Affiliations: [a]
School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo, China
| [b] Henan Key Laboratory of Intelligent Detection and Control of Coal Mine Equipment, Jiaozuo, China
Correspondence:
[*]
Corresponding author. Wei Zhang, School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo, China. E-mail: [email protected].
Note: [1] This work was supported by National Natural Science Foundation of China under Grants 61703145 and by Key Scientific and Technological Projects of Henan Province under Grants 222102210213.
Abstract: In this paper, a self-organizing RBF (SORBF) neural network with an adaptive threshold is proposed based on improved particle swarm optimization (IPSO) and neural strength (NS). The parameters and structure of SORBF can be optimized simultaneously and dynamically. Moreover, the tiresome problem of threshold setting is solved. Firstly, the network size and parameters of SORBF are mapped into the particle information of PSO. Secondly, an IPSO algorithm, based on diversity inertia weight and elite knowledge guiding, is proposed to reduce the probability of the population falling into the local optimum. Then, IPSO is used for optimizing the parameters of SORBF. Based on neuron growth intensity and competition intensity, SORBF can realize the hidden neuron addition and deletion adaptively. Moreover, the thresholds during the structure adjustment can be provided adaptively based on the network scale and neuron strength, which avoids the subjectivity setting and can improve the adaptive ability. Finally, the convergence analysis of IPSO is provided to ensure the performance of SORBF. Experiment results show that the proposed SORBF has good self-organizing ability and compact network structure compared with other methods.
