Unlock instant, AI-driven research and patent intelligence for your innovation.

An equipment fault detection method based on machine learning

A technology of equipment failure and detection methods, which is applied in the direction of instruments, computer parts, structured data retrieval, etc., can solve the problems of low degree of automation, inability to widely apply data types, and inability to automatically detect, etc., so as to improve economic benefits and eliminate mechanical The occurrence of failures and the effect of improving production efficiency

Active Publication Date: 2019-04-16
成都航天科工大数据研究院有限公司
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the current process of equipment maintenance, it is usually to wait until the equipment reports a fault or finds that it is not working properly, and then manually check and verify the industrial equipment in real time. This manual detection method cannot automatically detect the faults of industrial equipment. Detection, low degree of automation
[0003] In the existing technology, there is rolling bearing fault detection based on machine learning, but this technology is mainly aimed at analyzing various characteristic data and the information represented by rolling bearings in the production process, so it cannot be widely applied to various processing Data types of equipment such as machine tools to ensure the safe production of equipment

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
  • An equipment fault detection method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Such as figure 1 As shown, the present embodiment provides a machine learning-based device fault detection method, comprising the following steps:

[0040] S1. Acquiring the collected initial data of the faulty equipment;

[0041] S2. Perform a cleaning operation on the initial data, and perform secondary screening on the initial data after the cleaning operation is completed to obtain pre-data;

[0042] S3. Optimizing the pre-data by genetic algorithm, randomly generating multiple starting points from the pre-analyzed data, and then retrieving the starting points at the same time, and outputting the retrieval results;

[0043] S4. Weight the retrieval results by AdaBoost meta-algorithm, and classify the data to obtain the initial result set;

[0044] S5. Classify the initial result set successively according to the set weight of the samples in each classifier, so as to obtain the weighted average result;

[0045] S6. By comparing the weighted average result and the ...

Embodiment 2

[0049] On the basis of Example 1, such as figure 1 As shown, the present embodiment provides a machine learning-based device fault detection method, comprising the following steps:

[0050] S1. Acquiring the collected initial data of the faulty equipment;

[0051] S2. Perform a cleaning operation on the initial data, and perform secondary screening on the initial data after the cleaning operation is completed to obtain pre-data;

[0052]S3. Optimizing the pre-data by genetic algorithm, randomly generating multiple starting points from the pre-analyzed data, and then retrieving the starting points at the same time, and outputting the retrieval results;

[0053] S4. Weight the retrieval results by AdaBoost meta-algorithm, and classify the data to obtain the initial result set;

[0054] S5. Classify the initial result set successively according to the set weight of the samples in each classifier, so as to obtain the weighted average result;

[0055] S6. By comparing the weight...

Embodiment 3

[0060] On the basis of Example 1, such as figure 1 As shown, the present embodiment provides a machine learning-based device fault detection method, comprising the following steps:

[0061] S1. Acquiring the collected initial data of the faulty equipment;

[0062] S2. Perform a cleaning operation on the initial data, and perform secondary screening on the initial data after the cleaning operation is completed to obtain pre-data;

[0063] S3. Optimizing the pre-data by genetic algorithm, randomly generating multiple starting points from the pre-analyzed data, and then retrieving the starting points at the same time, and outputting the retrieval results;

[0064] S4. Weight the retrieval results by AdaBoost meta-algorithm, and classify the data to obtain the initial result set;

[0065] S5. Classify the initial result set successively according to the set weight of the samples in each classifier, so as to obtain the weighted average result;

[0066] S6. By comparing the weigh...

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 belongs to the technical field of industrial equipment data acquisition and analysis, and discloses an equipment fault detection method based on machine learning. According to the technical scheme, the method comprises the steps that S1, acquiring collected initial data of equipment with faults; S2, performing cleaning operation and secondary screening on the initial data; S3, performing optimization operation on the pre-data and outputting a retrieval result; S4, classifying the data to obtain an initial result set; S5, classifying the initial result set successively; S6, judging whether the equipment fault represented by the initial data belongs to a known fault or not by comparing the weighted average result with the initial result set; And S7, outputting fault informationthrough a human-computer interface or adding the initial data into a fault database. The self-learning function of the machine can be achieved, meanwhile, the fault database of the equipment is established, the equipment fault and the solution can be accurately and timely determined, the maintenance frequency of the mechanical equipment can be reduced, the maintenance efficiency is remarkably improved, and the method is suitable for application and popularization.

Description

technical field [0001] The invention belongs to the technical field of data collection and analysis of industrial equipment, and in particular relates to a machine learning-based equipment fault detection method. Background technique [0002] In the process of industrial production, equipment maintenance is an essential work. However, in the current process of equipment maintenance, it is usually to wait until the equipment reports a fault or finds that it is not working properly, and then manually check and verify the industrial equipment in real time. This manual detection method cannot automatically detect the faults of industrial equipment. Detection, low degree of automation. [0003] In the existing technology, there is rolling bearing fault detection based on machine learning, but this technology is mainly aimed at analyzing various characteristic data and the information represented by rolling bearings in the production process, so it cannot be widely applied to var...

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): G06F16/2458G06F16/22G06F16/215G06K9/62
CPCG06F18/254
Inventor 祝守宇张辉熊楗洲刘勇王开业樊妍睿马波涛朱芝濡
Owner 成都航天科工大数据研究院有限公司