the world for fault diagnosis of nuclear facilities to assist operators. In order to make full use of the characteristic information of time series data and improve the accuracy of fault diagnosis of electric valves in nuclear facilities, this paper proposes a new convolutional gated recurrent unit and support vector machine (CGRU_SVM) fault diagnosis network model. This model uses the convolution kernel to extract the features of the data, then uses the gated recurrent unit (GRU) to extract the timing features, and finally inputs the processed feature information into the support vector machine (SVM) for classification. Experiments have shown that the accuracy of this method for fault diagnosis of electric valves can reach more than 99.9%, for the failure to detect nuclear facilities electric valves, electric valves guarantee safe and reliable operation of guiding significance.
{"title":"Research on Fault Diagnosis Method of Electric Valve Based on Convolutional Gated Recurrent Unit and Support vector machine","authors":"Qiang Deng, Hang Wang, Xiaokun Wang","doi":"10.1109/IAI53119.2021.9619381","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619381","url":null,"abstract":"Ensuring the safe operation of nuclear facilities has always been an important research topic in the development of nuclear energy. Therefore, a variety of methods have been proposed in the world for fault diagnosis of nuclear facilities to assist operators. In order to make full use of the characteristic information of time series data and improve the accuracy of fault diagnosis of electric valves in nuclear facilities, this paper proposes a new convolutional gated recurrent unit and support vector machine (CGRU_SVM) fault diagnosis network model. This model uses the convolution kernel to extract the features of the data, then uses the gated recurrent unit (GRU) to extract the timing features, and finally inputs the processed feature information into the support vector machine (SVM) for classification. Experiments have shown that the accuracy of this method for fault diagnosis of electric valves can reach more than 99.9%, for the failure to detect nuclear facilities electric valves, electric valves guarantee safe and reliable operation of guiding significance.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"6 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":"123848945","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}
Industrial software testing including software development and debugging depends on the external input interface. The development, debugging and adaptation of interface software simulation consumes a lot of time. The process of software evaluation and self-test lack a portable general software testing equipment suitable for the industrial field, in order to greatly improve the testing efficiency, test integrity and adequacy. Therefore, it is urgent for the general interface generation platform to be transformed into high performance such as hardware, distributed, hardware interface adaptation, test task load and high real-time. In this paper, the overall design framework of portable general software test equipment is carried out, which includes the design and software development of the execution host, the software transformation of general control host and other research contents. At the same time, a portable general software testing equipment for complex industrial system software and multiple interfaces is developed. This platform can satisfy the diversity of complex industrial software system interfaces and the real-time requirements of special systems. It is expected to further promote the development of interface testing automation.
{"title":"Research on an autonomous and controllable portable universal interface test platform","authors":"Yiming Xu, Baoqiang Liu, Xiaoqiang Wang, Haitao Zhang, Zhongcai Zhang","doi":"10.1109/IAI53119.2021.9619437","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619437","url":null,"abstract":"Industrial software testing including software development and debugging depends on the external input interface. The development, debugging and adaptation of interface software simulation consumes a lot of time. The process of software evaluation and self-test lack a portable general software testing equipment suitable for the industrial field, in order to greatly improve the testing efficiency, test integrity and adequacy. Therefore, it is urgent for the general interface generation platform to be transformed into high performance such as hardware, distributed, hardware interface adaptation, test task load and high real-time. In this paper, the overall design framework of portable general software test equipment is carried out, which includes the design and software development of the execution host, the software transformation of general control host and other research contents. At the same time, a portable general software testing equipment for complex industrial system software and multiple interfaces is developed. This platform can satisfy the diversity of complex industrial software system interfaces and the real-time requirements of special systems. It is expected to further promote the development of interface testing automation.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"71 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":"124725269","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/IAI53119.2021.9619400
Xian-geng Shen, Jinhai Liu, He Zhao, Xiaoyuan Liu, Baojin Zhang
Magnetic Flux Leakage (MFL)internal detection is the main technology to detect long-distance oil pipelines. Aiming at the low detection accuracy and poor versatility of existing pipeline magnetic flux leakage signal target recognition algorithms, this paper proposes a pipeline magnetic flux leakage signal target recognition algorithm based on improved Cascade RCNN. Firstly, an adaptive image conversion method is proposed to convert the original magnetic flux leakage data into colormap. Secondly, Feature Pyramid Networks (FPN) and Online Hard Example Mining (OHEM) are added to Cascade RCNN to improve target detection accuracy. Finally, the effectiveness of the method is verified through comparative experiments. The results indicate that the method proposed in this paper is effective.
{"title":"Research on Multi-target Recognition Algorithm of Pipeline Magnetic Flux Leakage Signal Based on Improved Cascade RCNN","authors":"Xian-geng Shen, Jinhai Liu, He Zhao, Xiaoyuan Liu, Baojin Zhang","doi":"10.1109/IAI53119.2021.9619400","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619400","url":null,"abstract":"Magnetic Flux Leakage (MFL)internal detection is the main technology to detect long-distance oil pipelines. Aiming at the low detection accuracy and poor versatility of existing pipeline magnetic flux leakage signal target recognition algorithms, this paper proposes a pipeline magnetic flux leakage signal target recognition algorithm based on improved Cascade RCNN. Firstly, an adaptive image conversion method is proposed to convert the original magnetic flux leakage data into colormap. Secondly, Feature Pyramid Networks (FPN) and Online Hard Example Mining (OHEM) are added to Cascade RCNN to improve target detection accuracy. Finally, the effectiveness of the method is verified through comparative experiments. The results indicate that the method proposed in this paper is effective.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"46 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":"122799726","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/IAI53119.2021.9619288
Jiyang Yuan, Mengwen Zhang, Yumei Wang
To promote the standardization and institutionalization of public cultural services and improve the service level. The improvement of public cultural service system in the Internet era is an important way to constantly meet the diverse cultural needs of the public. This paper analyzes the influencing factors and mechanism of public cultural service level, constructs a scientific index system, and puts forward targeted countermeasures, so as to promote the overall level of public cultural service in the Internet era.
{"title":"Research on Big Data Evaluation of China’s Public Cultural Service Level in the Internet Era","authors":"Jiyang Yuan, Mengwen Zhang, Yumei Wang","doi":"10.1109/IAI53119.2021.9619288","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619288","url":null,"abstract":"To promote the standardization and institutionalization of public cultural services and improve the service level. The improvement of public cultural service system in the Internet era is an important way to constantly meet the diverse cultural needs of the public. This paper analyzes the influencing factors and mechanism of public cultural service level, constructs a scientific index system, and puts forward targeted countermeasures, so as to promote the overall level of public cultural service in the Internet era.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"4 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":"131869791","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/IAI53119.2021.9619392
Qianle Tao, Chengxin Xian, Yu Zhao
This paper considers the Nash equilibrium seeking problem of the game in the multi-agent system. Different from the existing research, a new method is proposed by multi-step planning to solve the pre-specified-time game, which based on the technique of the leader-following consensus protocol and gradient play. The algorithm, which players can update their action at each sampling moment, is designed to enable each player’s behavior converge to the Nash equilibrium point of the game at a specified time that can be appointed in advance. In addition, the players communicate via an undirected and connected network. Finally, the algorithm proposed in this paper is verified by numerical simulations.
{"title":"Pre-specified-time Distributed Nash Equilibrium Seeking for Games","authors":"Qianle Tao, Chengxin Xian, Yu Zhao","doi":"10.1109/IAI53119.2021.9619392","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619392","url":null,"abstract":"This paper considers the Nash equilibrium seeking problem of the game in the multi-agent system. Different from the existing research, a new method is proposed by multi-step planning to solve the pre-specified-time game, which based on the technique of the leader-following consensus protocol and gradient play. The algorithm, which players can update their action at each sampling moment, is designed to enable each player’s behavior converge to the Nash equilibrium point of the game at a specified time that can be appointed in advance. In addition, the players communicate via an undirected and connected network. Finally, the algorithm proposed in this paper is verified by numerical simulations.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"88 10 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":"127999280","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/IAI53119.2021.9619305
Tianyi Lu, Qiong Xia, Liangliang Sun, Yupeng Li, Wanying Zhu, Juan Wang, Baolong Yuan, Yi Pan
The objective of this paper is to optimise the slab heating process in a dynamic environment. Considering the nonlinear and hysteresis characteristics of slab heating in the furnace production process, an operational optimisation model based on a mixture of mechanism and data and a predictive control model for the furnace are developed. The operation optimisation model determines the current optimal furnace temperature distribution based on the desired slab temperature and the current slab temperature, which is then fed into the predictive control model. The predictive control model uses a rolling optimisation method to predict the furnace temperature and adjusts the fuel flow to change the furnace temperature with the desired temperature as the target, thus enabling the slab to reach the desired temperature through an integrated optimisation method. Finally, a large number of simulation data experiments prove that the furnace temperature change process meets the set requirements, and the goal of improving the production process of the heating furnace is achieved.
{"title":"Study on the Integrated Optimization of Heating Furnace Production Process","authors":"Tianyi Lu, Qiong Xia, Liangliang Sun, Yupeng Li, Wanying Zhu, Juan Wang, Baolong Yuan, Yi Pan","doi":"10.1109/IAI53119.2021.9619305","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619305","url":null,"abstract":"The objective of this paper is to optimise the slab heating process in a dynamic environment. Considering the nonlinear and hysteresis characteristics of slab heating in the furnace production process, an operational optimisation model based on a mixture of mechanism and data and a predictive control model for the furnace are developed. The operation optimisation model determines the current optimal furnace temperature distribution based on the desired slab temperature and the current slab temperature, which is then fed into the predictive control model. The predictive control model uses a rolling optimisation method to predict the furnace temperature and adjusts the fuel flow to change the furnace temperature with the desired temperature as the target, thus enabling the slab to reach the desired temperature through an integrated optimisation method. Finally, a large number of simulation data experiments prove that the furnace temperature change process meets the set requirements, and the goal of improving the production process of the heating furnace is achieved.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"5 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":"126187694","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：