Pub Date : 2022-08-24DOI: 10.1109/IAI55780.2022.9976820
Hongcheng Wang, Yuchen Jiang, Hao Wang, Hao Luo
Flexible production lines are the mainstream choice in the current manufacturing industry. In a flexible line, a single machine can execute a variety of processing tasks. Machine breakdowns are common unexpected disturbances in manufacturing. Machine breakdowns in a flexible production line that result in the unexpected shutdown of the flexible production line's operation unit will have a significant influence on the overall manufacturing process. A two-stage dynamic scheduling strategy is used in this paper to solve the problem that the repair time of the machine cannot be accurately estimated when the machine fails in the production process of the flexible production lines. When any machine fails or is repaired, this strategy is used to set up the best production schedule for flexible production lines. The two-stage scheduling strategy can avoid estimating the repair time of the machine so that dynamic scheduling can be carried out accurately according to the actual situation. The imperialist competitive algorithm(ICA) is originally suitable for continuous optimization problems, while this problem falls within the category of discrete optimization. In this paper, the idea of hybridization of genetic algorithm is used to improve the ICA, so that it is suitable for discrete optimization problems to solve dynamic scheduling. Experiments demonstrate the effectiveness of the two-stage dynamic scheduling strategy and the improved imperialist competitive algorithm.
{"title":"An online optimization scheme of the dynamic flexible job shop scheduling problem for intelligent manufacturing","authors":"Hongcheng Wang, Yuchen Jiang, Hao Wang, Hao Luo","doi":"10.1109/IAI55780.2022.9976820","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976820","url":null,"abstract":"Flexible production lines are the mainstream choice in the current manufacturing industry. In a flexible line, a single machine can execute a variety of processing tasks. Machine breakdowns are common unexpected disturbances in manufacturing. Machine breakdowns in a flexible production line that result in the unexpected shutdown of the flexible production line's operation unit will have a significant influence on the overall manufacturing process. A two-stage dynamic scheduling strategy is used in this paper to solve the problem that the repair time of the machine cannot be accurately estimated when the machine fails in the production process of the flexible production lines. When any machine fails or is repaired, this strategy is used to set up the best production schedule for flexible production lines. The two-stage scheduling strategy can avoid estimating the repair time of the machine so that dynamic scheduling can be carried out accurately according to the actual situation. The imperialist competitive algorithm(ICA) is originally suitable for continuous optimization problems, while this problem falls within the category of discrete optimization. In this paper, the idea of hybridization of genetic algorithm is used to improve the ICA, so that it is suitable for discrete optimization problems to solve dynamic scheduling. Experiments demonstrate the effectiveness of the two-stage dynamic scheduling strategy and the improved imperialist competitive algorithm.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"19 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":"121963254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, an adaptive neural network finite-time fault-tolerant control scheme is proposed for a fixed-wing UAV under state constraints and actuator fault. To build a state-constraint model, the inertial position dynamics are first formulated to compact model. A Butterworth low-pass filter is introduced to solve the algebraic loop involved by control input. Moreover, the lumped unknown nonlinearities inherent in the UAV system, actuator fault, external disturbances, and approximation errors are respectively identified by utilizing neural network and nonlinear disturbance observer. Furthermore, a barrier Lyapunov function is used to constrain the states of the UAV and verify the finite-time stability of the designed control scheme. Eventually, the effectiveness is demonstrated by simulation results.
{"title":"Adaptive Neural Network Finite-Time Fault-Tolerant Control of Fixed-Wing UAV Under State Constraints and Actuator Fault","authors":"Yiwei Xu, Zhong Yang, Ruifeng Zhou, Ziquan Yu, Fuyang Chen, You Zhang","doi":"10.1109/IAI55780.2022.9976698","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976698","url":null,"abstract":"In this paper, an adaptive neural network finite-time fault-tolerant control scheme is proposed for a fixed-wing UAV under state constraints and actuator fault. To build a state-constraint model, the inertial position dynamics are first formulated to compact model. A Butterworth low-pass filter is introduced to solve the algebraic loop involved by control input. Moreover, the lumped unknown nonlinearities inherent in the UAV system, actuator fault, external disturbances, and approximation errors are respectively identified by utilizing neural network and nonlinear disturbance observer. Furthermore, a barrier Lyapunov function is used to constrain the states of the UAV and verify the finite-time stability of the designed control scheme. Eventually, the effectiveness is demonstrated by simulation results.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"84 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":"115784445","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}
Short-term power load forecasting is an important guarantee to ensure the smooth and efficient operation of power systems, and an important basis for building new digital and intelligent power systems. Given that short-term power system load is affected by various factors (e.g., climate, time), power system load has strong randomness and volatility while being periodic. Hence, the traditional power load forecasting method is no longer applicable. To improve the accuracy of short-term power load forecasting, this paper proposes a support vector machine (SVM) short-term power load forecasting method based on grey relational analysis and K-means clustering. First, similar days in historical days are extracted by using the grey relational analysis method to form a rough set of similar days. Second, the rough set of similar days is classified by K-means clustering, and the final set of similar days is obtained. Third, SVM is trained to determine the final predicted daily load. Lastly, the proposed method is verified by the actual electricity consumption data of a city in China, and the results show the effectiveness of this method.
{"title":"Short-term Power Load Forecasting Based on Grey Relational Analysis and Support Vector Machine","authors":"Wei Sun, Xinfu Pang, Wei Liu, Yibao Wang, Changfeng Luan","doi":"10.1109/IAI55780.2022.9976828","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976828","url":null,"abstract":"Short-term power load forecasting is an important guarantee to ensure the smooth and efficient operation of power systems, and an important basis for building new digital and intelligent power systems. Given that short-term power system load is affected by various factors (e.g., climate, time), power system load has strong randomness and volatility while being periodic. Hence, the traditional power load forecasting method is no longer applicable. To improve the accuracy of short-term power load forecasting, this paper proposes a support vector machine (SVM) short-term power load forecasting method based on grey relational analysis and K-means clustering. First, similar days in historical days are extracted by using the grey relational analysis method to form a rough set of similar days. Second, the rough set of similar days is classified by K-means clustering, and the final set of similar days is obtained. Third, SVM is trained to determine the final predicted daily load. Lastly, the proposed method is verified by the actual electricity consumption data of a city in China, and the results show the effectiveness of this method.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"72 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":"126351024","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/IAI55780.2022.9976589
Junguo Song, Jin‐Xi Zhang
This paper designs an output tracking controller for a class of uncertain second-order nonlinear systems with input quantization to solve the prescribed performance control problem. The performance function restrains the convergence rate and precision of the output tracking error. The barrier function is used to confine this error. A simple input quantizer is specially designed for the controller. The resulting control strategy ensures that the prescribed output tracking performance is achieved and all the closed-loop signals are bounded. The control strategy is verified through the simulation result.
{"title":"Quantized Prescribed Performance Control for Second-Order Nonlinear Systems","authors":"Junguo Song, Jin‐Xi Zhang","doi":"10.1109/IAI55780.2022.9976589","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976589","url":null,"abstract":"This paper designs an output tracking controller for a class of uncertain second-order nonlinear systems with input quantization to solve the prescribed performance control problem. The performance function restrains the convergence rate and precision of the output tracking error. The barrier function is used to confine this error. A simple input quantizer is specially designed for the controller. The resulting control strategy ensures that the prescribed output tracking performance is achieved and all the closed-loop signals are bounded. The control strategy is verified through the simulation result.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"16 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":"125296760","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/IAI55780.2022.9976809
J. Leventides, E. Melas, C. Poulios, A. Vardulakis
We present a method for linearizing control and stabilization of chaotic systems in finance. This method considers the deviation of some trajectory of the system from an ideal or desirable orbit. Using Koopman operators and EDMD, we model this deviation as a linear dynamical system. The linear system is necessarily defined in some augmented state space whose dimension is bigger than the dimension of the original state space. The linear system can then be used for control and stabilization properties. Namely, one may apply feedback control to drive the deviation to zero, which means that the trajectory is close to the desired one. This approach can also be applied to more than one trajectories. However, in order to maintain good approximation properties, the more trajectories we consider the larger the dimensions of the linear system will become and at some stage the method will not be computationally effective. For this reason, we do not take into consideration the whole set of trajectories, but we start with a smaller set of orbits. This is a realistic scenario, since in economic studies the macroeconomic variables (such as the gross domestic product) are not arbitrary numbers but depend on the data of the economy.
{"title":"Data arising from hyperchaotic financial systems. Control through Koopman operators and EDMD","authors":"J. Leventides, E. Melas, C. Poulios, A. Vardulakis","doi":"10.1109/IAI55780.2022.9976809","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976809","url":null,"abstract":"We present a method for linearizing control and stabilization of chaotic systems in finance. This method considers the deviation of some trajectory of the system from an ideal or desirable orbit. Using Koopman operators and EDMD, we model this deviation as a linear dynamical system. The linear system is necessarily defined in some augmented state space whose dimension is bigger than the dimension of the original state space. The linear system can then be used for control and stabilization properties. Namely, one may apply feedback control to drive the deviation to zero, which means that the trajectory is close to the desired one. This approach can also be applied to more than one trajectories. However, in order to maintain good approximation properties, the more trajectories we consider the larger the dimensions of the linear system will become and at some stage the method will not be computationally effective. For this reason, we do not take into consideration the whole set of trajectories, but we start with a smaller set of orbits. This is a realistic scenario, since in economic studies the macroeconomic variables (such as the gross domestic product) are not arbitrary numbers but depend on the data of the economy.","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":"124163673","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/IAI55780.2022.9976643
Yijun Xiao, Hui Lv, Xing’an Wang
In this article, a special attention is paid to the biochemical controller synthesis for time delay systems and try to implement the well-established Smith predictor approach in the context of biochemical systems. Then, chemical reaction networks (CRNs) are adopted to construct a modified Smith predictor scheme (integrating Smith predictor and feedback compensation controllers) for the first time. Taking a delayed protein translation model as the background, the CRNs-based proposed scheme has access to a method that can solve the effect of co-translated mRNA decay in protein translation. In addition, considering that the decay of mRNA affects mRNA stability and protein production, the co-translated mRNA degradation is treated as an interference input of the protein translation process. Our results show that the impact of a disturbance input (mRNA degradation) is restrained by the modified control strategy. The CRNs-based modified Smith predictor makes the protein translation process more robust and achieves protein output quickly and stably.
{"title":"Implementing a modified Smith predictor using chemical reaction networks and its application to protein translation","authors":"Yijun Xiao, Hui Lv, Xing’an Wang","doi":"10.1109/IAI55780.2022.9976643","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976643","url":null,"abstract":"In this article, a special attention is paid to the biochemical controller synthesis for time delay systems and try to implement the well-established Smith predictor approach in the context of biochemical systems. Then, chemical reaction networks (CRNs) are adopted to construct a modified Smith predictor scheme (integrating Smith predictor and feedback compensation controllers) for the first time. Taking a delayed protein translation model as the background, the CRNs-based proposed scheme has access to a method that can solve the effect of co-translated mRNA decay in protein translation. In addition, considering that the decay of mRNA affects mRNA stability and protein production, the co-translated mRNA degradation is treated as an interference input of the protein translation process. Our results show that the impact of a disturbance input (mRNA degradation) is restrained by the modified control strategy. The CRNs-based modified Smith predictor makes the protein translation process more robust and achieves protein output quickly and stably.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"40 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":"131568068","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/IAI55780.2022.9976758
Shupeng Yu, Xiang Li, Bin Yang, Y. Lei
The rolling bearing is essential for the rotating machinery and can be easily damaged in the real working conditions. It is very important to monitor the health status of rolling bearings. Aiming at this problem, fault diagnosis based on deep learning at present is popular, which automatically extracts features from raw data. However, the accuracy of fault diagnosis based on deep learning is dependent mostly on the quantity of data. In the real industries, a large amount of data may not be available, which largely deteriorates the performance of deep learning. To solve this problem, it is promising to exploit the features extracted with the expert knowledge for relaxing the limitations of deep learning. In this paper, a new hybrid intelligent method for rolling fault diagnosis is proposed, which is integrated with deep convolutional neural network and the expert knowledge. The features extracted with expert knowledge are used to improve the feature learning effect and efficiency of deep learning. The experiments on the Case Western Reserve University (CWRU) bearing data validate the effectiveness of the proposed hybrid rolling bearing fault diagnosis method.
{"title":"A Hybrid Intelligent Method for Rolling Bearing Fault Diagnosis Integrated with Expert Knowledge and Deep Learning","authors":"Shupeng Yu, Xiang Li, Bin Yang, Y. Lei","doi":"10.1109/IAI55780.2022.9976758","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976758","url":null,"abstract":"The rolling bearing is essential for the rotating machinery and can be easily damaged in the real working conditions. It is very important to monitor the health status of rolling bearings. Aiming at this problem, fault diagnosis based on deep learning at present is popular, which automatically extracts features from raw data. However, the accuracy of fault diagnosis based on deep learning is dependent mostly on the quantity of data. In the real industries, a large amount of data may not be available, which largely deteriorates the performance of deep learning. To solve this problem, it is promising to exploit the features extracted with the expert knowledge for relaxing the limitations of deep learning. In this paper, a new hybrid intelligent method for rolling fault diagnosis is proposed, which is integrated with deep convolutional neural network and the expert knowledge. The features extracted with expert knowledge are used to improve the feature learning effect and efficiency of deep learning. The experiments on the Case Western Reserve University (CWRU) bearing data validate the effectiveness of the proposed hybrid rolling bearing fault diagnosis method.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"279 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":"132833959","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}
High-density polyethylene (HDPE) are colorless and transparent particles, which are critical raw materials of many plastic products. HDPE particles with defects would affect the quality of final products and the economic benefits of enterprises. At present, there is lack of methods to identify defective HDPE particles quickly and efficiently. To address above problems, intelligent vision detection is introduced into the quality analysis of HDPE, and a set of quality analysis and detection schemes of HDPE are designed in this paper. Firstly, for obtaining better imaging quality, analysis and selection of the background color of the detection scenario is conducted. Secondly, particle conveying and photographing sensing strategy is designed for upgrading production line. Thirdly, intelligent detection of defective particles based on YOLO is merged into the analysis system. According to the experiment results, the blue color is selected as the optimal background. The recognition accuracy reaches 99.39% with the blue background color samples, thus defect particles of HDPE could be detected and identified effectively.
{"title":"Quality Analysis of high-density polyethylene based on Intelligent Vision Detection","authors":"Jianchun Jiang, Xu-hui Zhan, Yangyang Liu, Chong Tang, Jianan Wang, Jianwei Liu","doi":"10.1109/IAI55780.2022.9976537","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976537","url":null,"abstract":"High-density polyethylene (HDPE) are colorless and transparent particles, which are critical raw materials of many plastic products. HDPE particles with defects would affect the quality of final products and the economic benefits of enterprises. At present, there is lack of methods to identify defective HDPE particles quickly and efficiently. To address above problems, intelligent vision detection is introduced into the quality analysis of HDPE, and a set of quality analysis and detection schemes of HDPE are designed in this paper. Firstly, for obtaining better imaging quality, analysis and selection of the background color of the detection scenario is conducted. Secondly, particle conveying and photographing sensing strategy is designed for upgrading production line. Thirdly, intelligent detection of defective particles based on YOLO is merged into the analysis system. According to the experiment results, the blue color is selected as the optimal background. The recognition accuracy reaches 99.39% with the blue background color samples, thus defect particles of HDPE could be detected and identified effectively.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"54 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":"114845029","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/IAI55780.2022.9976837
J. Leventides, E. Melas, C. Poulios
In this paper, we consider bilinear compartmental models. Using the Koopman operator in connection with the Extended Dynamic Mode Decomposition (EDMD), we try to obtain a linear approximation of the original system in a vector space whose dimension is bigger than the original state space. This approach is based on the choice of a dictionary of observables. In the case of bilinear compartmental models there is a natural choice of observables. We present this choice and we examine the efficiency of the method. Especially, we focus on the SIR model which is used to describe the transmission of a disease through some population.
{"title":"EDMD methods for analysis and prediction of bilinear compartmental models","authors":"J. Leventides, E. Melas, C. Poulios","doi":"10.1109/IAI55780.2022.9976837","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976837","url":null,"abstract":"In this paper, we consider bilinear compartmental models. Using the Koopman operator in connection with the Extended Dynamic Mode Decomposition (EDMD), we try to obtain a linear approximation of the original system in a vector space whose dimension is bigger than the original state space. This approach is based on the choice of a dictionary of observables. In the case of bilinear compartmental models there is a natural choice of observables. We present this choice and we examine the efficiency of the method. Especially, we focus on the SIR model which is used to describe the transmission of a disease through some population.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"61 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":"124565599","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/IAI55780.2022.9976874
Hai Yang, Hong Zhu, Yefeng Liu, Yuan Zhao
Aiming at the characteristic of frequency density of non-stationary random vibration signals of industrial robots during machining, a multi-component process neural network (PNN) auto-regressive model was proposed based on empirical mode decomposition (EMD). First, the original time series were decomposed into intrinsic mode functions (IMF) of different scales by EMD. Then, the time-varying parameters of each IMF were analyzed by PNN and the time-varying power spectral density was determined. Finally, the time-varying independent power spectral density of all components is reconstructed by linear superposition as the time-varying independent power spectral density of the original signal. The calculation results show that the frequency resolution performance of this method is better than that of traditional analysis method.
{"title":"Analysis of non-stationary random vibration environment of industrial robot based on EMD and PNN","authors":"Hai Yang, Hong Zhu, Yefeng Liu, Yuan Zhao","doi":"10.1109/IAI55780.2022.9976874","DOIUrl":"https://doi.org/10.1109/IAI55780.2022.9976874","url":null,"abstract":"Aiming at the characteristic of frequency density of non-stationary random vibration signals of industrial robots during machining, a multi-component process neural network (PNN) auto-regressive model was proposed based on empirical mode decomposition (EMD). First, the original time series were decomposed into intrinsic mode functions (IMF) of different scales by EMD. Then, the time-varying parameters of each IMF were analyzed by PNN and the time-varying power spectral density was determined. Finally, the time-varying independent power spectral density of all components is reconstructed by linear superposition as the time-varying independent power spectral density of the original signal. The calculation results show that the frequency resolution performance of this method is better than that of traditional analysis method.","PeriodicalId":138951,"journal":{"name":"2022 4th International Conference on Industrial Artificial Intelligence (IAI)","volume":"34 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":"127810059","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：