CN115018120A - Predictive maintenance method, system and readable storage medium based on health index - Google Patents
Predictive maintenance method, system and readable storage medium based on health index Download PDFInfo
- Publication number
- CN115018120A CN115018120A CN202210469078.2A CN202210469078A CN115018120A CN 115018120 A CN115018120 A CN 115018120A CN 202210469078 A CN202210469078 A CN 202210469078A CN 115018120 A CN115018120 A CN 115018120A
- Authority
- CN
- China
- Prior art keywords
- health
- equipment
- performance
- data
- maintenance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06Q10/04—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
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a health index-based equipment predictive maintenance method and system, which comprises the following steps: obtaining device data, the device data comprising: operating condition data, maintenance data, and maintenance data; extracting performance characteristics according to the equipment data, and acquiring deviation indexes according to the performance characteristics to construct health indexes; acquiring a current health index of the equipment according to the performance characteristic, and evaluating a health grade of the equipment according to the health index; predicting a remaining usable life of the device based on the health indicator; and establishing the optimal health management measures of the equipment according to the health grade and/or the remaining usable life of the equipment. Through the mode, when the failure rate is reduced, the utilization efficiency of maintenance resources is greatly improved, and the non-reasonable inventory pressure cost of spare parts is reduced.
Description
Technical Field
The invention relates to the technical field of engineering machinery, in particular to a health index-based predictive maintenance method, a health index-based predictive maintenance system and a readable storage medium.
Background
In the engineering machinery industry, most of the maintenance is carried out in a mode of combining timing maintenance and fault maintenance at present. Namely regular maintenance of main systems and parts and passively initiated troubleshooting after customer complaints or warranties occur.
The existing maintenance mode has the following problems: 1. the maintenance is insufficient, so that equipment failure is caused, and economic loss of companies and enterprises is caused; 2. maintenance resources are wasted due to excessive maintenance; 3. the stock of spare parts is overstocked seriously, and the stock pressure cost is huge.
Therefore, a method, system and readable storage medium for predictive maintenance based on health index are needed to solve the above problems.
Disclosure of Invention
The invention provides a predictive maintenance method, a system and a readable storage medium based on a health index, which can evaluate the health grade of equipment according to the health index of the equipment, predict the residual service life of the equipment, make a predictive maintenance plan in advance, and determine the time, content, mode and necessary technology and spare part support of equipment repair.
The technical problem to be solved by the invention is realized by adopting the following technical scheme:
a method for predictive maintenance of equipment based on health indices, comprising: obtaining device data, the device data comprising: operating condition data, maintenance data, and maintenance data; extracting performance characteristics according to the equipment data, and acquiring deviation indexes according to the performance characteristics to construct health indexes; acquiring a current health index of the equipment according to the performance characteristics, and evaluating the health grade of the equipment according to the health index; predicting a remaining usable life of the device based on the health indicator; and establishing the optimal health management measures of the equipment according to the health grade and/or the remaining usable life of the equipment.
In a preferred embodiment of the present invention, the step of extracting the performance characteristic according to the device data and obtaining the deviation index according to the performance characteristic to construct the health index includes: preprocessing the equipment data and then extracting the performance characteristics; constructing a performance model according to the performance characteristics and the influence factors; calculating to obtain a performance deviation index according to the measured value of the performance index and the expected value of the performance index obtained by the performance model; and constructing the health index according to the performance deviation index.
In a preferred embodiment of the present invention, the step of constructing the performance model according to the performance characteristics and the influencing factors includes: preprocessing the equipment data to obtain the performance characteristics; setting the performance characteristics and the influence factors thereof as variables of a performance model to construct the performance model; evaluating the performance model; if the evaluation is passed, carrying out model parameter optimization on the constructed performance model; and if the evaluation fails, reconstructing the performance model.
In a preferred embodiment of the present invention, the step of obtaining a current health index of the device according to the performance characteristics and evaluating a health level of the device according to the health index includes: acquiring health indexes of all parts of the equipment; and synthesizing the health indexes of the components to judge a first health grade of the equipment.
In a preferred embodiment of the present invention, the step of obtaining a current health index of the device according to the performance characteristics and evaluating a health level of the device according to the health index further includes: acquiring the failure rate and the maintenance grade of the equipment; determining a second health level of the equipment based on the failure rate, the maintenance level, and the first health level of the equipment.
In a preferred embodiment of the present invention, after the step of obtaining the current health index of the device according to the performance characteristics and evaluating the health level of the device according to the health index, the method includes: and judging the availability of the equipment according to the health level of the equipment, and confirming the task types which can be borne by the equipment so as to optimize the operation scheduling of the equipment.
In a preferred embodiment of the present invention, the step of predicting the remaining usable life of the equipment according to the health indicator includes: predicting the operable time of the equipment according to the health index and a given failure threshold value; and predicting the remaining usable life of the equipment according to the working time and the current working time of the equipment.
In a preferred embodiment of the invention, the step of establishing an optimal health management measure for the equipment based on the health level and/or remaining usable life of the equipment comprises reconfirming the health level and remaining usable life of the equipment based on the feedback from the maintenance activity.
A system for the predictive maintenance of equipment based on health indices of any of the above, comprising: the data acquisition module is used for acquiring equipment data; the data processing module is used for preprocessing the equipment data and calling the preprocessed equipment data to perform health index construction, health grade evaluation, residual life calculation and maintenance decision generation; and the health management module is used for receiving the maintenance decision so as to generate a maintenance plan.
A readable storage medium, having stored thereon a computer program which, when executed by a processor, carries out the steps of the health index based equipment predictive maintenance method as claimed in any one of the preceding claims.
The technical effect achieved by adopting the technical scheme is as follows: the method comprises the steps of predicting the remaining service life of equipment or components based on health indexes of the equipment or the components, evaluating the health grade of the equipment, pre-making a predictive maintenance plan according to the future development trend and possible failure modes of the equipment or the components, determining the time, content and mode of equipment repair and necessary technology and spare part support, reducing the failure rate, greatly improving the utilization efficiency of maintenance resources and reducing the non-reasonable spare part inventory pressure cost.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical means of the present invention more clearly understood, the present invention may be implemented in accordance with the content of the description, and in order to make the above and other objects, features, and advantages of the present invention more clearly understood, the following preferred embodiments are specifically illustrated in the accompanying drawings and described in detail.
Drawings
FIG. 1 is a flow chart illustrating a method for predictive maintenance of equipment based on health indices in accordance with an embodiment of the present invention;
FIG. 2 is a data flow diagram illustrating an embodiment of the present invention;
FIG. 3 is a flow chart illustrating a health indicator construction process according to an embodiment of the present invention;
FIG. 4 is a flow chart illustrating performance model construction according to an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating performance modeling according to an embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating model-based bias calculation according to an embodiment of the present invention;
FIG. 7 is a flow chart illustrating a health level assessment in accordance with an embodiment of the present invention;
FIG. 8 is a schematic diagram illustrating a prediction of remaining usable life according to an embodiment of the present invention;
FIG. 9 is a flow chart illustrating a maintenance decision according to an embodiment of the present invention;
FIG. 10 is a flowchart illustrating a predictive maintenance case according to an embodiment of the invention;
FIG. 11 is a block diagram of a health index based predictive maintenance system for equipment in accordance with an embodiment of the present invention;
fig. 12 is a block diagram of a preventive maintenance system according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical measures and effects taken to achieve the intended objects of the present invention, embodiments of the present invention will be described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below are only a part of the embodiments of the present invention, and not all of them. All other embodiments that can be obtained by a person skilled in the art based on the embodiments of the present invention without any inventive step belong to the scope of the embodiments of the present invention. While the present invention has been described in connection with the preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but is intended to cover various modifications, equivalent arrangements, and specific embodiments thereof.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for predictive maintenance of equipment based on health index according to an embodiment of the present invention.
As shown in fig. 1, the method of this embodiment includes the following steps:
s11: obtaining device data, the device data comprising: operating condition data, maintenance data, and maintenance data;
s12: extracting performance characteristics according to the equipment data, and constructing a health index according to the performance characteristics;
s13: acquiring a current health index of the equipment according to the performance characteristics, and evaluating the health grade of the equipment according to the health index;
s14: predicting the remaining usable life of the equipment according to the health index;
s15: optimal health management measures for the equipment are established based on the health level and/or remaining usable life of the equipment.
As shown in fig. 2, the present disclosure provides a health index-based equipment predictive maintenance method to meet the challenge of the traditional maintenance method in the engineering machinery industry. The technical scheme is based on big data and cloud computing, a predictive maintenance algorithm based on health indexes is adopted, the maintenance priority of the system or the components can be quickly and effectively classified, reasonable and effective maintenance suggestions are pushed, and powerful digital service is provided for reasonably arranging maintenance resources and planning spare parts for after-sale service.
The data flow based on the technical scheme can comprise five steps of data acquisition, health index construction, health state evaluation, residual life prediction and maintenance decision generation.
The first step is as follows: data acquisition and data acquisition are acquired in two ways, namely, engineering mechanical equipment is acquired through a sensor in the process, and data generated by recording, calibrating, feeding back and the like of an operator at a mobile phone or a personal computer terminal are acquired. Data of the sensor end is processed by the edge device of the device end and then transmitted to the data center, and terminal data is directly transmitted to the data center through the terminal device.
And secondly, constructing health indexes, namely after the collected data are transmitted to a data center, constructing the health indexes by a calculation center. The health index construction steps proposed by the technical scheme consist of three parts, namely performance feature extraction, performance deviation calculation and health index construction, and are shown in figure 3.
Optionally, the step of extracting a performance characteristic according to the device data, and obtaining a deviation index according to the performance characteristic to construct a health index includes:
preprocessing the equipment data and then extracting the performance characteristics;
constructing a performance model according to the performance characteristics and the influence factors;
calculating to obtain a performance deviation index according to the measured value of the performance index and the expected value of the performance index obtained by the performance model;
and constructing the health index according to the performance deviation index.
And (3) extracting performance characteristics, wherein the performance indexes are used for selecting data representing functions or performances of the system or the component as a data source for characteristic extraction, and the characteristic extraction method provides two modes. The method comprises the steps of firstly, extracting features based on a physical mechanism, and calculating feature indexes of the system or the component by combining the physical mechanism according to functions or performances of the system or the component. Such as engine speed, power, torque, fuel efficiency; flow rate of the pump, shaft power, efficiency, etc. Secondly, feature extraction of key statistical features, time domain and frequency domain features are calculated according to working conditions, operation and time periods, and the time domain features are as follows: mean, variance, waveform index, pulse index, margin index, etc., and the frequency domain characteristics are as follows: center of gravity frequency, mean square frequency, root mean square frequency, frequency variance, frequency standard deviation, etc.
Calculating deviation indexes, wherein the calculation of the deviation indexes is divided into two steps, and in the first step, a performance model is established; and secondly, calculating a performance deviation index.
The process of establishing the functional relation between the performance index and the influencing factors of the engineering equipment under an ideal state (no fault and no performance decline), namely the construction of a performance model. And in the performance modeling, the extracted performance characteristics are selected as dependent variables, the influence factors of the dependent variables are selected as independent variables, a regression model is established, and then the deviation between the actual value and the fitting value of the model is calculated to serve as a new characteristic index. The flow of the performance modeling build is shown in FIG. 4.
Optionally, the step of constructing a performance model according to the performance characteristics and the influencing factors includes:
preprocessing the equipment data to obtain the performance characteristics;
setting the performance characteristics and the influence factors thereof as variables of a performance model to construct the performance model;
evaluating the performance model;
if the evaluation is passed, performing model parameter optimization on the constructed performance model;
and if the evaluation fails, reconstructing the performance model.
Step 1, data preparation, namely preprocessing data and then extracting performance indexes and corresponding variables; and 2, selecting a proper model and an appropriate algorithm (possibly multiple types) to establish a performance model, 3, evaluating the model, determining the model and the algorithm (selecting one type), returning to the step 2 to adjust and optimize the parameters of the model, returning to the step 2 to repeatedly execute if the model is not evaluated, and 4, calculating the difference between an actually measured value and an expected value to form a performance deviation index.
The performance model reflects the ideal state of the system or equipment under various working conditions, is an important reference standard for evaluating the health state of the system or equipment, and is very important for establishing a proper performance model. The general form of performance modeling is illustrated as:
please refer to fig. 5.
The expected value of the reference system performance indicator may form a curve, commonly referred to as a baseline. In practice, the performance baseline may be a reference value, a curve, a set of curves, or even a distribution in the feature space. The baseline is suitable for scenes with obvious changes in working conditions and high change frequency.
The performance model (baseline) can be established in a number of different ways, and in general, the modeling methods can be divided into parametric methods and non-parametric methods. Parametric methods such as linear regression, logistic regression, perceptron, etc., and non-parametric methods such as decision trees, KNN, support vector machines, complex neural networks, etc.
The performance deviation index is calculated by subtracting the expected value of the performance index from the measured value of the performance index after the performance model is established,
as shown in fig. 6.
And (4) building a health index, and building the health index after the performance deviation calculation is completed. After the model is successfully constructed, calculating a deviation index S z . The magnitude of the performance deviation, i.e., the degree to which the true value deviates from the model baseline, the larger the absolute value of the deviation, the farther away from the model baseline the lower the score, and the smaller the absolute value of the deviation, the closer to the model baseline the lower the score. Generally, the health index is constructed by designing a reasonable mapping function to ensure that the health index falls within a specified interval. The mapping function includes, but is not limited to, a probability distribution function, a cracking function, and the like.
Considering the intuitiveness of the health index to the health state representation, the value of the health index is limited to a specific interval [0, 100], and the health index is healthier when the score is larger. Additionally, the health index should trend, typically decline, over time (engine hours, number of operating cycles, mileage, etc.) to meet the reality of system or component health degradation over time.
Optionally, the step of obtaining a current health indicator of the device according to the performance feature, and evaluating a health level of the device according to the health indicator includes:
acquiring health indexes of all parts of the equipment;
and synthesizing the health indexes of the components to judge a first health level of the equipment.
Optionally, the step of obtaining a current health indicator of the device according to the performance characteristic, and evaluating a health level of the device according to the health indicator further includes:
acquiring the failure rate and the maintenance grade of the equipment;
determining a second health level of the equipment based on the failure rate, the maintenance level, and the first health level of the equipment.
The first health grade is a fuzzy evaluation grade, and the second health grade is an accurate evaluation grade.
Optionally, after the step of obtaining a current health indicator of the device according to the performance characteristic and evaluating a health level of the device according to the health indicator, the method includes:
and judging the availability of the equipment according to the health level of the equipment, and confirming the task types which can be borne by the equipment so as to optimize the operation scheduling of the equipment.
And thirdly, health state evaluation is used for providing support for life prediction and operation and maintenance decisions of the system or the components, for example, the usability and the types of tasks which can be born are judged according to the health state of the system, and then operation scheduling is optimized. And judging whether maintenance measures are necessary or not according to the system health state evaluation result, and improving the response speed of maintenance decisions. The health status evaluation flow is shown in fig. 7.
When defining the health level, the health level needs to be defined as a level having the meaning of the actual service as far as possible from the actual operation and maintenance service, rather than simply and randomly divided. The health level may be generally defined by a failure rate, a level of maintenance activity.
Optionally, the step of predicting the remaining usable life of the device according to the health indicator comprises:
predicting the operable time of the equipment according to the health index and a given failure threshold value;
and predicting the remaining usable life of the equipment according to the working time and the current working time of the equipment.
The fourth step, remaining life prediction, is to predict the Remaining Usable Life (RUL). Generally, the number of times of operation, load time, and the like of a switch or a relay can be counted, and the remaining usable time is calculated in real time under the condition of a given limit value. For non-life parts or systems, a model is typically constructed to predict. The model prediction method is divided into two methods, namely residual usable life prediction based on reliability data and residual usable life prediction based on health indexes.
When the monitoring data are unavailable, based on a residual available life prediction model of the reliability data, a reliability model can be established by utilizing group data of the same type system working under similar environment and working condition conditions to estimate the average life, and then the RUL is calculated. For example: the weibull distribution is applicable to the description of the cumulative failure of most electromechanical products and the fatigue life distribution of metal materials.
In the context of big data, to make full use of the data, a remaining usable life prediction model based on health index may be employed. Firstly, performing performance modeling on a system, constructing a performance index, and constructing a deviation time sequence by calculating the deviation of expected values and measured values of the performance index, thereby converting the problem of predicting the residual usable life into a problem (1) of predicting the deviation time sequence of the performance index and a problem (2) of estimating failure time based on a prediction result and a given threshold value. As shown in fig. 8.
For the first problem, time series analysis (ARMA, etc.), machine learning (CNN, SVM, LSTM), etc. models can be used for prediction. In the specific prediction, a single-step or multi-step prediction method and the like can be adopted for long-term prediction. For the second problem, the predicted result can be obtained by comparing with a given threshold value on the basis of the predicted result. If uncertainty needs to be considered, and the prediction result is expressed as a prediction interval, the uncertainty needs to be modeled, so that the problem is complex.
And fifthly, generating a maintenance decision, and performing maintenance activity arrangement and making an optimal health management measure by combining the maintenance resource condition on the basis of health state evaluation and residual life prediction. The flow is shown in fig. 9.
Optionally, the step of establishing an optimal health management measure for the equipment based on the health level and/or remaining usable life of the equipment comprises
And re-confirming the health level and the remaining usable life of the equipment according to the feedback result of the maintenance activities.
According to the component-level predictive maintenance example of the rotary drilling rig, in the using process of the rotary drilling rig, an inner key plate of a power head, a power head sliding block and a main hoisting steel wire rope are irreversibly worn along with the increase of the using time, the wear loss and the replacement date are predicted through the predictive maintenance based on health indexes, maintenance resources are distributed in advance, and the advance maintenance and replacement are guided, so that the occurrence of faults is prevented, and risks and losses are reduced.
And establishing a relation among the abrasion loss, the load and the sliding distance according to the Archard abrasion model.
The overall flow of the component-level predictive maintenance of the rotary drilling rig is shown in fig. 10.
The method comprises the steps of establishing a wear characteristic, extracting the wear characteristic based on a wear formula, wherein after maintenance and maintenance activities are generated based on predictive maintenance of a health index, the health state evaluation model and the residual available life prediction model can be adjusted and optimized according to feedback results of the maintenance activities, the accuracy of the models is continuously improved, and finally a closed loop is formed.
Compared with the traditional method, the equipment predictive maintenance method based on the health index provided by the invention has the following advantages: 1. the failure rate is reduced, and the economic loss of companies and enterprises is reduced; 2. maintenance resources are guided to be reasonably arranged, and waste of the maintenance resources is avoided; 3. spare parts prediction based on life prediction is reasonably arranged in advance, and the inventory pressure of a warehouse is reduced. The method comprises the steps of predicting the remaining service life of equipment or components based on health indexes of the equipment or the components, evaluating the health grade of the equipment, pre-making a predictive maintenance plan according to the future development trend and possible failure modes of the equipment or the components, determining the time, content and mode of equipment repair and necessary technology and spare part support, reducing the failure rate, greatly improving the utilization efficiency of maintenance resources and reducing the non-reasonable spare part inventory pressure cost.
As shown in fig. 11, the health index-based equipment predictive maintenance system according to an embodiment of the present invention includes: the data acquisition module 10 is used for acquiring equipment data; the data processing module 20 is configured to preprocess the device data, and call the preprocessed device data to perform health index construction, health level evaluation, remaining life calculation, and maintenance decision generation; a health management module 30 for receiving the maintenance decisions to generate a maintenance plan. The health index-based equipment predictive maintenance system is used for executing the health index-based equipment predictive maintenance method in the embodiment.
In another embodiment, as shown in fig. 12, the health index-based equipment predictive maintenance system is composed of five parts, namely a sensor, a client, an edge, a cloud and a service center.
The sensor acquires construction state data of the mechanical equipment of the measured engineering, such as temperature, pressure, temperature, flow, vibration, noise, displacement, rotating speed and the like, and different sensors can be selected according to different monitoring requirements, cost requirements and the like aiming at vibration signals.
The client side and the man-machine interaction terminal, such as a mobile phone, a personal computer and the like, are used for recording maintenance records, dismounting and replacing pieces, maintenance suggestion feedback information and the like by after-sales service personnel.
And the edge end is composed of edge computing equipment, receives the data from the sensor, performs denoising and compression processing on the data, and transmits the data to the data center.
And the cloud end consists of a data center, a computing center and a management center, and is used for processing, computing, storing and pushing data from the edge end and the client end. And the data center decompresses the data from the edge end, transmits the data to the computing center, and stores a return result of the computing center. And the calculation center calls data of the data center, health index construction, health state evaluation, residual life calculation and maintenance decision generation are carried out, process results are pushed to the data center, and maintenance decisions are pushed to the service center. And the management center is used for monitoring the data center, the computing center and the edge computing equipment.
And the service center receives the maintenance decision activity result from the data center, pushes the maintenance decision activity result to an after-sales service department and carries out subsequent maintenance planning and arrangement.
The equipment predictive maintenance system based on the health index predicts the residual service life of the equipment or the components based on the health indexes of the equipment or the components, evaluates the health grade of the equipment, pre-formulates a predictive maintenance plan according to the future development trend and the possible failure modes of the equipment, determines the time, content and mode of equipment repair and necessary technology and spare part support, reduces the failure rate, greatly improves the utilization efficiency of maintenance resources and reduces the non-reasonable spare part inventory pressure cost.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the figures may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, in different orders, and may be performed alternately or at least partially with respect to other steps or sub-steps of other steps.
Through the above description of the embodiments, it is clear to those skilled in the art that the embodiments of the present invention may be implemented by hardware, or by software plus a necessary general hardware platform. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, or the like), and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, or the like) to execute the methods described in the embodiments of the present invention.
The present invention is not limited to the details of the above embodiments, which are exemplary, and the modules or processes in the drawings are not necessarily essential to the implementation of the embodiments of the present invention, and should not be construed as limiting the present invention.
Claims (10)
1. A method for predictive maintenance of equipment based on health indices, comprising:
obtaining device data, the device data comprising: operating condition data, maintenance data, and maintenance data;
extracting performance characteristics according to the equipment data, and acquiring deviation indexes according to the performance characteristics to construct health indexes;
acquiring a current health index of the equipment according to the performance characteristic, and evaluating a health grade of the equipment according to the health index;
predicting a remaining usable life of the device based on the health indicator;
and establishing the optimal health management measures of the equipment according to the health grade and/or the remaining usable life of the equipment.
2. The method of claim 1, wherein the step of extracting performance characteristics from the device data and obtaining deviation indicators from the performance characteristics for health indicator construction comprises:
preprocessing the equipment data and then extracting the performance characteristics;
constructing a performance model according to the performance characteristics and the influence factors;
calculating to obtain a performance deviation index according to the measured value of the performance index and the expected value of the performance index obtained by the performance model;
and constructing the health index according to the performance deviation index.
3. The method of claim 2, wherein the step of constructing a performance model based on the performance characteristics and influencing factors comprises:
preprocessing the equipment data to obtain the performance characteristics;
setting the performance characteristics and the influence factors thereof as variables of a performance model to construct the performance model;
evaluating the performance model;
if the evaluation is passed, performing model parameter optimization on the constructed performance model;
and if the evaluation fails, reconstructing the performance model.
4. The method of claim 1, wherein the step of obtaining a current health indicator of the device based on the performance characteristic and assessing a health level of the device based on the health indicator comprises:
acquiring health indexes of all parts of the equipment;
and synthesizing the health indexes of the components to judge a first health level of the equipment.
5. The method of claim 4, wherein the step of obtaining a current health indicator of the device based on the performance characteristic and assessing a health level of the device based on the health indicator further comprises:
acquiring the failure rate and the maintenance grade of the equipment;
and determining a second health level of the equipment according to the failure rate, the maintenance level and the first health level of the equipment.
6. The method of claim 1 or 4, wherein the step of obtaining a current health indicator of the device based on the performance characteristic and assessing a health level of the device based on the health indicator is followed by the step of:
and judging the availability of the equipment according to the health level of the equipment, and confirming the task types which can be borne by the equipment so as to optimize the operation scheduling of the equipment.
7. The method of claim 1, wherein the step of predicting the remaining usable life of the device based on the health indicator comprises:
predicting the operable time of the equipment according to the health index and a given failure threshold value;
and predicting the remaining usable life of the equipment according to the working time and the current working time of the equipment.
8. The method of claim 1, wherein said step of formulating an optimal health management measure for said equipment based on said equipment's health level and/or remaining usable life comprises
And re-confirming the health level and the remaining usable life of the equipment according to the feedback result of the maintenance activities.
9. A system for the predictive maintenance of equipment based on health indices of any of claims 1 to 8, comprising:
the data acquisition module is used for acquiring equipment data;
the data processing module is used for preprocessing the equipment data and calling the preprocessed equipment data to perform health index construction, health grade evaluation, residual life calculation and maintenance decision generation;
and the health management module is used for receiving the maintenance decision so as to generate a maintenance plan.
10. A readable storage medium, characterized in that the readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the health index based device predictive maintenance method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210469078.2A CN115018120A (en) | 2022-04-29 | 2022-04-29 | Predictive maintenance method, system and readable storage medium based on health index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210469078.2A CN115018120A (en) | 2022-04-29 | 2022-04-29 | Predictive maintenance method, system and readable storage medium based on health index |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115018120A true CN115018120A (en) | 2022-09-06 |
Family
ID=83067089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210469078.2A Pending CN115018120A (en) | 2022-04-29 | 2022-04-29 | Predictive maintenance method, system and readable storage medium based on health index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115018120A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115759408A (en) * | 2022-11-21 | 2023-03-07 | 贵州电网有限责任公司 | Power transmission and transformation equipment service life prediction method, device, equipment and storage medium |
-
2022
- 2022-04-29 CN CN202210469078.2A patent/CN115018120A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115759408A (en) * | 2022-11-21 | 2023-03-07 | 贵州电网有限责任公司 | Power transmission and transformation equipment service life prediction method, device, equipment and storage medium |
| CN115759408B (en) * | 2022-11-21 | 2024-03-08 | 贵州电网有限责任公司 | Power transmission and transformation equipment life prediction method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Louen et al. | A new framework for remaining useful life estimation using support vector machine classifier | |
| CN111915026B (en) | Fault processing method and device, electronic equipment and storage medium | |
| CN107403279B (en) | Oil transfer pump working condition self-adaptive state early warning system and method | |
| CN116992346A (en) | Enterprise production data processing system based on artificial intelligence big data analysis | |
| JP7475978B2 (en) | Maintenance improvement support device and maintenance improvement support method | |
| CN116909712A (en) | Intelligent task scheduling system and method based on machine learning | |
| CN115018120A (en) | Predictive maintenance method, system and readable storage medium based on health index | |
| CN118092242A (en) | Industrial robot state monitoring method and system of distributed intelligent network | |
| CN117422447A (en) | Transformer maintenance strategy generation method, system, electronic equipment and storage medium | |
| CN113805564A (en) | Equipment fault early warning and diagnosis system based on CEP | |
| CN116882756B (en) | Power safety control method based on block chain | |
| CN117592682A (en) | Supply chain risk monitoring method and system based on real-time audit data flow analysis system | |
| CN117523793A (en) | Power plant equipment fault early warning method and computer equipment | |
| CN116993215A (en) | Intelligent evaluation and early warning method and system for manufacturing quality of electric power equipment | |
| Bey-Temsamani et al. | A practical approach to combine data mining and prognostics for improved predictive maintenance | |
| Baker et al. | Degrader analysis for diagnostic and predictive capabilities: a demonstration of progress in DoD CBM+ initiatives | |
| Fernandez-Anakabe et al. | An attribute oriented induction based methodology for data driven predictive maintenance | |
| Schneider et al. | Implementation of maintenance strategies in the life cycle costing of product-service systems | |
| CN113076217A (en) | Disk fault prediction method based on domestic platform | |
| CN118296562B (en) | Digital twinning-based wind turbine generator health management method and system | |
| CN117708508B (en) | Method, device, equipment and storage medium for predicting service life of disconnecting switch | |
| CN118469405B (en) | Processing method, device, equipment and storage medium for household supply chain data | |
| CN117609740B (en) | Intelligent prediction maintenance system based on industrial large model | |
| CN117807129A (en) | Big data mining method and system based on application architecture | |
| CN117574303B (en) | Construction condition monitoring and early warning method, device, equipment and storage medium |
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 |