Neural network prediction control method for fuel cell oxygen surplus coefficient

A neural network and excess coefficient technology, applied in the field of control, can solve the problems of difficult mechanism modeling, complex structure of fuel cell air supply system, difficult controller design, etc., and achieve the effect of avoiding mechanism modeling

Active Publication Date: 2018-02-23
JILIN UNIV
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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 t

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Neural network prediction control method for fuel cell oxygen surplus coefficient
  • Neural network prediction control method for fuel cell oxygen surplus coefficient
  • Neural network prediction control method for fuel cell oxygen surplus coefficient

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] Research method of the present invention is the model predictive control based on neural network, comprises the following steps:

[0049] Firstly, select appropriate input and output variables according to the internal structure of the system; secondly, design appropriate training samples and test samples according to the dynamic characteristics of the system, and select the training samples and remove similar samples to ensure that the characteristics of the system are fully extracted while maintaining The number of training samples is the smallest; the obtained training samples are again trained offline for the neural network to obtain the initial weights and thresholds of the neural network model; then, the weights are updated through online training, and the above training samples are used as the initial training of online training When the obtained new sample is similar to the old sample data, it will be replaced, otherwise it will be added to the training set; Fina...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G05B13/04
CPCG05B13/042
Inventor 胡云峰陈欢许志国史少云陈虹
Owner JILIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap