Optimization design of elastic constrained mechanism in swashplate engine based on neural network and genetic algorithm

Aiming at the fact that the current method of designing elastic constrained mechanism in swashplate engine is deficient and the vibration noise is very large, a new method for optimization design of constrained mechanism is put forward based on back propagation (BP) artificial neural network and genetic algorithm (GA). Firstly the dynamics model of constrained mechanism-shafting in swashplate engine is set up, and the samples are gained by numerical simulation; then the non-linear mapping relationship of elastic constrained mechanism´s designed parameters and the objective function is established with BP neural network; finally the trained network is called back by GA to make global optimization. The optimization results show that the global optimal resolution can be searched rapidly and correctly with the method, besides, the method is precise, and the vibration damping effect of the optimized elastic constrained mechanism is very conspicuous.