Research on Pump-jack Fault Diagnosis Method Based on Particle Swarm Optimization

A new particle swarm optimization(VCPSO) based on unifying the study factor was proposed,to ensure the particles careful search in the neighborhood of its own in the earlier stage,prevent the particles fast convergence to a local optimal solution for having missed theirs own neighborhood that may exist in the global optimal solution.Particles were rapidly and accurately converged to the global optimal solution and the algorithm convergence rapidity and accuracy in the later stage was improved.The connecting weights,thresholds and structure of the neural network were optimized by the new particle swarm optimizers.The new neural network was used in pumping unit fault intelligent diagnosis system.The diagnostic results between the new VCPSO and BP algorithm were compared.The conclusion is that the network based on VCPSO has better training performance,faster convergence rate and higher accuracy.