Check patentability & draft patents in minutes with Patsnap Eureka AI!

A Predictive Control Parallel Computing Method for Gas Path Coordination of Turbocharged Gasoline Engine

A parallel computing and turbocharging technology, applied in electrical control, engine control, fuel injection control, etc., can solve the problems of poor real-time control and difficulty in using the gas path coordination control system, so as to improve real-time performance and real-time calculation performance and improve computational efficiency

Active Publication Date: 2022-06-07
TONGJI UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the huge amount of calculation of the particle swarm optimization algorithm will lead to poor real-time control, and the gas path pressure control of the gasoline engine is a fast response system, which makes it difficult to apply the gas path coordinated control system based on nonlinear neural network predictive control. Gasoline engine gas circuit system control

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
  • A Predictive Control Parallel Computing Method for Gas Path Coordination of Turbocharged Gasoline Engine
  • A Predictive Control Parallel Computing Method for Gas Path Coordination of Turbocharged Gasoline Engine
  • A Predictive Control Parallel Computing Method for Gas Path Coordination of Turbocharged Gasoline Engine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0053] A parallel calculation method of predictive control for gas circuit coordination of turbocharged gasoline engine, such as figure 1 shown, including the following steps:

[0054] S1: Build a prediction model for intake manifold pressure and boost pressure of turbocharged gasoline engine air system.

[0055] The prediction model is a prediction model that takes the throttle valve opening, bypass valve opening, intake manifold pressure, boost pressure and engine speed as inputs, and takes intake manifold pressure and boost pressure as outputs.

[0056] In an embodiment of the present invention, in order to reduce the complexity of the model and improve the real-time performance of the model, a three-layer neural network is used in this paper, and the nonlinear mapping relationship from the input layer to the hidden layer adopts the Gaussian basis function, and its formula as follows;

[0057]

[0058] where: c i is the center vector of the jth hidden layer neuron; b ...

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

The invention relates to a predictive control parallel calculation method for gas circuit coordination of a turbocharged gasoline engine, comprising the following steps: constructing a prediction model of intake manifold pressure and supercharging pressure of the gas circuit system of a turbocharged gasoline engine; building an objective function of the system ; establish a parallel computing architecture for the prediction model and the objective function, the parallel computing architecture adopts the trigger parallel computing method to synchronously calculate the prediction model and the objective function; adopt the backpropagation method to solve the calculation gradient, and use the gradient descent method to optimize the actuator node The control amount of valve opening and bypass valve opening realizes real-time coordinated control of the turbine engine gas circuit. Compared with the prior art, the present invention uses the gradient descent method to solve the optimal solution, which shortens the solution time of the model predictive control, improves the real-time performance of the gas path coordination control system based on the nonlinear neural network predictive control, and makes the control system It is possible to apply it to the actual gasoline engine gas system control.

Description

technical field [0001] The invention relates to the field of predictive control computing, in particular to a predictive control parallel computing method for gas path coordination of a turbocharged gasoline engine. Background technique [0002] With the continuous development of automobile technology, it brings convenience to our life, but also brings the problems of environmental pollution and energy crisis. Therefore, energy saving and emission reduction is an important direction for the development of China's auto industry. The supercharging technology has the characteristics of making the combustion in the cylinder more sufficient, and is one of the key technologies widely used to reduce the fuel consumption and pollutant emission of the engine. However, the coupling between the intake part and the exhaust part of the turbocharged gasoline engine makes the actions of the throttle valve and the bypass valve interact with each other, and the nonlinear theoretical model i...

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
Patent Type & Authority Patents(China)
IPC IPC(8): F02D41/00F02D41/14F02D23/00
CPCF02D41/0007F02D41/1405F02D2041/1412Y02T10/12
Inventor 陈虹孟强李斌张琳黄岩军胡浩奇
Owner TONGJI UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More