×

Interval neural network modeling method based on adaptive momentum factor. (Chinese. English summary) Zbl 1399.93158

Summary: The modeling of interval neural network is not only a component of interval control, but also an important role to improve the robustness of systems. An adaptive algorithm of momentum factor is proposed to solve the problem of slow convergence speed on the interval neural network. In this paper, interval calculation method is used to establish the mapping model of input and output variables. By introducing a momentum term with adaptive characteristics, the steepest descent algorithm is applied to update the adaptive momentum factor. Compared with the traditional method, this method not only accelerates the convergence speed, but also overcomes the disadvantages of the system steady state error and easily to fall into local minimum. According to the nonlinear experiments, interval neural networks are able to establish the zone models, and the algorithm of adaptive momentum factor increases the overall performance of the network. Classic bench mark experiments show that our work can be used to more accurately establish interval network model, while the adaptive momentum factor algorithm also can improve the overall performance of the interval neural network.

MSC:

93C55 Discrete-time control/observation systems
93A30 Mathematical modelling of systems (MSC2010)
68T05 Learning and adaptive systems in artificial intelligence
93B35 Sensitivity (robustness)
93B15 Realizations from input-output data
93C40 Adaptive control/observation systems
PDFBibTeX XMLCite
Full Text: DOI