A Neural Network Structure with Parameter Expansion for Adaptive Modeling of Dynamic Systems

被引：0

作者：

Sitompul, Erwin ^{[1
]}

机构：

[1] President Univ, Fac Engn, Study Program Elect Engn, Bekasi, Indonesia

来源：

2014 6TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND ELECTRICAL ENGINEERING (ICITEE) | 2014年

关键词：

neural networks; adaptive modeling; parameter expansion; IDENTIFICATION;

D O I：

暂无

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

A new neural network structure for adaptive modeling of dynamic system is presented in this paper. Based on multi-layer perceptron (MLP), the network possesses parameter expansion and external recurrence. Parameter expansion is obtained by using tapped delay lines (TDLs) to the outputs of the hidden layer. This increases the number of parameters between the hidden layer and the output layer. Furthermore, external recurrence is obtained by connecting the output and the input of the network Proper learning algorithm is derived to accommodate the aforementioned modifications. Afterwards, the network is integrated in an adaptive scheme so that it can model systems with changing property or operating condition. The application in modeling of a water tank system demonstrates the ability of the proposed scheme.

引用

页码：388 / 393

页数：6

共 50 条

[41] A neural network to evaluate dynamic systems
Paladini, EP
1998 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-5, 1998, : 1790 - 1795
[42] Hybrid Adaptive control Based on a Hopfield Dynamic Neural Network for Nonlinear Dynamical Systems
Li, I-Hsum
Lee, Lian-Wang
Wang, Wei-Yen
2012 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2012,
[43] Dynamic adaptive neural network control of systems with uncertain multiple-time-delays
Zhang, Min
Hu, Shou-Song
Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics, 2009, 31 (02): : 434 - 438
[44] ADAPTIVE-CONTROL OF UNKNOWN DYNAMIC-SYSTEMS VIA NEURAL NETWORK APPROACH
LAN, MS
PROCEEDINGS OF THE 1989 AMERICAN CONTROL CONFERENCE, VOLS 1-3, 1989, : 910 - 915
[45] Adaptive Neural Network Finite-Time Dynamic Surface Control for Nonlinear Systems
Li, Kewen
Li, Yongming
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 32 (12) : 5688 - 5697
[46] A dynamic recurrent neural-network-based adaptive observer for a class of nonlinear systems
Kim, YH
Lewis, FL
Abdallah, CT
AUTOMATICA, 1997, 33 (08) : 1539 - 1543
[47] Dynamic Learning From Adaptive Neural Network Control of a Class of Nonaffine Nonlinear Systems
Dai, Shi-Lu
Wang, Cong
Wang, Min
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2014, 25 (01) : 111 - 123
[48] Adaptive Control of Dynamic Nonlinear Systems Using Sigmoid Diagonal Recurrent Neural Network
Aboueldahab, Tarek
Fakhreldin, Mahumod
IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS (SMC 2010), 2010,
[49] DasNet: Dynamic Adaptive Structure for Accelerating Multi-task Convolutional Neural Network
Ma, Yinan
Wu, Jing
Long, Chengnian
NEURAL INFORMATION PROCESSING (ICONIP 2019), PT I, 2019, 11953 : 138 - 150
[50] Modular neural network structure for skill growing and structure expansion
Li, CK
2003 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-5, PROCEEDINGS, 2003, : 1067 - 1072

← 1 2 3 4 5 →