Research on Dynamic System Simulation Model and Algorithm Based on Artificial Neural Network
- 10.2991/emcm-16.2017.157How to use a DOI?
- Neural Network; Dynamic System; System Simulation
With the continuous expansion of applications field on the computer system simulation, the problems of system modeling faced has become more and more complex. At present, there are two main problems: First, modeling object is complex, with a variety of uncertainties and nonlinear characteristics difficult to describe accurately; Second, the requirements of the system modeling more and more higher, urgent to improve the capacity of description of the system model, flexibility, universality and intelligence of the modeling approach. Artificial neural network (ANN) is a new theory and technology for the rapid development of computer intelligent research in recent years. It is applied to computer system simulation modeling because it is used to solve the problem without the need to establish accurate physical model and mathematical model in advance. The multi-layer network can approximate any continuous function, and is equivalent to a differential equation (group) to describe the actual system. It is a kind of system modeling method with strong applicability. At the same time, the method has the ability to learn and acquire the knowledge from the environment (e.g. by learning input/output of the typical sample data input / output to the system, to obtain the hidden rules), so it has good adaptability to the system simulation problem.
- © 2017, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Shoubai Xiao PY - 2017/02 DA - 2017/02 TI - Research on Dynamic System Simulation Model and Algorithm Based on Artificial Neural Network BT - Proceedings of the 2016 7th International Conference on Education, Management, Computer and Medicine (EMCM 2016) PB - Atlantis Press SN - 2352-538X UR - https://doi.org/10.2991/emcm-16.2017.157 DO - 10.2991/emcm-16.2017.157 ID - Xiao2017/02 ER -