Abstract:For the shortages of the current oil wear particles monitoring technologies and the demand of oil wear particles monitoring,a new oil wear particles monitoring method that combines microfluidic technology with ferrography technology was proposed.In the system,the microfluidic chip is applied to replace the traditional ferrogram and obtain microscopic image,the image differentiation and autocorrelation function is used to estimate the fuzzy measure,the Wiener filter is applied to restore blurred image,the color features are used to identify the composition of wear particles,including iron wear particles,nonferrous wear particles and oxide abrasive,the scale and shape features are used to identify the wear mechanism,and the gray relational analysis mthod is applied to realize the automatic recognition of wear particles.This online monitoring system can count the wear particles,and also can recognize the types of particles.The accuracy of automatic recognition of wear particles can reach 90%.