Pub Date : 2018-05-01DOI: 10.1109/DDCLS.2018.8516067
Linwei Li, X. Ren, Y. Lv
In this paper, based on the measurement data, the identification of the multivariate Hammerstein controlled autoregressive moving average system is investigated. To facilitate the parameter identification, the considered system is transferred to a regression identification model in which the bilinear parameter and linear parameter are included in the identification model. To solve the bilinear parameter estimation problem, with the help of the hierarchical identification principle, two new identification models are constructed in which the each model is linear to parameter vector. For each identification model, a novel filtering identification algorithm is put forward to interactively estimate the parameters of the each model based on hierarchical identification principle. Filtering technique is used to improve the estimation accuracy of the presented algorithm, and the hierarchical identification idea is exploited to decrease the calculation burden of the proposed method. The conditions of convergence are introduced by using the martingale convergence theorem. Contrast examples indicate that the proposed method has a better identification performance than several existing estimation approaches.
{"title":"Filtering Identification for Multivariate Hammerstein Systems with Coloured Noise Using Measurement Data","authors":"Linwei Li, X. Ren, Y. Lv","doi":"10.1109/DDCLS.2018.8516067","DOIUrl":"https://doi.org/10.1109/DDCLS.2018.8516067","url":null,"abstract":"In this paper, based on the measurement data, the identification of the multivariate Hammerstein controlled autoregressive moving average system is investigated. To facilitate the parameter identification, the considered system is transferred to a regression identification model in which the bilinear parameter and linear parameter are included in the identification model. To solve the bilinear parameter estimation problem, with the help of the hierarchical identification principle, two new identification models are constructed in which the each model is linear to parameter vector. For each identification model, a novel filtering identification algorithm is put forward to interactively estimate the parameters of the each model based on hierarchical identification principle. Filtering technique is used to improve the estimation accuracy of the presented algorithm, and the hierarchical identification idea is exploited to decrease the calculation burden of the proposed method. The conditions of convergence are introduced by using the martingale convergence theorem. Contrast examples indicate that the proposed method has a better identification performance than several existing estimation approaches.","PeriodicalId":6565,"journal":{"name":"2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"63 1","pages":"486-491"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83313993","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 : 2018-05-01DOI: 10.1109/DDCLS.2018.8516036
Chaoqun Tan, Fei Liu
In this technical note, the problem of event-triggered output-feedback control is considered for a linear system whose states are unavailable or partial available. In order to realize the reduction of communication in both the sensor to controller(S-C) and the controller to actuator(C-A) channels, a piecewise linear model is introduced, by which the communication in dual channels can be simultaneously considered. For S-C channel, the event-triggered strategy based on the observer is applied. For C-A channel, classical fixed threshold, relative threshold strategy and switching threshold strategy which combines the benefits of the first two mechanisms are discussed respectively. It is shown that the proposed event-triggered scheme can realize the reduction of communication while guaranteeing the stability of the system. The simulation results also confirm the superiority of switching threshold strategy.
{"title":"Dual-Channel Event-Triggered Output Feedback Control for Linear System with Unavailable States","authors":"Chaoqun Tan, Fei Liu","doi":"10.1109/DDCLS.2018.8516036","DOIUrl":"https://doi.org/10.1109/DDCLS.2018.8516036","url":null,"abstract":"In this technical note, the problem of event-triggered output-feedback control is considered for a linear system whose states are unavailable or partial available. In order to realize the reduction of communication in both the sensor to controller(S-C) and the controller to actuator(C-A) channels, a piecewise linear model is introduced, by which the communication in dual channels can be simultaneously considered. For S-C channel, the event-triggered strategy based on the observer is applied. For C-A channel, classical fixed threshold, relative threshold strategy and switching threshold strategy which combines the benefits of the first two mechanisms are discussed respectively. It is shown that the proposed event-triggered scheme can realize the reduction of communication while guaranteeing the stability of the system. The simulation results also confirm the superiority of switching threshold strategy.","PeriodicalId":6565,"journal":{"name":"2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"30 1","pages":"633-638"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87415396","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 : 2018-05-01DOI: 10.1109/DDCLS.2018.8516041
Bi Zhang, Xingang Zhao, Zhuang Xu, Ming Zhao
In this work, a novel nonlinear self-tuning adaptive control scheme based on the neural Wiener model has been proposed to copy with a class of nonlinear uncertain systems. First the parameterization model with uncertain parameters is derived based on a linear transfer function model followed by neural networks. Then based on the performance index, the adaptive control strategy includes the system parameters identification and the control law calculation. Since the networks are linearly described by some basis functions, the closed-loop system stability can be ensured under some realistic assumptions. Finally, the proposed controller is applied to a pH control problem. The simulation results have demonstrated that the proposed nonlinear self-tuning control method is applicable, especially for its reliable set-point tracking and adaptive abilities.
{"title":"A Nonlinear Self-tuning Control Method Based on Neural Wiener Model","authors":"Bi Zhang, Xingang Zhao, Zhuang Xu, Ming Zhao","doi":"10.1109/DDCLS.2018.8516041","DOIUrl":"https://doi.org/10.1109/DDCLS.2018.8516041","url":null,"abstract":"In this work, a novel nonlinear self-tuning adaptive control scheme based on the neural Wiener model has been proposed to copy with a class of nonlinear uncertain systems. First the parameterization model with uncertain parameters is derived based on a linear transfer function model followed by neural networks. Then based on the performance index, the adaptive control strategy includes the system parameters identification and the control law calculation. Since the networks are linearly described by some basis functions, the closed-loop system stability can be ensured under some realistic assumptions. Finally, the proposed controller is applied to a pH control problem. The simulation results have demonstrated that the proposed nonlinear self-tuning control method is applicable, especially for its reliable set-point tracking and adaptive abilities.","PeriodicalId":6565,"journal":{"name":"2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"163 1","pages":"107-111"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85165879","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 : 2018-05-01DOI: 10.1109/DDCLS.2018.8516007
Congcong Jia, N. Bu
In this paper, the right coprime factorization method based on operator theory is applied to deal with the stability issue of nonlinear feedback system, wherein the inverse of the right factor obtained from the isomorphism-based factorization method is discussed and is proved to be stable, thus the Bezout identity is satisfied with the designed controllers. Meanwhile, the nonlinear feedback system is stable.
{"title":"A simplified control scheme for nonlinear feedback system based on operator theory","authors":"Congcong Jia, N. Bu","doi":"10.1109/DDCLS.2018.8516007","DOIUrl":"https://doi.org/10.1109/DDCLS.2018.8516007","url":null,"abstract":"In this paper, the right coprime factorization method based on operator theory is applied to deal with the stability issue of nonlinear feedback system, wherein the inverse of the right factor obtained from the isomorphism-based factorization method is discussed and is proved to be stable, thus the Bezout identity is satisfied with the designed controllers. Meanwhile, the nonlinear feedback system is stable.","PeriodicalId":6565,"journal":{"name":"2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"28 1","pages":"903-907"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90990000","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 : 2018-05-01DOI: 10.1109/DDCLS.2018.8516033
Z. Zen, Rongmin Cao, Z. Hou
Aimed at plane nonlinear two-degree-of-freedom (2-dof) manipulator, which is a nonlinear multi-input and multi-output(MIMO) system, its joint angles are controlled by model-free adaptive control (MFAC) theory to realize trajectory tracking. The nonlinear system model is replaced by the compact form dynamic linearization time-varying model, and the pseudo-Jacobian matrix of the system is estimated on the basis of the input and output data of the manipulator model. The simulation results show that the compact form dynamic linearized model-free adaptive control (CFDL-MFAC) algorithm can effectively ensure the tracking performance of the system output, and the error remains within a certain range.
{"title":"MIMO Model Free Adaptive Control of Two Degree of Freedom Manipulator","authors":"Z. Zen, Rongmin Cao, Z. Hou","doi":"10.1109/DDCLS.2018.8516033","DOIUrl":"https://doi.org/10.1109/DDCLS.2018.8516033","url":null,"abstract":"Aimed at plane nonlinear two-degree-of-freedom (2-dof) manipulator, which is a nonlinear multi-input and multi-output(MIMO) system, its joint angles are controlled by model-free adaptive control (MFAC) theory to realize trajectory tracking. The nonlinear system model is replaced by the compact form dynamic linearization time-varying model, and the pseudo-Jacobian matrix of the system is estimated on the basis of the input and output data of the manipulator model. The simulation results show that the compact form dynamic linearized model-free adaptive control (CFDL-MFAC) algorithm can effectively ensure the tracking performance of the system output, and the error remains within a certain range.","PeriodicalId":6565,"journal":{"name":"2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"132 1","pages":"693-697"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76715526","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 : 2018-05-01DOI: 10.1109/DDCLS.2018.8516111
Jingbo Wang, Weiming Shao, Zhihuan Song
The Gaussian mixture regression (GMR) is an effective approach to predict those difficult-to-measure quality variables for industrial processes with multiple operating modes. However, the GMR easily gets stuck into overfitting in the scenario of insufficient labeled samples, particularly when the dimensionality of the secondary variables is high. To alleviate this issue, this paper proposes the Bayesian regularized GMR (BGMR), and applies it to soft sensor modeling. In the BGMR, an alternative model structure, which explicitly considers the functional dependency between the primary and secondary variables, is presented to facilitate the Bayesian regularization that is widely used for anti-overfitting. In addition, an efficient learning procedure is developed for the BGMR based on the expectation-maximization algorithm. The performance of the BGMR is evaluated through two case studies including a numerical example and a real-life industrial process, which demonstrates the effectiveness of the proposed approach.
{"title":"Bayesian Regularized Gaussian Mixture Regression with Application to Soft Sensor Modeling for Multi-Mode Industrial Processes","authors":"Jingbo Wang, Weiming Shao, Zhihuan Song","doi":"10.1109/DDCLS.2018.8516111","DOIUrl":"https://doi.org/10.1109/DDCLS.2018.8516111","url":null,"abstract":"The Gaussian mixture regression (GMR) is an effective approach to predict those difficult-to-measure quality variables for industrial processes with multiple operating modes. However, the GMR easily gets stuck into overfitting in the scenario of insufficient labeled samples, particularly when the dimensionality of the secondary variables is high. To alleviate this issue, this paper proposes the Bayesian regularized GMR (BGMR), and applies it to soft sensor modeling. In the BGMR, an alternative model structure, which explicitly considers the functional dependency between the primary and secondary variables, is presented to facilitate the Bayesian regularization that is widely used for anti-overfitting. In addition, an efficient learning procedure is developed for the BGMR based on the expectation-maximization algorithm. The performance of the BGMR is evaluated through two case studies including a numerical example and a real-life industrial process, which demonstrates the effectiveness of the proposed approach.","PeriodicalId":6565,"journal":{"name":"2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"453 1","pages":"463-468"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75110612","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 : 2018-05-01DOI: 10.1109/DDCLS.2018.8515939
Qi Zhang, Kai Xu, Peng Jiao, Quanjun Yin
In modern training, entertainment and education applications, behavior trees (BTs) have been the fantastic alternative to FSMs to model and control autonomous agents. However, manually creating BTs for various task scenarios is expensive. Recently the genetic programming method has been devised to learn BTs automatically but produced limited success. One of the main reasons is the scalability problem stemming from random space search. This paper proposes a modified evolving behavior trees approach to model agent behavior as a BT. The main features lay on the model free method through dynamic frequent subtree mining to adjust select probability of crossover point then reduce random search in evolution. Preliminary experiments, carried out on the Mario AI benchmark, show that the proposed method outperforms standard evolving behavior tree by achieving better final behavior performance with less learning episodes. Besides, some useful behavior subtrees can be mined to facilitate knowledge engineering.
{"title":"Behavior Modeling for Autonomous Agents Based on Modified Evolving Behavior Trees","authors":"Qi Zhang, Kai Xu, Peng Jiao, Quanjun Yin","doi":"10.1109/DDCLS.2018.8515939","DOIUrl":"https://doi.org/10.1109/DDCLS.2018.8515939","url":null,"abstract":"In modern training, entertainment and education applications, behavior trees (BTs) have been the fantastic alternative to FSMs to model and control autonomous agents. However, manually creating BTs for various task scenarios is expensive. Recently the genetic programming method has been devised to learn BTs automatically but produced limited success. One of the main reasons is the scalability problem stemming from random space search. This paper proposes a modified evolving behavior trees approach to model agent behavior as a BT. The main features lay on the model free method through dynamic frequent subtree mining to adjust select probability of crossover point then reduce random search in evolution. Preliminary experiments, carried out on the Mario AI benchmark, show that the proposed method outperforms standard evolving behavior tree by achieving better final behavior performance with less learning episodes. Besides, some useful behavior subtrees can be mined to facilitate knowledge engineering.","PeriodicalId":6565,"journal":{"name":"2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"40 1","pages":"1140-1145"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75161647","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 : 2018-05-01DOI: 10.1109/DDCLS.2018.8516065
Jing Ding, Ling Zhao, Darong Huang
For the non-stationary and nonlinear complex characteristics of gearbox vibration signals under fault condition, the identification of pitting failure, gear breakage and wear fault of gear box is recognized based on de-trended wave analysis and multifractal method. Multifractal spectrum has a clear physical significance, and it can characterize the kinetic mechanism of the signal, which makes it suitable to be the fault feature parameter of stationary signal, but not suitable for non-stationary signal. De-trended fluctuation analysis can filter out the trend component in the sequence effectively, and determine the long-range correlation characteristics in detecting signal and noise which can be used to deal with non-stationary data. In this paper, the two methods are combined to be the fault diagnosis method of gearbox. First, de-trended fluctuation analysis is used to process the gearbox signal, then the multifractal parameters are extracted that can be treated as the fault features to diagnose the gearbox fault. Finally, the experimental data of the gearbox are compared and analyzed. The experimental results show that the fault diagnosis method of MF - DFA improves the classification precision of the fault diagnosis.
{"title":"On Fault Diagnosis of Gear Box Based on De-Trending Multifractal","authors":"Jing Ding, Ling Zhao, Darong Huang","doi":"10.1109/DDCLS.2018.8516065","DOIUrl":"https://doi.org/10.1109/DDCLS.2018.8516065","url":null,"abstract":"For the non-stationary and nonlinear complex characteristics of gearbox vibration signals under fault condition, the identification of pitting failure, gear breakage and wear fault of gear box is recognized based on de-trended wave analysis and multifractal method. Multifractal spectrum has a clear physical significance, and it can characterize the kinetic mechanism of the signal, which makes it suitable to be the fault feature parameter of stationary signal, but not suitable for non-stationary signal. De-trended fluctuation analysis can filter out the trend component in the sequence effectively, and determine the long-range correlation characteristics in detecting signal and noise which can be used to deal with non-stationary data. In this paper, the two methods are combined to be the fault diagnosis method of gearbox. First, de-trended fluctuation analysis is used to process the gearbox signal, then the multifractal parameters are extracted that can be treated as the fault features to diagnose the gearbox fault. Finally, the experimental data of the gearbox are compared and analyzed. The experimental results show that the fault diagnosis method of MF - DFA improves the classification precision of the fault diagnosis.","PeriodicalId":6565,"journal":{"name":"2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"49 1","pages":"830-835"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75284869","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 : 2018-05-01DOI: 10.1109/DDCLS.2018.8515941
Zhewen Cao, Er Jin, Siqi Zhou, Ye Wu, Yongqiang Li, Yuanjing Feng
Whole-brain fiber imaging allows nondestructive detection of human brain structural connections. The clinical application of this method is often classified as a series of fiber bundle structures of certain significance (function, structure, shape, etc.). Due to the lack of edge structure information of fiber bundles and the high variability of complex white matter structures in individual samples, fiber clustering based on anatomical information is still an open problem. In this paper, a new fiber clustering technique is proposed, which combines spatial features of whole-brain fibers and prior anatomical information as fiber similarity matching and feature extraction. In this work, we focus on the coverage of highly consistent fiber bundles in white matter structures to match anatomic features. The method is based on multiple tests of simulated data and in vivol data. The experimental results show that this method not only improves the highly consistent coverage of fiber bundles and prior anatomical knowledge, but also simplifies the fiber data space to improve the fiber clustering similarity measured population consistency. Finally, we also discuss the application of this method in clinical research.
{"title":"A Data-driven Voxel-wise White Matter Fiber Clustering Model Based on Priori Anatomical Data","authors":"Zhewen Cao, Er Jin, Siqi Zhou, Ye Wu, Yongqiang Li, Yuanjing Feng","doi":"10.1109/DDCLS.2018.8515941","DOIUrl":"https://doi.org/10.1109/DDCLS.2018.8515941","url":null,"abstract":"Whole-brain fiber imaging allows nondestructive detection of human brain structural connections. The clinical application of this method is often classified as a series of fiber bundle structures of certain significance (function, structure, shape, etc.). Due to the lack of edge structure information of fiber bundles and the high variability of complex white matter structures in individual samples, fiber clustering based on anatomical information is still an open problem. In this paper, a new fiber clustering technique is proposed, which combines spatial features of whole-brain fibers and prior anatomical information as fiber similarity matching and feature extraction. In this work, we focus on the coverage of highly consistent fiber bundles in white matter structures to match anatomic features. The method is based on multiple tests of simulated data and in vivol data. The experimental results show that this method not only improves the highly consistent coverage of fiber bundles and prior anatomical knowledge, but also simplifies the fiber data space to improve the fiber clustering similarity measured population consistency. Finally, we also discuss the application of this method in clinical research.","PeriodicalId":6565,"journal":{"name":"2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"32 1","pages":"65-70"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74663456","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 : 2018-05-01DOI: 10.1109/DDCLS.2018.8516049
Lin Liang, Zhengwei Lei, Maolin Li, Xiangwei Kong
As key components in a mechanical transmission chain, gearboxes work in non-stationary conditions in many cases and the effect of conventional vibration analysis is limited by low signal-noise ratio. Considering the advantage of Instantaneous Angular Speed (IAS), this paper proposes a gearbox feature extraction method based on the order analysis of IAS signals. Firstly, IAS signals of the input and output shafts are sampled synchronously by photoelectric encoders. Then the instantaneous angular speed difference (IASD) between the input shaft and output shaft is calculated to eliminate the interference of the transmission channel. Finally, the order spectrum of the gearbox can be obtained by the Fourier transform of IASD signal. Thus, gearbox’s working status can be judged according to the characteristic distribution of rotational components in the order spectrum. The effectiveness of this method has been validated experimentally on a two-stage gearbox test rig.
{"title":"Feature Extraction of Gearbox based on Order Analysis of Instantaneous Angular Speed","authors":"Lin Liang, Zhengwei Lei, Maolin Li, Xiangwei Kong","doi":"10.1109/DDCLS.2018.8516049","DOIUrl":"https://doi.org/10.1109/DDCLS.2018.8516049","url":null,"abstract":"As key components in a mechanical transmission chain, gearboxes work in non-stationary conditions in many cases and the effect of conventional vibration analysis is limited by low signal-noise ratio. Considering the advantage of Instantaneous Angular Speed (IAS), this paper proposes a gearbox feature extraction method based on the order analysis of IAS signals. Firstly, IAS signals of the input and output shafts are sampled synchronously by photoelectric encoders. Then the instantaneous angular speed difference (IASD) between the input shaft and output shaft is calculated to eliminate the interference of the transmission channel. Finally, the order spectrum of the gearbox can be obtained by the Fourier transform of IASD signal. Thus, gearbox’s working status can be judged according to the characteristic distribution of rotational components in the order spectrum. The effectiveness of this method has been validated experimentally on a two-stage gearbox test rig.","PeriodicalId":6565,"journal":{"name":"2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"30 1","pages":"498-501"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72641229","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：