699,533 Hits in 6.4 sec

Research on Model Predictive Control of IPMSM Based on Adaline Neural Network Parameter Identification

Lihui Wang, Guojun Tan, Jie Meng
2019 Energies  
In order to solve the problem that the MPC algorithm has a large dependence on system parameters, a method which integrates MPC control method and parameter identification for IPMSM is proposed.  ...  In this method, the d-q axis inductances and rotor permanent magnet flux of IPMSM motor are identified by the Adaline neural network algorithm, and then, the identification results are applied to the predictive  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/en12244803 fatcat:kp3ttlw2ufdaflmwg66skrosxe

Fault Identification for a Closed-Loop Control System Based on an Improved Deep Neural Network

Bowen Sun, Jiongqi Wang, Zhangming He, Haiyin Zhou, Fengshou Gu
2019 Sensors  
Fault identification for closed-loop control systems is a future trend in the field of fault diagnosis.  ...  In this work, a new fault identification method is proposed, which is based on the deep neural network for closed-loop control systems.  ...  The difficulty of fault identification for closed-loop control systems was revealed. The deep neural network method has been proposed.  ... 
doi:10.3390/s19092131 fatcat:bcxf2oy4afajxm7tqs3jr5qqgm

Dynamic Neural Network Identification and Decoupling Control Approach for MIMO Time-Varying Nonlinear Systems

Zhixi Shen, Kai Zhao
2014 Abstract and Applied Analysis  
Based on the neural network identifier, the adaptive controller of complex system is designed in the latter.  ...  In this paper, the main methodology, on which the method is based, is dynamic neural networks (DNN) and adaptive control with the Lyapunov methodology for the time-varying, coupling, uncertain, and nonlinear  ...  Motivated by the seminal paper [18] , there is a continuously increasing interest in applying neural network to identification and control of nonlinear system.  ... 
doi:10.1155/2014/316206 fatcat:6dvsrmbwrrbover3yyecv42zt4

Identification of an Open-loop Plasma Vertical Position Using Fractional Order Dynamic Neural Network [article]

Z. Aslipour, A. Yazdizadeh
2017 arXiv   pre-print
The aim of this paper is to propose a fractional order nonlinear model to predict the vertical position of a plasma column system in a Tokamak by using real data from Damavand Tokamak.  ...  The system is identified based on a newly introduced fractional order dynamic neural network.  ...  In this method, the process is controlled in a closed loop structure while the input and output data of the process are used for identification of the system.  ... 
arXiv:1706.05892v1 fatcat:dstyxwdo5jhr5bwdko2uajyhae

An Artificial Neural Network Based Preestimation Fitler for Bad Data Defection, Identification and Elimination in State Estimation

Mehmet Uzunoğlu, Celal Kocatepe, Recep Yumurtaca
1996 Mathematical and Computational Applications  
State estimators are vitally important in energy control centers. The measurements that come from control system are generally analysed by a state estimator.  ...  In this paper, by using an artificial neural network (ANN), a bad data detection, identification and then elimination preestimation filter is outlined.  ...  State Estimation Detection of bad data In our study, as stated before, a back propagation ANN based bad data detection, identification and elimination method is applied on an example system as shown in  ... 
doi:10.3390/mca1010159 fatcat:rkuynfsxffdvfmjeqgoym7iywm

Exploration and Mining Learning Robot of Autonomous Marine Resources Based on Adaptive Neural Network Controller

Lisheng Pan
2018 Polish Maritime Research  
In summary, the identification method of underwater robot system based on neural network is effective.  ...  To study the autonomous learning model of the learning robot for marine resource exploration, an adaptive neural network controller was applied.  ...  A series-parallel identification structure is adopted between the controlled system and the identification network. The identification network uses a modified Elman network.  ... 
doi:10.2478/pomr-2018-0115 fatcat:todswaykxndf7fdjsbn3hv6fre

A Survey on Method of System Identification

Gao Weipeng, He Qiwei, Yan Zhengtao
2017 DEStech Transactions on Engineering and Technology Research  
After all, one system identification method based on adaptive filter ,the method has been usually used in active vibration control. Neural Network System Identification Algorithm[8].  ...  Its basic thought is to put the network weights as a state of the corresponding dynamic system, using augmented kalman filter estimation to get good results.  ...  Introduction In the Vibration control, identification, state estimation and control theory are three mutual penetrable domain, along with the increasingly complex control process, the improvement of the  ... 
doi:10.12783/dtetr/mdm2016/4997 fatcat:gst6dioqybaijozyywm7bdfko4


Oleksandr Shmatko, German Zviertsev
2021 InterConf  
One of the ways to eliminate this problem is to use neural networks as a mechanism to detect network attacks.  ...  There are many methods for detecting network attacks, but since attacks are constantly changing, special databases of rules or signatures to detect attacks require continuous administration, it becomes  ...  3 3 Identification of misuse by method "supervised learning" Identification methods Systems Method characteristics State modeling USTAT, IDIOT A set of defined states is used to determine an intrusion  ... 
doi:10.51582/interconf.21-22.04.2021.051 fatcat:kuupe54nwbf5tjpyf5sircofxe

To Identify a Torque Controller System Approximating a Neural Network Based on Model Reference Technique

Priyaranjan Mandal
2016 International Journal Of Engineering And Computer Science  
The 'process of learning' uses a method of training (trainlm) to train the network. Then the outputs of the proposed system and this PINNC are compared.  ...  The NNMRC is configured by learning the behavior of a reference model system, provided to it. The 'process of learning' uses a method of training (trainbfgc) to train this network.  ...  DIFFERENT TYPES OF NEURAL NETWORK CONTROLLERS Neural Network Toolbox in MATLAB 7.2 offers three methods for identification of different linear and nonlinear system.  ... 
doi:10.18535/ijecs/v5i9.06 fatcat:kjaz37qz6vhkzdyle27ykl4csy

Application of functional link neural network to HVAC thermal dynamic system identification

J. Teeter, Mo-Yuen Chow
1998 IEEE transactions on industrial electronics (1982. Print)  
This paper describes a functional link neural network approach to performing the HVAC thermal dynamic system identification.  ...  Index Terms-Functional link, HVAC, intelligent control, neural network, system identification.  ...  The use of neural networks for identification and control provides a means of adapting a controller on line in an effort to minimize a given cost index.  ... 
doi:10.1109/41.661318 fatcat:hhsahet3jbgjtahihwcmb7vsk4

Modeling and Identification of Permanent Magnet Synchronous Motor via Deterministic Learning

Wei Yu, Henghui Liang, Xunde Dong, Ying Luo
2020 IEEE Access  
A state estimator is built using the RBF neural network with the system state of the motor as input. The weights of the RBF neural network are updated using Lyapunov-based law.  ...  adaptive (MRAS) method, state observer method, intelligent identification method and so on.  ... 
doi:10.1109/access.2020.3020848 fatcat:m2icbrjenzh7zgoz4relcxobpi

Study of the Angular Positioning of a Rotating Object with Neural Model Reference Control

Constantin Voloşencu
2021 WSEAS Transactions on Computers  
The purpose of the paper is to make a comparative analysis of the neural predictive control technic with the linear control for angular positioning of mechanical parts.  ...  The structure of the neural predictive control system and its design are presented. Transient characteristics obtained are compared from the point of view of their control efficiency criteria.  ...  Analyzing the obtained characteristics it can be said that with the help of a neural modfel reference control system a behavior similar to the linear state control system can be obtained: a zero error  ... 
doi:10.37394/23205.2021.20.25 fatcat:s5uhty3pvfdjhkhszce7tnju2q

Local time-varying topology identification of network with unknown parameters based on adaptive synchronization

Hai-Peng Ren, Kun Tian, Ren Zhou
2018 Automatika  
The network topology identification using the observing output data of the network is a crucial step for complex network analysis, which is of great importance to understand the networks' properties and  ...  The network with some or all of characteristics including self-organization, self-similarity, attractor, small world and scale-free is referred to as a complex network.  ...  Funding This work was supported by Key program of Natural Science Foundation of Shaanxi Province [grant number 2016 ZDJC-01].  ... 
doi:10.1080/00051144.2018.1552473 fatcat:iwdij3eugvba3ayv2mhlzdzzzq

Rotor Resistance Online Identification of Vector Controlled Induction Motor Based on Neural Network

Bo Fan, Zhixin Yang, Wei Xu, Xianbo Wang
2014 Mathematical Problems in Engineering  
This paper proposes a novel model for rotor resistance parameters identification based on Elman neural networks.  ...  This identification method is able to enhance the performance of induction motor's variable-frequency speed regulation.  ...  Its ability is not enough to adapt to the requirement of high performance of the control system. However, Elman neural network online identification method is a very good solution.  ... 
doi:10.1155/2014/831839 fatcat:tdxcmalvqjdidct35iidknspqm

Intelligent Modeling and Design of a Novel Temperature Control System for a Cantilever-Based Gas-Sensitive Material Analyzer

Tianhai Lu, Chao Fei, Lin Xuan, Haitao Yu, Dacheng Xu, Xinxin Li
2021 IEEE Access  
The LSTM network identification is obviously better than that of previous Peltier system identification methods, and the NHCOPSO algorithm is found to be superior to other improved PSO and evolutionary  ...  A proportional-integral-derivative (PID) algorithm is used to achieve accurate and fast temperature control, with a long short-term memory (LSTM) network trained to identify the nonlinear dynamics of the  ...  SYSTEM IDENTIFICATION BASED ON AN LSTM NETWORK This paper proposes a method of model identification for the Peltier temperature control system based on an LSTM network.  ... 
doi:10.1109/access.2021.3051339 fatcat:mitrjdvovbf4foohl2p6og64hu
« Previous Showing results 1 — 15 out of 699,533 results