CN112052979B - Equipment spare part demand prediction system based on fault prediction and health management - Google Patents
Equipment spare part demand prediction system based on fault prediction and health management Download PDFInfo
- Publication number
- CN112052979B CN112052979B CN202010692410.2A CN202010692410A CN112052979B CN 112052979 B CN112052979 B CN 112052979B CN 202010692410 A CN202010692410 A CN 202010692410A CN 112052979 B CN112052979 B CN 112052979B
- Authority
- CN
- China
- Prior art keywords
- data
- index
- module
- equipment
- feature
- 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.)
- Active
Links
- 230000036541 health Effects 0.000 title claims abstract description 47
- 238000004364 calculation method Methods 0.000 claims abstract description 84
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000004458 analytical method Methods 0.000 claims abstract description 27
- 238000012423 maintenance Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 19
- 230000000007 visual effect Effects 0.000 claims abstract description 11
- 238000011156 evaluation Methods 0.000 claims abstract description 8
- 230000015556 catabolic process Effects 0.000 claims description 23
- 238000006731 degradation reaction Methods 0.000 claims description 23
- 239000013598 vector Substances 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 2
- 239000000306 component Substances 0.000 description 16
- 230000008569 process Effects 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000000354 decomposition reaction Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 239000004568 cement Substances 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
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
- G06Q10/04—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
- 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
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- 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
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a device spare part demand prediction system based on fault prediction and health management, which comprises a data acquisition and edge calculation module, wherein the data acquisition and edge calculation module is used for acquiring data by using edge equipment, and extracting characteristics required by modeling by analyzing and calculating the data; the data service module is used for uniformly managing the data assets of the field device and the system and providing data support for the intelligent analysis model; the intelligent analysis module is used for carrying out signal processing and characteristic processing on the acquired data and carrying out health assessment according to the processed signal data; and the visual application module is used for visually displaying the results of the fault prediction and the health evaluation. The method and the device are easy to implement, can enable spare part demand prediction to be more accurate on the premise of ensuring normal operation of the device, minimize spare part stock, reduce equipment maintenance times, reduce overall maintenance cost of the device from spare part and labor cost, and reduce enterprise operation cost.
Description
Technical Field
The application relates to a device spare part demand prediction system based on fault prediction and health management, which is applicable to the technical field of device fault and health management.
Background
Because in the use of equipment, equipment spare parts are the necessary guarantee that guarantees equipment can normal operating. However, the premature stock of spare parts can lead to long-term occupation of enterprise funds; the spare parts are not in place due to the overlong exchange period of the spare parts, and the production loss caused by the fact that enterprise equipment cannot be started in time is caused.
The equipment is the basis of guaranteeing enterprise production efficiency and product quality, and the damage of equipment key parts will directly influence the performance of equipment, even lead to equipment trouble shut down, influence going on smoothly of production plan, and then lead to the benefit of enterprise impaired. The key parts of the equipment are often expensive and have long purchasing period, and the high spare part stock occupies enterprise funds, so that the value created by the cash flow of the enterprise is weakened; insufficient stock of spare parts can lead to untimely spare part supply, thereby affecting the operation efficiency of the equipment and causing huge economic loss. At present, more algorithms are researched for predicting equipment spare parts.
Chinese patent application 201711278040.2 discloses a method and system for predicting the life of equipment spare parts in a cement plant, the method comprising: acquiring historical running state data and historical management data of key equipment in a cement plant; marking the historical running state data and the historical management data of the key equipment to obtain network training data of each spare part; training the neural network by using the network training data until the training is successful; and collecting current running state data of the target equipment, constructing state input parameters according to the current running state data, inputting the state input parameters into a neural network successfully trained, and taking an output result of the neural network as a prediction result of the spare part life.
Chinese patent application 201710354221.2 discloses a method for configuring spare parts of a communication device based on risk quantization control, the method comprising: setting an upper limit value and a lower limit value of probability that the number of used equipment of the same type exceeds the stock number of spare parts in a risk assessment period which can be born by the existing network according to an experience value; calculating an upper limit value and a lower limit value of the inventory quantity of spare parts of the equipment with the same model; and according to the calculated upper limit value and lower limit value of the stock quantity of spare parts of the equipment with the same model, the actual stock quantity of spare parts of the equipment with the same model is configured.
Chinese patent application 201410605089.4 discloses a method for computing the configuration of spare parts of an electronic device based on a reliability model, comprising: determining the lowest acceptable value of the optimized spare part guarantee probability according to the condition of equipment guarantee resources and the requirements of equipment users, and determining basic configuration parameters of spare part configuration calculation according to the working stress condition and the physical structure of equipment; analyzing the interrelationship among all the model components when the equipment completes the task, analyzing the reliability logic relation among the model components, establishing a reliability model, and calculating the total failure rate of the model components according to a mathematical model corresponding to the reliability model; and constructing an iterative model of spare part configuration calculation to obtain the number of spare parts required to be configured for the part.
The above algorithms are more serious for predicting spare parts, and the replacement of spare parts is actually caused by the health states of equipment and corresponding parts, which causes great limitation and inaccuracy in the process of predicting the spare parts.
On the other hand, predicting a spare part of a device generally requires evaluating the Remaining Useful Life (RUL) of the device, with the objective of predicting the remaining useful life of the device by mining out the trend of continuous degradation of the device from historical monitoring data of the device. The remaining useful life of a device is defined as the time that elapses from the current state of the device until the device fails. In most of the remaining life prediction and health assessment scenarios, the health status of the device is slowly declining, so the selection of trend features becomes critical. In general, features required for RUL predictive modeling and device health assessment modeling processes need to exhibit four characteristics of degradability, stability (also known as robustness), monotonicity, and consistency throughout the device's full life cycle. If the above feature selection and evaluation method is adopted singly, the feature selection and evaluation method is more or less interfered by other factors, such as noise, feature mutation and the like, it is difficult to select the trend feature which really meets the requirement.
Disclosure of Invention
The invention aims to provide a device spare part demand prediction system based on fault prediction and health management, which accurately predicts the spare part demand by combining the health assessment of devices and the residual life prediction of key parts with the spare part purchasing period and the device maintenance plan.
The equipment spare part demand prediction system based on fault prediction and health management according to the application comprises: the data acquisition and edge calculation module is used for acquiring data by utilizing edge equipment and extracting characteristics required by modeling by analyzing and calculating the data; the data service module is used for uniformly managing the data assets of the field device and the system and providing data support for the intelligent analysis model; the intelligent analysis module is used for carrying out signal processing and characteristic processing on the acquired data and carrying out health assessment according to the processed signal data; and the visual application module is used for visually displaying the results of the fault prediction and the health evaluation.
The data acquisition and edge calculation module can align the acquired data with data through a time stamp, then process the acquired signal data, and calculate and extract the characteristics required by modeling through intelligent modeling analysis in the edge equipment. The data service module can be provided with a multi-source data interface which can access the data from the data acquisition and edge calculation module and the data of the existing system. And the intelligent analysis module multiplies the calculated equipment health index and the key component health index value by risk coefficients of the equipment and the key component respectively, and performs weighted calculation to obtain the priority of replacement of equipment spare parts. The intelligent analysis module is used for establishing a spare part demand prediction model by combining the equipment maintenance plan, the equipment key part fault probability and the residual service life, and predicting the minimum spare part inventory.
The intelligent analysis module further comprises a data preprocessing module, a feature extraction module, a feature effectiveness index calculation module and a feature selection module. The characteristic effectiveness index calculation module calculates characteristic degradation index, monotonicity index, robustness index and consistency index through the degradation index calculation module, monotonicity index calculation module, robustness index calculation module and consistency index calculation module respectively, and obtains comprehensive weight index through weighting calculation. The feature selection module reserves the features with the calculated comprehensive weight index being greater than or equal to a preset weight threshold value, omits the features with the comprehensive weight index being smaller than the weight threshold value, and takes the remaining features as selected trend indexes.
The data preprocessing module carries out filtering and analog-to-digital conversion processing on the acquired data; the feature extraction module obtains a feature vector representing the signal through a feature extraction method; the characteristic effectiveness index calculation module calculates characteristic degradation indexes, monotonicity indexes, robustness indexes and consistency indexes respectively through the degradation index calculation module, the monotonicity index calculation module, the robustness index calculation module and the consistency index calculation module, and obtains comprehensive weight indexes through weighted calculation; the feature selection module reserves the features with the calculated comprehensive weight index being greater than or equal to a preset weight threshold value, discards the features with the comprehensive weight index being smaller than the weight threshold value, and takes the remaining features as selected trend indexes.
The method for calculating the feature effectiveness index comprises the following steps:
(1) Collecting operation data of equipment through a sensor, preprocessing the collected operation data, and obtaining full life cycle characteristic data of at least one group of equipment;
(2) A plurality of feature vectors representing the data signals are obtained by utilizing a feature extraction method;
(3) Performing degradation index calculation, monotonicity index calculation, robustness index calculation and consistency index calculation on the plurality of feature vectors to respectively obtain degradation index, monotonicity index, robustness index and consistency index of each feature vector;
(4) Setting a weight coefficient for the weight of each index, and obtaining a comprehensive weight index through weight calculation;
(5) And comparing the calculated comprehensive weight index with a set weight threshold value, and removing the characteristic that the comprehensive weight index is smaller than the weight threshold value to serve as a validity index.
According to the method, the fault prediction and health management technology is utilized, health assessment and life prediction are carried out on the slave equipment and the corresponding parts, accurate prediction of spare part requirements is carried out on equipment parts, particularly key parts of the equipment, and inventory management of spare parts is optimized. The system is easy to implement, can enable the spare part demand prediction to be more accurate on the premise of ensuring the normal operation of the equipment, minimize the stock quantity of the spare parts, reduce the maintenance times of the equipment, reduce the overall maintenance cost of the equipment from the aspects of spare parts and labor cost, and finally achieve the aim of reducing the operation cost of enterprises.
Drawings
Fig. 1 shows a framework diagram of a device spare part demand prediction system based on fault prediction and health management according to the present application.
Fig. 2 shows a flowchart of the spare part demand prediction using the equipment spare part demand prediction system of the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the present application more apparent, embodiments of the present application will be described in detail hereinafter with reference to the accompanying drawings. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be arbitrarily combined with each other.
According to the equipment spare part demand prediction system based on fault prediction and health management, as shown in fig. 1, the equipment spare part demand prediction system consists of four functional modules, namely data acquisition and edge calculation, data service, intelligent analysis and visualization application.
Data acquisition and edge calculation module
The module collects data by using the edge equipment and can finish edge calculation in the edge equipment, thereby reducing the calculation amount and the workload of a server side. Wherein the acquired data includes low frequency data and high frequency data as described below, the data may be aligned by a time stamp. The collected signal data is then processed, and features required for modeling are calculated and extracted in the edge device through intelligent modeling analysis. Meanwhile, the data acquisition and edge calculation module supports unified management of edge intelligent hardware, configuration of data acquisition rules and unified storage and management of data acquired by uploading the acquired data to a data service module of the system. The collected data mainly comprise equipment operation data and physical quantity data of equipment.
The equipment operation data, including working time, processing batch information, equipment state, operation process data, alarm information and the like, can be obtained through analyzing an interface protocol opened by an edge intelligent hardware for an equipment controller, and the reading frequency of the information is related to the performance of the equipment, and generally can adopt low-frequency data acquisition of a few times a second or once a few seconds. The collected device operational data may include historical data and real-time data.
Physical quantity data of the equipment, including physical quantity data such as vibration, temperature, sound, rotating speed and the like, can be used for collecting physical quantity signals related to the equipment through a self-contained or external sensor of the equipment. The corresponding filtering and analog-to-digital conversion are carried out by the edge intelligent hardware, the data acquisition frequency can be selected and configured according to actual requirements, generally, thousands or tens of thousands of high-frequency data acquisition is carried out in one second, and a hybrid model based on mechanism and data driving fusion is established by combining equipment operation data.
Data service module
The data service module can realize unified management of data assets of the field devices and the system and provide data support for the intelligent analysis model. The module can realize multi-source data access, including data from a data acquisition and edge calculation module and data of the existing system, such as data of systems of enterprise software systems MES, ERP and the like; the unified and normalized storage, calculation and management of the data are supported, and the classification management and maintenance of the low-cost data are realized through the standardized and systematic rule management; and supporting the release of data required by the intelligent analysis module or the visual application module in various data release forms such as files, API interfaces and the like.
Intelligent analysis module
In order to accurately predict the spare part requirements of key parts of equipment, accurate fault prediction and health management of the equipment are required to be realized, and the health state of the equipment is estimated. Firstly, completing data acquisition of field equipment through a data acquisition device, then performing signal processing and characteristic processing on the acquired data, and performing health assessment according to the processed signal data. When a problem occurs in the health of the equipment, fault diagnosis is performed, the time to the failed component and the time to the failure are located, that is, the life of the component is predicted, and relevant personnel are notified through the visualization of the analysis result.
And multiplying the equipment health index and the key component health index value obtained based on the analysis and calculation of the fault prediction and the health management model with risk coefficients of the equipment and the key component respectively, and carrying out weighted calculation to obtain the priority of replacement of equipment spare parts, wherein the risk coefficients can be obtained by adopting a failure mode and influence analysis method (FMEA) based on the occurrence frequency of faults and influence caused by the faults. Then, combining the equipment maintenance plan, the equipment key component fault probability and the residual service life, taking the equipment spare part purchasing period and the maintenance personnel work plan as constraint conditions, establishing a spare part demand prediction model, wherein the predicted result is the minimum spare part stock quantity meeting the minimum maintenance times and the minimum maintenance cost, and the specific flow is shown in figure 2. It should be noted that, the health index of the device in the present application refers to the health index of the whole device, and the health index of the key component is some key component in the device. For example, for a machine tool complete machine, the spindle is one of its key components; for the whole wind driven generator, the wind wheel is one of key components.
In the face of different equipment types, different key components and different faults on site, different models need to be established, so that fault prediction and health management of the key components are realized. Therefore, the intelligent analysis module needs to provide the data required by the model from the data layer to the corresponding model, and also needs to perform unified scheduling and execution management on various models running in the system, so that the models are executed at a specified time node, such as a certain moment of day, a certain event trigger, and the like. And simultaneously, unified management is carried out on the running time, the running state, the running result and the like of the model, and the result data of the model operation is pushed into an application layer visual interface to form closed-loop management on spare part management of key parts of the equipment.
Furthermore, the step of performing feature processing on the collected data by the intelligent analysis module includes selecting trend features, and predicting the remaining service life of the device by performing comprehensive weight evaluation on the degradability, monotonicity, robustness and consistency indexes of the trend features. Specifically, the data preprocessing module can preprocess the equipment operation data and the physical quantity data of the equipment, which are acquired by the data acquisition and edge calculation module, for example, the signal data of the sensor can be subjected to noise reduction, normalization, outlier processing, working condition segmentation and the like. Then, the feature vector characterizing the signal can be obtained by a feature extraction module by utilizing wavelet decomposition, wavelet packet decomposition, time domain statistical features, frequency spectrum peak features, time-frequency domain features and deep learning feature extraction methods such as SAE, CNN and the like. And then, calculating the effectiveness index of the feature by a feature effectiveness index calculation module, comparing the calculated comprehensive weight index with a set threshold value, and discarding the feature with the comprehensive weight index smaller than the weight threshold value as the effectiveness index to evaluate the degradation trend of the equipment so as to predict the residual service life of the equipment. And then, accurately predicting the spare part demand by combining the spare part purchasing period and the equipment maintenance plan.
Specifically, the intelligent analysis module may further include a data preprocessing module, a feature extraction module, a feature validity index calculation module, and a feature selection module.
The data preprocessing module mainly comprises, but is not limited to, noise reduction, normalization, outlier processing, working condition segmentation and other processing of the sensor data. For example, the data collected by the data collection module can be subjected to corresponding filtering and analog-to-digital conversion by the edge intelligent hardware, and the data collection frequency can be selected and configured according to actual requirements.
The feature extraction module mainly uses a method to obtain feature vectors for representing the signals, wherein the method comprises, but is not limited to, wavelet decomposition, wavelet packet decomposition, time domain statistical features, frequency spectrum peak features, time-frequency domain features and deep learning feature extraction methods such as SAE, CNN and the like.
The characteristic effectiveness index calculation module calculates the characteristic degradation index, the monotonicity index, the robustness index and the consistency index respectively through the degradation index calculation module, the monotonicity index calculation module, the robustness index calculation module and the consistency index calculation module, and obtains the comprehensive weight index through weighting calculation.
The feature selection module reserves the features with the calculated comprehensive weight index being greater than or equal to a preset weight threshold value, discards the features with the comprehensive weight index being smaller than the weight threshold value, and takes the remaining features as selected trend indexes.
In the application, the method for calculating the feature effectiveness index comprises the following steps:
(1) Collecting operation data of equipment through a sensor, preprocessing the collected operation data, and obtaining full life cycle characteristic data of at least one group of equipment;
(2) A plurality of feature vectors representing the data signals are obtained by utilizing a feature extraction method;
(3) Performing degradation index calculation, monotonicity index calculation, robustness index calculation and consistency index calculation on the plurality of feature vectors to respectively obtain degradation index, monotonicity index, robustness index and consistency index of each feature vector;
(4) Setting a weight coefficient for the weight of each index, and obtaining a comprehensive weight index through weight calculation;
(5) And comparing the calculated comprehensive weight index with a set weight threshold value, and removing the characteristic that the comprehensive weight index is smaller than the weight threshold value to serve as a validity index.
In the step (3), specific methods for performing the degradation index calculation, the monotonicity index calculation, the robustness index calculation, and the consistency index calculation on the plurality of feature vectors are described in detail below.
(1) The computing method of the degradation index computing module comprises the following steps:
(1) Before the trend feature weight calculation, a custom linear and nonlinear feature change Pattern (Pattern) needs to be designed, wherein the nonlinear feature change Pattern comprises a convex function and a concave function, and the convex function comprises y=x α (α>1),y=e αx (alpha > 0) and the like, and the concave functions comprise functions of y=log (alpha x), (alpha > 0), y=tanh (alpha x), (alpha > 0) and the like, and the concave functions and the convex functions only need to be selected to meet the definition. For example, two concave-convex functions are selected, and defined according to the following formula:
wherein x is i Data for the time field, i=1, 2,3, n; to simplify the calculation, α is an integer.
(2) And respectively solving the correlation coefficients between the extracted feature vectors and different feature change modes, wherein the correlation solving method can adopt a Pearson method and the like.
(3) Defining the coefficient when the correlation coefficient is maximized as a degradation index of the feature:
Trendability=max(corr(F,P α ) Formula (2)
Wherein F is a feature vector, P α Is a characteristic change pattern under different parameters alpha.
(4) When there is M (M > 1) group full lifecycle data, then to meet the consistency requirement, define
Wherein Trend m The sign is a sign function that is an index of the degradability of the mth full life cycle sample of the feature (m=1, 2, …, M).
(2) The calculation method of the monotonicity index calculation module comprises the following steps:
(1) The characteristics are subjected to sliding window processing, the data of each window is fitted, smoothing processing is carried out, and then the average slope k of the data of the ith window is obtained i 。
(2) Monotonicity index is defined as
Wherein k is i The resulting slope is fitted to the data for the ith window.
(3) When the M (M > 1) group full life cycle data exists, in order to meet the consistency requirement, taking the minimum monotonicity index in the plurality of groups of samples as the monotonicity index of the whole, defining as:
monotonicity=min(mon m ) M=1, 2, where, M formula (5)
Wherein mon is m As monotonicity index of the M-th set of full life cycle feature data, m=1, 2, …, M.
(3) The calculation method of the robustness index calculation module comprises the following steps:
(1) Fitting the feature data, wherein the fitting method is not limited, and smoothing treatment can be performed to obtain the fitted or smoothed feature Y k (k=1, 2,) N, the original features are denoted as X k (k=1,2,...,N)。
(2) Calculating a robustness index:
(3) When the M (M > 1) group full life cycle data exists, in order to meet the consistency requirement, taking the minimum robustness index in the multiple groups of samples as the overall robustness index, and defining:
Robustness=min(rob m ) M=1, 2, where, M formula (7)
Therein, rob m As a robustness index of the M-th group full life cycle feature data, m=1, 2, …, M.
(4) The calculation method of the consistency index calculation module comprises the following steps:
(1) Fitting the feature data to obtain a fitted feature Y k (k=1, 2., (a), N), definition ft=y N ,ST=Y 1 ;
(2) When M groups (M > 1) of full life cycle feature data exist, a consistency index is calculated:
where m=1, 2, …, M.
(5) The processing flow of the comprehensive index calculation module comprises the following steps:
(1) When only one group of full life cycle characteristic data exists, the comprehensive weight index is defined as follows:
Feature_effective_Index=ω 1 *trend+ω 2 *mon+ω 3 *rob
wherein trend is a degradation index, mon is a monotonicity index, rob is a stability index, ω i (i=1, 2, 3) is the weight of each index.
(2) When a plurality of groups of full life cycle characteristic data exist, defining the comprehensive weight index as follows:
Feature_effective_Index=ω 1 *trend+ω 2 *mon+ω 3 *rob+ω 4 *con
wherein trend is a degradation index, mon is a monotonicity index, rob is a stability index, con is a consistency index, ω i (i=1, 2,3, 4) is the weight, ω of each index i The setting of (2) can be adjusted according to the actual situation. For example, where the modeling process focuses only on the degradability of the feature, ω can be set 1 =1,ω 2 =0,ω 3 =0,ω 4 =0, can pass through ω i To select the type of feature required for modeling.
The method for selecting the trend features can effectively evaluate the linear trend features, can effectively evaluate some nonlinear features, is high in anti-noise performance of evaluation indexes, and reduces the phenomenon of unstable indexes caused by random errors by fitting the features in the feature consistency evaluation. In addition, the method can also detect the mutation of the characteristics, and provides a basis for the selection of a predictive modeling method.
Visual application module
The visual application module can carry out related visual interface design according to the actual demands of users, and the display information comprises: basic information of equipment, health state of equipment, fault diagnosis result of equipment, health state and residual service life of key parts of equipment, predictive maintenance advice of equipment and demand prediction result of spare parts, and stock information of spare parts, so that a user can purchase spare parts in time and replace the spare parts, and optimal management of the stock of the spare parts is realized.
Examples
In the embodiment, the equipment spare part demand prediction system based on fault prediction and health management is used for demand prediction of the numerical control machine tool spindle spare parts of the manufacturing plant. The main shaft is a core component of the numerical control machine tool, is generally expensive, and once damaged, the maintenance, replacement or purchase period is long, so that the machine tool can be stopped for a long time by fault, and the production plan is influenced. By carrying out fault prediction and health management on the main shaft, the abnormal condition of the main shaft can be timely detected, the spare part requirement of the main shaft is accurately predicted, the inventory is reasonably optimized or the purchase is arranged in advance, and the machine tool is prevented from being stopped for a long time. The specific implementation process is as follows:
data acquisition and edge calculation module
Setting a machine tool spindle variable rotation speed idle load test, mounting a vibration acceleration sensor on a spindle shell, and acquiring a spindle vibration signal and a machine tool controller signal during the spindle variable rotation speed idle load test by utilizing edge intelligent hardware; running a data preprocessing program on the edge intelligent hardware, dividing a main shaft vibration signal in real time according to the rotating speed information in a machine tool controller signal and a preset sectional time length to obtain vibration signals with a plurality of sections of time lengths under each rotating speed, extracting characteristics of each section of vibration signal, and calculating a characteristic value; and uploading the characteristic value to a data service module.
Data service module
And accessing and integrating the data uploaded by the data acquisition and edge calculation module, the equipment maintenance plan, the work order information, the spare part purchasing period and other data in the factory MES system into a data service module for unified storage and management, and providing a data interface to transmit the data to an intelligent analysis module for modeling and visual application module for display.
Intelligent analysis module
Model training is carried out by using a characteristic value sample accumulated by repeating the machine tool spindle variable rotation speed idle load test for a plurality of times, a spindle health condition baseline model is established by adopting a Principal Component Analysis (PCA) algorithm, and spindle abnormality is detected by calculating a residual error (SPE) and a Hotelling T2 statistic (T2) of a model predicted value. The health degree and the residual service life of the main shaft of up to 50 numerical control machine tools and the risk coefficient of the machine tools can be calculated, the main shaft is taken as input in combination with the maintenance schedule of the machine tools, the purchasing period of the main shaft and the labor cost of maintenance personnel are taken as constraint conditions, an accurate prediction model of the main shaft spare part requirement is established, and the spare part requirement is calculated.
Visual application module
The visual application module displays state information and decision suggestions, and mainly comprises the following steps: an overview interface and a single machine tool interface. The overview interface can display all machine tool running states, machine tool health states, spindle health states, maintenance plans, spindle spare part stock, spindle spare part purchasing cycles, spare part demand and spare part purchasing suggestions; the single machine tool interface can display single machine tool basic information, machine tool running state, machine tool health index, main shaft health index, life trend and maintenance decision advice.
Although the embodiments disclosed in the present application are described above, the descriptions are merely for facilitating understanding of the present application, and are not intended to limit the present application. Any person skilled in the art to which this application pertains will be able to make any modifications and variations in form and detail of implementation without departing from the spirit and scope of the disclosure, but the scope of the patent claims of this application shall be subject to the scope of the claims that follow.
Claims (7)
1. A device spare part demand prediction system based on fault prediction and health management, the prediction system comprising:
the data acquisition and edge calculation module is used for acquiring data by utilizing edge equipment and extracting characteristics required by modeling by analyzing and calculating the data;
the data service module is used for uniformly managing the data assets of the field device and the system and providing data support for the intelligent analysis model;
the intelligent analysis module is used for carrying out signal processing and characteristic processing on the acquired data and carrying out health assessment according to the processed signal data;
the visual application module is used for visually displaying the results of fault prediction and health evaluation;
the intelligent analysis module further comprises a data preprocessing module, a feature extraction module, a feature effectiveness index calculation module and a feature selection module; the characteristic effectiveness index calculation module calculates characteristic degradation indexes, monotonicity indexes, robustness indexes and consistency indexes respectively through the degradation index calculation module, the monotonicity index calculation module, the robustness index calculation module and the consistency index calculation module, and obtains comprehensive weight indexes through weighted calculation;
the method for calculating the feature effectiveness index comprises the following steps:
(1) Collecting operation data of equipment through a sensor, preprocessing the collected operation data, and obtaining full life cycle characteristic data of at least one group of equipment;
(2) A plurality of feature vectors representing the data signals are obtained by utilizing a feature extraction method;
(3) Performing degradation index calculation, monotonicity index calculation, robustness index calculation and consistency index calculation on the plurality of feature vectors to respectively obtain degradation index, monotonicity index, robustness index and consistency index of each feature vector;
(4) Setting a weight coefficient for the weight of each index, and obtaining a comprehensive weight index through weight calculation;
(5) Comparing the calculated comprehensive weight index with a set weight threshold value, and removing the characteristic that the comprehensive weight index is smaller than the weight threshold value to be used as a validity index;
the computing method of the degradation index computing module comprises the following steps:
before the trend feature weight calculation, the method needs to design a self-defined linear and nonlinear feature change mode, wherein the nonlinear feature change mode comprises a convex function and a concave function, and the following two functions are adopted respectively:
wherein x is i Data for the time field, i=1, 2,3, n; to simplify the calculation, α is an integer;
(3.2) respectively solving correlation coefficients between the extracted feature vectors and different feature change modes, wherein a Pearson method is adopted as a correlation solving method;
(3.3) defining the coefficient when the correlation coefficient is maximized as a degradation index of the feature:
Trendability=max(corr(F,P α ))
wherein F is a feature vector, P α Characteristic change modes under different parameters alpha;
(3.4) when there are M sets of full lifecycle data greater than 1, in order to meet the consistency requirement, define
Wherein Trend m Is an index of the degradability of the mth full life cycle sample of the feature, where m=1, 2, …, M, sign is a sign function.
2. The equipment spare part demand prediction system according to claim 1, wherein the data acquisition and edge calculation module is capable of aligning the acquired data with the time stamp and then processing the acquired signal data, and calculating and extracting features required for modeling through intelligent modeling analysis in the edge equipment.
3. The equipment spare part demand prediction system according to claim 1 or 2, wherein the data service module is provided with a multi-source data interface, and can access data from the data acquisition and edge calculation module and data of an existing system.
4. The equipment spare part demand prediction system according to claim 1 or 2, wherein the intelligent analysis module multiplies the calculated equipment health index and the calculated critical part health index value by risk coefficients of the equipment and the critical part respectively and performs weighted calculation to obtain the priority of equipment spare part replacement.
5. The equipment spare part demand prediction system according to claim 4, wherein the intelligent analysis module is used for establishing a spare part demand prediction model to predict the minimum spare part stock by combining an equipment maintenance plan, equipment key part failure probability and residual service life.
6. The equipment spare part demand prediction system according to claim 1, wherein the feature selection module retains features with calculated comprehensive weight indexes greater than or equal to a preset weight threshold, discards features with comprehensive weight indexes smaller than the weight threshold, and uses the remaining features as the selected trend index.
7. The equipment spare part demand prediction system according to claim 1 or 6, characterized in that:
the data preprocessing module carries out filtering and analog-to-digital conversion processing on the acquired data; the feature extraction module obtains feature vectors representing the signals through a feature extraction method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010692410.2A CN112052979B (en) | 2020-07-17 | 2020-07-17 | Equipment spare part demand prediction system based on fault prediction and health management |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010692410.2A CN112052979B (en) | 2020-07-17 | 2020-07-17 | Equipment spare part demand prediction system based on fault prediction and health management |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112052979A CN112052979A (en) | 2020-12-08 |
CN112052979B true CN112052979B (en) | 2024-02-13 |
Family
ID=73601964
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010692410.2A Active CN112052979B (en) | 2020-07-17 | 2020-07-17 | Equipment spare part demand prediction system based on fault prediction and health management |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112052979B (en) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112650654A (en) * | 2020-12-11 | 2021-04-13 | 西安诺瓦星云科技股份有限公司 | Early warning method and device for display control visualization system, storage medium and processor |
CN113094826A (en) * | 2021-03-29 | 2021-07-09 | 北京航空航天大学 | Task reliability-based remaining life prediction method for multi-state manufacturing system |
CN112712304A (en) * | 2021-03-29 | 2021-04-27 | 北京星际荣耀空间科技股份有限公司 | Spacecraft prediction and health management system evaluation system |
CN113467403B (en) * | 2021-07-23 | 2023-02-03 | 张家口卷烟厂有限责任公司 | Cigarette equipment management system |
CN114189520B (en) * | 2021-10-15 | 2022-08-19 | 中标慧安信息技术股份有限公司 | Terminal equipment service life prediction method and system based on edge calculation |
CN114102262B (en) * | 2021-12-27 | 2023-03-24 | 爱派尔(常州)数控科技有限公司 | Machine tool spindle safety detection method and system and machine tool |
CN114565161A (en) * | 2022-03-01 | 2022-05-31 | 北京九天翱翔科技有限公司 | Storage stage fault prediction and service life prolonging method based on multi-time-space dimension data fusion |
CN115169505B (en) * | 2022-09-06 | 2022-12-02 | 杭州浅水数字技术有限公司 | Early warning method and early warning system for mechanical fault of moving part of special equipment |
CN115994734B (en) * | 2023-03-14 | 2024-01-30 | 百福工业缝纫机(张家港)有限公司 | Production equipment maintenance part inventory management method and system |
CN116126836B (en) * | 2023-04-12 | 2023-06-13 | 山东越海通信科技股份有限公司 | Digital intelligent monitoring system and method for optical fiber device processing equipment |
CN117350492A (en) * | 2023-10-13 | 2024-01-05 | 宿迁云瑞国科信息技术有限公司 | MES operation management system capable of intelligently controlling comparison historical data |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108241343A (en) * | 2016-12-24 | 2018-07-03 | 青岛海尔模具有限公司 | A kind of intelligent plant management platform system |
CN108591104A (en) * | 2018-04-18 | 2018-09-28 | 广东寰球智能科技有限公司 | A kind of Research on Fan Fault Forecasting based on cloud platform and health management system arranged, method |
CN109909803A (en) * | 2019-04-17 | 2019-06-21 | 北京天泽智云科技有限公司 | A kind of machine tool chief axis method for detecting abnormality |
CN110057584A (en) * | 2019-04-01 | 2019-07-26 | 西安交通大学 | A kind of locomotive traction motor bearing degradation monitoring method |
KR20200077780A (en) * | 2018-12-21 | 2020-07-01 | 한국기술교육대학교 산학협력단 | Industrial equipment monitoring system using edge computing |
CN111401583A (en) * | 2020-03-18 | 2020-07-10 | 北京天泽智云科技有限公司 | Escalator full life cycle health management system based on predictive maintenance |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10607180B2 (en) * | 2014-03-10 | 2020-03-31 | Embraer S.A. | Inventory control for non-repairable items based on prognostics and health monitoring data |
-
2020
- 2020-07-17 CN CN202010692410.2A patent/CN112052979B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108241343A (en) * | 2016-12-24 | 2018-07-03 | 青岛海尔模具有限公司 | A kind of intelligent plant management platform system |
CN108591104A (en) * | 2018-04-18 | 2018-09-28 | 广东寰球智能科技有限公司 | A kind of Research on Fan Fault Forecasting based on cloud platform and health management system arranged, method |
KR20200077780A (en) * | 2018-12-21 | 2020-07-01 | 한국기술교육대학교 산학협력단 | Industrial equipment monitoring system using edge computing |
CN110057584A (en) * | 2019-04-01 | 2019-07-26 | 西安交通大学 | A kind of locomotive traction motor bearing degradation monitoring method |
CN109909803A (en) * | 2019-04-17 | 2019-06-21 | 北京天泽智云科技有限公司 | A kind of machine tool chief axis method for detecting abnormality |
CN111401583A (en) * | 2020-03-18 | 2020-07-10 | 北京天泽智云科技有限公司 | Escalator full life cycle health management system based on predictive maintenance |
Also Published As
Publication number | Publication date |
---|---|
CN112052979A (en) | 2020-12-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112052979B (en) | Equipment spare part demand prediction system based on fault prediction and health management | |
Baur et al. | A review of prognostics and health management of machine tools | |
US6871160B2 (en) | Intelligent condition-based engine/equipment management system | |
Al-Dahidi et al. | Remaining useful life estimation in heterogeneous fleets working under variable operating conditions | |
Lu et al. | Predictive condition‐based maintenance for continuously deteriorating systems | |
US20040049715A1 (en) | Computer networked intelligent condition-based engine/equipment management system | |
CN115244482A (en) | Hybrid risk model for maintenance optimization and system for performing such method | |
Cohen et al. | A smart process controller framework for Industry 4.0 settings | |
CN110757510B (en) | Method and system for predicting remaining life of robot | |
CN113036913B (en) | Method and device for monitoring state of comprehensive energy equipment | |
US20200250584A1 (en) | Modeling method for smart prognostics and health management system and computer program product thereof | |
CN117055502A (en) | Intelligent control system based on Internet of things and big data analysis | |
Kobbacy et al. | New technologies for maintenance | |
CN115526375A (en) | Space flight equipment predictive maintenance system | |
CN111241683A (en) | Equipment working condition fault prediction method and system based on dynamic time warping | |
CN112016800B (en) | Feature selection method and system based on effectiveness index | |
WO2020253950A1 (en) | Monitoring method, predicting method, monitoring system and computer program | |
CN117592975A (en) | Operation and maintenance decision processing method and system for electromechanical equipment of expressway based on cloud computing | |
Borissova et al. | A concept of intelligent e-maintenance decision making system | |
Koops | Optimized maintenance decision-making—A simulation-supported prescriptive analytics approach based on probabilistic cost-benefit analysis | |
Xin et al. | Dynamic probabilistic model checking for sensor validation in Industry 4.0 applications | |
JP7062505B2 (en) | Equipment management support system | |
CN116384876A (en) | Spare part dynamic inventory-production control method, system and medium based on wiener process | |
CN114880917A (en) | Method and device for building health state model and predicting performance trend of pumped storage unit | |
Mayadevi et al. | SCADA-based operator support system for power plant equipment fault forecasting |
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 |