Pub Date : 2022-08-24DOI: 10.1109/IAI55780.2022.9976628
Ying Qian, Lianbo Ma
Federated learning is an emerging machine learning paradigm for privacy protection for data owners, without private user data leaving the devices. Massive data collection devices are distributed in an edge computing terminal, which provide a scenario for the application of federated learning. In this article, a new federated learning algorithm to edge computing, via using transfer learning technology, is proposed to address the challenges of small data samples and resource-poor devices faced by training of deep neural networks (DNNs) on end devices. Due to edge servers have enough resources to train a DNN model compared with edge devices, the algorithm trains the model on the cloud server by using public data sets and adds batch-normalization (BN) layer which only contains a small set of parameters as patch in the model. Then, edge devices download the pre-training model, the weights of which are fixed except the patch layers. The patch layers parameters are trained by using local data, which aggregate by the edge server.
{"title":"Parameter-Efficient Federated Learning for Edge Computing with End Devices Resource Limitation","authors":"Ying Qian, Lianbo Ma","doi":"10.1109/IAI55780.2022.9976628","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976628","url":null,"abstract":"Federated learning is an emerging machine learning paradigm for privacy protection for data owners, without private user data leaving the devices. Massive data collection devices are distributed in an edge computing terminal, which provide a scenario for the application of federated learning. In this article, a new federated learning algorithm to edge computing, via using transfer learning technology, is proposed to address the challenges of small data samples and resource-poor devices faced by training of deep neural networks (DNNs) on end devices. Due to edge servers have enough resources to train a DNN model compared with edge devices, the algorithm trains the model on the cloud server by using public data sets and adds batch-normalization (BN) layer which only contains a small set of parameters as patch in the model. Then, edge devices download the pre-training model, the weights of which are fixed except the patch layers. The patch layers parameters are trained by using local data, which aggregate by the edge server.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131242876","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976614
Liang Zhao
The utility system is a popular research field in process optimization. At the same time, widespread uncertainties pose new challenges to this issue. This paper presents a data-driven two-stage stochastic programming (TSSP) to hedge against uncertainty. A kernel density estimation (KDE) method is used to calculate the probability density function from uncertain data. Based on the derived probability density function, Latin Hypercube Sampling (LHS) samples 8-dimension uncertain data to generate different scenarios. Lastly, a real-world case study is conducted to demonstrate the effectiveness of the approach.
{"title":"Data-driven two-stage stochastic programming for utility system optimization under uncertainty","authors":"Liang Zhao","doi":"10.1109/IAI55780.2022.9976614","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976614","url":null,"abstract":"The utility system is a popular research field in process optimization. At the same time, widespread uncertainties pose new challenges to this issue. This paper presents a data-driven two-stage stochastic programming (TSSP) to hedge against uncertainty. A kernel density estimation (KDE) method is used to calculate the probability density function from uncertain data. Based on the derived probability density function, Latin Hypercube Sampling (LHS) samples 8-dimension uncertain data to generate different scenarios. Lastly, a real-world case study is conducted to demonstrate the effectiveness of the approach.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131847472","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976721
Yuanqiang Zhou, Dewei Li, Xin Lai, F. Gao
Iterative learning control (ILC) and model predic-tive control (MPC) are both effective control methods for batch processes. Using ILC and MPC together, we propose a combined design scheme for nonlinear constrained batch processes. This scheme utilizes the historical batch data, as well as the current measurements about the process through a two-dimensional (2D) framework. In our combined 2D design scheme, the ILC part is designed using optimal run-to-run feedback with the historical batch data, while the MPC part is designed using real-time feed-back with the current sampled measurements within the batch. By combining the run-to-run ILC and the real-time feedback-based MPC, the current control inputs are optimized based on historical batch data and real-time measurements, resulting in enhanced control performance in both the batch and time directions, as well as the ability to deal with enforced constraints in the time direction. Our design allows control objectives to be attained in several successive batches, not necessarily in a single batch. Finally, a rigorous theoretical analysis has been presented to demonstrate the perfect tracking stability of the combined scheme.
{"title":"Combined Iterative Learning and Model Predictive Control Scheme for Nonlinear Batch Processes","authors":"Yuanqiang Zhou, Dewei Li, Xin Lai, F. Gao","doi":"10.1109/IAI55780.2022.9976721","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976721","url":null,"abstract":"Iterative learning control (ILC) and model predic-tive control (MPC) are both effective control methods for batch processes. Using ILC and MPC together, we propose a combined design scheme for nonlinear constrained batch processes. This scheme utilizes the historical batch data, as well as the current measurements about the process through a two-dimensional (2D) framework. In our combined 2D design scheme, the ILC part is designed using optimal run-to-run feedback with the historical batch data, while the MPC part is designed using real-time feed-back with the current sampled measurements within the batch. By combining the run-to-run ILC and the real-time feedback-based MPC, the current control inputs are optimized based on historical batch data and real-time measurements, resulting in enhanced control performance in both the batch and time directions, as well as the ability to deal with enforced constraints in the time direction. Our design allows control objectives to be attained in several successive batches, not necessarily in a single batch. Finally, a rigorous theoretical analysis has been presented to demonstrate the perfect tracking stability of the combined scheme.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124198505","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976530
Guangze Zhou, Zhong Luo, Yunpeng Zhu, Yi Gao, Zhiao Wang
Model based online fault detection often conducted by extracting features from models driven by system input and output data under various working conditions. The efficiency of online system modelling is therefore significant to improve the performance of online fault detections. In this study, a novel fast data-driven modelling approach, known as the OMP (Orthogonal Matching Pursuit)- ERR (Error Reduction Ratio) method is proposed to improve the efficiency of online fault detections. The new system identification method is motivated by noticing that the traditional OMP algorithm is much faster but usually less accurate than the OLS (Orthogonal least squares) algorithm in the identification of system NARX (Nonlinear Auto-Regressive with Exogenous inputs) models. The problem is first illustrated by the identification of a Single Degree of Freedom (SDoF) system. After that, the OMP-ERR algorithm is developed to improve the NARX modelling efficiency for the purpose of system model-based online fault detections. A case study on the crack detection of a cantilever beam shows that the new approach is over 10 times faster than the traditional OLS modelling process, demonstrating the promising applications of the new approach in online fault detections in engineering practice.
{"title":"Data-driven Model Based Online Fault Detection Using OMP-ERR","authors":"Guangze Zhou, Zhong Luo, Yunpeng Zhu, Yi Gao, Zhiao Wang","doi":"10.1109/IAI55780.2022.9976530","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976530","url":null,"abstract":"Model based online fault detection often conducted by extracting features from models driven by system input and output data under various working conditions. The efficiency of online system modelling is therefore significant to improve the performance of online fault detections. In this study, a novel fast data-driven modelling approach, known as the OMP (Orthogonal Matching Pursuit)- ERR (Error Reduction Ratio) method is proposed to improve the efficiency of online fault detections. The new system identification method is motivated by noticing that the traditional OMP algorithm is much faster but usually less accurate than the OLS (Orthogonal least squares) algorithm in the identification of system NARX (Nonlinear Auto-Regressive with Exogenous inputs) models. The problem is first illustrated by the identification of a Single Degree of Freedom (SDoF) system. After that, the OMP-ERR algorithm is developed to improve the NARX modelling efficiency for the purpose of system model-based online fault detections. A case study on the crack detection of a cantilever beam shows that the new approach is over 10 times faster than the traditional OLS modelling process, demonstrating the promising applications of the new approach in online fault detections in engineering practice.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116990710","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976857
Yuyu Weng, Gang Yang, Cailing Tang, Hui Yang, Rongxiu Lu, Fangping Xu, Jiang Luo
On the one hand, although the supervised learning methods have been used for image rain removal task, such methods have obvious limitations because maybe there is no or only few paired images with-without rain. On the other hand, problems such as color distortion and the inpainting of background information is not clear enough also limit the processing effect of unsupervised methods for image rain removal. An improved CycleGAN (iCycleGAN) was proposed to remove rain streak from a single image. First of all, CycleGAN's transfer learning ability and cyclic structure can solve the problem of the lack of paired data sets. Secondly, a densely connected convolutional network (DenseNet) was added to the generator backbone network to improve the protection of high-frequency information such as background textures, and a CBAM attention mechanism was added to the generator to focus on the repaired area near the rain streak and obtain a clearer repaired image. Finally, feature perceptual loss was introduced to strengthen the constraint of image feature restoration and obtain more realistic results. In order to verify the effectiveness of the proposed method, training was conducted on Rain100L and Rian800 data sets. The comparison of experimental results shows that the model is superior to the existing unsupervised methods in the overall repair effect, and also has comparable inpainting effect compared with mainstream supervised methods.
{"title":"iCycleGAN: An Improved CycleGAN for Rain Streak Removal From Single Image","authors":"Yuyu Weng, Gang Yang, Cailing Tang, Hui Yang, Rongxiu Lu, Fangping Xu, Jiang Luo","doi":"10.1109/IAI55780.2022.9976857","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976857","url":null,"abstract":"On the one hand, although the supervised learning methods have been used for image rain removal task, such methods have obvious limitations because maybe there is no or only few paired images with-without rain. On the other hand, problems such as color distortion and the inpainting of background information is not clear enough also limit the processing effect of unsupervised methods for image rain removal. An improved CycleGAN (iCycleGAN) was proposed to remove rain streak from a single image. First of all, CycleGAN's transfer learning ability and cyclic structure can solve the problem of the lack of paired data sets. Secondly, a densely connected convolutional network (DenseNet) was added to the generator backbone network to improve the protection of high-frequency information such as background textures, and a CBAM attention mechanism was added to the generator to focus on the repaired area near the rain streak and obtain a clearer repaired image. Finally, feature perceptual loss was introduced to strengthen the constraint of image feature restoration and obtain more realistic results. In order to verify the effectiveness of the proposed method, training was conducted on Rain100L and Rian800 data sets. The comparison of experimental results shows that the model is superior to the existing unsupervised methods in the overall repair effect, and also has comparable inpainting effect compared with mainstream supervised methods.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124070104","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976639
C. Ning, Longyan Li
In recent years, data-driven robust optimization (DDRO) is becoming a popular and effective paradigm to address the challenging issue of uncertainty in energy chemical processes. This paper provides an overview of recent advances in the field of DDRO, with a primary focus on its methods and applications in process industries. Firstly, a brief introduction to various robust optimization model formulations and solution algorithms is presented. Secondly, research achievements of machine-learning enabled uncertainty sets, the corresponding DDRO, and variant techniques are summarized and analyzed in a systematic manner. Additionally, tutorial-like numerical examples are used to illustrate merits of DDRO compared with conventional robust optimization. Finally, fruitful applications of DDRO in energy chemical processes are encapsulated and categorized from domain perspectives.
{"title":"Data-Driven Robust Optimization for Energy Chemical Processes under Uncertainties: A Review and Tutorial","authors":"C. Ning, Longyan Li","doi":"10.1109/IAI55780.2022.9976639","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976639","url":null,"abstract":"In recent years, data-driven robust optimization (DDRO) is becoming a popular and effective paradigm to address the challenging issue of uncertainty in energy chemical processes. This paper provides an overview of recent advances in the field of DDRO, with a primary focus on its methods and applications in process industries. Firstly, a brief introduction to various robust optimization model formulations and solution algorithms is presented. Secondly, research achievements of machine-learning enabled uncertainty sets, the corresponding DDRO, and variant techniques are summarized and analyzed in a systematic manner. Additionally, tutorial-like numerical examples are used to illustrate merits of DDRO compared with conventional robust optimization. Finally, fruitful applications of DDRO in energy chemical processes are encapsulated and categorized from domain perspectives.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129635876","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976621
Rongxiu Lu, Hongliang Liu, Hui Yang, Wenhao Dai
Discrete state transition algorithm relies on the initial solution and can easily fall into the local optimum. This paper proposes an improved discrete state transition algorithm (CDSTA) for the above problem. Firstly, the genetic algorithm is used to initialize to obtain the initial solution with high quality and quickly approximate the optimal value. Secondly, the optimal recovery strategy reduces the number of iterations to accelerate the algorithm's convergence rate. Finally, the chaotic perturbation strategy is introduced. When the algorithm falls into the stagnation state, a chaotic sequence is generated by Tent mapping to get rid of the local extremum. Two single-peaked and three multi-peaked functions are used to experiment with the improved algorithm, and the performance is compared and analyzed with other algorithms. The results show that the improved algorithm's solution accuracy and convergence rate are better than other comparative algorithms. The application of the improved algorithm to the traveling salesman problem demon-strates that CDSTA has good practical engineering application potential.
{"title":"Improvement and Application of Discrete State Transition Algorithm","authors":"Rongxiu Lu, Hongliang Liu, Hui Yang, Wenhao Dai","doi":"10.1109/IAI55780.2022.9976621","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976621","url":null,"abstract":"Discrete state transition algorithm relies on the initial solution and can easily fall into the local optimum. This paper proposes an improved discrete state transition algorithm (CDSTA) for the above problem. Firstly, the genetic algorithm is used to initialize to obtain the initial solution with high quality and quickly approximate the optimal value. Secondly, the optimal recovery strategy reduces the number of iterations to accelerate the algorithm's convergence rate. Finally, the chaotic perturbation strategy is introduced. When the algorithm falls into the stagnation state, a chaotic sequence is generated by Tent mapping to get rid of the local extremum. Two single-peaked and three multi-peaked functions are used to experiment with the improved algorithm, and the performance is compared and analyzed with other algorithms. The results show that the improved algorithm's solution accuracy and convergence rate are better than other comparative algorithms. The application of the improved algorithm to the traveling salesman problem demon-strates that CDSTA has good practical engineering application potential.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130748096","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976876
Jingrui Hou, Xinghuo Yu, Zhaohui Liu, M. Jalili
In this paper, the structural controllability of periodically switching networks is studied. Based on the n-walk theory, we study the effect of repeating a switching network on its temporal dilation, intersection and temporally independent walks respectively, and some digestible examples are given to illustrate the theoretical results. We conclude that periodically repeating a switching network can only increase or maintain its structural controllability. In addition, for periodically switching networks, we propose an algorithm to judge and calculate the minimum number of periods to achieve structural controllability, and a detailed example is also given to illustrate our algorithm. Our work provides a new perspective to study complex periodically switching networks in the real world.
{"title":"On Structural Controllability of Periodically Switching Networks","authors":"Jingrui Hou, Xinghuo Yu, Zhaohui Liu, M. Jalili","doi":"10.1109/IAI55780.2022.9976876","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976876","url":null,"abstract":"In this paper, the structural controllability of periodically switching networks is studied. Based on the n-walk theory, we study the effect of repeating a switching network on its temporal dilation, intersection and temporally independent walks respectively, and some digestible examples are given to illustrate the theoretical results. We conclude that periodically repeating a switching network can only increase or maintain its structural controllability. In addition, for periodically switching networks, we propose an algorithm to judge and calculate the minimum number of periods to achieve structural controllability, and a detailed example is also given to illustrate our algorithm. Our work provides a new perspective to study complex periodically switching networks in the real world.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130879111","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976667
Sanguan Zhong, Jie Qi, Yongyu Li
In the paper, we design an adaptive observer for the extruder system with three unknown parameters, namely, two dissipation coefficients and viscosity. The observer orientated model expresses the mass and energy balance in the extruder chamber of melt spinning governed by a group of coupled first order hyperbolic partial differential equations with a moving interface. The observer estimates the states and the three parameters simultaneously, where the estimated parameters converge to their real values exponentially fast. The results are demonstrated in simulation.
{"title":"Adaptive Observer for an Extrusion Process of Melt Spinning with Three Unknown Parameters","authors":"Sanguan Zhong, Jie Qi, Yongyu Li","doi":"10.1109/IAI55780.2022.9976667","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976667","url":null,"abstract":"In the paper, we design an adaptive observer for the extruder system with three unknown parameters, namely, two dissipation coefficients and viscosity. The observer orientated model expresses the mass and energy balance in the extruder chamber of melt spinning governed by a group of coupled first order hyperbolic partial differential equations with a moving interface. The observer estimates the states and the three parameters simultaneously, where the estimated parameters converge to their real values exponentially fast. The results are demonstrated in simulation.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130908699","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 : 2022-08-24DOI: 10.1109/IAI55780.2022.9976677
Hong Zhu, Hai Yang, Minghua Gao, Yefeng Liu, Yunge Li
This paper presents a method to analyze the mechanical environment of non-stationary random excitation process of industrial robots.In this method, the non-stationary stochastic process is represented by several slow-varying uniformly modulated stochastic processes so that the analysis process is greatly simplified.The demodulation method is used to analyze the vibration signal of an industrial robot, the characteristics of vibration excitation load can be evaluated, and interference samples can be provided for the control system of industrial robot, so as to improve the control precision of the robot.
{"title":"Mechanical environment analysis of non-stationary random excitation process of industrial robot","authors":"Hong Zhu, Hai Yang, Minghua Gao, Yefeng Liu, Yunge Li","doi":"10.1109/IAI55780.2022.9976677","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976677","url":null,"abstract":"This paper presents a method to analyze the mechanical environment of non-stationary random excitation process of industrial robots.In this method, the non-stationary stochastic process is represented by several slow-varying uniformly modulated stochastic processes so that the analysis process is greatly simplified.The demodulation method is used to analyze the vibration signal of an industrial robot, the characteristics of vibration excitation load can be evaluated, and interference samples can be provided for the control system of industrial robot, so as to improve the control precision of the robot.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121609546","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：