Nonlinear System Identification Method Based on Improved Deep Belief Network
| Title | Nonlinear System Identification Method Based on Improved Deep Belief Network |
| Publication Type | Conference Paper |
| Year of Publication | 2018 |
| Authors | Man, Y., Ding, L., Xiaoguo, Z. |
| Conference Name | 2018 Chinese Automation Congress (CAC) |
| Keywords | belief 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. |
| URL | https://ieeexplore.ieee.org/document/8623373 |
| DOI | 10.1109/CAC.2018.8623373 |
| Citation Key | man_nonlinear_2018 |
- Mathematical model
- Training
- single crystal furnace
- Silicon
- shallow BP network
- Scalability
- Resiliency
- resilience
- pubcrawl
- policy-based governance
- parameters identification
- nonlinear systems
- nonlinear system identification method
- nonlinear control systems
- Metrics
- belief networks
- improved deep belief network
- Human behavior
- higher identification accuracy
- Deep Belief Network
- DBN
- Data models
- Crystals
- CRBM
- continuous restricted Boltzmann machine
- Continuous Resricted Boltzmann Machine
- composability
- collaboration
- Boltzmann machines
- Biological neural networks