Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Optimal speed torque output method of asynchronous motor for electric bus based on random forest regression algorithm

A random forest and asynchronous motor technology, which is applied in the direction of motor generator control, control of electromechanical brakes, control of electromechanical transmissions, etc. The measured data is discontinuous, the real-time response is realized, and the current is adjusted accurately.

Active Publication Date: 2019-07-05
ANHUI UNIVERSITY
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantages of the existing technology are: 1. Formula derivation is required, which is highly dependent on motor parameters and has many influencing factors
2. Multiple PI regulators are required to control the field weakening area (the area above the rated speed), the system is complex and parameter setting is difficult
3. The actual input Inaccurate, resulting in the problem of response lag in the output voltage vector after passing through the PI controller

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
  • Optimal speed torque output method of asynchronous motor for electric bus based on random forest regression algorithm
  • Optimal speed torque output method of asynchronous motor for electric bus based on random forest regression algorithm
  • Optimal speed torque output method of asynchronous motor for electric bus based on random forest regression algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0034] To solve the above problems, such as figure 1 As shown, from the perspective of machine learning, the present invention models the VC control system based on the current ratio output model of the random forest regression algorithm, so that the excitation current and torque current for controlling the output speed and torque of the asynchronous motor are online predicted , to output the optimal current vector in real time to realize the optimal speed and torque output of the asynchronous motor. The main advantages are as follows: (1) The current ratio model based on the random forest regression algorithm can basically realize the synchronization of each system parameter input into the model with the output of the excitation current and torque current, and the current vector output response basically has no lag. (2) Avoid the formula oper...

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 discloses an optimal speed torque output method of an asynchronous motor for an electric bus based on a random forest regression algorithm. The method comprises steps of firstly, establishing an asynchronous motor vector control system based on a current ratio output model; secondly, establishing an analytical model of the maximum torque output according to a limiting condition of the maximum voltage (Usmax) and the maximum current (Ismax); thirdly, analyzing an excitation current torque current change law corresponding to the maximum torque output under different operating conditions, establishing a voltage closed-loop vector analysis model, and embedding a vector control system; then, establishing an AVL (AVL list GmbH) experimental platform, acquiring actually measured sample data, and establishing a random forest regression (RFR) model using the operating condition parameters as input and output; and finally, embedding the regression model in the vector control systemto realize the regression of the motor operating in different conditions, namely the optimal speed torque control. The method has accurate matching current, does not need to divide the asynchronous motor into operating areas, and improves the stability of the speed torque output.

Description

technical field [0001] The invention relates to the technical field of asynchronous motors, in particular to a method for outputting optimal speed and torque of asynchronous motors for electric buses based on a random forest regression algorithm. Background technique [0002] Common asynchronous motor control methods include direct torque control (Direct torque control, DTC) and vector control (vector control, VC). DTC performs Bang-Bang control on torque and stator flux linkage, which avoids the transformation of rotating coordinates and makes the structure of the control system simple, but it is easy to generate torque ripple, and the speed regulation width is not high; VC decouples torque and rotor flux linkage Control, easy to achieve continuous and stable torque control, wide speed range. Therefore, according to the operation of electric buses in all working conditions (electric buses operate in different environments, there are three typical working conditions: conges...

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 Applications(China)
IPC IPC(8): H02P21/22H02P21/20G06F17/50G06Q10/04G06Q50/06G06K9/62
CPCH02P21/22H02P21/20G06Q10/04G06Q50/06G06F30/367G06F18/24323
Inventor 谢芳邱臣铭吴文明
Owner ANHUI UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products