Neural network data fusion algorithm for electromechanical fault diagnosis based on Multisim
Download as PDF
DOI: 10.25236/mmmce.2020.016
Author(s)
Lijun Wang, Yuee Zhou
Corresponding Author
Lijun Wang
Abstract
In order to improve the efficiency of circuit pressure testing, a circuit pressure functional equivalent compression testing method based on parallel neural network algorithm is proposed. Firstly, aiming at the execution stage of circuit pressure test, the nonlinear time-varying circuit is modeled as a set of ordinary differential equations, and the circuit network is converted into ordinary differential equations by using the improved MNA to construct an optimization model for circuit pressure func-tional equivalent compression test, which is based on minimizing flux as an optimization target. Sec-ondly, neural network algorithm is introduced to optimize the minimization flux model for circuit pressure functional equivalent compression test. A parallel neural network circuit pressure test meth-od with multi-thread parallel execution is designed for large circuit pressure test. Finally, the simula-tion experiment verifies the effectiveness of the proposed algorithm in circuit pressure testing accu-racy and efficiency.
Keywords
Multisim circuit, Electronic circuit, Fault diagnosis, Neural network, Data fusion, Research on Algo-rithms