For the problem of the impact of the lubricant viscosity on the rear axle transmission efficiency,by using the adaptive neural- network fuzzy inference method,a five- dimensional transmission efficiency controller based on ANFIS structure is designed. By using the subtractive clustering method,a set of fuzzy rules with language property is generated adaptively. Through the training,the various parameters of the ANFIS controller are optimized. After the testing,the results show that the fuzzy controller can well predict the rear axle transmission efficiency of different types of lubricant at the different input speed and the input torque. According to the analysis of the surface map,when the rear axle load on the same condition,the lubricant which has the higher viscosity index has the greater contribution to the transmission efficiency. When the rear axle load is large,the effectiveness of the lubricant to the transmission efficiency is more apparent.