Neural network prediction control method for fuel cell oxygen surplus coefficient

Abstract

A neural network prediction control method for a fuel cell oxygen surplus coefficient belongs to the technical field of control. In order to solve the problem of oxygen surplus coefficient control ofan automobile fuel cell, a neural network prediction control algorithm is used for designing a controller, so that the optimal power of a fuel cell system is guaranteed while sufficient oxygen is obtained. The method comprises the steps of software selection, training sample design, off-line learning of a neural network prediction model, learning of the neural network prediction model and design of a neural network prediction controller. According to the method, system features are extracted directly by learning input and output data, and complex mechanism modeling is effectively avoided. Theloss of system characteristics in an online learning process can be reduced, and the precision of multi-step prediction is improved, so that the problem of constraint control of a nonlinear system canbe effectively solved.

Description

technical field [0001] The invention belongs to the technical field of control. Background technique [0002] With the increasing environmental pollution and energy crisis, fuel cell vehicles are considered to be the ultimate form of vehicles because of their advantages such as high energy conversion rate, zero emission, wide range of fuel (hydrogen) sources, and convenient fuel replenishment. The country has also issued a large number of preferential policies to support enterprises in researching fuel cell vehicles. Fuel cell vehicles have been included in the development framework of "three vertical and three horizontal" for electric vehicles. After more than ten years of accumulation, they have made breakthroughs as a whole; "It is clearly stated that by 2020, about 1,000 fuel cell vehicles will be produced and demonstration operations will be carried out. Whether it is a traditional vehicle or a fuel cell vehicle, the air supply system control problem is involved. Comp...

AI Technical Summary

Problems solved by technology

[0003] 1. The structure of the air supply system of the fuel cell is complex, and it is difficult to carry out mechanism modeling. Even if the mechanism model is obtained, it is difficult to carry out model-based controller design;

[0004] 2. Since the fuel cell air transmission and chemical reaction take time, the inertia and hysteresis characteristics of the system are relatively serious, and it is difficult to achieve good results with ordinary modeling methods;

[0005] 3. Due to the change of the environment, the aging of parts and other problems, the parameters of the fuel cell are time-varying

Images