Visible to the public Nonlinear System Identification Method Based on Improved Deep Belief Network

TitleNonlinear System Identification Method Based on Improved Deep Belief Network
Publication TypeConference Paper
Year of Publication2018
AuthorsMan, Y., Ding, L., Xiaoguo, Z.
Conference Name2018 Chinese Automation Congress (CAC)
Keywordsbelief networks, Biological neural networks, Boltzmann machines, Collaboration, composability, Continuous Resricted Boltzmann Machine, continuous restricted Boltzmann machine, CRBM, Crystals, Data models, DBN, deep belief network, higher identification accuracy, Human Behavior, improved deep belief network, Mathematical model, Metrics, nonlinear control systems, nonlinear system identification method, nonlinear systems, parameters identification, policy-based governance, pubcrawl, resilience, Resiliency, Scalability, shallow BP network, Silicon, single crystal furnace, Training
Abstract

Accurate model is very important for the control of nonlinear system. The traditional identification method based on shallow BP network is easy to fall into local optimal solution. In this paper, a modeling method for nonlinear system based on improved Deep Belief Network (DBN) is proposed. Continuous Restricted Boltzmann Machine (CRBM) is used as the first layer of the DBN, so that the network can more effectively deal with the actual data collected from the real systems. Then, the unsupervised training and supervised tuning were combine to improve the accuracy of identification. The simulation results show that the proposed method has a higher identification accuracy. Finally, this improved algorithm is applied to identification of diameter model of silicon single crystal and the simulation results prove its excellent ability of parameters identification.

URLhttps://ieeexplore.ieee.org/document/8623373
DOI10.1109/CAC.2018.8623373
Citation Keyman_nonlinear_2018