Blade number optimization method of hydraulic torque converter on the basis of neural network and complete machine

Abstract

The invention discloses a blade number optimization method of a hydraulic torque converter on the basis of a neural network and a complete machine. A blade number neural network model is established and is combined with a digital model of a complete machine system to optimize a blade number. The blade number optimization method comprises the following steps: taking the blade numbers of the pump impeller, the turbine and the guide wheel of the hydraulic torque converter as input variables; utilizing an orthogonal experiment method to reasonably arrange an experiment; taking a pump impeller torque and a turbine torque of three-dimensional fluid simulation as target vectors of a training sample of the neural network so as to determine the structure and the training sample of the natural network; in order to improve the design efficiency and the convergence precision of the natural network, importing a genetic algorithm to optimize the initial weight and the threshold value of the natural network, accurately predicting the performance of the hydraulic torque converter of a non-training sample set by the trained natural network; and combining the blade number neural network model with a digital model of the complete machine system to optimize the blade number. The method has an important engineering application value on improving the operation efficiency of the complete machine.

Description

technical field [0001] The invention belongs to the field of structural design of fluid rotating machinery, and relates to a method for optimizing the number of blades of a hydraulic torque converter based on a neural network and a complete machine. Background technique [0002] Torque converters are widely used in vehicles and construction machinery. Since the efficiency of the hydraulic transmission is lower than that of the mechanical transmission, and the medium of the hydraulic torque converter needs to dissipate heat, the structure is complex, the volume and weight are large, and the cost is high. However, the hydraulic torque converter has good adaptive performance and low-speed stability, which can improve the service life and passability of the vehicle, and the hydraulic torque converter can realize stepless speed regulation, improve driver comfort and simplify operation. Due to the superiority of hydraulic transmission which cannot be compared with other transmiss...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method for optimizing the number of blades of a hydraulic torque converter based on a neural network and a complete machine to solve the problem of separation of main equipment (main engine and parts) in the optimal design of the number of blades of a hydraulic torque converter

Images