Pub Date : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455689
Jiacheng Huang, Zuxin Li, Lingjian Ye, Zhe Zhou
In the process industry, the supervised learning methods cannot classify the unseen faults (i.e., those faults without training samples to participate in the establishment of the model). Although Zero-Shot Learning (ZSL) has been proposed and successfully solved the problem of unseen fault classification, it failed to classify the seen faults (i.e., those faults participate in the establishment of the model). To overcome their shortcomings, in this paper, a generalized Zero-Shot Learning (GZSL) method is proposed to classify all the faults including the seen and the unseen faults by only using the samples of the seen fault and the human-defined fault semantic attribute description information. We use a gating mechanism based on Conditional Variational Autoencoder (CVAE) and a binary classifier to distinguish the online sample into the classes of the seen and unseen faults. Thus, the GZSL problem can be transformed into a supervised fault classification problem and a ZSL fault classification problem. Firstly, we train a CVAE to generate pseudo unseen fault samples and seen fault samples. Secondly, a binary classifier is trained to classify the online samples into seen and unseen categories. Finally, the specific category of the online samples will be determined by the supervised method and ZSL method, respectively. We validate our approach on the Tennessee-Eastman benchmark process.
{"title":"Fault Classification of Industrial Processes based on Generalized Zero-Shot Learning","authors":"Jiacheng Huang, Zuxin Li, Lingjian Ye, Zhe Zhou","doi":"10.1109/DDCLS52934.2021.9455689","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455689","url":null,"abstract":"In the process industry, the supervised learning methods cannot classify the unseen faults (i.e., those faults without training samples to participate in the establishment of the model). Although Zero-Shot Learning (ZSL) has been proposed and successfully solved the problem of unseen fault classification, it failed to classify the seen faults (i.e., those faults participate in the establishment of the model). To overcome their shortcomings, in this paper, a generalized Zero-Shot Learning (GZSL) method is proposed to classify all the faults including the seen and the unseen faults by only using the samples of the seen fault and the human-defined fault semantic attribute description information. We use a gating mechanism based on Conditional Variational Autoencoder (CVAE) and a binary classifier to distinguish the online sample into the classes of the seen and unseen faults. Thus, the GZSL problem can be transformed into a supervised fault classification problem and a ZSL fault classification problem. Firstly, we train a CVAE to generate pseudo unseen fault samples and seen fault samples. Secondly, a binary classifier is trained to classify the online samples into seen and unseen categories. Finally, the specific category of the online samples will be determined by the supervised method and ZSL method, respectively. We validate our approach on the Tennessee-Eastman benchmark process.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121753828","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 : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455455
Hanguang Su, Huaguang Zhang, Yanhong Luo, Qiuye Sun
In this work, a novel event-based integral reinforcement learning (IRL) adaptive control method is developed to solve the multiplayer non-zero-sum (NZS) games of the nonlinear systems with unknown drift dynamics. By virtue of the IRL algorithm, the system drift dynamics is no more needed in the controller design. Moreover, different from the existing iteration computation methods, this method is online implemented, on which condition the event-triggered control framework can be combined with the IRL algorithm in solving the NZS game problems. In this method, a state-dependent triggering condition is proposed, thus the computation and communication loads are reduced in the control process. Moreover, the uniform ultimate boundedness (UUB) stability of the controlled system and the convergence of the critic weights have also been proved. Finally, a numerical example is provided to demonstrate the effectiveness of our method.
{"title":"Event-based Integral Reinforcement Learning Algorithm for Non-zero-sum Games of Partially Unknown Nonlinear Systems","authors":"Hanguang Su, Huaguang Zhang, Yanhong Luo, Qiuye Sun","doi":"10.1109/DDCLS52934.2021.9455455","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455455","url":null,"abstract":"In this work, a novel event-based integral reinforcement learning (IRL) adaptive control method is developed to solve the multiplayer non-zero-sum (NZS) games of the nonlinear systems with unknown drift dynamics. By virtue of the IRL algorithm, the system drift dynamics is no more needed in the controller design. Moreover, different from the existing iteration computation methods, this method is online implemented, on which condition the event-triggered control framework can be combined with the IRL algorithm in solving the NZS game problems. In this method, a state-dependent triggering condition is proposed, thus the computation and communication loads are reduced in the control process. Moreover, the uniform ultimate boundedness (UUB) stability of the controlled system and the convergence of the critic weights have also been proved. Finally, a numerical example is provided to demonstrate the effectiveness of our method.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127773694","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 : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455644
Yujia Yang, L. Jia
Promoting the effective use of energy with the Energy Hub(EH) is an important part of the construction of the Energy Internet. In this paper, an energy transaction model for the Multiple Energy Hub System(MEHS) based on blockchain technology is proposed, which is a distributed system composed of multiple energy hubs. Firstly, the concept of the EH and the current research and application of the energy hub technology are introduced. Then the definition, structure, classification, consensus mechanism, and smart contract of blockchain technology are described. The feasibility of applying blockchain technology to energy network is analyzed. Thirdly, the model structure and energy transaction framework based on blockchain technology are established. Meanwhile, a series of algorithms that give transaction priority are designed. Finally, the model of MEHS based on blockchain technology is given in detail, and compared with the traditional scheduling model to illustrate the superiority of using blockchain technology.
{"title":"Blockchain-based Energy Transaction Model for Multiple Energy Hubs","authors":"Yujia Yang, L. Jia","doi":"10.1109/DDCLS52934.2021.9455644","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455644","url":null,"abstract":"Promoting the effective use of energy with the Energy Hub(EH) is an important part of the construction of the Energy Internet. In this paper, an energy transaction model for the Multiple Energy Hub System(MEHS) based on blockchain technology is proposed, which is a distributed system composed of multiple energy hubs. Firstly, the concept of the EH and the current research and application of the energy hub technology are introduced. Then the definition, structure, classification, consensus mechanism, and smart contract of blockchain technology are described. The feasibility of applying blockchain technology to energy network is analyzed. Thirdly, the model structure and energy transaction framework based on blockchain technology are established. Meanwhile, a series of algorithms that give transaction priority are designed. Finally, the model of MEHS based on blockchain technology is given in detail, and compared with the traditional scheduling model to illustrate the superiority of using blockchain technology.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"418 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133645181","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 : 2021-05-14DOI: 10.1109/ddcls52934.2021.9455530
Shida Liu, Zhen Li, Honghai Ji, Z. Hou, Lingling Fan
This study focus on the problem of pure electric vehicle's braking energy recovery with the uncertain dynamic external factors. For this problem, a novel model free adaptive control with input and output constraints (IOC-MFAC) method is introduced. The dynamic process can be considered as a nonlinear two inputs and two outputs system with hydraulic braking torque and motor braking torque as inputs and braking energy and braking deceleration as outputs. By using IOC-MFAC, the constraints of limitation of current and voltage on the maximum motor braking torque and the constraints of the vehicle's comfort on braking deceleration are considered. Consequently, the recovered energy is controlled in a stable range while guaranteeing the energy recovery to prolong the storage battery's operating life. The major advantages of IOC-MFAC are that not only the controller is designed only with input and output data of the regenerative brake control system, but also the constraints of the system inputs and outputs are considered. Further, the efficiency of IOC-MFAC is verified with a series of numerical simulations.
{"title":"A Novel Electric Vehicle Braking Energy Recovery Method Based on Model Free Adaptive Control Algorithm with Input and Output Constraints","authors":"Shida Liu, Zhen Li, Honghai Ji, Z. Hou, Lingling Fan","doi":"10.1109/ddcls52934.2021.9455530","DOIUrl":"https://doi.org/10.1109/ddcls52934.2021.9455530","url":null,"abstract":"This study focus on the problem of pure electric vehicle's braking energy recovery with the uncertain dynamic external factors. For this problem, a novel model free adaptive control with input and output constraints (IOC-MFAC) method is introduced. The dynamic process can be considered as a nonlinear two inputs and two outputs system with hydraulic braking torque and motor braking torque as inputs and braking energy and braking deceleration as outputs. By using IOC-MFAC, the constraints of limitation of current and voltage on the maximum motor braking torque and the constraints of the vehicle's comfort on braking deceleration are considered. Consequently, the recovered energy is controlled in a stable range while guaranteeing the energy recovery to prolong the storage battery's operating life. The major advantages of IOC-MFAC are that not only the controller is designed only with input and output data of the regenerative brake control system, but also the constraints of the system inputs and outputs are considered. Further, the efficiency of IOC-MFAC is verified with a series of numerical simulations.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133966283","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 : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455497
W. Ai, M. Wu, Xinling Li, Xiangyang Li
Aiming at the problem of large torque ripple in switched reluctance motor (SRM), this paper designs a novel direct torque controller using active disturbance rejection based iterative learning control (ADR-ILC). Direct torque control (DTC) scheme shuns the complicated torque-to-current conversion as required in indirect torque control scheme. Without complex realtime implementation or an accurate model of SRM magnetization characteristics, the ADR-ILC method is used to improve the performance of DTC in SRM. The torque sharing function (TSF) is used to distribute the given torque to each phase, where the DTC based on ADR-ILC calculates the required PWM duty cycle value for the converter of SRM. Simulation results show the effectiveness of DTC based on ADR-ILC to achieve constant torque control of SRM.
{"title":"Active Disturbance Rejection Based Iterative Learning Control for Direct Torque Control of Switched Reluctance Motor Drive","authors":"W. Ai, M. Wu, Xinling Li, Xiangyang Li","doi":"10.1109/DDCLS52934.2021.9455497","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455497","url":null,"abstract":"Aiming at the problem of large torque ripple in switched reluctance motor (SRM), this paper designs a novel direct torque controller using active disturbance rejection based iterative learning control (ADR-ILC). Direct torque control (DTC) scheme shuns the complicated torque-to-current conversion as required in indirect torque control scheme. Without complex realtime implementation or an accurate model of SRM magnetization characteristics, the ADR-ILC method is used to improve the performance of DTC in SRM. The torque sharing function (TSF) is used to distribute the given torque to each phase, where the DTC based on ADR-ILC calculates the required PWM duty cycle value for the converter of SRM. Simulation results show the effectiveness of DTC based on ADR-ILC to achieve constant torque control of SRM.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131902857","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 : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455673
Jia Wang, Yingxia Zhou, Hong-xiang Hu
This paper studies the structural balance preserving and bipartite static consensus problem for multiple uncertain Euler-Lagrange systems in the state-dependent cooperation-competition network. The initial network is set to structural balance and connection, which implies that the network could be divided into two subnetworks, with cooperation internally while competition externally. A combination of the novel classification strategy and the distributed control protocol based on potential functions is given to solve this problem. Under this strategy and standard assumptions, the multiple uncertain Euler-Lagrange agents can maintain structural balance in cooperation-competition network and the bipartite static consensus can be reached in the evolution. Finally, the accuracy of the derived analytical results can be verified by a simulation example.
{"title":"Structural Balance Preserving and Consensus of Uncertain Euler-Lagrange Systems in Cooperation-Competition Networks","authors":"Jia Wang, Yingxia Zhou, Hong-xiang Hu","doi":"10.1109/DDCLS52934.2021.9455673","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455673","url":null,"abstract":"This paper studies the structural balance preserving and bipartite static consensus problem for multiple uncertain Euler-Lagrange systems in the state-dependent cooperation-competition network. The initial network is set to structural balance and connection, which implies that the network could be divided into two subnetworks, with cooperation internally while competition externally. A combination of the novel classification strategy and the distributed control protocol based on potential functions is given to solve this problem. Under this strategy and standard assumptions, the multiple uncertain Euler-Lagrange agents can maintain structural balance in cooperation-competition network and the bipartite static consensus can be reached in the evolution. Finally, the accuracy of the derived analytical results can be verified by a simulation example.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131909207","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 : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455536
Ruirui Huang, Liyun Su, Yutai Wei, Zhijun Yang
The rigid-flexible coupling motion stage (RFCMS) uses the elastic deformation of the flexure hinges to compensate the position error caused by the friction dead zone, and the disturbance to the working stage is converted from friction to elastic disturbance. After the observer estimates and compensates the elastic disturbance, the working stage can be equivalent to a frictionless system. However, due to the friction to the rigid frame in RFCMS and the machining error of the flexure hinges, as well as the measurement deviation, there will be errors in the measurement and the estimation of the observer, which affect the final position accuracy of RFCMS. This paper theoretically analyzes the influencing factors of the estimation error in extended state observer (ESO), and quantitatively studies the estimation performance of ESO, in order to provide a theoretical basis for the control scheme of RFCMS.
{"title":"The Estimation Error of Extended State Observer in Rigid-Flexible Coupling Motion Stage","authors":"Ruirui Huang, Liyun Su, Yutai Wei, Zhijun Yang","doi":"10.1109/DDCLS52934.2021.9455536","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455536","url":null,"abstract":"The rigid-flexible coupling motion stage (RFCMS) uses the elastic deformation of the flexure hinges to compensate the position error caused by the friction dead zone, and the disturbance to the working stage is converted from friction to elastic disturbance. After the observer estimates and compensates the elastic disturbance, the working stage can be equivalent to a frictionless system. However, due to the friction to the rigid frame in RFCMS and the machining error of the flexure hinges, as well as the measurement deviation, there will be errors in the measurement and the estimation of the observer, which affect the final position accuracy of RFCMS. This paper theoretically analyzes the influencing factors of the estimation error in extended state observer (ESO), and quantitatively studies the estimation performance of ESO, in order to provide a theoretical basis for the control scheme of RFCMS.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132234243","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 : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455694
Jiahao Du, N. Qin, Yiming Zhang, Bi Wu, Shiqian Chen
The coupler is an essential component on the train that has the function of connecting and buffering. The actual dynamic performance of the coupler directly influences the safety and comfort of the vehicle. When the heavy haul train passes through the curve, the extreme swing angles of the couplers will seriously threaten the safety of the train. Therefore, the kernelized correlation filter-template matching (KCF-Match) target tracking algorithm is proposed to track the position and calculate the swing angles of the couplers. After the tracked area is selected, the corresponding data of the area are input into the KCF target tracking model for tracking. During the tracking process, if the tracking effects are not satisfied with the given evaluation indexes, the template matching algorithm will be used to track again. Experiments show that KCF-Match target tracking algorithm can achieve 99.8% accuracy rate and 99.9% success rate on the premise of ensuring real-time performance.
{"title":"KCF-Match Target Tracking Algorithm for Tracking Swing Angle of Coupler Based on Video","authors":"Jiahao Du, N. Qin, Yiming Zhang, Bi Wu, Shiqian Chen","doi":"10.1109/DDCLS52934.2021.9455694","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455694","url":null,"abstract":"The coupler is an essential component on the train that has the function of connecting and buffering. The actual dynamic performance of the coupler directly influences the safety and comfort of the vehicle. When the heavy haul train passes through the curve, the extreme swing angles of the couplers will seriously threaten the safety of the train. Therefore, the kernelized correlation filter-template matching (KCF-Match) target tracking algorithm is proposed to track the position and calculate the swing angles of the couplers. After the tracked area is selected, the corresponding data of the area are input into the KCF target tracking model for tracking. During the tracking process, if the tracking effects are not satisfied with the given evaluation indexes, the template matching algorithm will be used to track again. Experiments show that KCF-Match target tracking algorithm can achieve 99.8% accuracy rate and 99.9% success rate on the premise of ensuring real-time performance.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133073704","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 : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455696
Guomin Zhong, Qile Yu, Qiang Chen, Mingxuan Sun
In this paper, iterative learning identification algorithms are proposed to estimate the time-varying parameters in multi-input-single-output (MISO) Wiener nonlinear time-varying systems. The regression model of the Wiener system is built by using the polynomial expansion of the nonlinear inverse function. Then, two iterative learning algorithms, including iterative learning gradient identification and iterative learning least squares identification, are presented to estimate the time-varying parameters of the regression model. The convergence performance of the iterative learning identification algorithms is analyzed, and numerical simulations are provided to verify the effectiveness of the proposed algorithms.
{"title":"Iterative learning identification for a class of Wiener nonlinear time-varying systems","authors":"Guomin Zhong, Qile Yu, Qiang Chen, Mingxuan Sun","doi":"10.1109/DDCLS52934.2021.9455696","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455696","url":null,"abstract":"In this paper, iterative learning identification algorithms are proposed to estimate the time-varying parameters in multi-input-single-output (MISO) Wiener nonlinear time-varying systems. The regression model of the Wiener system is built by using the polynomial expansion of the nonlinear inverse function. Then, two iterative learning algorithms, including iterative learning gradient identification and iterative learning least squares identification, are presented to estimate the time-varying parameters of the regression model. The convergence performance of the iterative learning identification algorithms is analyzed, and numerical simulations are provided to verify the effectiveness of the proposed algorithms.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133112478","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 : 2021-05-14DOI: 10.1109/DDCLS52934.2021.9455545
Naigong Yu, Zhen Zhang, Qiao Xu, Essaf Firdaous, Jia Lin
Image edge detection is the basis for precise positioning and accurate cutting of cloth pattern contours. Compared with the commonly used traditional edge detection methods, the Holistically-nested Edge Detection has clearer and more continuous detection results including the reduction of the false detection rate. However, this method extracts a coarser thick outline. In order to extract a high-precision cloth pattern outline, clearly distinguish the main body of the pattern from the background, provide convenience for the follow-up cutting machine for accurate cutting, this paper proposes an improved method for edge detection of cloth pattern cutting based on the holistically-nested Edge Detection method. The edge refinement and smoothing process are added, where the edge detection, edge refinement, and edge smoothing of the clothes images are carried out in sequences, so that the extracted cloth pattern contour is continuous, smooth, and detailed, allowing the respect of the cutting requirements of the cutting machine and the requirements of the factory production.
{"title":"An improved method for cloth pattern cutting based on Holistically-nested Edge Detection","authors":"Naigong Yu, Zhen Zhang, Qiao Xu, Essaf Firdaous, Jia Lin","doi":"10.1109/DDCLS52934.2021.9455545","DOIUrl":"https://doi.org/10.1109/DDCLS52934.2021.9455545","url":null,"abstract":"Image edge detection is the basis for precise positioning and accurate cutting of cloth pattern contours. Compared with the commonly used traditional edge detection methods, the Holistically-nested Edge Detection has clearer and more continuous detection results including the reduction of the false detection rate. However, this method extracts a coarser thick outline. In order to extract a high-precision cloth pattern outline, clearly distinguish the main body of the pattern from the background, provide convenience for the follow-up cutting machine for accurate cutting, this paper proposes an improved method for edge detection of cloth pattern cutting based on the holistically-nested Edge Detection method. The edge refinement and smoothing process are added, where the edge detection, edge refinement, and edge smoothing of the clothes images are carried out in sequences, so that the extracted cloth pattern contour is continuous, smooth, and detailed, allowing the respect of the cutting requirements of the cutting machine and the requirements of the factory production.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133871853","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：