Transient EGR control method based on neural network

A technology of neural network and control method, which is applied in the field of energy saving and emission reduction of marine diesel engines, can solve problems such as longer oxygen content stabilization time, lower power and economy, and more difficult adjustment, achieving easy implementation, large project value, Effect of reducing NOx emissions

Active Publication Date: 2017-05-31
HARBIN ENG UNIV
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The object of the present invention is to provide and can effectively improve traditional PI feedback regulation because the oxygen content stabilization time in the scavenging gas manifold that the severe hysteresis of the oxygen content sensor causes becomes longer, and adjustment ...

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
  • Transient EGR control method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0012] The present invention is described in more detail below in conjunction with accompanying drawing example:

[0013] combine figure 1 , the present invention includes the following processes:

[0014] Under all working conditions of the diesel engine, multiple EGR valve openings are artificially given, so that they change from 0 to diameter b at intervals of b / 100, (b is the maximum opening of the EGR valve), and then carry out the steady state of the diesel engine respectively Experiment, and then use the oxygen content sensor to measure the oxygen content in the scavenging manifold when the diesel engine is running stably and the EGR valve opening changes from 0 to b under each working condition, so 101 training samples can be obtained under each working condition of the diesel engine .The input of the neural network is the operating condition of the diesel engine and the opening of the EGR valve, and the output is the oxygen content in the scavenging manifold when t...

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 aims at providing a transient EGR control method based on a neural network. The cyclic oil supplying amount is calculated according to the current work condition of a diesel engine, then a cyclic oil supplying amount signal is transmitted to a target oxygen content calculating unit which works out a target oxygen content value A under the work condition, and A is transmitted to a PI controller unit; and the BP neural network predicts a predicted oxygen content in a scavenge air collection pipe of the diesel engine, the oxygen content value is fed back to the PI controller unit, the target oxygen content value A is compared with the fed-back predicted oxygen content in the scavenge air collection pipe to make a difference, an EGR valve opening degree signal is acquired through the PI controller unit and is transmitted to an executing mechanism of an EGR valve and the BP neutral network, and finally, the EGR valve opening degree is made stable. By means of the transient EGR control method based on the neural network, a series of problems caused when traditional PI feedback is controlled at a transient mode switching and under a TierIII mode, an oxygen content sensor seriously lags behind at the time of transient load increasing and decreasing can be well solved.

Description

technical field [0001] The invention relates to an energy saving and emission reduction method, in particular to a marine diesel engine energy saving and emission reduction method. Background technique [0002] With the enhancement of people's awareness of environmental protection, countries around the world have formulated corresponding emission regulations. Exhaust emissions from marine diesel engines are one of the main sources of air pollution. The International Maritime Organization (IMO) has put forward increasingly stringent requirements on the emissions of marine diesel engines. Up to now, TierIII emission regulations in specific emission control areas have been officially implemented. NOx emissions It is required to reduce 76% on the basis of Tier II, which brings more severe challenges to marine diesel engine researchers. As an in-engine purification technology, EGR reduces the oxygen content in it by introducing part of the exhaust gas into the scavenging manifol...

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): F02D41/14F02D41/00
CPCF02D41/0052F02D41/0077F02D41/1405Y02T10/40
Inventor 王银燕李宗营杨传雷王贺春周鹏程马正茂
Owner HARBIN ENG 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