Jiatang Cheng* and Yan Xiong Pages 277 - 283 ( 7 )
Background: The effective diagnosis of wind turbine gearbox fault is an important means to ensure the normal and stable operation and avoid unexpected accidents.
Methods: To accurately identify the fault modes of the wind turbine gearbox, an intelligent diagnosis technology based on BP neural network trained by the Improved Quantum Particle Swarm Optimization Algorithm (IQPSOBP) is proposed. In IQPSO approach, the random adjustment scheme of contractionexpansion coefficient and the restarting strategy are employed, and the performance evaluation is executed on a set of benchmark test functions. Subsequently, the fault diagnosis model of the wind turbine gearbox is built by using IQPSO algorithm and BP neural network.
Results: According to the evaluation results, IQPSO is superior to PSO and QPSO algorithms. Also, compared with BP network, BP network trained by Particle Swarm Optimization (PSOBP) and BP network trained by Quantum Particle Swarm Optimization (QPSOBP), IQPSOBP has the highest diagnostic accuracy.
Conclusion: The presented method provides a new reference for the fault diagnosis of wind turbine gearbox.
Wind turbine, gearbox, fault diagnosis, Quantum Particle Swarm Optimization (QPSO), BP neural network, PSOBP.
The Engineering College, Honghe University, Mengzi 661199, The Engineering College, Honghe University, Mengzi 661199