Raul-Cristian Roman, R. Precup, E. Petriu, Mihai Muntyan
: The purpose of this paper is to propose a novel controller that is based on a combination of two data-driven algorithms, namely the Fictitious Reference Iterative Tuning (FRIT) algorithm and the Model-Free Adaptive Control (MFC) algorithm while considering a particular form of MFC, that is the intelligent proportional-integral-derivative (iPID) controller. The main advantage of this combination is that the FRIT algorithm optimally tunes the parameters of the iPID controller by solving an optimization problem based on a metaheuristic African Vultures Optimization Algorithm (AVOA). The novel controller, referred to as the FRIT-iPID controller, is validated experimentally on a three-degree-of-freedom tower crane system laboratory equipment in the context of controlling the cart position, the arm angular position and the payload position for this system.
{"title":"Fictitious Reference Iterative Tuning of Discrete-Time Model-Free Control for Tower Crane Systems","authors":"Raul-Cristian Roman, R. Precup, E. Petriu, Mihai Muntyan","doi":"10.24846/v32i1y202301","DOIUrl":"https://doi.org/10.24846/v32i1y202301","url":null,"abstract":": The purpose of this paper is to propose a novel controller that is based on a combination of two data-driven algorithms, namely the Fictitious Reference Iterative Tuning (FRIT) algorithm and the Model-Free Adaptive Control (MFC) algorithm while considering a particular form of MFC, that is the intelligent proportional-integral-derivative (iPID) controller. The main advantage of this combination is that the FRIT algorithm optimally tunes the parameters of the iPID controller by solving an optimization problem based on a metaheuristic African Vultures Optimization Algorithm (AVOA). The novel controller, referred to as the FRIT-iPID controller, is validated experimentally on a three-degree-of-freedom tower crane system laboratory equipment in the context of controlling the cart position, the arm angular position and the payload position for this system.","PeriodicalId":49466,"journal":{"name":"Studies in Informatics and Control","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42763716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Venkatesan Mani, S. Yarlagadda, Srikanth Ravipati, Subashkumar CHELLAPPAN SWARNAMMA
{"title":"ANN Optimized Hybrid Energy Management Control System for Electric Vehicles","authors":"Venkatesan Mani, S. Yarlagadda, Srikanth Ravipati, Subashkumar CHELLAPPAN SWARNAMMA","doi":"10.24846/v32i1y202310","DOIUrl":"https://doi.org/10.24846/v32i1y202310","url":null,"abstract":"","PeriodicalId":49466,"journal":{"name":"Studies in Informatics and Control","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47034893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An Improved Vehicle Trajectory Prediction Model Based on Video Generation","authors":"David-Traian Iancu, A. Florea","doi":"10.24846/v32i1y202303","DOIUrl":"https://doi.org/10.24846/v32i1y202303","url":null,"abstract":"","PeriodicalId":49466,"journal":{"name":"Studies in Informatics and Control","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45151381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
: Continuous population growth is causing an increasing electricity demand. In order to provide enough electricity, it should be possible to predict the prospective consumption. This is especially important nowadays, when energy-saving measures aimed at improving the energy efficiency of all energy sources, especially electrical ones, are gaining importance. Neural networks play an important role in predicting electricity consumption. This paper aims to provide the neural network architecture that will facilitate the prediction of the monthly consumption of different types of consumers with a minimum error. The proposed model is based on two uncommon types of layers, and its reliability is tested on a real dataset related to the electricity consumption of all consumers on the territory of the City of Užice in Serbia. To ensure that more precise results are obtained, this paper also sets forth another approach involving the dataset partitioning into meaningful units (subclusters) before applying the proposed model to them. Finally, the architecture of the Electricity Consumption Prediction System (ECPS) is presented, as an interactive GUI intended for the end user. The dataset employed for training the implemented models contains the consumption data collected over a period of three years, whereas the test set contains data from the fourth year, which corresponds to the actual conditions in which the application will be used.
{"title":"Еlectricity Consumption Prediction Model for Improving Energy Efficiency Based on Artificial Neural Networks","authors":"D. Knežević, M. Blagojevic, A. Ranković","doi":"10.24846/v32i1y202307","DOIUrl":"https://doi.org/10.24846/v32i1y202307","url":null,"abstract":": Continuous population growth is causing an increasing electricity demand. In order to provide enough electricity, it should be possible to predict the prospective consumption. This is especially important nowadays, when energy-saving measures aimed at improving the energy efficiency of all energy sources, especially electrical ones, are gaining importance. Neural networks play an important role in predicting electricity consumption. This paper aims to provide the neural network architecture that will facilitate the prediction of the monthly consumption of different types of consumers with a minimum error. The proposed model is based on two uncommon types of layers, and its reliability is tested on a real dataset related to the electricity consumption of all consumers on the territory of the City of Užice in Serbia. To ensure that more precise results are obtained, this paper also sets forth another approach involving the dataset partitioning into meaningful units (subclusters) before applying the proposed model to them. Finally, the architecture of the Electricity Consumption Prediction System (ECPS) is presented, as an interactive GUI intended for the end user. The dataset employed for training the implemented models contains the consumption data collected over a period of three years, whereas the test set contains data from the fourth year, which corresponds to the actual conditions in which the application will be used.","PeriodicalId":49466,"journal":{"name":"Studies in Informatics and Control","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42092983","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
: Robustness for single-phase pulse-width modulation (PWM) rectifiers which are employed for electric locomotives is essential since a train works in a dynamic environment where faults such as parameter perturbations and measurement errors often occur. These faults may lead to a subsequent failure and damage of costly components; thus, robust control is highly recommended. Apart from the robustness of a rectifier, its dynamic performance should also be considered. This paper presents the implementation of a direct current control (DCC)-based mixed H 2 /H ∞ controller for single-phase PWM rectifiers with the purpose of achieving robustness and a decent dynamic response in the presence of inductance variation, where settling time and percentage overshoot can be addressed by means of the pole placement method. In addition, the v-gap metric has been used as a tool for estimating robust stability. The proposed controller is compared with the direct current control-based H ∞ mixed sensitivity controller (DCC-H ∞ MS controller). The experiment results demonstrate that the proposed controller has a good dynamic performance against parametric uncertainties.
{"title":"Robust Direct Current Control of Single-Phase PWM Rectifiers Based on a Mixed H2/H∞ Controller","authors":"M. Ibrahim, Lei Ma, Yiming Zhao, Haoran Liu","doi":"10.24846/v32i1y202308","DOIUrl":"https://doi.org/10.24846/v32i1y202308","url":null,"abstract":": Robustness for single-phase pulse-width modulation (PWM) rectifiers which are employed for electric locomotives is essential since a train works in a dynamic environment where faults such as parameter perturbations and measurement errors often occur. These faults may lead to a subsequent failure and damage of costly components; thus, robust control is highly recommended. Apart from the robustness of a rectifier, its dynamic performance should also be considered. This paper presents the implementation of a direct current control (DCC)-based mixed H 2 /H ∞ controller for single-phase PWM rectifiers with the purpose of achieving robustness and a decent dynamic response in the presence of inductance variation, where settling time and percentage overshoot can be addressed by means of the pole placement method. In addition, the v-gap metric has been used as a tool for estimating robust stability. The proposed controller is compared with the direct current control-based H ∞ mixed sensitivity controller (DCC-H ∞ MS controller). The experiment results demonstrate that the proposed controller has a good dynamic performance against parametric uncertainties.","PeriodicalId":49466,"journal":{"name":"Studies in Informatics and Control","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43430653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Digital Transformation Impact on Organization Management and Several Necessary Protective Actions","authors":"D. Banciu, A. Vevera, I. Popa","doi":"10.24846/v32i1y202305","DOIUrl":"https://doi.org/10.24846/v32i1y202305","url":null,"abstract":"","PeriodicalId":49466,"journal":{"name":"Studies in Informatics and Control","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44381707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
: Multi-attribute decision making (MADM) as a component of decision science is a significant and essential aspect of engineering planning that may be utilized in a variety of contexts. Due to the complexity of real-life systems, decision-makers (DMs) may encounter several uncertainties throughout the decision-making process. Neutrosophic theory, a generalization of fuzzy set theory and intuitionistic fuzzy set theory, is an efficient tool for dealing with inconsistent, imprecise, and vague values. This paper proposes an autocratic strategy for dealing with multi-attribute group decision-making problems under a neutrosophic environment. The transformation of multiple management decisions and weight matrices into a uniform aggregated assessment matrix is the core aspect of the proposed decision-making strategy. The tourism sector has a unique role on the market and contributes the most to a sustainable economic growth. Due to the picturesque surroundings that may include a green forest, hills, rivers, and marshes, people could often select such a location for relaxation purposes. Therefore, the goal of this paper is to make it possible to choose the best tourist destinations from a range of available options. The proposed method is utilized for prioritizing recreation areas in a tourist industry, where the evaluated values of the attributes for the selected alternatives and the weights of the respective attributes are represented by decision‐makers based on single‐valued neutrosophic triplets.
{"title":"An Autocratic Strategy for Multi-attribute Group Decision Making Based on Neutrosophic Triplets: A Case Study in Prioritizing Recreation Areas in the Tourist Industries","authors":"Kuo-Wei Lee","doi":"10.24846/v32i1y202302","DOIUrl":"https://doi.org/10.24846/v32i1y202302","url":null,"abstract":": Multi-attribute decision making (MADM) as a component of decision science is a significant and essential aspect of engineering planning that may be utilized in a variety of contexts. Due to the complexity of real-life systems, decision-makers (DMs) may encounter several uncertainties throughout the decision-making process. Neutrosophic theory, a generalization of fuzzy set theory and intuitionistic fuzzy set theory, is an efficient tool for dealing with inconsistent, imprecise, and vague values. This paper proposes an autocratic strategy for dealing with multi-attribute group decision-making problems under a neutrosophic environment. The transformation of multiple management decisions and weight matrices into a uniform aggregated assessment matrix is the core aspect of the proposed decision-making strategy. The tourism sector has a unique role on the market and contributes the most to a sustainable economic growth. Due to the picturesque surroundings that may include a green forest, hills, rivers, and marshes, people could often select such a location for relaxation purposes. Therefore, the goal of this paper is to make it possible to choose the best tourist destinations from a range of available options. The proposed method is utilized for prioritizing recreation areas in a tourist industry, where the evaluated values of the attributes for the selected alternatives and the weights of the respective attributes are represented by decision‐makers based on single‐valued neutrosophic triplets.","PeriodicalId":49466,"journal":{"name":"Studies in Informatics and Control","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46871769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
: Machine learning services are widely used for big data, cloud computing, and distributed artificial intelligence applications. Multiple parties participating in the provision of these services may access the users’ sensitive data because most machine learning models use and share plaintext directly. Therefore, it is necessary to utilize cryptographic mechanisms for protecting user privacy. Homomorphic encryption provides an important information security guarantee for machine learning models. However, the complexity of fully homomorphic encryption increases with the depth of neural networks. Especially with the increase in the number of ciphertext multiplications, the time and space costs will also raise exponentially. Using homomorphic encryption in order to protect the model and data security while ensuring the computational efficiency of the employed model over encrypted data is a challenging problem. This paper proposes a BFV-based cryptographic low-latency convolutional neural network (CLOL-CNN) for solving this problem. This new network model performs deep learning and prediction over encrypted data instead of sharing plaintext data. A series of optimization operations are elaborately presented and implemented, such as cryptographic batch normalization, polynomial approximation, cryptographic convolution, and full cryptographic connection. The performance of the proposed model is evaluated with regard to its accuracy and computational overhead obtained by employing deep learning for homomorphically encrypted data. The experiments were conducted on a MNIST image dataset. The obtained results demonstrated that the proposed model has a higher accuracy and a lower time cost than other models and that it is an effective privacy-preserving deep neural network.
{"title":"Encrypted Data Learning and Prediction Using a BFV-based Cryptographic Convolutional Neural Network","authors":"W. Pan, Zepei Sun, Huanyu Sang, Zihao WANG","doi":"10.24846/v32i1y202304","DOIUrl":"https://doi.org/10.24846/v32i1y202304","url":null,"abstract":": Machine learning services are widely used for big data, cloud computing, and distributed artificial intelligence applications. Multiple parties participating in the provision of these services may access the users’ sensitive data because most machine learning models use and share plaintext directly. Therefore, it is necessary to utilize cryptographic mechanisms for protecting user privacy. Homomorphic encryption provides an important information security guarantee for machine learning models. However, the complexity of fully homomorphic encryption increases with the depth of neural networks. Especially with the increase in the number of ciphertext multiplications, the time and space costs will also raise exponentially. Using homomorphic encryption in order to protect the model and data security while ensuring the computational efficiency of the employed model over encrypted data is a challenging problem. This paper proposes a BFV-based cryptographic low-latency convolutional neural network (CLOL-CNN) for solving this problem. This new network model performs deep learning and prediction over encrypted data instead of sharing plaintext data. A series of optimization operations are elaborately presented and implemented, such as cryptographic batch normalization, polynomial approximation, cryptographic convolution, and full cryptographic connection. The performance of the proposed model is evaluated with regard to its accuracy and computational overhead obtained by employing deep learning for homomorphically encrypted data. The experiments were conducted on a MNIST image dataset. The obtained results demonstrated that the proposed model has a higher accuracy and a lower time cost than other models and that it is an effective privacy-preserving deep neural network.","PeriodicalId":49466,"journal":{"name":"Studies in Informatics and Control","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42343985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Majid Fayti, Mostafa Mjahed, Hasan Ayad, Abdeljalil El Kari
: Recently, several methods and techniques, including the metaheuristic algorithms, have been developed, to identify and control systems. In this paper, four recent algorithms, such as Ant Lion optimizer (ALO), Differential Evolution (DE), Bat Algorithm (BA), and Harmony Search (HS), are chosen and considered for a one-paper comparison for the first time and exclusively applied to four different types of behaviors. The present contribution concerns the systematic analysis and comparison between the mentioned algorithms for the two tasks of system modeling and for the tuning of proportional, integral, and derivative (PID) controllers. Comparisons with conventional methods, such as Least Squares (LS) for identification and Reference Model (RM) for control, are made with different instructions to highlight the efficiency of this methods Further, the details on their performance metrics in terms of premature convergence and dynamic searches are provided. Simulations results demonstrate how accurately they help to obtain optimal solutions and show the most reliable method for the two main tasks of control and identification. Moreover, the present results confirm that the Differential Evolution strategy has the best performance, stable convergence feature, robustness, and insensitivity to disturbance and signal excitation .
{"title":"Recent Metaheuristic-Based Optimization for System Modeling and PID Controllers Tuning","authors":"Majid Fayti, Mostafa Mjahed, Hasan Ayad, Abdeljalil El Kari","doi":"10.24846/v32i1y202306","DOIUrl":"https://doi.org/10.24846/v32i1y202306","url":null,"abstract":": Recently, several methods and techniques, including the metaheuristic algorithms, have been developed, to identify and control systems. In this paper, four recent algorithms, such as Ant Lion optimizer (ALO), Differential Evolution (DE), Bat Algorithm (BA), and Harmony Search (HS), are chosen and considered for a one-paper comparison for the first time and exclusively applied to four different types of behaviors. The present contribution concerns the systematic analysis and comparison between the mentioned algorithms for the two tasks of system modeling and for the tuning of proportional, integral, and derivative (PID) controllers. Comparisons with conventional methods, such as Least Squares (LS) for identification and Reference Model (RM) for control, are made with different instructions to highlight the efficiency of this methods Further, the details on their performance metrics in terms of premature convergence and dynamic searches are provided. Simulations results demonstrate how accurately they help to obtain optimal solutions and show the most reliable method for the two main tasks of control and identification. Moreover, the present results confirm that the Differential Evolution strategy has the best performance, stable convergence feature, robustness, and insensitivity to disturbance and signal excitation .","PeriodicalId":49466,"journal":{"name":"Studies in Informatics and Control","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44656586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A New Neural Network-Based Adaptive Time-Delay Control for Nonlinear Car Active Suspension System","authors":"Ghazally I. Y. Mustafa, Xinian Li, Haoping Wang","doi":"10.24846/v31i4y202202","DOIUrl":"https://doi.org/10.24846/v31i4y202202","url":null,"abstract":"","PeriodicalId":49466,"journal":{"name":"Studies in Informatics and Control","volume":" ","pages":""},"PeriodicalIF":1.6,"publicationDate":"2022-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43373417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","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：