CN111680800A - Method for realizing equipment predictive maintenance model based on deep learning - Google Patents
Method for realizing equipment predictive maintenance model based on deep learning Download PDFInfo
- Publication number
- CN111680800A CN111680800A CN202010399270.XA CN202010399270A CN111680800A CN 111680800 A CN111680800 A CN 111680800A CN 202010399270 A CN202010399270 A CN 202010399270A CN 111680800 A CN111680800 A CN 111680800A
- Authority
- CN
- China
- Prior art keywords
- equipment
- predictive maintenance
- maintenance model
- use data
- maintenance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a method for realizing an equipment predictive maintenance model based on deep learning, which comprises the following steps: s1, collecting multiple groups of equipment use data; s2, presetting an equipment predictive maintenance model; s3, randomly selecting 80% of equipment use data as a training set; respectively substituting the equipment use data in the training set into a preset equipment predictive maintenance model as an input item and an output item, and calculating a preliminary control function to obtain a preliminary equipment predictive maintenance model; s4, using the remaining 20% of the device use data as a test set; substituting the equipment use data in the test set into the preliminary equipment predictive maintenance model as an input item, and comparing the output result with the output item of the equipment use data in the test set to obtain a comparison result; and S5, correcting the preliminary control function according to the comparison result to obtain a final control function, and obtaining a final equipment predictive maintenance model through the final control function.
Description
Technical Field
The invention relates to the field of equipment maintenance, in particular to a method for realizing an equipment predictive maintenance model based on deep learning.
Background
At present, with the rapid development of science and technology, various devices increasingly present the characteristics of high technology, high cost, high efficiency, high precision, high complexity and the like, which puts forward unprecedented high requirements on the device maintenance, the requirements not only reflect the technology, but also reflect the management, the device maintenance must adapt to the requirement of the high-speed development of the device, and therefore, the predictive maintenance is in force. In order to reduce unnecessary shutdown of equipment and loss of the equipment to enterprises, maintenance activities are arranged according to the requirement of the actual state of the equipment; there is no research on the predictive maintenance in the market, and therefore, it is necessary to conduct deep research on the predictive maintenance to improve the working efficiency of the equipment.
Disclosure of Invention
The invention aims to solve the problems and provides a method for realizing a device predictive maintenance model based on deep learning, which has better use effect.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a method for realizing an equipment predictive maintenance model based on deep learning comprises the following steps:
s1, collecting multiple groups of equipment use data;
s2, presetting an equipment predictive maintenance model; the preset equipment predictive maintenance model comprises a training set and a testing set;
s3, randomly selecting 80% of equipment use data as a training set; respectively substituting the equipment use data in the training set into a preset equipment predictive maintenance model as an input item and an output item, and calculating a preliminary control function to obtain a preliminary equipment predictive maintenance model;
s4, using the remaining 20% of the device use data as a test set; substituting the equipment use data in the test set into the preliminary equipment predictive maintenance model as an input item, and comparing the output result with the output item of the equipment use data in the test set to obtain a comparison result;
and S5, correcting the preliminary control function according to the comparison result to obtain a final control function, and obtaining a final equipment predictive maintenance model through the final control function.
Further, the equipment use data comprises equipment maintenance rate, equipment maintenance time, equipment maintenance times, equipment operation time and equipment residual life.
Further, in step S3, the equipment maintenance rate, the equipment maintenance time, the equipment maintenance frequency, and the equipment operation time are used as input items of an equipment predictive maintenance model preset in the training set, and the remaining life of the equipment is used as an output item of the equipment predictive maintenance model preset in the training set.
Further, in step S4, the equipment maintenance rate, the equipment maintenance time, the equipment maintenance frequency, and the equipment operation time are used as input items of the preliminary equipment predictive maintenance model in the test set, and the output result is compared with the remaining life of the equipment in the test set.
Compared with the prior art, the invention has the advantages and positive effects that:
according to the invention, through the design of establishing the equipment predictive maintenance model, the residual service life of the equipment as an output item can be calculated, so that the residual service life of the equipment can be known in advance, people can conveniently maintain and replace the equipment in advance, the condition that the equipment cannot normally operate due to sudden failure in the operation process of the equipment is avoided, the condition that the production rate of the equipment is reduced due to the fact that the equipment cannot operate is avoided, and the use effect of the equipment is improved; on the other hand, the method firstly calculates the preliminary control function through the training set, and then corrects the preliminary control function by using the test set, so that the finally obtained equipment predictive maintenance model has smaller error, the accuracy of the equipment predictive maintenance model is improved, and the use effect of the equipment is further improved.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived from the embodiments of the present invention by a person skilled in the art without any creative effort, should be included in the protection scope of the present invention.
The embodiment discloses an implementation method of an equipment predictive maintenance model based on deep learning, which comprises the following steps:
s1, collecting multiple groups of equipment use data; the equipment use data comprises equipment maintenance rate, equipment maintenance time, equipment maintenance times, equipment running time and equipment residual life;
s2, presetting an equipment predictive maintenance model; the preset equipment predictive maintenance model comprises a training set and a testing set;
s3, randomly selecting 80% of equipment use data as a training set; respectively substituting the equipment use data in the training set into a preset equipment predictive maintenance model as an input item and an output item, and calculating a preliminary control function to obtain a preliminary equipment predictive maintenance model;
namely, the equipment maintenance rate, the equipment maintenance time, the equipment maintenance times and the equipment operation time are used as input items of an equipment predictive maintenance model preset in a training set, and the residual service life of the equipment is used as an output item of the equipment predictive maintenance model preset in the training set;
s4, using the remaining 20% of the device use data as a test set; substituting the equipment use data in the test set into the preliminary equipment predictive maintenance model as an input item, and comparing the output result with the output item of the equipment use data in the test set to obtain a comparison result;
taking the equipment maintenance rate, the equipment maintenance time, the equipment maintenance times and the equipment operation time as input items of a preliminary equipment predictive maintenance model in the test set, and comparing the output result with the residual service life of the equipment in the test set to obtain a comparison result;
and S5, correcting the preliminary control function according to the comparison result to obtain a final control function, and obtaining a final equipment predictive maintenance model through the final control function.
According to the invention, through the design of establishing the equipment predictive maintenance model, the residual service life of the equipment as an output item can be calculated, so that the residual service life of the equipment can be known in advance, people can conveniently maintain and replace the equipment in advance, the condition that the equipment cannot normally operate due to sudden failure in the operation process of the equipment is avoided, the condition that the production rate of the equipment is reduced due to the fact that the equipment cannot operate is avoided, and the use effect of the equipment is improved; on the other hand, the method firstly calculates the preliminary control function through the training set, and then corrects the preliminary control function by using the test set, so that the finally obtained equipment predictive maintenance model has smaller error, the accuracy of the equipment predictive maintenance model is improved, and the use effect of the equipment is further improved.
Claims (4)
1. A method for realizing an equipment predictive maintenance model based on deep learning is characterized by comprising the following steps: the method comprises the following steps:
s1, collecting multiple groups of equipment use data;
s2, presetting an equipment predictive maintenance model; the preset equipment predictive maintenance model comprises a training set and a testing set;
s3, randomly selecting 80% of equipment use data as a training set; respectively substituting the equipment use data in the training set into a preset equipment predictive maintenance model as an input item and an output item, and calculating a preliminary control function to obtain a preliminary equipment predictive maintenance model;
s4, using the remaining 20% of the device use data as a test set; substituting the equipment use data in the test set into the preliminary equipment predictive maintenance model as an input item, and comparing the output result with the output item of the equipment use data in the test set to obtain a comparison result;
and S5, correcting the preliminary control function according to the comparison result to obtain a final control function, and obtaining a final equipment predictive maintenance model through the final control function.
2. The method for implementing the deep learning-based equipment predictive maintenance model as claimed in claim 1, wherein: the equipment use data comprises equipment maintenance rate, equipment maintenance time, equipment maintenance times, equipment running time and equipment residual life.
3. The method for implementing the equipment predictive maintenance model based on deep learning as claimed in claim 2, wherein: in the step S3, the equipment maintenance rate, the equipment maintenance time, the equipment maintenance frequency, and the equipment operation time are used as input items of an equipment predictive maintenance model preset in the training set, and the remaining life of the equipment is used as an output item of the equipment predictive maintenance model preset in the training set.
4. The implementation method of the deep learning-based equipment predictive maintenance model as claimed in claim 3, characterized in that: in step S4, the device maintenance rate, the device maintenance time, the device maintenance frequency, and the device operation time are used as input items of a preliminary device predictive maintenance model in the test set, and the output result is compared with the remaining life of the device in the test set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010399270.XA CN111680800A (en) | 2020-05-12 | 2020-05-12 | Method for realizing equipment predictive maintenance model based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010399270.XA CN111680800A (en) | 2020-05-12 | 2020-05-12 | Method for realizing equipment predictive maintenance model based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111680800A true CN111680800A (en) | 2020-09-18 |
Family
ID=72433536
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010399270.XA Pending CN111680800A (en) | 2020-05-12 | 2020-05-12 | Method for realizing equipment predictive maintenance model based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111680800A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110175369A (en) * | 2019-04-30 | 2019-08-27 | 南京邮电大学 | A kind of gear method for predicting residual useful life based on two-dimensional convolution neural network |
| CN110889495A (en) * | 2019-12-04 | 2020-03-17 | 河南中烟工业有限责任公司 | State maintenance analysis method for silk making equipment based on active parameters |
-
2020
- 2020-05-12 CN CN202010399270.XA patent/CN111680800A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110175369A (en) * | 2019-04-30 | 2019-08-27 | 南京邮电大学 | A kind of gear method for predicting residual useful life based on two-dimensional convolution neural network |
| CN110889495A (en) * | 2019-12-04 | 2020-03-17 | 河南中烟工业有限责任公司 | State maintenance analysis method for silk making equipment based on active parameters |
Non-Patent Citations (1)
| Title |
|---|
| 张新生等: "腐蚀油气管道维修策略优化研究", 《中国安全科学学报》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109358587B (en) | Hydroelectric generating set state maintenance decision method and system | |
| WO2015109736A1 (en) | Method for intelligently comparing information about primary and standby channels of electric power scheduling automation system | |
| CN111765075B (en) | Hydraulic forging press pump source fault prediction method and system | |
| CN111680879A (en) | Power distribution network operation toughness evaluation method and device considering sensitive load failure | |
| CN104091289A (en) | Large-scale power distribution network N-1 rapid verification method based on wiring mode rules | |
| CN108616142A (en) | A kind of governor head opens limit combination curve self-adaptation control method with load | |
| CN115296903A (en) | Data security supervision method based on privacy calculation | |
| CN111680800A (en) | Method for realizing equipment predictive maintenance model based on deep learning | |
| CN106557839B (en) | Equipment maintenance strategy optimization method and system based on big data | |
| CN111914426A (en) | Transformer intelligent maintenance method based on correlation analysis | |
| CN108256663B (en) | Real-time prediction method for nuclear power operation accident risk | |
| CN115358423A (en) | Transformer area line loss abnormity analysis processing system and analysis processing method thereof | |
| CN101945030A (en) | Communication method for monitoring inverter on basis of MODBUS protocol | |
| CN113591909A (en) | Abnormality detection method, abnormality detection device, and storage medium for power system | |
| CN105631174A (en) | Transformer station distribution apparatus maintenance prevention method | |
| CN112800625A (en) | Method and system for determining full-clean power supply operation boundary of regional power grid | |
| Singh et al. | Diffusion Process for Multi-Repairmen Machining System with Spares Aand Balking | |
| CN112564100B (en) | Method and system for evaluating maximum output of thermal power generating unit in real time based on differential pressure of air preheater | |
| CN114614969B (en) | Method for judging and coping attack type in information physical system, electronic equipment and storage medium | |
| Liu et al. | Product Assembling Quality Risk Control Strategy Based on Reverse RQR Chain | |
| CN114362148B (en) | Emergency control method and device for coping with transient uncertainty of new energy | |
| CN112100578B (en) | Probability assignment determination method for steam turbine fault diagnosis | |
| CN213986725U (en) | High-speed DSP board intellectual detection system | |
| CN107294367A (en) | Avoid the method that power supply unit repeatedly restarts | |
| CN111797496B (en) | New energy station power generation output time sequence construction method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200918 |