CN112200327A - MES equipment maintenance early warning method and system - Google Patents
MES equipment maintenance early warning method and system Download PDFInfo
- Publication number
- CN112200327A CN112200327A CN202011095562.0A CN202011095562A CN112200327A CN 112200327 A CN112200327 A CN 112200327A CN 202011095562 A CN202011095562 A CN 202011095562A CN 112200327 A CN112200327 A CN 112200327A
- Authority
- CN
- China
- Prior art keywords
- equipment
- early warning
- maintenance
- mes
- sub
- 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.)
- Granted
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 149
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000004458 analytical method Methods 0.000 claims abstract description 27
- 238000011156 evaluation Methods 0.000 claims abstract description 23
- 238000005259 measurement Methods 0.000 claims abstract description 11
- 230000036541 health Effects 0.000 claims description 39
- 238000007726 management method Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 14
- 238000013527 convolutional neural network Methods 0.000 claims description 13
- 238000000513 principal component analysis Methods 0.000 claims description 13
- 238000013213 extrapolation Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000004519 manufacturing process Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 238000003064 k means clustering Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000006866 deterioration Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 description 31
- 239000013598 vector Substances 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000007689 inspection Methods 0.000 description 4
- 230000009466 transformation Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000003449 preventive effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- 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
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an MES equipment maintenance early warning method and a system, wherein the early warning method comprises the following steps: constructing a multi-level MES equipment maintenance early warning decision analysis system, wherein the analysis system comprises a target layer, a criterion layer and a sub-criterion layer; the target layer comprises the level of MES equipment maintenance early warning, and the criterion layer comprises reliability and economy; the sub-criterion layer comprises the remaining service life, the failure frequency and the remaining economic life of the equipment; calculating a value for each element of a sub-criteria layer of the device based on the measurement data; and determining the maintenance early warning level of the equipment by adopting an APH algorithm according to the value of each element of the sub-criterion layer. The invention establishes a multilevel MES equipment maintenance early warning decision analysis system with economy and reliability, adopts a fuzzy comprehensive evaluation method based on AHP to determine the maintenance early warning grade of the equipment, and carries out maintenance according to a decision scheme corresponding to the maintenance early warning grade, thereby improving the accuracy of the equipment maintenance decision.
Description
Technical Field
The invention relates to the technical field of equipment maintenance, in particular to an MES equipment maintenance early warning method and system.
Background
MES is a set of production information management system facing the workshop execution layer of manufacturing enterprises, and the important characteristics of equipment maintenance management and inventory management are.
The equipment maintenance comprises equipment spot inspection, preventive maintenance and predictive maintenance. In the equipment point inspection process, point inspection data are transmitted back to a server side in real time for storage, analysis and alarm, equipment maintenance is executed by using a field terminal through a maintenance plan/rule, and the data are transmitted back in real time for progress tracking.
The equipment maintenance under the industrial internet is carried out from after-service to preventive maintenance to later state maintenance. The state maintenance is based on the data of state monitoring, the equipment fault diagnosis and prediction are carried out, the development trend of the health state of the equipment is summarized, and finally, the maintenance decision is made. The maintenance time of the equipment is saved by the state maintenance work, and the economic benefit is improved. In the early warning work of state maintenance, only the state monitoring condition of the equipment is generally considered, and factors such as the economical efficiency of equipment maintenance are ignored, so that the equipment is not beneficial to making more economical and reasonable maintenance decisions.
Disclosure of Invention
The invention aims to provide an MES equipment maintenance early warning method and system to improve the accuracy of equipment maintenance decisions.
In order to achieve the purpose, the invention provides the following scheme:
an MES equipment maintenance early warning method comprises the following steps:
constructing a multi-level MES equipment maintenance early warning decision analysis system, wherein the analysis system comprises a target layer, a criterion layer and a sub-criterion layer; the target layer comprises the level of MES equipment maintenance early warning, and the criterion layer comprises reliability and economy; the sub-criterion layer comprises the remaining service life, the failure frequency and the remaining economic life of the equipment;
calculating a value for each element of a sub-criteria layer of the device based on the measurement data;
determining the maintenance early warning level of the equipment by adopting an APH algorithm according to the value of each element of the sub-criterion layer;
and managing the equipment according to the decision scheme specified by the maintenance early warning level.
Optionally, the calculating, according to the measurement data, a value of each element of the sub-criterion layer of the device specifically includes:
inputting the current operation data of the equipment into the trained equipment health value prediction model, and predicting the residual service life of the equipment by adopting an extrapolation mode;
calculating the residual economic life of the equipment according to the current operating cost data of the equipment;
the failure frequency of the device is calculated from the MES event log.
Optionally, the step of inputting the current operation data of the equipment into the trained equipment health value prediction model, and predicting the remaining service life of the equipment by using an extrapolation method further includes:
acquiring equipment operation data of the whole service life of the equipment from an MES time sequence database, and establishing an equipment operation data set;
clustering the operation data in the equipment operation data set by adopting a k-means clustering method to obtain the equipment operation data under different working conditions;
and training the equipment health value prediction model by using the operating data under different working conditions to obtain the trained equipment health value prediction model.
Optionally, the training of the device health value prediction model by using the operating data under different working conditions to obtain the trained device health value prediction model further includes:
respectively carrying out standardization processing on the operation data under different working conditions to obtain the processed operation data under different working conditions;
and performing feature extraction on the processed operating data under different working conditions by adopting a CNN (convolutional neural network), DAE (digital Address enhancement) or PCA (principal component analysis) algorithm to obtain feature data of the operating data under different working conditions.
Optionally, the calculating the remaining economic life of the device according to the current operating cost data of the device specifically includes:
wherein, y1Representing the average equipment maintenance cost per year,CP1λ is a deterioration value for the maintenance charge of the equipment in the first year, (C)P1+ (t-1) lambda) represents the maintenance charge of year t; y is2The purchase cost is averagely distributed every year,k is the original value of the equipment;
determining the service life of the equipment when the average annual total equipment cost is minimum;
using the formula T ═ T0+ Δ t- (today () -get _ date ()), and correcting the equipment service life when the average annual total equipment cost is minimum to obtain the corrected equipment service life when the average annual total equipment cost is minimum;
wherein, Δ t represents the correction amount of the remaining economic life of the equipment affected by the working environment, the manufacturer, the maintenance quality and the manufacturing process, and get _ date () represents the equipment use time acquired from the equipment identification information; today () represents the current time;
using formulasNormalizing the service life of the equipment with the minimum total equipment cost per year after correction to obtain the service life of the equipment with the minimum total equipment cost per year after normalization, wherein the service life of the equipment is used as the residual economic life of the equipment;
wherein, TminIndicating the shortest remaining economic life of the equipment, TmaxIndicating the longest remaining economic life of the device.
Optionally, the method for performing an early warning decision for equipment maintenance based on APH specifically includes:
determining the weight of each element of the sub-standard layer relative to the standard layer and the weight of each element of the standard layer relative to the target layer by adopting a fuzzy comprehensive evaluation method;
and determining the maintenance early warning level of the equipment by adopting a fuzzy comprehensive evaluation method according to the weight of each element of the sub-criterion layer relative to the criterion layer, the weight of each element of the criterion layer relative to the target layer and the value of each element of the sub-criterion layer.
An MES equipment maintenance early warning system, the early warning system comprising:
the system comprises an evaluation system construction module, a judgment system analysis module and a warning decision analysis module, wherein the evaluation system construction module is used for constructing a multi-level MES equipment maintenance and warning decision analysis system which comprises a target layer, a criterion layer and a sub-criterion layer; the target layer comprises the level of MES equipment maintenance early warning, and the criterion layer comprises reliability and economy; the sub-criterion layer comprises the remaining service life, the failure frequency and the remaining economic life of the equipment;
the device information acquisition module is used for calculating the value of each element of the sub-criterion layer of the device according to the measurement data;
an early warning module for determining the maintenance early warning level of the equipment by adopting an APH algorithm according to the value of each element of the sub-criterion layer
And the equipment management module is used for managing the equipment according to the decision scheme specified by the maintenance early warning level.
Optionally, the device information obtaining module specifically includes:
the residual service life prediction submodule of the equipment is used for inputting the current operation data of the equipment into the trained equipment health value prediction model and predicting the residual service life of the equipment by adopting an extrapolation mode;
the economic residual life calculating submodule is used for calculating the residual economic life of the equipment according to the current operating expense data of the equipment;
and the fault frequency calculation submodule is used for calculating the fault frequency of the equipment according to the MES event log.
Optionally, the device information obtaining module further includes:
the equipment running data acquisition submodule of the equipment full life is used for acquiring equipment running data of the equipment full life from an MES time sequence database and establishing an equipment running data set;
the clustering submodule is used for clustering the operation data in the equipment operation data set by adopting a k-means clustering method to obtain the equipment operation data under different working conditions;
and the model training submodule is used for training the equipment health value prediction model by utilizing the operating data under different working conditions to obtain the trained equipment health value prediction model.
Optionally, the device information obtaining module further includes:
the standardization processing submodule is used for respectively carrying out standardization processing on the operation data under different working conditions to obtain the processed operation data under different working conditions;
and the characteristic extraction submodule is used for extracting the characteristics of the processed operating data under different working conditions by adopting a CNN (convolutional neural network), DAE (data acquisition) or PCA (principal component analysis) algorithm to obtain the characteristic data of the operating data under different working conditions.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention discloses an MES equipment maintenance early warning method, which comprises the following steps: constructing a multi-level MES equipment maintenance early warning decision analysis system, wherein the analysis system comprises a target layer, a criterion layer and a sub-criterion layer; the target layer comprises the level of MES equipment maintenance early warning, and the criterion layer comprises reliability and economy; the sub-criterion layer comprises the remaining service life, the failure frequency and the remaining economic life of the equipment; calculating a value for each element of a sub-criteria layer of the device based on the measurement data; and determining the maintenance early warning level of the equipment by adopting an APH algorithm according to the value of each element of the sub-criterion layer. The invention establishes a multilevel MES equipment maintenance early warning decision analysis system with economy and reliability, adopts a fuzzy comprehensive evaluation method based on AHP to determine the maintenance early warning grade of the equipment, and carries out maintenance according to a decision scheme corresponding to the maintenance early warning grade, thereby improving the accuracy of the equipment maintenance decision.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a MES equipment maintenance early warning method provided by the present invention;
FIG. 2 is a diagram of a MES equipment maintenance early warning system according to the present invention;
FIG. 3 is a MES equipment maintenance early warning decision analysis system diagram provided by the present invention;
FIG. 4 is a flowchart of the remaining useful life prediction for the device provided by the present invention;
FIG. 5 is a graph of maintenance cost over time for a device provided by the present invention;
FIG. 6 is a graph illustrating the average annual total cost of equipment provided by the present invention.
Detailed Description
The invention aims to provide an MES equipment maintenance early warning method and system to improve the accuracy of equipment maintenance decisions.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Because factors influencing the selection of the maintenance mode are multi-element and fuzzy, an analytic hierarchy process is an effective decision method for qualitative and quantitative analysis, and a multi-level MES equipment maintenance early warning maintenance mode decision model is finally constructed by combining two layers of fuzzy comprehensive judgment, so that a scientific basis is provided for the maintenance and early warning decision of the equipment.
The invention provides an MES (Manufacturing Execution System) equipment maintenance early warning method and System. Constructing a multi-level MES equipment maintenance early warning decision analysis system, and analyzing elements influencing equipment maintenance early warning decisions; acquiring and transmitting equipment information, acquiring the remaining service life, the failure frequency and the remaining economic life of the equipment in the step 1, shutdown economic loss caused by equipment maintenance, spare part supply capacity, technical transformation capacity and other factors, and evaluating; the information of the equipment elements is transmitted to an MES equipment maintenance early warning module, the weight is determined by combining the selection of the early warning scheme with a fuzzy comprehensive evaluation method, and an AHP (analytic Hierarchy Process) based equipment maintenance early warning decision method is adopted to finally obtain an early warning scheme; and finally, spare part management is carried out, the MES equipment management system has the functions of spare part basic information recording, information management, warehouse entry and exit management, inventory management and the like, when equipment is subjected to level 1 early warning, corresponding equipment needs to be scrapped and updated, a spare part management module inquires inventory and requests updating, and if no inventory exists, an order is placed to an upstream manufacturer of the equipment in time.
As shown in fig. 1, the present invention provides an MES equipment maintenance early warning method, which comprises the following steps:
102, calculating the value of each element of the sub-criterion layer of the equipment according to the measurement data;
Wherein, the current operation data of the equipment is input into the trained equipment health value prediction model, and the residual service life of the equipment is predicted by adopting an extrapolation mode, and the method also comprises the following steps:
acquiring equipment operation data of the whole service life of the equipment from an MES time sequence database, and establishing an equipment operation data set;
clustering the operation data in the equipment operation data set by adopting a k-means clustering method to obtain the equipment operation data under different working conditions;
respectively carrying out standardization processing on the operation data under different working conditions to obtain the processed operation data under different working conditions;
and performing feature extraction on the processed operating data under different working conditions by adopting a CNN (Convolutional Neural Networks), DAE (Deep Auto Encoder) or PCA (Principal Component Analysis) algorithm to obtain feature data of the operating data under different working conditions.
And training the equipment health value prediction model by using the operating data under different working conditions to obtain the trained equipment health value prediction model.
The calculating the remaining economic life of the equipment according to the current operating cost data of the equipment specifically comprises:
wherein, y1Representing the average equipment maintenance cost per year,CP1λ is a deterioration value for the maintenance charge of the equipment in the first year, (C)P1+ (t-1) lambda) represents the maintenance charge of year t; y is2The purchase cost is averagely distributed every year,k is the original value of the equipment;
determining the service life of the equipment when the average annual total equipment cost is minimum;
using the formula T ═ T0+ Δ t- (today () -get _ date ()), and correcting the equipment service life when the average annual total equipment cost is minimum to obtain the corrected equipment service life when the average annual total equipment cost is minimum;
wherein, Δ t represents the correction amount of the remaining economic life of the equipment affected by the working environment, the manufacturer, the maintenance quality and the manufacturing process, and get _ date () represents the equipment use time acquired from the equipment identification information; today () represents the current time;
using formulasNormalizing the service life of the equipment with the minimum total equipment cost per year after correction to obtain the service life of the equipment with the minimum total equipment cost per year after normalization, wherein the service life of the equipment is used as the residual economic life of the equipment;
wherein, TminIndicating the shortest remaining economic life of the equipment, TmaxIndicating the longest remaining economic life of the device.
And 103, determining the maintenance early warning level of the equipment by adopting an APH algorithm according to the value of each element of the sub-criterion layer.
The method for using an APH-based device maintenance early warning decision making in step 103 specifically includes:
determining the weight of each element of the sub-standard layer relative to the standard layer and the weight of each element of the standard layer relative to the target layer by adopting a fuzzy comprehensive evaluation method;
and determining the maintenance early warning level of the equipment by adopting a fuzzy comprehensive evaluation method according to the weight of each element of the sub-criterion layer relative to the criterion layer, the weight of each element of the criterion layer relative to the target layer and the value of each element of the sub-criterion layer.
And 104, managing the equipment according to the decision scheme specified by the maintenance early warning level.
An MES equipment maintenance early warning system, the early warning system comprising:
the system comprises an evaluation system construction module, a judgment system analysis module and a warning decision analysis module, wherein the evaluation system construction module is used for constructing a multi-level MES equipment maintenance and warning decision analysis system which comprises a target layer, a criterion layer and a sub-criterion layer; the target layer comprises the level of MES equipment maintenance early warning, and the criterion layer comprises reliability and economy; the sub-criterion layer comprises the remaining service life, the failure frequency and the remaining economic life of the equipment;
and the equipment information acquisition module is used for calculating the value of each element of the sub-criterion layer of the equipment according to the measurement data.
The device information obtaining module specifically includes: the residual service life prediction submodule of the equipment is used for inputting the current operation data of the equipment into the trained equipment health value prediction model and predicting the residual service life of the equipment by adopting an extrapolation mode; the economic residual life calculating submodule is used for calculating the residual economic life of the equipment according to the current operating expense data of the equipment; and the fault frequency calculation submodule is used for calculating the fault frequency of the equipment according to the MES event log.
The device information acquisition module further includes: the equipment running data acquisition submodule of the equipment full life is used for acquiring equipment running data of the equipment full life from an MES time sequence database and establishing an equipment running data set; the clustering submodule is used for clustering the operation data in the equipment operation data set by adopting a k-means clustering method to obtain the equipment operation data under different working conditions; and the model training submodule is used for training the equipment health value prediction model by utilizing the operating data under different working conditions to obtain the trained equipment health value prediction model.
The device information acquisition module further includes: the standardization processing submodule is used for respectively carrying out standardization processing on the operation data under different working conditions to obtain the processed operation data under different working conditions; and the characteristic extraction submodule is used for extracting the characteristics of the processed operating data under different working conditions by adopting a CNN (convolutional neural network), DAE (data acquisition) or PCA (principal component analysis) algorithm to obtain the characteristic data of the operating data under different working conditions.
And the early warning module is used for determining the maintenance early warning level of the equipment by adopting an APH algorithm according to the value of each element of the sub-criterion layer.
And the equipment management module is used for managing the equipment according to the decision scheme specified by the maintenance early warning level.
The present invention also provides a specific embodiment for illustrating the specific implementation and technical effects of the method and system of the present invention.
An MES equipment maintenance early warning method and system in the embodiment of the present invention are respectively shown in fig. 1 and 2, and the method includes the following steps:
step 1: and constructing a multi-level MES equipment maintenance early warning decision analysis system, wherein the analysis system comprises a target layer criterion layer, a sub-criterion layer and a scheme layer.
The target layer is an equipment maintenance early warning decision; the criterion layer includes: reliability, economy, and other factors; the sub-criteria include: the remaining service life of the equipment, the failure frequency, the remaining economic life of the equipment, the shutdown economic loss due to equipment maintenance, the spare part supply capacity, and the technical transformation capacity; the scheme layer comprises four early warning levels P1, P2, P3 and P4 and four corresponding early warning schemes, the scheme layer is shown in a table 1, and a multi-level MES equipment maintenance early warning decision analysis system is shown in an attached figure 3.
Table 1 correspondence table of early warning level and early warning scheme:
step 2: and (3) acquiring a plurality of elements of the criterion layer in the step 1, and evaluating the factors of the sub-criterion layer, such as the residual service life, the failure frequency, the residual economic life of the equipment, the shutdown economic loss caused by equipment maintenance, spare part supply capacity, technical transformation capacity and the like.
And 2.1, establishing an equipment health value prediction model to obtain one of decision factors for equipment maintenance early warning and a residual service life value of the equipment. The specific steps are shown in fig. 4.
Step 2.1.1 obtaining industrial production data of the device. And acquiring equipment operation data from an MES time sequence database, and constructing a multi-dimensional time sequence matrix of the whole service life of the equipment.
The MES system adopts OPC UA (Unified Architecture) as a Unified standard for industrial equipment identification data acquisition, reads real-time data through the OPC UA, and then stores the read data into a time sequence database with time tags, wherein sufficient and valuable data are important cornerstones for researching equipment degradation characteristics.
Step 2.1.2 data preprocessing.
Before preprocessing, working condition classification is carried out according to operating conditions and operating parameters, and the operating parameters are clustered by adopting a k-means clustering method, so that the speed is high and the robustness is strong.
And (3) cleaning the original data acquired in the step (2.1.1), reducing the interference of abnormal information, standardizing the sample data under different working conditions, and eliminating the influence of working condition change, wherein the standardized processing formula is shown as a formula (1).
Wherein x is the sensor data, u is the calculated mean, and σ is the standard deviation.
And 2.1.3, extracting the characteristics of the multi-dimensional sensor data and removing redundant characteristics.
And the data is subjected to feature selection by using models such as CNN and DAE, or the data is subjected to dimension reduction by using methods such as PCA.
And 2.1.4, constructing an equipment health index and training an equipment health value prediction model.
And 2.1.3, determining the health index of the multi-sensor data fusion. Taking an engine as an example, the health index calculation formula is shown in formula (2)
Wherein M is the number of sensors of the engine,the data preprocessed by the jth sensor of the ith engine,is the fusion coefficient of the jth sensor, and represents its health weight.
And setting a model training label, training a health value prediction model on the basis of a machine learning algorithm and a deep learning algorithm, and obtaining a smaller output error by adjusting parameters. Predefined failure threshold lablethreshldAnd calculating the RUL (Remaining Useful Life) prediction result at a certain position on the health value prediction curve by judging the cycle number of the distance reaching a threshold value at the position.
Step 2.1.5 input test set data to carry out RUL prediction.
After the step 2.1.4, a health curve is constructed by an indirect method, an equipment health value prediction model is trained, a test set is input into the equipment health value prediction model, and the RUL value is obtained in an extrapolation mode.
Taking an engine as an example, the service life of the residual equipment is represented by the residual operation cycle number before the equipment is failed, and the longest residual service life of the equipment, namely the maximum operation cycle number is RULmaxThe shortest remaining service life of the device, i.e. the remaining service life close to the failure threshold, is RULminHaving a RUL min0. To pairThe service life of the remaining equipment of the equipment is normalized, the wear degree and the remaining service life of the equipment can be clearly determined, the maintenance early warning is conveniently decided, the normalization formula is shown as a formula (3), RUL' represents the service life of the normalized remaining equipment, the remaining service life of the equipment mentioned hereinafter is the normalized remaining service life of the equipment, and the range is [0,1]]In the meantime.
And 2.2, acquiring the running cost data of the equipment and calculating the economic life of the equipment.
The full Life Cycle Cost (LCC) includes the total Cost of the product during the Life Cycle, i.e., during the effective use period. The total cost of one device mainly comprises two parts of depreciation cost and maintenance cost. Wherein the maintenance cost refers to the cost for maintaining the production operation of the equipment, and comprises maintenance cost, overhaul cost, fuel power cost, labor cost and the like; the depreciation cost is the cost for compensating the abrasion of the equipment so as to ensure that the equipment completes the reproduction. Along with the increase of the service life of the equipment, the maintenance and overhaul cost of the equipment is increased, the equipment is gradually degraded, the maintenance cost is increased year by year, the investment cost allocated each year is gradually reduced, and the depreciation cost is reduced year by year. According to the change rule of depreciation fee and maintenance fee, the change trend of the total amount of the two parts of the fees can be obtained, and the age limit of the two parts of the total amount of the fees, which is the minimum year, is the economic life value of the equipment.
2.2.1 determining economic Life of a device in static mode
In the static mode, the economic life of the equipment is calculated, regardless of the time value of the capital.
Let K represent the original value of the equipment, O represent the residual value of the scrapped and recycled equipment, and the maintenance cost of the equipment in the first year is CP1The deterioration value is lambda, and the maintenance charge in the t-th year is CP1T-1 λ, the maintenance cost of the equipment increases with time as shown in FIG. 5, and the average equipment maintenance cost per year is y1:
Neglecting residual error O when updating the equipment, the annual average purchase cost is y2Is provided withSumming these two terms yields the average annual total cost of the equipment y:
the average annual total equipment cost variation curve is shown in FIG. 6, where the average annual total equipment cost minimum total equipment cost is set as the average annual total equipment cost minimum total equipment cost life t0。
And 2.2.2, correcting the optimal economic life and calculating the residual economic life of the equipment.
The economic life of the equipment is influenced by factors such as working environment, manufacturers, maintenance quality, manufacturing process and the like, and the delta t is used as a correction quantity. After correction, the residual economic life of the equipment is T, which is represented by the time of the minimum annual total cost of the equipment from the present to the average year, and the longest residual service life of the equipment, namely the corrected economic life value of the equipment is Tmax,Tmax=t0+ Δ T, the shortest remaining economic life of the plant is TminHaving a value of T min0. The device use time can be obtained from the device identification information, and is set as get _ date (), the current time is day (), and T ═ T-0+Δt-(today()-get_date())。
2.2.3 carry on the normalization to the surplus economic life of apparatus, can be clear confirm the economy used of apparatus and, offer the reference for apparatus renewal, facilitate and carry on the decision to the maintenance early warning, the normalization formula is shown as formula (6):
t' represents the normalized remaining economic life of the equipment, and the remaining economic life of the equipment mentioned in the following is the normalized remaining economic life of the equipment and ranges between 0 and 1.
And 2.3, acquiring the failure frequency of the equipment through an MES event log, expert feedback and the like, and acquiring information such as shutdown economic loss, spare part supply capacity, technical transformation capacity and the like generated by equipment maintenance.
And step 3: and an MES equipment maintenance early warning module, wherein an AHP-based equipment maintenance early warning decision method is adopted for selecting an early warning scheme. The method specifically comprises the following steps:
step 3.1, decision factors of the equipment maintenance early warning scheme are compared in pairs, weight A is determined by constructing a judgment matrix, namely the importance degree of different factors, and A is set to be (a)1,a2,···,am),aiRepresenting the weight of the ith factor.
Has a is more than or equal to 0iIs less than or equal to 1, andthe method specifically comprises the following steps:
the three factors of the same layer were compared two by two to determine their relative importance, and the scale of 1-9 for the sali base (t.l. saay) is shown in table 2.
Table 2 Scale definition table for decision matrix elements
And establishing a judgment matrix of a first layer according to expert evaluation by taking scientific decision of the equipment maintenance early warning scheme P as a target, wherein the value of the judgment matrix after the expert evaluation is shown in a table 3.
Table 3 judgment matrix value table of one layer
P | C1 | | C3 |
C1 | |||
1 | 4 | 2 | |
|
1/4 | 1 | 1/3 |
|
1/2 | 3 | 1 |
And obtaining the eigenvector w (0.5584,0.1220,0.3196) according to the judgment matrix Q.
And obtaining a judgment matrix of the second layer according to expert evaluation as shown in tables 4-6.
TABLE 4 first and second layer judgment matrix value-taking table
C1 | | Z2 |
Z1 | ||
1 | 2 | |
|
1/2 | 1 |
TABLE 5 second-level decision matrix value-taking table
C2 | | Z4 |
Z3 | ||
1 | 3 | |
|
1/3 | 1 |
TABLE 6 judgment matrix value-taking table of the third and second layers
C3 | | Z5 |
Z5 | ||
1 | 4 | |
|
1/4 | 1 |
And 3.2, performing consistency check on the judgment matrix obtained in the step 3.1, wherein the consistency check is introduced to detect whether the weight obtained by the judgment matrix is reasonable.
CI is consistency index, RI is average random consistency index, the value of RI is related to the order number of the judgment matrix, and when the order number of the judgment matrix P is 1 to 9, the average consistency index RI is 0,0, 0.58, 0.90, 1.12, 1.24, 1.32, 1.41 and 1.45 respectively. The consistency check formula is shown in equation (7):
when CR of the matrix P is < 0.1 or lambdamaxIf the element value is less than 0.1, CI is 0, the consistency of the judgment matrix is acceptable, otherwise, the element value of the judgment matrix needs to be corrected until the element value passes the inspection.
And (3) carrying out consistency check on the matrix P: as calculated, for the decision matrix P, CR is 0.0080 < 0.1, and the consistency is acceptable, so that the eigenvector w is (0.5584,0.1220,0.3196), i.e., a is (0.5584,0.1220, 0.3196).
Likewise, the matrices C1, C2, C3 were checked for consistency: all have maximum eigenvalue lambdamaxWhen CI is 0, the identity check of the second layer is also acceptable, and matrices C1, C2, and C3 have a, respectively1=(0.6667,0.3333),A2=(0.7500,0.2500),A3=(0.8000,0.2000)。
And 3.3, combining the weights obtained in the step 3.2, constructing a fuzzy relation matrix according to the membership degree of each layer of factors to the equipment maintenance early warning scheme, and obtaining an evaluation result through two layers of fuzzy evaluation. The method comprises the following specific steps:
(1) and combining the step 1 and the step 2, the reliability mainly consists of two factors of the residual service life and the fault frequency of the equipment, and the economy mainly consists of two factors of the residual economic life and the maintenance loss of the equipment.
The fuzzy relation matrix of the remaining service life of the equipment to the equipment maintenance early warning scheme is shown in table 7. The remaining lifetime RUL 'of the device is obtained from step 1, assuming that the remaining lifetime RUL' of a certain device is obtained via step 1 as 0.9, and a2If Z1 is 0.9, the fuzzy relation vector p corresponding to Z1 is (0.9,0.1,0, 0).
TABLE 7 fuzzy relation matrix table of remaining service life of device to device maintenance early warning scheme
Similarly, the fuzzy relation matrix of the remaining economic life of the device is table 8. The remaining economic life T' of the equipment is obtained from the step 2, and is assumed to beThe remaining economic life T' of a certain device is 0.8 from step 2, and b2If Z3 is 0.9, the fuzzy relation vector corresponding to Z3 is q (0.8,0.2,0, 0).
TABLE 8 fuzzy relation matrix table of remaining economic life of equipment to equipment maintenance early warning scheme
Z3 | P1 | P2 | P3 | P4 |
[0,b1) | 0 | 0.2 | 0.3 | 0.5 |
(b1,b2) | 0.1 | 0.4 | 0.4 | 0.1 |
(b2,1] | 0.8 | 0.2 | 0 | 0 |
Similarly, fuzzy relation matrixes for comparing the importance of the indexes of the sub-criterion layers are shown in the following tables 9-11:
TABLE 9 fuzzy relationship matrix table of operational data versus remaining useful life of the device
C1 | P1 | P2 | P3 | P4 |
Z1 | 0.9 | 0.1 | 0 | 0 |
Z2 | 0.1 | 0.2 | 0.3 | 0.4 |
TABLE 10 fuzzy relation matrix table of current operation cost to economic life of equipment
C2 | P1 | P2 | P3 | P4 |
Z3 | 0.8 | 0.2 | 0 | 0 |
Z4 | 0.1 | 0.4 | 0.1 | 0.4 |
TABLE 11 MES event Log vs. failure Rate fuzzy relationship matrix Table
C3 | P1 | P2 | P3 | P4 |
Z5 | 0.3 | 0.2 | 0.2 | 0.3 |
Z6 | 0.2 | 0.3 | 0.2 | 0.3 |
(2) And synthesizing the weight vector A and the fuzzy relation matrix R to obtain a comprehensive evaluation vector B of the equipment maintenance early warning scheme decision. The specific calculation formula is shown as formula (8):
obtaining fuzzy relation matrixes R corresponding to C1, C2 and C3 according to tables 9-11 in (1)1、R2、R2According to step 3.2, the weight vectors A corresponding to the second levels C1, C2, C3 can be obtained1、A2、A3Then A can be calculated separately1R1,A2R2,A3R3See formula (9).
The weight vector corresponding to P of the first layer can be obtained according to step 3.2. The evaluation vector B of the two-layer integrated calculation is shown in formula (10):
B=AR=(a1,a1,a3)(A1R1,A2R2,A3R3)T=(0.5182,0.1747,0.1228,0.1823) (10)
(3) and according to the maximum membership principle, the last judgment result is obtained, and the maintenance early warning scheme of the equipment in the MES system is P1, namely the equipment runs normally without alarming.
And 4, step 4: spare part management module. The early warning result in the last step is P1, the equipment does not need to be inquired under the condition that the equipment operates normally and does not need to give an alarm, if the early warning result is P4, namely, the equipment level 1 early warning, the corresponding equipment needs to be scrapped and updated, the spare part management module inquires inventory and requests for updating, and if the equipment does not have the inventory, an order is timely placed to an upstream manufacturer of the equipment.
The spare part management module organizes and manages planning, production, ordering, supply and storage of spare parts, has the functions of spare part basic information recording, information management, warehouse entry and exit management, inventory management and the like in the MES equipment management system, realizes scientific management and control of the spare parts, and reasonably utilizes inventory space.
According to the features of the present invention, the present invention discloses the following technical effects:
1. according to the AHP-based fuzzy comprehensive evaluation model provided by the maintenance early warning module, several subjective factors influencing final decision are quantitatively analyzed in the ways of determining weight, constructing a fuzzy relation matrix and the like, and compared with the traditional qualitative evaluation, the AHP-based fuzzy comprehensive evaluation model is more visual and accurate; the method is beneficial to making a more scientific and reasonable decision and provides a reference basis for a more reasonable equipment maintenance early warning decision.
2. In the process of establishing an equipment health value prediction model and obtaining the residual service life value of the equipment, the full-life multi-feature data of the industrial equipment is processed in different working conditions, and feature extraction and service life prediction are performed by combining algorithms such as machine learning and deep learning, so that the prediction capability and generalization capability of the prediction model and the prediction accuracy of the residual service life value of the equipment are improved.
3. In the early warning process of the equipment, not only reliability factors such as the prediction of the residual service life of the equipment are considered, but also economic factors such as the residual economic life of the equipment and shutdown loss caused by equipment maintenance are considered, so that the decision on maintenance modes such as equipment maintenance or scrapping updating can be made more comprehensively.
4. In the process of making the early warning scheme, various indexes can be added, deleted and modified according to actual conditions, corresponding measures are taken to improve weak links in equipment operation, and the improvement of the health management capability of an MES system on the equipment is facilitated.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The principle and the implementation manner of the present invention are explained by applying specific examples, the above description of the embodiments is only used to help understanding the method of the present invention and the core idea thereof, the described embodiments are only a part of the embodiments of the present invention, not all embodiments, and all other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the protection scope of the present invention.
Claims (10)
1. An MES equipment maintenance early warning method is characterized by comprising the following steps:
constructing a multi-level MES equipment maintenance early warning decision analysis system, wherein the analysis system comprises a target layer, a criterion layer and a sub-criterion layer; the target layer comprises the level of MES equipment maintenance early warning, and the criterion layer comprises reliability and economy; the sub-criterion layer comprises the remaining service life, the failure frequency and the remaining economic life of the equipment;
calculating a value for each element of a sub-criteria layer of the device based on the measurement data;
determining the maintenance early warning level of the equipment by adopting an APH algorithm according to the value of each element of the sub-criterion layer;
and managing the equipment according to the decision scheme specified by the maintenance early warning level.
2. The MES apparatus maintenance early warning method of claim 1, wherein the calculating a value of each element of the sub-criteria layer of the apparatus according to the measurement data specifically comprises:
inputting the current operation data of the equipment into the trained equipment health value prediction model, and predicting the residual service life of the equipment by adopting an extrapolation mode;
calculating the residual economic life of the equipment according to the current operating cost data of the equipment;
the failure frequency of the device is calculated from the MES event log.
3. The MES equipment maintenance early warning method of claim 2, wherein the step of inputting the current operating data of the equipment into the trained equipment health value prediction model to predict the remaining service life of the equipment by extrapolation further comprises:
acquiring equipment operation data of the whole service life of the equipment from an MES time sequence database, and establishing an equipment operation data set;
clustering the operation data in the equipment operation data set by adopting a k-means clustering method to obtain the equipment operation data under different working conditions;
and training the equipment health value prediction model by using the operating data under different working conditions to obtain the trained equipment health value prediction model.
4. The MES equipment maintenance early warning method according to claim 3, wherein the method for training the equipment health value prediction model by using the operation data under different working conditions to obtain the trained equipment health value prediction model further comprises the following steps:
respectively carrying out standardization processing on the operation data under different working conditions to obtain the processed operation data under different working conditions;
and performing feature extraction on the processed operating data under different working conditions by adopting a CNN (convolutional neural network), DAE (digital Address enhancement) or PCA (principal component analysis) algorithm to obtain feature data of the operating data under different working conditions.
5. The MES equipment maintenance early warning method of claim 2, wherein the calculating of the remaining economic life of the equipment from the current operating cost data of the equipment comprises:
wherein, y1Representing the average equipment maintenance cost per year,CP1λ is a deterioration value for the maintenance charge of the equipment in the first year, (C)P1+ (t-1) lambda) represents the maintenance charge of year t; y is2The purchase cost is averagely distributed every year,k is the original value of the equipment;
determining the service life t of the device when the average annual total cost of the device is minimal0;
Using the formula T ═ T0+ Δ t- (today () -get _ date ()), and correcting the equipment service life when the average annual total equipment cost is minimum to obtain the corrected equipment service life when the average annual total equipment cost is minimum;
wherein, Δ t represents the correction amount of the remaining economic life of the equipment affected by the working environment, the manufacturer, the maintenance quality and the manufacturing process, and get _ date () represents the equipment use time acquired from the equipment identification information; today () represents the current time;
using formulasNormalizing the service life of the equipment with the minimum total equipment cost per year after correction to obtain the service life of the equipment with the minimum total equipment cost per year after normalization, wherein the service life of the equipment is used as the residual economic life of the equipment;
wherein, TminIndicating the shortest remaining economic life of the equipment, TmaxIndicating the longest remaining economic life of the device.
6. The MES equipment maintenance early warning method of claim 1, wherein the determining the maintenance early warning level of the equipment using the APH algorithm specifically comprises:
determining the weight of each element of the sub-standard layer relative to the standard layer and the weight of each element of the standard layer relative to the target layer by adopting a fuzzy comprehensive evaluation method;
and determining the maintenance early warning level of the equipment by adopting a fuzzy comprehensive evaluation method according to the weight of each element of the sub-criterion layer relative to the criterion layer, the weight of each element of the criterion layer relative to the target layer and the value of each element of the sub-criterion layer.
7. An MES equipment maintenance early warning system, the early warning system comprising:
the system comprises an evaluation system construction module, a judgment system analysis module and a warning decision analysis module, wherein the evaluation system construction module is used for constructing a multi-level MES equipment maintenance and warning decision analysis system which comprises a target layer, a criterion layer and a sub-criterion layer; the target layer comprises the level of MES equipment maintenance early warning, and the criterion layer comprises reliability and economy; the sub-criterion layer comprises the remaining service life, the failure frequency and the remaining economic life of the equipment;
the device information acquisition module is used for calculating the value of each element of the sub-criterion layer of the device according to the measurement data;
the early warning module is used for determining the maintenance early warning level of the equipment by adopting an APH algorithm according to the value of each element of the sub-criterion layer;
and the equipment management module is used for managing the equipment according to the decision scheme specified by the maintenance early warning level.
8. The MES equipment maintenance early warning system of claim 7, wherein the equipment information obtaining module specifically comprises:
the residual service life prediction submodule of the equipment is used for inputting the current operation data of the equipment into the trained equipment health value prediction model and predicting the residual service life of the equipment by adopting an extrapolation mode;
the economic residual life calculating submodule is used for calculating the residual economic life of the equipment according to the current operating expense data of the equipment;
and the fault frequency calculation submodule is used for calculating the fault frequency of the equipment according to the MES event log.
9. The MES equipment maintenance and early warning system of claim 8, wherein the equipment information acquisition module further comprises:
the equipment running data acquisition submodule of the equipment full life is used for acquiring equipment running data of the equipment full life from an MES time sequence database and establishing an equipment running data set;
the clustering submodule is used for clustering the operation data in the equipment operation data set by adopting a k-means clustering method to obtain the equipment operation data under different working conditions;
and the model training submodule is used for training the equipment health value prediction model by utilizing the operating data under different working conditions to obtain the trained equipment health value prediction model.
10. The MES equipment maintenance and early warning system of claim 9, wherein the equipment information acquisition module further comprises:
the standardization processing submodule is used for respectively carrying out standardization processing on the operation data under different working conditions to obtain the processed operation data under different working conditions;
and the characteristic extraction submodule is used for extracting the characteristics of the processed operating data under different working conditions by adopting a CNN (convolutional neural network), DAE (data acquisition) or PCA (principal component analysis) algorithm to obtain the characteristic data of the operating data under different working conditions.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011095562.0A CN112200327B (en) | 2020-10-14 | 2020-10-14 | MES equipment maintenance early warning method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011095562.0A CN112200327B (en) | 2020-10-14 | 2020-10-14 | MES equipment maintenance early warning method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112200327A true CN112200327A (en) | 2021-01-08 |
CN112200327B CN112200327B (en) | 2023-10-17 |
Family
ID=74009643
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011095562.0A Active CN112200327B (en) | 2020-10-14 | 2020-10-14 | MES equipment maintenance early warning method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112200327B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113191698A (en) * | 2021-06-03 | 2021-07-30 | 云上(南昌)大数据运营有限公司 | Resource planning system and method based on urban brain platform |
CN115657533A (en) * | 2022-10-19 | 2023-01-31 | 扬力集团股份有限公司 | Edge control equipment and control method for press machine |
CN116050950A (en) * | 2023-04-03 | 2023-05-02 | 西南交通大学 | Method, device, equipment and medium for evaluating railway junction passenger train schedule |
CN116629843A (en) * | 2023-07-25 | 2023-08-22 | 山东比沃斯机电工程有限公司 | Remote early warning and maintenance decision support system of intelligent diesel generator set |
CN117592383A (en) * | 2024-01-19 | 2024-02-23 | 四川晟蔚智能科技有限公司 | Method, system, equipment and medium for predicting equipment health life |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018053935A1 (en) * | 2016-09-20 | 2018-03-29 | 西南石油大学 | Failure mode occurrence probability based operating status fuzzy evaluation and prediction method for rotating device |
CN108229042A (en) * | 2018-01-12 | 2018-06-29 | 中国大唐集团科学技术研究院有限公司华东分公司 | A kind of generator tube remaining life early warning system and method for early warning |
CN109255524A (en) * | 2018-08-16 | 2019-01-22 | 广西电网有限责任公司电力科学研究院 | A kind of measuring equipment data analyzing evaluation method and system |
US20190156226A1 (en) * | 2017-11-21 | 2019-05-23 | Institute For Information Industry | Equipment maintenance prediction system and operation method thereof |
CN111160685A (en) * | 2019-09-23 | 2020-05-15 | 上海安恪企业管理咨询有限公司 | Maintenance decision method based on equipment comprehensive health condition analysis and management |
-
2020
- 2020-10-14 CN CN202011095562.0A patent/CN112200327B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018053935A1 (en) * | 2016-09-20 | 2018-03-29 | 西南石油大学 | Failure mode occurrence probability based operating status fuzzy evaluation and prediction method for rotating device |
US20190156226A1 (en) * | 2017-11-21 | 2019-05-23 | Institute For Information Industry | Equipment maintenance prediction system and operation method thereof |
CN108229042A (en) * | 2018-01-12 | 2018-06-29 | 中国大唐集团科学技术研究院有限公司华东分公司 | A kind of generator tube remaining life early warning system and method for early warning |
CN109255524A (en) * | 2018-08-16 | 2019-01-22 | 广西电网有限责任公司电力科学研究院 | A kind of measuring equipment data analyzing evaluation method and system |
CN111160685A (en) * | 2019-09-23 | 2020-05-15 | 上海安恪企业管理咨询有限公司 | Maintenance decision method based on equipment comprehensive health condition analysis and management |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113191698A (en) * | 2021-06-03 | 2021-07-30 | 云上(南昌)大数据运营有限公司 | Resource planning system and method based on urban brain platform |
CN115657533A (en) * | 2022-10-19 | 2023-01-31 | 扬力集团股份有限公司 | Edge control equipment and control method for press machine |
CN116050950A (en) * | 2023-04-03 | 2023-05-02 | 西南交通大学 | Method, device, equipment and medium for evaluating railway junction passenger train schedule |
CN116629843A (en) * | 2023-07-25 | 2023-08-22 | 山东比沃斯机电工程有限公司 | Remote early warning and maintenance decision support system of intelligent diesel generator set |
CN116629843B (en) * | 2023-07-25 | 2023-10-20 | 山东比沃斯机电工程有限公司 | Remote early warning and maintenance decision support system of intelligent diesel generator set |
CN117592383A (en) * | 2024-01-19 | 2024-02-23 | 四川晟蔚智能科技有限公司 | Method, system, equipment and medium for predicting equipment health life |
CN117592383B (en) * | 2024-01-19 | 2024-03-26 | 四川晟蔚智能科技有限公司 | Method, system, equipment and medium for predicting equipment health life |
Also Published As
Publication number | Publication date |
---|---|
CN112200327B (en) | 2023-10-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112200327B (en) | MES equipment maintenance early warning method and system | |
CN111813084B (en) | Mechanical equipment fault diagnosis method based on deep learning | |
CN116629577A (en) | Intelligent supply chain management system based on big data | |
CN113779496A (en) | Power equipment state evaluation method and system based on equipment panoramic data | |
CN115796372B (en) | SCOR-based supply chain management optimization method and system | |
CN112284440B (en) | Sensor data deviation self-adaptive correction method | |
WO2002031613A2 (en) | System and method for monitoring process quality control | |
CN111582931B (en) | Main component analysis-based cigarette market saturation evaluation method and system | |
CN114595623A (en) | XGboost algorithm-based unit equipment reference value prediction method and system | |
CN113221441A (en) | Method and device for health assessment of power plant equipment | |
CN112446509A (en) | Complex electronic equipment prediction maintenance method | |
CN117193222A (en) | Intelligent quality control system based on industrial Internet of things and big data and control method thereof | |
CN117726240A (en) | Quality evaluation classification method and system based on convolutional neural network | |
Wang et al. | Applying machine learning and GA for process parameter optimization in car steering wheel manufacturing | |
CN117786373A (en) | Equipment operation diagnosis system based on big data corrugated paper processing | |
CN111832993B (en) | Predictive maintenance method for warehouse logistics system and related components | |
CN117454771A (en) | Mechanical equipment dynamic maintenance decision-making method based on evaluation and prediction information | |
CN116205622A (en) | Intelligent fault early warning and maintenance decision method for smoke machine equipment | |
CN115115414A (en) | Second-hand car valuation method based on machine learning | |
CN112488432B (en) | Equipment health assessment method, storage device and terminal | |
CN116702030B (en) | Blast furnace state monitoring method and device based on sensor reliability analysis | |
CN113327162B (en) | Credit wind control rule making system | |
CN118014165B (en) | Traceability management method and traceability management system for lithium ion battery production | |
CN116894588B (en) | Big data-based intelligent grain supply and demand management method, system and medium | |
CN118263863A (en) | Intelligent control method for power load balance |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |