Pub Date : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9803994
Haluk Altay, F. Caliskan
Model Based Design (MBD) is a development method that integrates the design, implementation, and verification of any system, and has grown in popularity in recent years. This method makes the simulation the main element of the development process, allowing continuous prototyping. In this article, the experimental verification of simulation model of small jet DEHA UAV is realized. Within the scope of the study, an aircraft simulation model is developed with model-based design approach using model-based design tools and simulation model was verified by novel experimental verification platforms. Model verification studies are carried out with experimental platforms for the aircraft-specific models “Mass Properties”, “Actuators”, “Propulsion” and “Landing Gear” in the DEHA simulation model. As a result, a simulation model verified with experimental platforms for DEHA, which is an experimental jet unmanned aerial vehicle, was obtained with a model-based design approach and tools. Thanks to the validation platforms, the accuracy of the model has been increased.
{"title":"Experimental Verification of a Simulation Model for Jet UAV With Model Based Design","authors":"Haluk Altay, F. Caliskan","doi":"10.1109/CoDIT55151.2022.9803994","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9803994","url":null,"abstract":"Model Based Design (MBD) is a development method that integrates the design, implementation, and verification of any system, and has grown in popularity in recent years. This method makes the simulation the main element of the development process, allowing continuous prototyping. In this article, the experimental verification of simulation model of small jet DEHA UAV is realized. Within the scope of the study, an aircraft simulation model is developed with model-based design approach using model-based design tools and simulation model was verified by novel experimental verification platforms. Model verification studies are carried out with experimental platforms for the aircraft-specific models “Mass Properties”, “Actuators”, “Propulsion” and “Landing Gear” in the DEHA simulation model. As a result, a simulation model verified with experimental platforms for DEHA, which is an experimental jet unmanned aerial vehicle, was obtained with a model-based design approach and tools. Thanks to the validation platforms, the accuracy of the model has been increased.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126380520","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9803989
Sh. Kalantari, A. Kalhor, Babak Nadjar Araabi
In this paper, a fast, intelligent model is proposed for the order determination of linear dynamical systems by using convolutional neural networks. This model estimates the dynamic order of the system with considerably lower excitation order of stimulation signal and without any prior knowledge in comparison to former works. To this end, only step response of the system is taken to estimate the dynamic order for both stable and unstable linear systems. Unlike the conventional methods, in this deep-based approach, the order determination is performed quickly, automatically, at a low cost, and without any iteration. In addition, it is demonstrated that the proposed approach has low sensitivity against delay and noise. Such an intelligent model can satisfy the demands for a fast identifier in online and plug-and-play controllers.
{"title":"Order Determination of Linear Systems Using Convolutional Neural Networks","authors":"Sh. Kalantari, A. Kalhor, Babak Nadjar Araabi","doi":"10.1109/CoDIT55151.2022.9803989","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9803989","url":null,"abstract":"In this paper, a fast, intelligent model is proposed for the order determination of linear dynamical systems by using convolutional neural networks. This model estimates the dynamic order of the system with considerably lower excitation order of stimulation signal and without any prior knowledge in comparison to former works. To this end, only step response of the system is taken to estimate the dynamic order for both stable and unstable linear systems. Unlike the conventional methods, in this deep-based approach, the order determination is performed quickly, automatically, at a low cost, and without any iteration. In addition, it is demonstrated that the proposed approach has low sensitivity against delay and noise. Such an intelligent model can satisfy the demands for a fast identifier in online and plug-and-play controllers.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122338439","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804093
S. Kamel, Baazouzi Mansour, F. Bacha
Wind farms will need to continue to provide voltage and frequency stability to the grid even during periods of disturbance or faults. Particular attention has been paid to the maintenance of production under disturbed conditions (fault ride-through capability LVRT) and grid support capability. The maintenance of the production in disturbed regime is possible by the design and the dimensioning of controllers able to maintain the connection to the grid and that in the presence of network defects. Control of reactive energy in the grid using flexible alternative current transmission systems (FACTs) can improve the transient and permanent stability of the later. This paper deals with the behavior of a double-fed induction generator (DFIG) under asymmetric voltage faults. A static compensator (STATCOM) is connected to the common coupling point (PCC) and serves as a reactive support to regulate the mains voltage and keep the DFIG connected. The different converters used in this paper are controlled by the oriented voltage control strategy (VOC) decomposed in positive and negative sequences. Simulation results under MATLAB/SIMULINK environment are introduced to show the validity and efficiency of the control strategy.
{"title":"Enhancement of DFIG Operation Using a STATCOM Under a Voltage Grid Faults","authors":"S. Kamel, Baazouzi Mansour, F. Bacha","doi":"10.1109/CoDIT55151.2022.9804093","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804093","url":null,"abstract":"Wind farms will need to continue to provide voltage and frequency stability to the grid even during periods of disturbance or faults. Particular attention has been paid to the maintenance of production under disturbed conditions (fault ride-through capability LVRT) and grid support capability. The maintenance of the production in disturbed regime is possible by the design and the dimensioning of controllers able to maintain the connection to the grid and that in the presence of network defects. Control of reactive energy in the grid using flexible alternative current transmission systems (FACTs) can improve the transient and permanent stability of the later. This paper deals with the behavior of a double-fed induction generator (DFIG) under asymmetric voltage faults. A static compensator (STATCOM) is connected to the common coupling point (PCC) and serves as a reactive support to regulate the mains voltage and keep the DFIG connected. The different converters used in this paper are controlled by the oriented voltage control strategy (VOC) decomposed in positive and negative sequences. Simulation results under MATLAB/SIMULINK environment are introduced to show the validity and efficiency of the control strategy.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126026375","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804022
M. Stanković, M. Beko, S. Stankovic
In this paper a new Actor-Critic algorithm is proposed for distributed off-policy multi-agent reinforcement learning. It is composed of the Emphatic Temporal Difference ETD${left(lambda right)}$ algorithm (at the Critic stage) and a complementary distributed consensus-based algorithm using the exact gradients of a given criterion function (at the Actor stage). It is demonstrated that the algorithm converges weakly to the invariant set of an ordinary differential equation (ODE) characterizing the whole algorithm. Simulation results are presented as an illustration of high efficiency of the proposed algorithm.
{"title":"Distributed Actor-Critic Learning Using Emphatic Weightings","authors":"M. Stanković, M. Beko, S. Stankovic","doi":"10.1109/CoDIT55151.2022.9804022","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804022","url":null,"abstract":"In this paper a new Actor-Critic algorithm is proposed for distributed off-policy multi-agent reinforcement learning. It is composed of the Emphatic Temporal Difference ETD${left(lambda right)}$ algorithm (at the Critic stage) and a complementary distributed consensus-based algorithm using the exact gradients of a given criterion function (at the Actor stage). It is demonstrated that the algorithm converges weakly to the invariant set of an ordinary differential equation (ODE) characterizing the whole algorithm. Simulation results are presented as an illustration of high efficiency of the proposed algorithm.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125230223","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804146
I. Zaitceva, N. Kuznetsov, B. Andrievsky
The paper considers an electromechanical mobile robotic system in which the behavior of a human operator is imitated through computer modeling. Identification algorithms of the parameters of the human operator for linear and nonlinear systems are proposed. The application of this approach in the design of an automated human-machine control system is also described. The results of the research are illustrated by the example of a fly-by-wired pilot-aircraft system. It is shown how the change in the system parameters affects the handling quality characteristics of the robotic system.
{"title":"Identification of Human Model Parameters for the Human-Machine Control Systems Design","authors":"I. Zaitceva, N. Kuznetsov, B. Andrievsky","doi":"10.1109/CoDIT55151.2022.9804146","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804146","url":null,"abstract":"The paper considers an electromechanical mobile robotic system in which the behavior of a human operator is imitated through computer modeling. Identification algorithms of the parameters of the human operator for linear and nonlinear systems are proposed. The application of this approach in the design of an automated human-machine control system is also described. The results of the research are illustrated by the example of a fly-by-wired pilot-aircraft system. It is shown how the change in the system parameters affects the handling quality characteristics of the robotic system.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"171 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113985958","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9803993
Harika Putta, Karl Daher, Mira El Kamali, Omar Abou Khaled, D. Lalanne, E. Mugellini
The communication between humans and artificial agents is becoming crucial and significant in daily life, especially with the advancements in the fields of human-robot and human-computer interaction. For these artificial agents to be recognized as social beings, they should exhibit emotional and empathic behaviors. However, there is no global agreement on measuring the empathic capabilities of these agents. For this reason, the scientific community has paid a significant focus on developing a standardized metric to perceive artificial agents' empathy. In this regard, this article provides a discussion on challenges in artificial empathy evaluation and researches the developments to discuss the factors and recommendations to design a globally accepted metric. It also discusses the qualities required for a globally accepted and standardized metric. Finally, an adaptation to an existing questionnaire is proposed for the evaluation of empathy in artificial agents.
{"title":"Empathy scale adaptation for artificial agents: a review with a new subscale proposal","authors":"Harika Putta, Karl Daher, Mira El Kamali, Omar Abou Khaled, D. Lalanne, E. Mugellini","doi":"10.1109/CoDIT55151.2022.9803993","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9803993","url":null,"abstract":"The communication between humans and artificial agents is becoming crucial and significant in daily life, especially with the advancements in the fields of human-robot and human-computer interaction. For these artificial agents to be recognized as social beings, they should exhibit emotional and empathic behaviors. However, there is no global agreement on measuring the empathic capabilities of these agents. For this reason, the scientific community has paid a significant focus on developing a standardized metric to perceive artificial agents' empathy. In this regard, this article provides a discussion on challenges in artificial empathy evaluation and researches the developments to discuss the factors and recommendations to design a globally accepted metric. It also discusses the qualities required for a globally accepted and standardized metric. Finally, an adaptation to an existing questionnaire is proposed for the evaluation of empathy in artificial agents.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122540519","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804087
Nicola Mignoni, Paolo Scarabaggio, Raffaele Carli, M. Dotoli
In the last decade, distributed energy generation and storage have significantly contributed to the widespread of energy communities. In this context, we propose an energy community model constituted by prosumers, characterized by their own demand and renewable generation, and service-oriented energy storage providers, able to store energy surplus and release it upon a fee payment. We address the problem of optimally schedule the energy flows in the community, with the final goal of making the prosumers' energy supply more efficient, while creating a sustainable and profitable business model for storage providers. The proposed resolution algorithms are based on decentralized and distributed game theoretical control schemes. These approaches are mathematically formulated and then effectively validated and compared with a centralized method through numerical simulations on realistic scenarios.
{"title":"Game Theoretical Control Frameworks for Multiple Energy Storage Services in Energy Communities","authors":"Nicola Mignoni, Paolo Scarabaggio, Raffaele Carli, M. Dotoli","doi":"10.1109/CoDIT55151.2022.9804087","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804087","url":null,"abstract":"In the last decade, distributed energy generation and storage have significantly contributed to the widespread of energy communities. In this context, we propose an energy community model constituted by prosumers, characterized by their own demand and renewable generation, and service-oriented energy storage providers, able to store energy surplus and release it upon a fee payment. We address the problem of optimally schedule the energy flows in the community, with the final goal of making the prosumers' energy supply more efficient, while creating a sustainable and profitable business model for storage providers. The proposed resolution algorithms are based on decentralized and distributed game theoretical control schemes. These approaches are mathematically formulated and then effectively validated and compared with a centralized method through numerical simulations on realistic scenarios.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"427 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131497443","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9803902
Zahra Yahyaoui, M. Hajji, M. Mansouri, Kais Bouzrara, H. Nounou, M. Nounou
This paper proposes an effective fault detection and diagnosis (FDD) paradigm in Wind Energy Converter (WEC) Systems. The developed FDD frame-work merges the benefits of kernel principal component analysis (KPCA) model and bidirectional long short-term memory (BiLSTM) feature classifier. KPCA is used to extract and select the most effective features. While, BiLSTM is used for classification purposes. The proposed KPCA-based BiLSTM approach involves two main steps; feature extraction and selection and fault classification. It is tackled in such a way that KPCA model is developed in order to select and extract the more efficient features where the final features are fed to BiLSTM to distinguish between different working modes. Different simulation scenarios are considered in this study in order to show the robustness and performances of the developed technique when compared to the conventional FDD methods.
{"title":"Kernel PCA based BiLSTM for Fault Detection and Diagnosis for Wind Energy Converter Systems*","authors":"Zahra Yahyaoui, M. Hajji, M. Mansouri, Kais Bouzrara, H. Nounou, M. Nounou","doi":"10.1109/CoDIT55151.2022.9803902","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9803902","url":null,"abstract":"This paper proposes an effective fault detection and diagnosis (FDD) paradigm in Wind Energy Converter (WEC) Systems. The developed FDD frame-work merges the benefits of kernel principal component analysis (KPCA) model and bidirectional long short-term memory (BiLSTM) feature classifier. KPCA is used to extract and select the most effective features. While, BiLSTM is used for classification purposes. The proposed KPCA-based BiLSTM approach involves two main steps; feature extraction and selection and fault classification. It is tackled in such a way that KPCA model is developed in order to select and extract the more efficient features where the final features are fed to BiLSTM to distinguish between different working modes. Different simulation scenarios are considered in this study in order to show the robustness and performances of the developed technique when compared to the conventional FDD methods.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131707010","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804016
F. B. Amor, Manel Kammoun, T. Loukil
Without a doubt, healthcare is currently one of the main social and economic problem in the world and one of the most important problems treated we have healthcare facility location which is our interest in this study. Given the growth of the population in Tunisia, we need to increase the number of the health-care facilities over the next years. Actually, we are interested to the case of the specific pharmacy of the National Social Security Fund policlinic of Tunisia (NSSF). The specific pharmacy is charged of providing specific treatments for serious diseases requiring long-term care such as: Chemotherapy, Osteoporosis and the Parkinson. This pharmacy is a separate pharmacy in the NSSF’ policlinics which is available only in 3 policlinics. From this, we can notice that they are not well located and we can imagine congestion and the waste of time, so we can conclude that they are not able to cover all regions. In this paper, we hope to solve this situation by engaging a set of other pharmacies of the 24 Tunisian cities to deliver these drugs. More precisely, if the city is scheduled in the tour, so it's request will be served directly. If it isn't the case and the city isn't along the tour, it will be covered by another visited city.
{"title":"Exact Method and Iterative Approach to Solve a Case Study of the National Social Security Fund","authors":"F. B. Amor, Manel Kammoun, T. Loukil","doi":"10.1109/CoDIT55151.2022.9804016","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804016","url":null,"abstract":"Without a doubt, healthcare is currently one of the main social and economic problem in the world and one of the most important problems treated we have healthcare facility location which is our interest in this study. Given the growth of the population in Tunisia, we need to increase the number of the health-care facilities over the next years. Actually, we are interested to the case of the specific pharmacy of the National Social Security Fund policlinic of Tunisia (NSSF). The specific pharmacy is charged of providing specific treatments for serious diseases requiring long-term care such as: Chemotherapy, Osteoporosis and the Parkinson. This pharmacy is a separate pharmacy in the NSSF’ policlinics which is available only in 3 policlinics. From this, we can notice that they are not well located and we can imagine congestion and the waste of time, so we can conclude that they are not able to cover all regions. In this paper, we hope to solve this situation by engaging a set of other pharmacies of the 24 Tunisian cities to deliver these drugs. More precisely, if the city is scheduled in the tour, so it's request will be served directly. If it isn't the case and the city isn't along the tour, it will be covered by another visited city.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"304 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133929460","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 : 2022-05-17DOI: 10.1109/CoDIT55151.2022.9804082
Manel Marweni, R. Fezai, M. Hajji, M. Mansouri, Kais Bouzrara, H. Nounou, M. Nounou
PV systems are subject to failures during their operation due to the aging effects and exter-nal/environmental conditions. These faults may affect the different system components such as PV modules, connection lines, converters/inverters, which can lead to a decrease in the efficiency, performance, and fur-ther system collapse. Thus, a key factor to be taken into consideration in high-efficiency grid-connected PV systems is the fault detection and diagnosis (FDD). The most well-known data-driven methods are Deep Learning (DL) approaches. The biggest advantage of DL algorithms, in diagnosis, are that they try to learn high- level features from PV data in a high-order, non-linear and adaptive manners. Then, the fault is classified using soft-max activation function. This work therefore presents a comparative study of FDD based DL techniques. These techniques include Artificial Neural Network (ANN), Recurrent Neural Network (RNN) and Long-Short Term Memory (LSTM). The DL techniques-based fault diagnosis are implemented using an emulated Grid-Connected PV (GCPV) system. The classification results for the pretrained DL models is exhibited and performance of the models are evaluated.
{"title":"Efficient Fault Detection and Diagnosis in Photovoltaic System Using Deep Learning Technique*","authors":"Manel Marweni, R. Fezai, M. Hajji, M. Mansouri, Kais Bouzrara, H. Nounou, M. Nounou","doi":"10.1109/CoDIT55151.2022.9804082","DOIUrl":"https://doi.org/10.1109/CoDIT55151.2022.9804082","url":null,"abstract":"PV systems are subject to failures during their operation due to the aging effects and exter-nal/environmental conditions. These faults may affect the different system components such as PV modules, connection lines, converters/inverters, which can lead to a decrease in the efficiency, performance, and fur-ther system collapse. Thus, a key factor to be taken into consideration in high-efficiency grid-connected PV systems is the fault detection and diagnosis (FDD). The most well-known data-driven methods are Deep Learning (DL) approaches. The biggest advantage of DL algorithms, in diagnosis, are that they try to learn high- level features from PV data in a high-order, non-linear and adaptive manners. Then, the fault is classified using soft-max activation function. This work therefore presents a comparative study of FDD based DL techniques. These techniques include Artificial Neural Network (ANN), Recurrent Neural Network (RNN) and Long-Short Term Memory (LSTM). The DL techniques-based fault diagnosis are implemented using an emulated Grid-Connected PV (GCPV) system. The classification results for the pretrained DL models is exhibited and performance of the models are evaluated.","PeriodicalId":185510,"journal":{"name":"2022 8th International Conference on Control, Decision and Information Technologies (CoDIT)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133121860","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：