Pub Date : 2021-11-08DOI: 10.1109/IAI53119.2021.9619297
Xi Liu, Zhifu Tao, Qiang Liu, Ligang Zhou
In this study, some concepts are developed such as probabilistic hesitant fuzzy soft set (PHFSS), a combination of probabilistic hesitant fuzzy set and soft set. PHFSS can be used to describe the uncertainty and complexity in practical evaluation problems. Herein, the relationships between any two PHFSSs are proposed, including the relation of inclusion, equivalence and complement. Considering that correlation coefficient is one of the most important tools in data analysis and decision making, we develop a novel correlation coefficient formulation to measure the interrelationship between the PHFSSs. Meanwhile, the mean and the variance of a PHFSS are defined. The properties of the proposed correlation coefficient are also discussed. Finally, a numerical evaluation example in business environment satisfaction is proposed to illustrate the feasibility and rationality of the given correlation coefficient between PHFSSs.
{"title":"Correlation Coefficient of Probabilistic Hesitant Fuzzy Soft Set and Its Applications in Decision Making","authors":"Xi Liu, Zhifu Tao, Qiang Liu, Ligang Zhou","doi":"10.1109/IAI53119.2021.9619297","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619297","url":null,"abstract":"In this study, some concepts are developed such as probabilistic hesitant fuzzy soft set (PHFSS), a combination of probabilistic hesitant fuzzy set and soft set. PHFSS can be used to describe the uncertainty and complexity in practical evaluation problems. Herein, the relationships between any two PHFSSs are proposed, including the relation of inclusion, equivalence and complement. Considering that correlation coefficient is one of the most important tools in data analysis and decision making, we develop a novel correlation coefficient formulation to measure the interrelationship between the PHFSSs. Meanwhile, the mean and the variance of a PHFSS are defined. The properties of the proposed correlation coefficient are also discussed. Finally, a numerical evaluation example in business environment satisfaction is proposed to illustrate the feasibility and rationality of the given correlation coefficient between PHFSSs.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"31 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":"126590744","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/IAI53119.2021.9619276
Heng Xia, Jian Tang
Recently deep forest has been modified and applied to regression modeling, namely Deep Forest Regression (DFR). Its results are satisfactory in small sample datasets. However, the diversity of forests is not fully utilized. Therefore, in this paper, an improved DFR (ImDFR) algorithm is proposed to promote regression modeling. With the structural framework unchanged, random forest, completely random forest, GBDT and XGBoost are used as sub-forests at each layer to increase diversity. We applied the proposed method to the high-dimensional and low-dimensional benchmark datasets. Experimental results demonstrate that ImDFR can achieve better prediction results than other approaches, and the results prove that proposed model is effective.
{"title":"An Improved Deep Forest Regression*","authors":"Heng Xia, Jian Tang","doi":"10.1109/IAI53119.2021.9619276","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619276","url":null,"abstract":"Recently deep forest has been modified and applied to regression modeling, namely Deep Forest Regression (DFR). Its results are satisfactory in small sample datasets. However, the diversity of forests is not fully utilized. Therefore, in this paper, an improved DFR (ImDFR) algorithm is proposed to promote regression modeling. With the structural framework unchanged, random forest, completely random forest, GBDT and XGBoost are used as sub-forests at each layer to increase diversity. We applied the proposed method to the high-dimensional and low-dimensional benchmark datasets. Experimental results demonstrate that ImDFR can achieve better prediction results than other approaches, and the results prove that proposed model is effective.","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":"125144062","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/IAI53119.2021.9619317
P. Albertos, Alicia Esparza
There are processes whose dynamic behavior is defined at different frequencies, their models being difficult to deal with as a whole. The modeling and the control design procedures can be simplified if the process is split in different components characterizing its behavior in a given range of frequencies. This idea was successfully applied in the iterative identification and control design strategy and it was reported in some previous papers. In this paper, assuming the full model of the plant, the control is designed dealing with partial process models being appropriate to represent the plant behavior in the frequency range where this control is intended to act. This brings some advantages: first, the control design is simplified as it only takes care of a range of frequencies. Moreover, in order to save resources, the control can be implemented in a multirate scheme. Several examples of processes with flexible components are considered to design their control.
{"title":"Plant model frequency scale decomposition for identification and control design","authors":"P. Albertos, Alicia Esparza","doi":"10.1109/IAI53119.2021.9619317","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619317","url":null,"abstract":"There are processes whose dynamic behavior is defined at different frequencies, their models being difficult to deal with as a whole. The modeling and the control design procedures can be simplified if the process is split in different components characterizing its behavior in a given range of frequencies. This idea was successfully applied in the iterative identification and control design strategy and it was reported in some previous papers. In this paper, assuming the full model of the plant, the control is designed dealing with partial process models being appropriate to represent the plant behavior in the frequency range where this control is intended to act. This brings some advantages: first, the control design is simplified as it only takes care of a range of frequencies. Moreover, in order to save resources, the control can be implemented in a multirate scheme. Several examples of processes with flexible components are considered to design their control.","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":"131397667","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/IAI53119.2021.9619388
J. Wang, A. Zhang, Le Ren, D. Chang, Jing Ma, Qianyu He
a preprocessing method is proposed for welding electrical signals based on Variational Mode Decomposition (VMD) and Hilbert marginal spectrum. This method solves the problem of poor quality of welding electric signal caused by multifactor interference, especially high frequency interference of inverted power source. In this paper, an acquisition system of the electrical signals of ultra-narrow gap welding was constructed to obtain the electrical signals of welding arc and resistance box load. Based on analyzing the signal characteristics, the signals were decomposed by VMD, and then Hilbert marginal spectrum was used for comparative analysis to filter out the interference noise and realize the preprocessing of welding electrical signal. The results show the proposed method can effectively eliminate the noise while retaining the valuable high-frequency components in the signal, which improves the authenticity of the signal.
{"title":"A preprocessing method of welding electrical signal","authors":"J. Wang, A. Zhang, Le Ren, D. Chang, Jing Ma, Qianyu He","doi":"10.1109/IAI53119.2021.9619388","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619388","url":null,"abstract":"a preprocessing method is proposed for welding electrical signals based on Variational Mode Decomposition (VMD) and Hilbert marginal spectrum. This method solves the problem of poor quality of welding electric signal caused by multifactor interference, especially high frequency interference of inverted power source. In this paper, an acquisition system of the electrical signals of ultra-narrow gap welding was constructed to obtain the electrical signals of welding arc and resistance box load. Based on analyzing the signal characteristics, the signals were decomposed by VMD, and then Hilbert marginal spectrum was used for comparative analysis to filter out the interference noise and realize the preprocessing of welding electrical signal. The results show the proposed method can effectively eliminate the noise while retaining the valuable high-frequency components in the signal, which improves the authenticity of the signal.","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":"115108851","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/IAI53119.2021.9619344
Xiasheng Shi, Lei Ma, Xuesong Wang
In this paper, the economic dispatch problem over the undirected network is considered, which aims to minimize the total power generation cost. In order to solve the equality constraint, the Lagrangian dual problem is developed and a fast distributed continuous-time algorithm is designed for the dual variable based on the fixed-time stability theory. Furthermore, the optimal solution of the economic dispatch problem is obtained by a well-developed projector and the above proposed algorithm is initialization-free and privacy-guaranteed. Finally, several examples are provided for illustrating the effectiveness of our proposed algorithms.
{"title":"A distributed continuous-time algorithm for economic dispatch problem","authors":"Xiasheng Shi, Lei Ma, Xuesong Wang","doi":"10.1109/IAI53119.2021.9619344","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619344","url":null,"abstract":"In this paper, the economic dispatch problem over the undirected network is considered, which aims to minimize the total power generation cost. In order to solve the equality constraint, the Lagrangian dual problem is developed and a fast distributed continuous-time algorithm is designed for the dual variable based on the fixed-time stability theory. Furthermore, the optimal solution of the economic dispatch problem is obtained by a well-developed projector and the above proposed algorithm is initialization-free and privacy-guaranteed. Finally, several examples are provided for illustrating the effectiveness of our proposed algorithms.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"84 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":"116095687","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/IAI53119.2021.9619229
Li Chi, Yong-Feng Gao
In this communique, a technique is proposed to convert general nonlinear continuous event-triggered control systems to periodic event-triggered control systems. The main idea is based on a nonlinear time invariant dynamic, that can be used to upper bound a internal variant between two successive sampling times. The redesigned periodic event-triggering mechanism guarantees the corresponding periodic event-triggered control system preserving the control performance of the original continuous event-triggered control system.
{"title":"Periodic Event-Triggering Mechanisms for Nonlinear Event-triggered Control Systems","authors":"Li Chi, Yong-Feng Gao","doi":"10.1109/IAI53119.2021.9619229","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619229","url":null,"abstract":"In this communique, a technique is proposed to convert general nonlinear continuous event-triggered control systems to periodic event-triggered control systems. The main idea is based on a nonlinear time invariant dynamic, that can be used to upper bound a internal variant between two successive sampling times. The redesigned periodic event-triggering mechanism guarantees the corresponding periodic event-triggered control system preserving the control performance of the original continuous event-triggered control system.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"24 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":"123753724","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}
Fast, robust and accurate system identification is of importance to the process industry, and identification from step response is a prevalent approach. Recently, a new method based on rank constraint using low-quality industrial data has been proposed. However, with mean square error (MSE) used as the loss function, this identification method is sensitive to outliers, which may occasionally lead to invalid models. In this paper, we propose an improved robust process identification approach from step response data based on the Huber loss, which is less sensitive to outliers than generic MSE, and leads to a higher successful rate. A tailored solution algorithm based on alternating direction method of multipliers is developed, which, however, requires heavy computational cost especially when there are massive control loops to be identified simultaneously. To address this issue, we leverage recent advances in parallel computing. We show that this solution procedure can be parallelized, which leads to significant computation savings with graphical processing units used, and thus better conforms to requirement in practical situations. Numerical studies demonstrate that our proposed method is more robust against outliers, and the parallel implementation gives a faster speed in the presence of massive data.
{"title":"Robust Process Identification from Step Response Data and Parallel Implementation","authors":"Yucheng Han, Qingyuan Liu, Chao Shang, Dexian Huang","doi":"10.1109/IAI53119.2021.9619360","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619360","url":null,"abstract":"Fast, robust and accurate system identification is of importance to the process industry, and identification from step response is a prevalent approach. Recently, a new method based on rank constraint using low-quality industrial data has been proposed. However, with mean square error (MSE) used as the loss function, this identification method is sensitive to outliers, which may occasionally lead to invalid models. In this paper, we propose an improved robust process identification approach from step response data based on the Huber loss, which is less sensitive to outliers than generic MSE, and leads to a higher successful rate. A tailored solution algorithm based on alternating direction method of multipliers is developed, which, however, requires heavy computational cost especially when there are massive control loops to be identified simultaneously. To address this issue, we leverage recent advances in parallel computing. We show that this solution procedure can be parallelized, which leads to significant computation savings with graphical processing units used, and thus better conforms to requirement in practical situations. Numerical studies demonstrate that our proposed method is more robust against outliers, and the parallel implementation gives a faster speed in the presence of massive data.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"40 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":"127001573","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/IAI53119.2021.9619308
Yunpeng He, C. Zang, Peng Zeng, Mingxin Wang, Qingwei Dong, Yuqi Liu
As an essential component of mechanical equipment, the state of the rolling bearing has a substantial impact on the operation of the entire automatic system. The fault diagnostic technology based on deep learning surpasses the traditional fault diagnosis technology in many aspects and dramatically improves the accuracy of fault diagnosis but requires a massive amount of labeled data for training. Generally, it takes a lot of effort to obtain tagged data in a natural industrial environment. Therefore, this paper proposes a rolling bearing fault diagnosis method based on meta-learning, which applies the experience learned in the past to new tasks to use few-shot labeled rolling bearing fault samples for training to obtain reliable diagnosis accuracy. The results show that the proposed method can significantly improve few-shot rolling bearing fault samples' accuracy than other traditional methods.
{"title":"Rolling Bearing Fault Diagnosis Based on Meta-Learning with Few-Shot Samples","authors":"Yunpeng He, C. Zang, Peng Zeng, Mingxin Wang, Qingwei Dong, Yuqi Liu","doi":"10.1109/IAI53119.2021.9619308","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619308","url":null,"abstract":"As an essential component of mechanical equipment, the state of the rolling bearing has a substantial impact on the operation of the entire automatic system. The fault diagnostic technology based on deep learning surpasses the traditional fault diagnosis technology in many aspects and dramatically improves the accuracy of fault diagnosis but requires a massive amount of labeled data for training. Generally, it takes a lot of effort to obtain tagged data in a natural industrial environment. Therefore, this paper proposes a rolling bearing fault diagnosis method based on meta-learning, which applies the experience learned in the past to new tasks to use few-shot labeled rolling bearing fault samples for training to obtain reliable diagnosis accuracy. The results show that the proposed method can significantly improve few-shot rolling bearing fault samples' accuracy than other traditional methods.","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":"129296568","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/IAI53119.2021.9619441
Xiangwei Zeng, Guojian He, Yan Zhuang
In this paper, a B-Spline-based trajectory estimation method is proposed and implemented based on the state-of-the-art LiDAR-SLAM framework LIOM. The proposed method parameterizes the trajectory with the cubic uniform B-Spline and performs a batch optimization within a local map to get LiDAR poses. Real-world experiments are conducted and the results demonstrate the high robustness and accuracy of the proposed method in challenging environments for handled LiDAR-SLAM applications.
{"title":"B-Spline-Based Trajectory Estimation for Handheld LiDAR-SLAM Device","authors":"Xiangwei Zeng, Guojian He, Yan Zhuang","doi":"10.1109/IAI53119.2021.9619441","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619441","url":null,"abstract":"In this paper, a B-Spline-based trajectory estimation method is proposed and implemented based on the state-of-the-art LiDAR-SLAM framework LIOM. The proposed method parameterizes the trajectory with the cubic uniform B-Spline and performs a batch optimization within a local map to get LiDAR poses. Real-world experiments are conducted and the results demonstrate the high robustness and accuracy of the proposed method in challenging environments for handled LiDAR-SLAM applications.","PeriodicalId":106675,"journal":{"name":"2021 3rd International Conference on Industrial Artificial Intelligence (IAI)","volume":"128 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":"133571525","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/IAI53119.2021.9619455
Haitao Guo, Jian Tang, Hao Zhang, Dandan Wang
This article is to provide qualified images of abnormal combustion state for the research of machine vision in municipal solid waste incineration (MSWI) process. Owing to the scarcity of the images of abnormal combustion state and the high cost of labeling, it is difficult to obtain sufficient images of abnormal combustion state. Aim at the problem, this paper proposes a method for generating images of abnormal combustion state based on a deep convolutional generative adversarial network (DCGAN). First, the real image data of abnormal combustion state is preprocessed. Second, the abnormal combustion state image generation generates false combustion images. Third, the real images and the generated images are fed into the discrimination network. The loss values are used to train the discrimination and generation. Finally, whether to update the parameters of the generation and discrimination network is determined by the error and epoch. The qualified generated abnormal combustion state images are obtained after the epoch setting met. The evaluation result of the generated image quality based on the Fréchet Inception Distance (FID) shows that DCGAN can realize the generation of abnormal combustion state images.
{"title":"A method for generating images of abnormal combustion state in MSWI process based on DCGAN","authors":"Haitao Guo, Jian Tang, Hao Zhang, Dandan Wang","doi":"10.1109/IAI53119.2021.9619455","DOIUrl":"https://doi.org/10.1109/IAI53119.2021.9619455","url":null,"abstract":"This article is to provide qualified images of abnormal combustion state for the research of machine vision in municipal solid waste incineration (MSWI) process. Owing to the scarcity of the images of abnormal combustion state and the high cost of labeling, it is difficult to obtain sufficient images of abnormal combustion state. Aim at the problem, this paper proposes a method for generating images of abnormal combustion state based on a deep convolutional generative adversarial network (DCGAN). First, the real image data of abnormal combustion state is preprocessed. Second, the abnormal combustion state image generation generates false combustion images. Third, the real images and the generated images are fed into the discrimination network. The loss values are used to train the discrimination and generation. Finally, whether to update the parameters of the generation and discrimination network is determined by the error and epoch. The qualified generated abnormal combustion state images are obtained after the epoch setting met. The evaluation result of the generated image quality based on the Fréchet Inception Distance (FID) shows that DCGAN can realize the generation of abnormal combustion state images.","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":"130517370","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：