Pub Date : 2011-12-01DOI: 10.1109/ICCIAUTOM.2011.6356655
H. Salarieh, M. Ghorbani
In this paper, the problem of Optimal Trajectory Planning for a high speed planing boat under nonlinear equality and inequality path constraints, is addressed. First, a nonlinear mathematical model of the craft's dynamic is constructed. To solve a trajectory optimization problem, we can utilize the indirect or direct methods. In the indirect methods, the maximum principle of Pontryagin is used to transform the optimal control problem into Euler-Lagrange equations, on the other hand, in the direct methods it is necessary to transcribe the optimal control problem into a nonlinear programming problem (NLP) by discretization of states and controls. The resulted NLP can be solved by well-developed algorithms such as SNOPT. We use direct method to optimize the trajectories by solving an optimal control problem using the Gauss pseudospectral method (GPM). An example of boat berthing in a circular obstacle environment is presented to demonstrate the effectiveness of the approach for designing optimal maneuvers.
{"title":"Trajectory optimization for a high speed planing boat based on Gauss pseudospectral method","authors":"H. Salarieh, M. Ghorbani","doi":"10.1109/ICCIAUTOM.2011.6356655","DOIUrl":"https://doi.org/10.1109/ICCIAUTOM.2011.6356655","url":null,"abstract":"In this paper, the problem of Optimal Trajectory Planning for a high speed planing boat under nonlinear equality and inequality path constraints, is addressed. First, a nonlinear mathematical model of the craft's dynamic is constructed. To solve a trajectory optimization problem, we can utilize the indirect or direct methods. In the indirect methods, the maximum principle of Pontryagin is used to transform the optimal control problem into Euler-Lagrange equations, on the other hand, in the direct methods it is necessary to transcribe the optimal control problem into a nonlinear programming problem (NLP) by discretization of states and controls. The resulted NLP can be solved by well-developed algorithms such as SNOPT. We use direct method to optimize the trajectories by solving an optimal control problem using the Gauss pseudospectral method (GPM). An example of boat berthing in a circular obstacle environment is presented to demonstrate the effectiveness of the approach for designing optimal maneuvers.","PeriodicalId":438427,"journal":{"name":"The 2nd International Conference on Control, Instrumentation and Automation","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116205026","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 : 2011-12-01DOI: 10.1109/ICCIAUTOM.2011.6356738
S. Beheshti, H. Khaloozadeh
In secure communication applications, time delay chaotic systems are more confidential than the simple chaotic systems. Therefore, in this paper synchronization of time delay chaotic systems has been investigated. Sliding mode observer based approach has been applied as a synchronization method and the stability of the proposed observer has been guaranteed. In order to enhance the level of security of the communication system, the parameters of drive system (transmitter) are assumed to be unknown at the response system (receiver). These uncertainties lie in linear part of the system but sliding mode observer just compensates the uncertainties that lie in nonlinear parts, so the proposed sliding mode observer cannot retrieve the actual states correctly. The proposed solution is on-line identification of the uncertain parameters using the states which have been estimated by the observer. In order to identify the uncertain parameters, the model of the system must be rewritten linearly in terms of unknown parameters. Then the parameters are estimated using Recursive Least Squares (RLS) algorithm. The estimated parameters are used simultaneously in state estimation by the observer. Consequently, the synchronization performance is increased significantly. The result is illustrated numerically on the synchronization of chaotic time-delay Chua's circuit and the simulation results demonstrate the efficiency of the proposed scheme.
{"title":"Synchronization of time-delay chaotic systems in the presence of parameters uncertainties with sliding mode observer design","authors":"S. Beheshti, H. Khaloozadeh","doi":"10.1109/ICCIAUTOM.2011.6356738","DOIUrl":"https://doi.org/10.1109/ICCIAUTOM.2011.6356738","url":null,"abstract":"In secure communication applications, time delay chaotic systems are more confidential than the simple chaotic systems. Therefore, in this paper synchronization of time delay chaotic systems has been investigated. Sliding mode observer based approach has been applied as a synchronization method and the stability of the proposed observer has been guaranteed. In order to enhance the level of security of the communication system, the parameters of drive system (transmitter) are assumed to be unknown at the response system (receiver). These uncertainties lie in linear part of the system but sliding mode observer just compensates the uncertainties that lie in nonlinear parts, so the proposed sliding mode observer cannot retrieve the actual states correctly. The proposed solution is on-line identification of the uncertain parameters using the states which have been estimated by the observer. In order to identify the uncertain parameters, the model of the system must be rewritten linearly in terms of unknown parameters. Then the parameters are estimated using Recursive Least Squares (RLS) algorithm. The estimated parameters are used simultaneously in state estimation by the observer. Consequently, the synchronization performance is increased significantly. The result is illustrated numerically on the synchronization of chaotic time-delay Chua's circuit and the simulation results demonstrate the efficiency of the proposed scheme.","PeriodicalId":438427,"journal":{"name":"The 2nd International Conference on Control, Instrumentation and Automation","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114589133","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 : 2011-12-01DOI: 10.1109/ICCIAUTOM.2011.6356754
R. Zaeri, A. Ghanbarzadeh, B. Attaran, Shapour Moradi
Any industry needs an efficient predictive plan in order to optimize the management of resources and improve the economy of the plant by reducing unnecessary costs and increasing the level of safety. A great percentage of breakdowns in productive processes are caused by bearings. This paper presents a methodology for fault diagnosis of ball bearings based on continuous wavelet transform (CWT) and artificial neural network (ANN). Three wavelet selection criteria Maximum Energy, Minimum Shannon Entropy, and Maximum Energy to Shannon Entropy ratio are used and compared to select an appropriate wavelet to extract statistical features. Total 15 feature set and 87 mother wavelet candidates were studied, and results show that complex morlet 1-1 has a best diagnosis performance based on minimum shannon entropy than the other mother wavelets and criteria. Also results show the potential application of proposed methodology with ANN for the development of on-line fault diagnosis systems for machine condition.
{"title":"Artificial neural network based fault diagnostics of rolling element bearings using continuous wavelet transform","authors":"R. Zaeri, A. Ghanbarzadeh, B. Attaran, Shapour Moradi","doi":"10.1109/ICCIAUTOM.2011.6356754","DOIUrl":"https://doi.org/10.1109/ICCIAUTOM.2011.6356754","url":null,"abstract":"Any industry needs an efficient predictive plan in order to optimize the management of resources and improve the economy of the plant by reducing unnecessary costs and increasing the level of safety. A great percentage of breakdowns in productive processes are caused by bearings. This paper presents a methodology for fault diagnosis of ball bearings based on continuous wavelet transform (CWT) and artificial neural network (ANN). Three wavelet selection criteria Maximum Energy, Minimum Shannon Entropy, and Maximum Energy to Shannon Entropy ratio are used and compared to select an appropriate wavelet to extract statistical features. Total 15 feature set and 87 mother wavelet candidates were studied, and results show that complex morlet 1-1 has a best diagnosis performance based on minimum shannon entropy than the other mother wavelets and criteria. Also results show the potential application of proposed methodology with ANN for the development of on-line fault diagnosis systems for machine condition.","PeriodicalId":438427,"journal":{"name":"The 2nd International Conference on Control, Instrumentation and Automation","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129553902","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 : 2011-12-01DOI: 10.1109/ICCIAUTOM.2011.6356808
F. Alambeigi, S. Behzadipour, G. Vossoughi, F. Farahmand
A tele-surgery system with force feedback is completely modeled in the MATLAB-Simulink software. The virtual rapid robot prototyping is used to import the SolidWorks models of the master and slave robots to MATLAB-SimMechanics. This method provides us with the 3D vision of the robot performance in the virtual reality environment. Each robot has 4- DOF in motion and is equipped with a 6-DOF force/torque sensor. A proper damping controller is designed in order to provide the sense of real surgery. This method uses the differences between the measured forces in master and slave sensors in order to generate the velocity command for the master actuators. To model the behavior of the surgeon hand in the real operation, a variable force/torque is applied to the tool handle and the reaction of the system is studied in the virtual reality environment. It can be claimed from the results that this method acceptably provides the situation of a real surgery for a multi-DOF robotic surgery system.
{"title":"Simulation and control of a multi-DOF laparoscopic tele-surgery system in virtual reality","authors":"F. Alambeigi, S. Behzadipour, G. Vossoughi, F. Farahmand","doi":"10.1109/ICCIAUTOM.2011.6356808","DOIUrl":"https://doi.org/10.1109/ICCIAUTOM.2011.6356808","url":null,"abstract":"A tele-surgery system with force feedback is completely modeled in the MATLAB-Simulink software. The virtual rapid robot prototyping is used to import the SolidWorks models of the master and slave robots to MATLAB-SimMechanics. This method provides us with the 3D vision of the robot performance in the virtual reality environment. Each robot has 4- DOF in motion and is equipped with a 6-DOF force/torque sensor. A proper damping controller is designed in order to provide the sense of real surgery. This method uses the differences between the measured forces in master and slave sensors in order to generate the velocity command for the master actuators. To model the behavior of the surgeon hand in the real operation, a variable force/torque is applied to the tool handle and the reaction of the system is studied in the virtual reality environment. It can be claimed from the results that this method acceptably provides the situation of a real surgery for a multi-DOF robotic surgery system.","PeriodicalId":438427,"journal":{"name":"The 2nd International Conference on Control, Instrumentation and Automation","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129639792","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 : 2011-12-01DOI: 10.1109/ICCIAUTOM.2011.6356642
A. Maleki, A. Geramipour
This paper presents a closed-loop control system for regulating blood glucose level in type-1 diabetic patients. The goals of designing controller are 1. avoidance of hypoglycemia (blood glucose concentrations should be above 3mmol/l) and 2. reduction in the blood glucose level (average blood glucose should be less than 7mmol/l) in diabetic patients. An intensive therapy for these patients is described by a continuous subcutaneous insulin infusion pump which mimics the natural insulin secretion in healthy person. The control algorithm uses experience of physicians to treat this disease by using Mamdani-type fuzzy logic controller (FLC). Robustness of this controller is tested by a group of diabetic patients models. Then to assess the performance and capabilities of fuzzy controller, the results of FLC were compared to PID controller for each diabetic patient. The results showed that FLC has a more stable response in presence of uncertainty in system parameters which can vary from patient to patient.
{"title":"Continuous control of blood glucose in TIDM using fuzzy logic controller in insulin pump: A simulation study","authors":"A. Maleki, A. Geramipour","doi":"10.1109/ICCIAUTOM.2011.6356642","DOIUrl":"https://doi.org/10.1109/ICCIAUTOM.2011.6356642","url":null,"abstract":"This paper presents a closed-loop control system for regulating blood glucose level in type-1 diabetic patients. The goals of designing controller are 1. avoidance of hypoglycemia (blood glucose concentrations should be above 3mmol/l) and 2. reduction in the blood glucose level (average blood glucose should be less than 7mmol/l) in diabetic patients. An intensive therapy for these patients is described by a continuous subcutaneous insulin infusion pump which mimics the natural insulin secretion in healthy person. The control algorithm uses experience of physicians to treat this disease by using Mamdani-type fuzzy logic controller (FLC). Robustness of this controller is tested by a group of diabetic patients models. Then to assess the performance and capabilities of fuzzy controller, the results of FLC were compared to PID controller for each diabetic patient. The results showed that FLC has a more stable response in presence of uncertainty in system parameters which can vary from patient to patient.","PeriodicalId":438427,"journal":{"name":"The 2nd International Conference on Control, Instrumentation and Automation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130487473","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 : 2011-12-01DOI: 10.1109/ICCIAUTOM.2011.6356824
M. Ghadiri-Modarres, M. Mojiri
This paper is concerned with the identification and rejection of exponentially damped sinusoidal (EDS) signals. For identification, a new algorithm, based on adaptive identifier concept is presented for online estimation of damping factor and frequency of an EDS signal. Stability analysis of the proposed algorithm is carried out using averaging theory. For rejection, the estimated parameters are employed in an adaptive feedforward cancelation scheme to cancel the EDS type disturbances affecting a linear system. The approach is an indirect algorithm in the sense that the frequency and damping factor of the disturbance are estimated, and the estimates are used in another adaptive algorithm which continuously adjust the control parameters and cancel the effect of the disturbance. The proposed algorithm is simple in structure and can be easily designed, as long as the plant is known and stable. Simulation results are also presented to confirm the analytical derivations and the desirable performance of the proposed algorithm.
{"title":"Control of oscillatory damped disturbances-an indirect approach","authors":"M. Ghadiri-Modarres, M. Mojiri","doi":"10.1109/ICCIAUTOM.2011.6356824","DOIUrl":"https://doi.org/10.1109/ICCIAUTOM.2011.6356824","url":null,"abstract":"This paper is concerned with the identification and rejection of exponentially damped sinusoidal (EDS) signals. For identification, a new algorithm, based on adaptive identifier concept is presented for online estimation of damping factor and frequency of an EDS signal. Stability analysis of the proposed algorithm is carried out using averaging theory. For rejection, the estimated parameters are employed in an adaptive feedforward cancelation scheme to cancel the EDS type disturbances affecting a linear system. The approach is an indirect algorithm in the sense that the frequency and damping factor of the disturbance are estimated, and the estimates are used in another adaptive algorithm which continuously adjust the control parameters and cancel the effect of the disturbance. The proposed algorithm is simple in structure and can be easily designed, as long as the plant is known and stable. Simulation results are also presented to confirm the analytical derivations and the desirable performance of the proposed algorithm.","PeriodicalId":438427,"journal":{"name":"The 2nd International Conference on Control, Instrumentation and Automation","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121201951","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 : 2011-12-01DOI: 10.1109/ICCIAUTOM.2011.6356800
A. B. Pournazhdi, M. Mirzaei, A. Ghiasi
This paper presents a dynamic modeling and control for fast walking of seven link biped robots in the sagittal plane. First, the dynamic equations of motion are derived with a convenient method that simplifies the deriving procedure significantly. The impact of biped's foot with the ground is considered and the corresponding effects are taken into accounts. By a systematic approach, the trajectories of hip and two ankle joints are formulated first and then the joint angle profiles are expressed according to the biped geometry. Finally, the sliding mode controller is developed to control bipedal walking. The computer simulation results attest good walking process for seven link biped robot.
{"title":"Dynamic modeling and sliding mode control for fast walking of seven-link biped robot","authors":"A. B. Pournazhdi, M. Mirzaei, A. Ghiasi","doi":"10.1109/ICCIAUTOM.2011.6356800","DOIUrl":"https://doi.org/10.1109/ICCIAUTOM.2011.6356800","url":null,"abstract":"This paper presents a dynamic modeling and control for fast walking of seven link biped robots in the sagittal plane. First, the dynamic equations of motion are derived with a convenient method that simplifies the deriving procedure significantly. The impact of biped's foot with the ground is considered and the corresponding effects are taken into accounts. By a systematic approach, the trajectories of hip and two ankle joints are formulated first and then the joint angle profiles are expressed according to the biped geometry. Finally, the sliding mode controller is developed to control bipedal walking. The computer simulation results attest good walking process for seven link biped robot.","PeriodicalId":438427,"journal":{"name":"The 2nd International Conference on Control, Instrumentation and Automation","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116329412","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 : 2011-12-01DOI: 10.1109/ICCIAUTOM.2011.6356719
T. Taleshian, N. Ranjbar, R. Ghaderi
An optimal control for an AUV (only pitch channel) based on IPSO_SQP algorithm is achieved. The control input (fin angle) is assumed to be bounded and piecewise constant. In the first stage of the optimization process by using the IPSO algorithm, the chance of converging to the global optimum is significantly increased. In the second stage, the code is switched to a SQP algorithm. This is shown improve the speed of convergence and accuracy. The combined technique gains benefits of its both original algorithms. To control an AUV a pitch programming is investigated in this paper. To track a desired pitch angle in the pitch programming problem a PID controller with optimal gain is used. The gain of PID controller is also optimized through an IPSO-SQP algorithm. Simulations show the effectiveness of the proposed controller.
{"title":"Optimal control of an autonomous underwater vehicle using IPSO_SQP algorithm","authors":"T. Taleshian, N. Ranjbar, R. Ghaderi","doi":"10.1109/ICCIAUTOM.2011.6356719","DOIUrl":"https://doi.org/10.1109/ICCIAUTOM.2011.6356719","url":null,"abstract":"An optimal control for an AUV (only pitch channel) based on IPSO_SQP algorithm is achieved. The control input (fin angle) is assumed to be bounded and piecewise constant. In the first stage of the optimization process by using the IPSO algorithm, the chance of converging to the global optimum is significantly increased. In the second stage, the code is switched to a SQP algorithm. This is shown improve the speed of convergence and accuracy. The combined technique gains benefits of its both original algorithms. To control an AUV a pitch programming is investigated in this paper. To track a desired pitch angle in the pitch programming problem a PID controller with optimal gain is used. The gain of PID controller is also optimized through an IPSO-SQP algorithm. Simulations show the effectiveness of the proposed controller.","PeriodicalId":438427,"journal":{"name":"The 2nd International Conference on Control, Instrumentation and Automation","volume":"1135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113995029","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 : 2011-12-01DOI: 10.1109/ICCIAUTOM.2011.6356659
M. Sadeghi, F. Bavafa, M. H. Zarif, S. Alavi
In this paper, a new approach is proposed to tune a proportional-integral (PI) controller. By conceptual analyzing the operations of the proportional and integral parts of the controller, the design procedure is developed. Because of using nonlinear functions to tune the controller coefficients, the controller is categorized as a nonlinear PI controller. The proposed idea for tuning the PI controller includes the two steps. First, the proportional coefficient is tuned to increase the speed of the plant response. To achieve this objective, the control signal is set at maximum level for all error values larger than a pre-specified value. Second, the integral coefficient is tuned to decrease the overshoot of the plant response. To get this objective, the integral part of the controller is eliminated when the error is big. To validate the proposed idea, a highly nonlinear plant, named Continuous Stirred Tank Reactor (CSTR) is controlled by the nonlinear PI controller. A classical linear PI controller and a neurocontroller are selected for comparison. Simulation results and comparisons show the priority of the proposed nonlinear PI controller to achieve faster response with least overshoot.
{"title":"New approach to design a nonlinear PI controller for a CSTR system","authors":"M. Sadeghi, F. Bavafa, M. H. Zarif, S. Alavi","doi":"10.1109/ICCIAUTOM.2011.6356659","DOIUrl":"https://doi.org/10.1109/ICCIAUTOM.2011.6356659","url":null,"abstract":"In this paper, a new approach is proposed to tune a proportional-integral (PI) controller. By conceptual analyzing the operations of the proportional and integral parts of the controller, the design procedure is developed. Because of using nonlinear functions to tune the controller coefficients, the controller is categorized as a nonlinear PI controller. The proposed idea for tuning the PI controller includes the two steps. First, the proportional coefficient is tuned to increase the speed of the plant response. To achieve this objective, the control signal is set at maximum level for all error values larger than a pre-specified value. Second, the integral coefficient is tuned to decrease the overshoot of the plant response. To get this objective, the integral part of the controller is eliminated when the error is big. To validate the proposed idea, a highly nonlinear plant, named Continuous Stirred Tank Reactor (CSTR) is controlled by the nonlinear PI controller. A classical linear PI controller and a neurocontroller are selected for comparison. Simulation results and comparisons show the priority of the proposed nonlinear PI controller to achieve faster response with least overshoot.","PeriodicalId":438427,"journal":{"name":"The 2nd International Conference on Control, Instrumentation and Automation","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127601442","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 : 2011-12-01DOI: 10.1109/ICCIAUTOM.2011.6356757
M. Jafari, A. Safavi
One of the most applicable approaches in data driven process monitoring techniques is Principal Component Analysis (PCA). This approach assumes existence of uncorrelated stationary observations. Restriction of PCA-based process monitoring approaches on distribution function of observations has turned attentions to the use of Independent Component Analysis (ICA) algorithms. ICA is based on the assumption that at most one of the sources is Gaussian. Therefore, recent process monitoring approaches are based on FastICA algorithm which maximizes non-Gaussianity. As process variables can have any form of distribution function, implementing a method that has the ability to face all of the situations improves the monitoring quality. While both PCA-based and ICA-based monitoring approaches are restricted methods, this paper proposes extracting both Gaussian and non- Gaussian sources through Second Order Blind Identification for process monitoring. Besides, a new criterion for sorting sources is introduced. The applicability of the proposed method will be investigated through Tennessee Eastman Process.
{"title":"Incorporating second order statistics in process monitoring","authors":"M. Jafari, A. Safavi","doi":"10.1109/ICCIAUTOM.2011.6356757","DOIUrl":"https://doi.org/10.1109/ICCIAUTOM.2011.6356757","url":null,"abstract":"One of the most applicable approaches in data driven process monitoring techniques is Principal Component Analysis (PCA). This approach assumes existence of uncorrelated stationary observations. Restriction of PCA-based process monitoring approaches on distribution function of observations has turned attentions to the use of Independent Component Analysis (ICA) algorithms. ICA is based on the assumption that at most one of the sources is Gaussian. Therefore, recent process monitoring approaches are based on FastICA algorithm which maximizes non-Gaussianity. As process variables can have any form of distribution function, implementing a method that has the ability to face all of the situations improves the monitoring quality. While both PCA-based and ICA-based monitoring approaches are restricted methods, this paper proposes extracting both Gaussian and non- Gaussian sources through Second Order Blind Identification for process monitoring. Besides, a new criterion for sorting sources is introduced. The applicability of the proposed method will be investigated through Tennessee Eastman Process.","PeriodicalId":438427,"journal":{"name":"The 2nd International Conference on Control, Instrumentation and Automation","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128095993","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：