No abstract

Mine fan is the lifeblood of coal mine safety production, which plays an important role in ensuring the safety of the lives of mine workers. Once it fails to operate, it will cause irreparable serious consequences. Therefore, in order to ensure the safe operation of mine fan, this paper takes the common motor bearing faults in fan faults as the object of study, proposes a method of using rough set attribute reduction combined with Beetle antennae search to optimize BP neural network to establish diagnosis model, and compares it with genetic algorithm, particle swarm optimization, imperial competition algorithm and ant lion optimization algorithm. The experimental results show that the method achieves 90% accuracy in fault diagnosis of mine fan bearing, and has faster convergence speed and shorter operation time. Compared with other optimization algorithms, the method has greater advantages. After many tests, the diagnosis results are stable, which proves that the method is feasible and effective in fault diagnosis of mine fan.