基于GA-BP神经网络的汽车润滑系统中磨粒分类的研究

Study on Wear Particle Classification in Automotive Lubrication System Based on GA-BP Neural Network

磨粒是汽车润滑系统运转过程中部件与部件之间摩擦的副产物。针对目前磨粒分类准确度低和分类效率低的问题,提出了基于GA-BP神经网络的汽车润滑系统中磨粒分类的算法。采用BP神经网络深度学习,同时对BP神经网络运用遗传算法进行改进,通过GA-BP神经网络同BP神经网络相对比,结果表明GA-BP神经网络更稳定、更迅速。经过对磨粒分类的对比,可知深度学习过的GA-BP神经网络分类的准确率高达96.92%,符合汽车润滑系统中磨粒分类的准确性及高效率性的要求。

Wear particles are by-products of friction between parts during the operation of automotive lubrication system.Aiming at the current problems of low accuracy and efficiency in wear particle classification,an algorithm based on GA-BP neural network for wear particle classification of automotive lubrication system is proposed.By using BP neural network for deep learning and genetic algorithm for improving,the GA-BP neural network is compared with the BP neural network model,the results show that the GA-BP neural network is more stable and faster.After comparing the classification of wear particles in automotive lubrication system,it can be seen that the accuracy of the deeply studied GA-BP neural network classification is as high as 96.92%,which meets the requirements of accuracy and efficiency in wear particle classification in automotive lubrication system.