Pub Date : 2022-10-19DOI: 10.1109/ICSTCC55426.2022.9931856
I. Voncilă, Elena Selim, M. Voncila
This paper presents a new quality evaluation method of control assessments used nowadays for induction motor drives systems. To visualize the accuracy of the new evaluation method, a comparative analysis is performed between this new method and the method widely used in modern drive systems, respectively, the spectral analysis method. By determining the fractal dimension of temporal variation of the quantities of interest, specific to electrical and mechanical access gates, which represents the proposed method, the established hierarchy was validated, for these assessments, hierarchy obtained using the spectral analysis method. The variation of the quantities of interest on the two access gates, electrical and mechanical, was obtained by simulation in PSIM (including the corresponding frequency spectrum), and the determination of the fractal size was performed in MATLAB.
{"title":"Use of fractal analysis for quality evaluation of control methods in induction motor drive systems","authors":"I. Voncilă, Elena Selim, M. Voncila","doi":"10.1109/ICSTCC55426.2022.9931856","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931856","url":null,"abstract":"This paper presents a new quality evaluation method of control assessments used nowadays for induction motor drives systems. To visualize the accuracy of the new evaluation method, a comparative analysis is performed between this new method and the method widely used in modern drive systems, respectively, the spectral analysis method. By determining the fractal dimension of temporal variation of the quantities of interest, specific to electrical and mechanical access gates, which represents the proposed method, the established hierarchy was validated, for these assessments, hierarchy obtained using the spectral analysis method. The variation of the quantities of interest on the two access gates, electrical and mechanical, was obtained by simulation in PSIM (including the corresponding frequency spectrum), and the determination of the fractal size was performed in MATLAB.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130430527","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 : 2022-10-19DOI: 10.1109/ICSTCC55426.2022.9931833
S. Zanoli, C. Pepe, G. Astolfi
The present work describes an Advanced Process Control solution applied to a cement plant grate cooler. The grate cooler is located downstream of a clinker rotary kiln with the purpose of suitably cooling the clinker. Clinker is cooled through the action of multiple cold air fan units as it is transported by the clinker rotary kiln. A Model Predictive Control strategy was designed in order to minimize the electrical energy consumption of the cold air fan units while guaranteeing the necessary heat recovery for the kiln and the preheater. At the same time, clinker quality constraints are taken into account. The designed controller has been installed on the real plant, obtaining satisfactory results in terms of kiln tertiary air increase and of kiln combustion improvement. In particular, a major process stabilization has been achieved, proven by a significant reduction of the standard deviation related to the pressure of cooler grate.
{"title":"Advanced Process Control of a cement plant grate cooler","authors":"S. Zanoli, C. Pepe, G. Astolfi","doi":"10.1109/ICSTCC55426.2022.9931833","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931833","url":null,"abstract":"The present work describes an Advanced Process Control solution applied to a cement plant grate cooler. The grate cooler is located downstream of a clinker rotary kiln with the purpose of suitably cooling the clinker. Clinker is cooled through the action of multiple cold air fan units as it is transported by the clinker rotary kiln. A Model Predictive Control strategy was designed in order to minimize the electrical energy consumption of the cold air fan units while guaranteeing the necessary heat recovery for the kiln and the preheater. At the same time, clinker quality constraints are taken into account. The designed controller has been installed on the real plant, obtaining satisfactory results in terms of kiln tertiary air increase and of kiln combustion improvement. In particular, a major process stabilization has been achieved, proven by a significant reduction of the standard deviation related to the pressure of cooler grate.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"609 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131425530","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 : 2022-10-19DOI: 10.1109/ICSTCC55426.2022.9931788
A. Nair, Jonas Weitzel, A. Hykkerud, H. Ratnaweera
Online water-quality sensors installed in Wastewater Treatment Plants (WWTPs) are prone to process disturbances that generate erroneous data. Faulty sensor data can disrupt automation systems and result in sub-optimal performance of WWTPs. This paper presents a machine-learning-based system for real-time detection and the subsequent correction of faulty sensor data installed in a full-scale municipal WWTP. The fault detection system is developed by training a k-nearest neighbour (kNN) classifier with labelled historical data. The trained kNN classifier is then deployed in the WWTP's web-based Supervisory Control And Data Acquisition (SCADA) system to assess the performance in real-time. A qualitative comparison between raw and corrected sensor data demonstrates the system's potential to detect sensor faults and provide stable and reliable surrogate values.
{"title":"Supervised machine learning based system for automatic fault-detection in water-quality sensors","authors":"A. Nair, Jonas Weitzel, A. Hykkerud, H. Ratnaweera","doi":"10.1109/ICSTCC55426.2022.9931788","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931788","url":null,"abstract":"Online water-quality sensors installed in Wastewater Treatment Plants (WWTPs) are prone to process disturbances that generate erroneous data. Faulty sensor data can disrupt automation systems and result in sub-optimal performance of WWTPs. This paper presents a machine-learning-based system for real-time detection and the subsequent correction of faulty sensor data installed in a full-scale municipal WWTP. The fault detection system is developed by training a k-nearest neighbour (kNN) classifier with labelled historical data. The trained kNN classifier is then deployed in the WWTP's web-based Supervisory Control And Data Acquisition (SCADA) system to assess the performance in real-time. A qualitative comparison between raw and corrected sensor data demonstrates the system's potential to detect sensor faults and provide stable and reliable surrogate values.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129656649","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 : 2022-10-19DOI: 10.1109/ICSTCC55426.2022.9931873
Hamid Boukerrou, G. Millérioux, M. Minier
Among several solutions to face the unprecedented increase of attacks towards Cyber Physical Systems, encryption plays a central role. In the form of a Proof of Concept, this contribution gives a new methodology for designing self-synchronizing automata, having in mind their use in symmetric cryptography, namely the Self-Synchronizing Stream Ciphers. The contribution of the paper is to recast the design as control theoretical issues. It calls for a graph-based approach and results borrowed from control theory and dynamical systems, in particular LPV systems. The design leads to not necessarily $T$-functions as state transition functions of the automata involved in the ciphering and deciphering sides. It is a consideration that is important for the sake of security. Another asset of the approach is that the resulting ciphers admit possibly vectorial inputs to enhance the throughput.
{"title":"Towards a new design of ciphers to secure CPS: the role of control theory","authors":"Hamid Boukerrou, G. Millérioux, M. Minier","doi":"10.1109/ICSTCC55426.2022.9931873","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931873","url":null,"abstract":"Among several solutions to face the unprecedented increase of attacks towards Cyber Physical Systems, encryption plays a central role. In the form of a Proof of Concept, this contribution gives a new methodology for designing self-synchronizing automata, having in mind their use in symmetric cryptography, namely the Self-Synchronizing Stream Ciphers. The contribution of the paper is to recast the design as control theoretical issues. It calls for a graph-based approach and results borrowed from control theory and dynamical systems, in particular LPV systems. The design leads to not necessarily $T$-functions as state transition functions of the automata involved in the ciphering and deciphering sides. It is a consideration that is important for the sake of security. Another asset of the approach is that the resulting ciphers admit possibly vectorial inputs to enhance the throughput.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129800732","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 : 2022-10-19DOI: 10.1109/ICSTCC55426.2022.9931780
Maryam Naghdi, I. Izadi
This paper investigates the motion tracking problem for piezoelectric actuators (PEAs) using a sampled-data control method known as sampled-data model-free adaptive control (SMFAC). The fundamental architecture of the proposed scheme is based on input-output data, and the sampling period is an integral part of the design. PEA with the Bouc-Wen hysteresis model is first considered to obtain a sampled-data nonlinear model using the integral mean value theorem and the discrete-time Euler approximation. Then, a sampled-data control rule subject to input rate constraint is constructed by applying a sampled-data extended state observer (SESO) and a sampled-data parameter estimation technique. The SESO is used to estimate the unknown residual nonlinearity and external disturbances. The convergence of the tracking error is proven through theoretical analysis. Experimental results confirm the adequate performance of the proposed scheme.
{"title":"Sampled-Data Model-Free Adaptive Control of Piezoelectric Actuators with Input Rate Constraint Using Extended State Observer","authors":"Maryam Naghdi, I. Izadi","doi":"10.1109/ICSTCC55426.2022.9931780","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931780","url":null,"abstract":"This paper investigates the motion tracking problem for piezoelectric actuators (PEAs) using a sampled-data control method known as sampled-data model-free adaptive control (SMFAC). The fundamental architecture of the proposed scheme is based on input-output data, and the sampling period is an integral part of the design. PEA with the Bouc-Wen hysteresis model is first considered to obtain a sampled-data nonlinear model using the integral mean value theorem and the discrete-time Euler approximation. Then, a sampled-data control rule subject to input rate constraint is constructed by applying a sampled-data extended state observer (SESO) and a sampled-data parameter estimation technique. The SESO is used to estimate the unknown residual nonlinearity and external disturbances. The convergence of the tracking error is proven through theoretical analysis. Experimental results confirm the adequate performance of the proposed scheme.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130019262","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 : 2022-10-19DOI: 10.1109/ICSTCC55426.2022.9931787
Octavian Duca, E. Minca, A. Filipescu, R. Șolea, D. Cernega, M. Paun
In the flexible manufacturing environment some processes that until now did not need a close loop control need to be controlled so that the precision of the task permits the continuing of the manufacturing. As the processes are optimized and the manufacturing consists of multiple parallel processes, there is a need of assuring that a product is at a certain location at a certain time. In the control of a task, usually, the output of the system is measured in a timely manner at a certain sampling time. This is usually not possible in the manufacturing processes as a product position is given based on events, by sensors placed at certain locations. Certain event-based PID controllers were proposed and implemented in other control areas but in this controllers the event triggering is given by the error passing a certain level. This kind of controller cannot be implemented given the necessity of high frequency measurement of product position. In this paper we propose an PID event-base controller that uses as triggering event the activation of one of the manufacturing process sensors by the product. As the sensors are placed only in key positions the number of activations is limited. Based on these sensors the PID controller determines the necessary control signals between the key locations.
{"title":"Event-based PID control in a flexible manufacturing process","authors":"Octavian Duca, E. Minca, A. Filipescu, R. Șolea, D. Cernega, M. Paun","doi":"10.1109/ICSTCC55426.2022.9931787","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931787","url":null,"abstract":"In the flexible manufacturing environment some processes that until now did not need a close loop control need to be controlled so that the precision of the task permits the continuing of the manufacturing. As the processes are optimized and the manufacturing consists of multiple parallel processes, there is a need of assuring that a product is at a certain location at a certain time. In the control of a task, usually, the output of the system is measured in a timely manner at a certain sampling time. This is usually not possible in the manufacturing processes as a product position is given based on events, by sensors placed at certain locations. Certain event-based PID controllers were proposed and implemented in other control areas but in this controllers the event triggering is given by the error passing a certain level. This kind of controller cannot be implemented given the necessity of high frequency measurement of product position. In this paper we propose an PID event-base controller that uses as triggering event the activation of one of the manufacturing process sensors by the product. As the sensors are placed only in key positions the number of activations is limited. Based on these sensors the PID controller determines the necessary control signals between the key locations.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134581759","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 : 2022-10-19DOI: 10.1109/ICSTCC55426.2022.9931860
Ravi kiran Inapakurthi, K. Mitra
Uncertainty in process conditions makes the optimal solution from the deterministic optimization case infeasible or suboptimal. This mandates a special treatment for process uncertainty. The advent of unsupervised machine learning technique like clustering can be used to address this problem. Data arising from process conditions is meager and, to perform robust optimization, it is necessary to have enough representation of the uncertain region. For this, the collected data from process conditions is clustered using Support Vector Clustering (SVC). The hyper-parameters of SVC play a crucial role in clustering exercise. To promote this, a novel algorithm for determining optimal SVC models, is proposed. The proposed algorithm is used to cluster the uncertain process data and once clustered, can be used to sample additional data points inside each cluster using the convex hull. The additionally sampled data points in each cluster increases the cluster representativeness. The proposed methodology is implemented on industrial grinding circuits for performing Optimization Under Uncertainty (OUU) for the worst-case scenario and tested against the budget-uncertainty set based OUU.
{"title":"Artificial Intelligence Assisted Optimization Under Uncertainty for Robust Solutions","authors":"Ravi kiran Inapakurthi, K. Mitra","doi":"10.1109/ICSTCC55426.2022.9931860","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931860","url":null,"abstract":"Uncertainty in process conditions makes the optimal solution from the deterministic optimization case infeasible or suboptimal. This mandates a special treatment for process uncertainty. The advent of unsupervised machine learning technique like clustering can be used to address this problem. Data arising from process conditions is meager and, to perform robust optimization, it is necessary to have enough representation of the uncertain region. For this, the collected data from process conditions is clustered using Support Vector Clustering (SVC). The hyper-parameters of SVC play a crucial role in clustering exercise. To promote this, a novel algorithm for determining optimal SVC models, is proposed. The proposed algorithm is used to cluster the uncertain process data and once clustered, can be used to sample additional data points inside each cluster using the convex hull. The additionally sampled data points in each cluster increases the cluster representativeness. The proposed methodology is implemented on industrial grinding circuits for performing Optimization Under Uncertainty (OUU) for the worst-case scenario and tested against the budget-uncertainty set based OUU.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"295 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132909197","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 : 2022-10-19DOI: 10.1109/ICSTCC55426.2022.9931813
Alin Burz, N. Hajjar, P. Tucan, C. Radu, A. Pîslă, F. Graur, C. Vaida, C. Popa, T. Antal, D. Pisla
The paper presents the control system of two medical instruments used in percutaneous cancer treatment. One instrument is designed for radiofrequency ablation and the other one for brachytherapy. The instruments may be attached to various robots capable of providing 5 Degrees of Freedom. Two robotic solutions are used for exemplifying this capability, namely the Kuka iiwa robot and the PARA-BRACHYROB. The developed control system is capable to communicate with both robots using MATLAB environment and different communication protocols to establish the connections between the robot control units.
{"title":"On the control system for the robotic assisted instruments used in percutaneous cancer treatment","authors":"Alin Burz, N. Hajjar, P. Tucan, C. Radu, A. Pîslă, F. Graur, C. Vaida, C. Popa, T. Antal, D. Pisla","doi":"10.1109/ICSTCC55426.2022.9931813","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931813","url":null,"abstract":"The paper presents the control system of two medical instruments used in percutaneous cancer treatment. One instrument is designed for radiofrequency ablation and the other one for brachytherapy. The instruments may be attached to various robots capable of providing 5 Degrees of Freedom. Two robotic solutions are used for exemplifying this capability, namely the Kuka iiwa robot and the PARA-BRACHYROB. The developed control system is capable to communicate with both robots using MATLAB environment and different communication protocols to establish the connections between the robot control units.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128171187","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 : 2022-10-19DOI: 10.1109/ICSTCC55426.2022.9931869
Ionut Procop, F. Pacuraru, Sandita Pacuaru, R. Șolea, George Cotoc, Adrian Caramatescu
The purpose of this paper is to outline the development of a robust and low-cost semi-autonomous, remotely operated unmanned surface vessel (USV) used as a platform for environmental remediation technologies. By defining the shape as a catamaran, the first practical purpose is to build the collection mechanism in form of a cage to collect floating waste from rivers and lakes - in particular, plastic recipients that accumulate at the surface of the water. The unit was named “GreenCat” deriving from the purpose and the shape. Preliminary hull shape numerical investigation studies enabled carefully managed manufacturing processes resulting in a reduced manufacturing time. Based on hydrodynamic numerical simulations it is suggested that 6 km/h is an optimal travel speed. The electronic equipment was fitted and tested using two different controllers, manoeuvred by using both a radio command and a touch screen. Full-scale tests showed an autonomy of more than 60 minutes on one LiFePO04 - 12.8V-50Ah accumulator. The hull was designed to fit several accumulators making it possible to increase the autonomy to an estimated 8 hours. The data collected from the LiDAR system provided key information for the next level of autonomy, where obstacles can be avoided and the USV can charge automatically in a charging dock.
{"title":"Semi-Autonomous System for Lakes and Rivers Depollution","authors":"Ionut Procop, F. Pacuraru, Sandita Pacuaru, R. Șolea, George Cotoc, Adrian Caramatescu","doi":"10.1109/ICSTCC55426.2022.9931869","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931869","url":null,"abstract":"The purpose of this paper is to outline the development of a robust and low-cost semi-autonomous, remotely operated unmanned surface vessel (USV) used as a platform for environmental remediation technologies. By defining the shape as a catamaran, the first practical purpose is to build the collection mechanism in form of a cage to collect floating waste from rivers and lakes - in particular, plastic recipients that accumulate at the surface of the water. The unit was named “GreenCat” deriving from the purpose and the shape. Preliminary hull shape numerical investigation studies enabled carefully managed manufacturing processes resulting in a reduced manufacturing time. Based on hydrodynamic numerical simulations it is suggested that 6 km/h is an optimal travel speed. The electronic equipment was fitted and tested using two different controllers, manoeuvred by using both a radio command and a touch screen. Full-scale tests showed an autonomy of more than 60 minutes on one LiFePO04 - 12.8V-50Ah accumulator. The hull was designed to fit several accumulators making it possible to increase the autonomy to an estimated 8 hours. The data collected from the LiDAR system provided key information for the next level of autonomy, where obstacles can be avoided and the USV can charge automatically in a charging dock.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"177 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129560110","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 : 2022-10-19DOI: 10.1109/ICSTCC55426.2022.9931844
M. Nicola, C. Nicola, C. Ionete, D. Sendrescu, M. Roman
This article presents a Permanent Magnet Synchronous Motor (PMSM) control system which retains its performance for a significant variation of the parameters and load torque which represent disturbance for the control system. Classically, the PMSM control system is built in the form of a Field Oriented Control (FOC) control strategy structure built around PI speed (outer loop) and current (inner loop) controllers. We present the design stages and the numerical simulations performed in Matlab/Simulink, which prove the superiority of the robust control, by comparison with the classic FOC-type control structure. Because the Reinforcement Learning Twin-Delayed Deep Deterministic Policy Gradient (RL-TD3) agent is the most suitable for machine learning for process control, we synthesize a robust controller whose control quantities $boldsymbol{u}_{d}$ and $boldsymbol{u}_{q}$ are adjusted by a properly created and trained RL-TD3 agent. Using this robust combined controller plus RL-TD3 agent, superior performance is achieved in terms of response time and speed ripple.
{"title":"Improved Performance for PMSM Control Based on Robust Controller and Reinforcement Learning","authors":"M. Nicola, C. Nicola, C. Ionete, D. Sendrescu, M. Roman","doi":"10.1109/ICSTCC55426.2022.9931844","DOIUrl":"https://doi.org/10.1109/ICSTCC55426.2022.9931844","url":null,"abstract":"This article presents a Permanent Magnet Synchronous Motor (PMSM) control system which retains its performance for a significant variation of the parameters and load torque which represent disturbance for the control system. Classically, the PMSM control system is built in the form of a Field Oriented Control (FOC) control strategy structure built around PI speed (outer loop) and current (inner loop) controllers. We present the design stages and the numerical simulations performed in Matlab/Simulink, which prove the superiority of the robust control, by comparison with the classic FOC-type control structure. Because the Reinforcement Learning Twin-Delayed Deep Deterministic Policy Gradient (RL-TD3) agent is the most suitable for machine learning for process control, we synthesize a robust controller whose control quantities $boldsymbol{u}_{d}$ and $boldsymbol{u}_{q}$ are adjusted by a properly created and trained RL-TD3 agent. Using this robust combined controller plus RL-TD3 agent, superior performance is achieved in terms of response time and speed ripple.","PeriodicalId":220845,"journal":{"name":"2022 26th International Conference on System Theory, Control and Computing (ICSTCC)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130580230","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}