CN116402219A - Full life cycle operation and maintenance strategy method and device based on prediction model - Google Patents
Full life cycle operation and maintenance strategy method and device based on prediction model Download PDFInfo
- Publication number
- CN116402219A CN116402219A CN202310373427.5A CN202310373427A CN116402219A CN 116402219 A CN116402219 A CN 116402219A CN 202310373427 A CN202310373427 A CN 202310373427A CN 116402219 A CN116402219 A CN 116402219A
- Authority
- CN
- China
- Prior art keywords
- life cycle
- maintenance
- cycle operation
- prediction model
- full life
- 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
- 238000012423 maintenance Methods 0.000 title claims abstract description 142
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 54
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000013136 deep learning model Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 8
- 230000009471 action Effects 0.000 claims description 7
- 238000013079 data visualisation Methods 0.000 claims description 7
- 230000006399 behavior Effects 0.000 claims description 3
- 230000002035 prolonged effect Effects 0.000 abstract description 7
- 230000000875 corresponding effect Effects 0.000 description 18
- 238000012545 processing Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 206010011906 Death Diseases 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 230000000737 periodic effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000010687 lubricating oil Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
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)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the field of equipment maintenance, in particular to a full life cycle operation and maintenance strategy method and device based on a prediction model. The method and the device comprise the following steps: preprocessing the collected equipment data; constructing a bidirectional encoder prediction model based on a converter, inputting the preprocessed device data into the bidirectional encoder prediction model, and predicting the future state of the device by the bidirectional encoder prediction model; the full life cycle operation and maintenance platform is built, the bidirectional encoder prediction model is embedded into the full life cycle operation and maintenance platform, and the full life cycle operation and maintenance platform generates corresponding operation and maintenance strategies according to the future state of the equipment, so that enterprises can better manage the full life cycle of the equipment, the service life of the equipment is prolonged, and the operation and maintenance cost is reduced.
Description
Technical Field
The invention relates to the field of equipment maintenance, in particular to a full life cycle operation and maintenance strategy method and device based on a prediction model.
Background
Traditional full life cycle operation and maintenance strategies are mainly based on experience and periodic checks. The operation and maintenance personnel periodically check, maintain and repair the equipment according to the service time of the equipment, the maintenance record of the equipment and the operation state and maintenance requirement of the equipment judged by experience. Specifically, the traditional full lifecycle operation and maintenance strategy includes the following aspects:
1) Periodic inspection and maintenance: the operation and maintenance personnel can periodically check and maintain the equipment according to the instruction manual or experience of the equipment, such as replacing lubricating oil, cleaning the equipment, and the like.
2) And (3) periodically maintaining: routine maintenance of the equipment is performed on a regular basis, including replacement of wearing parts, adjustment of the equipment, etc.
3) And (3) fault maintenance: and (5) maintaining when the equipment fails.
4) Overhaul or update generation: when the equipment reaches a certain service life or cannot meet production requirements, overhaul or updating of the equipment is performed.
In addition, traditional full lifecycle operation and maintenance policies based on data driving are typically implemented by periodically checking devices and collecting various metrics. These indicators may include vibration, temperature, current, noise, etc. of the device. After the collected data is processed and analyzed, operation staff can be helped to know the operation state of the equipment, and operations such as maintenance, maintenance or replacement of parts can be performed according to the data, so that the service life of the equipment is prolonged.
The method has the advantages that the method can help operation staff to timely detect and diagnose equipment faults, and corresponding operation strategies are formulated according to data so as to protect the equipment to the greatest extent. In addition, since the data-driven method can make decisions based on the actual operating conditions of the device, device maintenance and management can be performed more efficiently.
However, conventional full life cycle operation and maintenance strategies based on experience and periodic checks suffer from the following drawbacks:
1) Relying on manual experience: experience-based operation and maintenance strategies often rely on experience and judgment of operation and maintenance personnel, which can lead to subjective judgment and misjudgment of operation and maintenance personnel, thereby affecting maintenance and use of equipment.
2) The maintenance cost is high: periodic inspection, maintenance, and repair require significant human, material, and time investment, which can increase the cost and complexity of maintenance.
3) Preventive maintenance shortages: traditional full life cycle operation and maintenance strategies are often maintained based on fixed time intervals, and accurate prediction and management of the actual operation state and service life of equipment cannot be performed.
4) Failure handling is not in time: traditional full life cycle operation and maintenance strategies may lead to untimely fault handling and reduced production efficiency due to the inability to accurately predict equipment failure and damage.
Thus, predictive full life cycle operation and maintenance strategies are becoming an increasingly popular option that can accurately predict the life and operational status of a device through data analysis and machine learning, thereby enabling more efficient and reliable maintenance and management of the device.
Meanwhile, the traditional full life cycle operation and maintenance strategy based on data driving has some defects. First, since data is typically obtained through manual inspection and recording, there is a risk of inaccuracy and incompleteness in the data collection. Second, because the data analysis and decision making process is typically done by personnel, there is a risk of subjectivity and human error. Finally, this approach typically requires a significant amount of time and resources to collect, process, and analyze the data, and thus may not be efficient and cost effective.
Disclosure of Invention
The embodiment of the invention provides a full life cycle operation and maintenance strategy method and device based on a prediction model, which are used for at least solving the technical problem of untimely equipment fault treatment.
According to an embodiment of the present invention, there is provided a full life cycle operation and maintenance policy method based on a prediction model, including the steps of:
s101, preprocessing collected equipment data;
s102, constructing a bidirectional encoder prediction model based on a converter, inputting preprocessed device data into the bidirectional encoder prediction model, and predicting the future state of the device by the bidirectional encoder prediction model;
and S103, constructing a full life cycle operation and maintenance platform, embedding a bidirectional encoder prediction model into the full life cycle operation and maintenance platform, and generating a corresponding operation and maintenance strategy by the full life cycle operation and maintenance platform according to the future state of the equipment.
Further, the method further comprises:
and S100, collecting equipment data.
Further, step S101 further includes:
and cleaning, converting and normalizing the preprocessed equipment data.
Further, step S101 further includes:
the device data is automatically stored in a reliable and secure location and set to an easy access and inquiry state.
Further, in step S102, further includes:
training the constructed bidirectional encoder prediction model, and inputting sufficient equipment data, wherein the equipment data contains enough samples to ensure that the bidirectional encoder prediction model learns the typical behavior and abnormal behavior of the equipment.
Further, the transformer-based bi-directional encoder processes time series data for a powerful deep learning model and learns complex feature representations.
Further, in step S103, the full lifecycle operations and maintenance platform provides real-time monitoring and analysis to detect abnormal behavior of the device and take action in time.
Further, in step S103, the full lifecycle operations and maintenance platform supports data visualization for users to better understand and analyze the data and to customize the analysis and reporting as needed.
According to another embodiment of the present invention, there is provided a full life cycle operation and maintenance policy apparatus based on a prediction model, including:
the preprocessing unit is used for preprocessing the acquired equipment data;
the model construction unit is used for constructing a bidirectional encoder prediction model based on the converter, inputting the preprocessed device data into the bidirectional encoder prediction model, and predicting the future state of the device by the bidirectional encoder prediction model;
the platform construction unit is used for constructing a full life cycle operation and maintenance platform, embedding the bidirectional encoder prediction model into the full life cycle operation and maintenance platform, and generating a corresponding operation and maintenance strategy by the full life cycle operation and maintenance platform according to the future state of the equipment.
Further, the apparatus further comprises:
the data acquisition unit is used for acquiring equipment data.
A storage medium storing a program file capable of implementing any one of the above full life cycle operation and maintenance policy methods based on a predictive model.
A processor for running a program, wherein the program executes any one of the above full life cycle operation and maintenance strategy methods based on the prediction model.
The full life cycle operation and maintenance strategy method and device based on the prediction model in the embodiment of the invention preprocess the collected equipment data; constructing a bidirectional encoder prediction model based on a converter, inputting the preprocessed device data into the bidirectional encoder prediction model, and predicting the future state of the device by the bidirectional encoder prediction model; the full life cycle operation and maintenance platform is built, the bidirectional encoder prediction model is embedded into the full life cycle operation and maintenance platform, and the full life cycle operation and maintenance platform generates corresponding operation and maintenance strategies according to the future state of the equipment, so that enterprises can better manage the full life cycle of the equipment, the service life of the equipment is prolonged, and the operation and maintenance cost is reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
FIG. 1 is a flow chart of a full life cycle operation and maintenance strategy method based on a predictive model of the present invention;
FIG. 2 is a preferred flow chart of the full lifecycle operation and maintenance strategy method of the present invention based on a predictive model;
FIG. 3 is a block diagram of a full life cycle operation and maintenance strategy device based on a predictive model according to the present invention;
FIG. 4 is a block diagram of a full life cycle operation and maintenance strategy device based on a predictive model according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
According to an embodiment of the present invention, a full life cycle operation and maintenance strategy method based on a prediction model is provided, referring to fig. 1, including the following steps:
s101, preprocessing collected equipment data;
s102, constructing a bidirectional encoder prediction model based on a converter, inputting preprocessed device data into the bidirectional encoder prediction model, and predicting the future state of the device by the bidirectional encoder prediction model;
and S103, constructing a full life cycle operation and maintenance platform, embedding a bidirectional encoder prediction model into the full life cycle operation and maintenance platform, and generating a corresponding operation and maintenance strategy by the full life cycle operation and maintenance platform according to the future state of the equipment.
The full life cycle operation and maintenance strategy method based on the prediction model in the embodiment of the invention carries out preprocessing on the collected equipment data; constructing a bidirectional encoder prediction model based on a converter, inputting the preprocessed device data into the bidirectional encoder prediction model, and predicting the future state of the device by the bidirectional encoder prediction model; the full life cycle operation and maintenance platform is built, the bidirectional encoder prediction model is embedded into the full life cycle operation and maintenance platform, and the full life cycle operation and maintenance platform generates corresponding operation and maintenance strategies according to the future state of the equipment, so that enterprises can better manage the full life cycle of the equipment, the service life of the equipment is prolonged, and the operation and maintenance cost is reduced.
Wherein, referring to fig. 2, the method further comprises:
and S100, collecting equipment data.
Wherein, step S101 further includes:
and cleaning, converting and normalizing the preprocessed equipment data.
Wherein, step S101 further includes:
the device data is automatically stored in a reliable and secure location and set to an easy access and inquiry state.
In step S102, the method further includes:
training the constructed bidirectional encoder prediction model, and inputting sufficient equipment data, wherein the equipment data contains enough samples to ensure that the bidirectional encoder prediction model learns the typical behavior and abnormal behavior of the equipment.
Wherein the transformer-based bi-directional encoder is a powerful deep learning model, processes time series data, and learns complex feature representations.
Wherein, in step S103, the full life cycle operation and maintenance platform provides real-time monitoring and analysis to detect abnormal behavior of the device and take action in time.
Wherein, in step S103, the full lifecycle operation and maintenance platform supports data visualization so that the user can better understand and analyze the data and customize the analysis and reporting as needed.
The full life cycle operation and maintenance strategy method based on the prediction model of the present invention is described in detail below with specific embodiments:
the technical scheme of the invention is specifically described as follows:
1. and (3) a data center: the method mainly relates to data acquisition, preprocessing, cleaning, conversion, normalization and the like. Since the quality and accuracy of the data is critical to the accuracy and reliability of the transducer-based bi-directional encoder prediction model, the data center can adaptively check and eliminate any errors and outliers that may affect the transducer-based bi-directional encoder prediction model. After processing the data, the data can also be automatically stored in a reliable and secure location and ensure that they are easy to access and query.
2. Bidirectional encoder prediction model based on transformer: this is the core keystone of the full lifecycle operation and maintenance strategy, which predicts the future lifetime of the device based on historical data. The transformer-based bi-directional encoder is a powerful deep learning model that can process time series data and learn complex feature representations. Before training the model, it is only necessary to ensure that the data set is sufficient and contains enough samples for the model to learn the typical and abnormal behavior of the device. After the model is trained, the model can be used for predicting the future state of the equipment, and corresponding operation and maintenance strategies are implemented according to the prediction result.
3. Full life cycle operation and maintenance platform: and executing the whole operation and maintenance strategy. And embedding the bidirectional encoder prediction model into a full life cycle operation and maintenance platform, and generating a corresponding operation and maintenance strategy according to a prediction result. For example, if the bi-directional encoder predictive model prediction device is about to reach an end-of-life stage, the full-lifecycle operation and maintenance platform may automatically alert the operation and maintenance personnel to perform the necessary overhaul or replacement of components, etc. The full lifecycle operation and maintenance platform can also provide real-time monitoring and analysis to detect abnormal behavior of the device and take action in time. Finally, the full lifecycle operations and maintenance platform also supports data visualization so that users can better understand and analyze data and customize analysis and reporting as needed.
In the technical scheme of the invention, three key implementation steps are provided:
1. establishing a data center: the data center is the first step in the data analysis flow. The method mainly comprises the operations of data acquisition, preprocessing, cleaning, conversion, normalization and the like. The goal of this step is to eliminate problems of outliers, missing values, etc. in the data and to ensure data quality and accuracy. After processing the data, it is necessary to store the data in a reliable and secure location for subsequent use.
2. Training a bi-directional encoder prediction model based on a transformer: the historical data is used to predict future life of the device, and the trained model uses a bi-directional encoder based on a transducer, which is a powerful deep learning model that can be used to process time series data and learn complex feature representations. Before training the model, it is necessary to ensure that the data set is adequate and contains enough samples to enable the model to learn the typical and abnormal behavior of the device. After training, the model can be used for predicting the future state of the equipment and implementing corresponding operation and maintenance strategies.
3. Full life cycle operation and maintenance platform: the platform is an execution part of the operation and maintenance strategy, and a bidirectional encoder prediction model can be embedded into the platform, and a corresponding operation and maintenance strategy can be generated according to a prediction result of the bidirectional encoder prediction model. For example, if the model predicts that the device will reach an end-of-life stage, the platform may automatically alert the service personnel to perform the necessary overhaul or replacement of the components, etc. The platform may also provide real-time monitoring and analysis to detect abnormal behavior of the device and take action in time. Finally, the platform also supports data visualization so that users can better understand and analyze the data and customize the analysis and reporting as needed.
The technical scheme of the invention has the main technical advantages and innovation points that:
1. the operation and maintenance strategy based on prediction is provided, so that enterprises can be helped to better manage the whole life cycle of equipment, the service life of the equipment is prolonged, and the operation and maintenance cost is reduced.
2. The historical data is processed by the centralized data center, the service life of future equipment is predicted, and the accuracy and reliability of prediction can be improved.
3. By using the deep learning model, the typical and abnormal behaviors of the equipment can be learned, and the generalization capability and accuracy of the model are improved.
4. The real-time monitoring and analyzing function is provided, so that abnormal behaviors of the equipment can be found in time, and corresponding actions can be taken.
Example 2
According to another embodiment of the present invention, there is provided a full life cycle operation and maintenance policy apparatus based on a prediction model, referring to fig. 3, including:
a preprocessing unit 201, configured to preprocess collected device data;
a model construction unit 202 for constructing a bidirectional encoder prediction model based on the transformer, inputting the preprocessed device data into the bidirectional encoder prediction model, and predicting a future state of the device by the bidirectional encoder prediction model;
the platform construction unit 203 is configured to construct a full-life-cycle operation and maintenance platform, embed the bidirectional encoder prediction model into the full-life-cycle operation and maintenance platform, and generate a corresponding operation and maintenance policy according to the future state of the device by the full-life-cycle operation and maintenance platform.
The full life cycle operation and maintenance strategy device based on the prediction model in the embodiment of the invention carries out preprocessing on the collected equipment data; constructing a bidirectional encoder prediction model based on a converter, inputting the preprocessed device data into the bidirectional encoder prediction model, and predicting the future state of the device by the bidirectional encoder prediction model; the full life cycle operation and maintenance platform is built, the bidirectional encoder prediction model is embedded into the full life cycle operation and maintenance platform, and the full life cycle operation and maintenance platform generates corresponding operation and maintenance strategies according to the future state of the equipment, so that enterprises can better manage the full life cycle of the equipment, the service life of the equipment is prolonged, and the operation and maintenance cost is reduced.
Wherein, referring to fig. 4, the device further comprises:
the data acquisition unit 200 is configured to acquire device data.
The following describes the full life cycle operation and maintenance strategy device based on the prediction model in detail by using a specific embodiment:
the technical scheme of the invention is specifically described as follows:
1. and (3) a data center: the preprocessing unit 201 mainly relates to acquisition, preprocessing, cleaning, conversion, normalization, and the like of data. Since the quality and accuracy of the data is critical to the accuracy and reliability of the transducer-based bi-directional encoder prediction model, the data center can adaptively check and eliminate any errors and outliers that may affect the transducer-based bi-directional encoder prediction model. After processing the data, the data can also be automatically stored in a reliable and secure location and ensure that they are easy to access and query.
2. Model construction unit 202 constructs a bidirectional encoder prediction model based on the transformer: this is the core keystone of the full lifecycle operation and maintenance strategy, which predicts the future lifetime of the device based on historical data. The transformer-based bi-directional encoder is a powerful deep learning model that can process time series data and learn complex feature representations. Before training the model, it is only necessary to ensure that the data set is sufficient and contains enough samples for the model to learn the typical and abnormal behavior of the device. After the model is trained, the model can be used for predicting the future state of the equipment, and corresponding operation and maintenance strategies are implemented according to the prediction result.
3. Platform construction unit 203, constructs full life cycle operation and maintenance platform: and executing the whole operation and maintenance strategy. And embedding the bidirectional encoder prediction model into a full life cycle operation and maintenance platform, and generating a corresponding operation and maintenance strategy according to a prediction result. For example, if the bi-directional encoder predictive model prediction device is about to reach an end-of-life stage, the full-lifecycle operation and maintenance platform may automatically alert the operation and maintenance personnel to perform the necessary overhaul or replacement of components, etc. The full lifecycle operation and maintenance platform can also provide real-time monitoring and analysis to detect abnormal behavior of the device and take action in time. Finally, the full lifecycle operations and maintenance platform also supports data visualization so that users can better understand and analyze data and customize analysis and reporting as needed.
In the technical scheme of the invention, three key implementation steps are provided:
1. establishing a data center: the data center is the first step in the data analysis flow. The method mainly comprises the operations of data acquisition, preprocessing, cleaning, conversion, normalization and the like. The goal of this step is to eliminate problems of outliers, missing values, etc. in the data and to ensure data quality and accuracy. After processing the data, it is necessary to store the data in a reliable and secure location for subsequent use.
2. Training a bi-directional encoder prediction model based on a transformer: the historical data is used to predict future life of the device, and the trained model uses a bi-directional encoder based on a transducer, which is a powerful deep learning model that can be used to process time series data and learn complex feature representations. Before training the model, it is necessary to ensure that the data set is adequate and contains enough samples to enable the model to learn the typical and abnormal behavior of the device. After training, the model can be used for predicting the future state of the equipment and implementing corresponding operation and maintenance strategies.
3. Full life cycle operation and maintenance platform: the platform is an execution part of the operation and maintenance strategy, and a bidirectional encoder prediction model can be embedded into the platform, and a corresponding operation and maintenance strategy can be generated according to a prediction result of the bidirectional encoder prediction model. For example, if the model predicts that the device will reach an end-of-life stage, the platform may automatically alert the service personnel to perform the necessary overhaul or replacement of the components, etc. The platform may also provide real-time monitoring and analysis to detect abnormal behavior of the device and take action in time. Finally, the platform also supports data visualization so that users can better understand and analyze the data and customize the analysis and reporting as needed.
The technical scheme of the invention has the main technical advantages and innovation points that:
1. the operation and maintenance strategy based on prediction is provided, so that enterprises can be helped to better manage the whole life cycle of equipment, the service life of the equipment is prolonged, and the operation and maintenance cost is reduced.
2. The historical data is processed by the centralized data center, the service life of future equipment is predicted, and the accuracy and reliability of prediction can be improved.
3. By using the deep learning model, the typical and abnormal behaviors of the equipment can be learned, and the generalization capability and accuracy of the model are improved.
4. The real-time monitoring and analyzing function is provided, so that abnormal behaviors of the equipment can be found in time, and corresponding actions can be taken.
Example 3
A storage medium storing a program file capable of implementing any one of the above full life cycle operation and maintenance policy methods based on a predictive model.
Example 4
A processor for running a program, wherein the program executes any one of the above full life cycle operation and maintenance strategy methods based on the prediction model.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
In the foregoing embodiments of the present invention, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed technology content may be implemented in other manners. The system embodiments described above are merely exemplary, and for example, the division of units may be a logic function division, and there may be another division manner in actual implementation, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method of the various embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.
Claims (10)
1. The full life cycle operation and maintenance strategy method based on the prediction model is characterized by comprising the following steps of:
s101, preprocessing collected equipment data;
s102, constructing a bidirectional encoder prediction model based on a converter, inputting preprocessed device data into the bidirectional encoder prediction model, and predicting the future state of the device by the bidirectional encoder prediction model;
and S103, constructing a full life cycle operation and maintenance platform, embedding a bidirectional encoder prediction model into the full life cycle operation and maintenance platform, and generating a corresponding operation and maintenance strategy by the full life cycle operation and maintenance platform according to the future state of the equipment.
2. The full life cycle operation and maintenance strategy method based on predictive model of claim 1, further comprising:
and S100, collecting equipment data.
3. The full life cycle operation and maintenance strategy method based on the predictive model as claimed in claim 1, wherein the step S101 further comprises:
and cleaning, converting and normalizing the preprocessed equipment data.
4. The full life cycle operation and maintenance strategy method based on the predictive model as claimed in claim 1, wherein the step S101 further comprises:
the device data is automatically stored in a reliable and secure location and set to an easy access and inquiry state.
5. The full life cycle operation and maintenance strategy method based on the predictive model as claimed in claim 1, further comprising, in step S102:
training the constructed bidirectional encoder prediction model, and inputting sufficient equipment data, wherein the equipment data contains enough samples to ensure that the bidirectional encoder prediction model learns the typical behavior and abnormal behavior of the equipment.
6. The full life cycle operation and maintenance strategy method based on predictive model as claimed in claim 1, wherein the bi-directional encoder based on the transformer is a powerful deep learning model, processes time series data, and learns complex feature representations.
7. The full life cycle operation and maintenance policy method based on predictive model as claimed in claim 1, wherein in step S103, the full life cycle operation and maintenance platform provides real time monitoring and analysis to detect abnormal behavior of the device and take action in time.
8. The full lifecycle operation and maintenance strategy method based on the predictive model as set forth in claim 1, wherein in step S103 the full lifecycle operation and maintenance platform supports data visualization for the user to better understand and analyze the data and to customize the analysis and reporting as needed.
9. A full life cycle operation and maintenance strategy device based on a predictive model, comprising:
the preprocessing unit is used for preprocessing the acquired equipment data;
the model construction unit is used for constructing a bidirectional encoder prediction model based on the converter, inputting the preprocessed device data into the bidirectional encoder prediction model, and predicting the future state of the device by the bidirectional encoder prediction model;
the platform construction unit is used for constructing a full life cycle operation and maintenance platform, embedding the bidirectional encoder prediction model into the full life cycle operation and maintenance platform, and generating a corresponding operation and maintenance strategy by the full life cycle operation and maintenance platform according to the future state of the equipment.
10. The predictive model-based full lifecycle operational policy apparatus of claim 9, further comprising:
the data acquisition unit is used for acquiring equipment data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310373427.5A CN116402219A (en) | 2023-03-29 | 2023-03-29 | Full life cycle operation and maintenance strategy method and device based on prediction model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310373427.5A CN116402219A (en) | 2023-03-29 | 2023-03-29 | Full life cycle operation and maintenance strategy method and device based on prediction model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116402219A true CN116402219A (en) | 2023-07-07 |
Family
ID=87008641
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310373427.5A Pending CN116402219A (en) | 2023-03-29 | 2023-03-29 | Full life cycle operation and maintenance strategy method and device based on prediction model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116402219A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110728443A (en) * | 2019-09-30 | 2020-01-24 | 鞍钢集团自动化有限公司 | Motor full life cycle management and control system |
| KR102226687B1 (en) * | 2019-11-20 | 2021-03-11 | (주)위세아이텍 | Apparatus and method of remaining maintenance cycle prediction based on times series prediction using deep learning |
| CN113094200A (en) * | 2021-06-07 | 2021-07-09 | 腾讯科技（深圳）有限公司 | Application program fault prediction method and device |
| CN114492174A (en) * | 2022-01-07 | 2022-05-13 | 北京科技大学 | Full life cycle shield tunneling parameter prediction method and device |
| CN115617554A (en) * | 2022-10-09 | 2023-01-17 | 阿里云计算有限公司 | System fault prediction method, device, equipment and medium based on time perception |
| CN115758225A (en) * | 2023-01-06 | 2023-03-07 | 中建科技集团有限公司 | Fault prediction method and device based on multi-mode data fusion and storage medium |
-
2023
- 2023-03-29 CN CN202310373427.5A patent/CN116402219A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110728443A (en) * | 2019-09-30 | 2020-01-24 | 鞍钢集团自动化有限公司 | Motor full life cycle management and control system |
| KR102226687B1 (en) * | 2019-11-20 | 2021-03-11 | (주)위세아이텍 | Apparatus and method of remaining maintenance cycle prediction based on times series prediction using deep learning |
| CN113094200A (en) * | 2021-06-07 | 2021-07-09 | 腾讯科技（深圳）有限公司 | Application program fault prediction method and device |
| CN114492174A (en) * | 2022-01-07 | 2022-05-13 | 北京科技大学 | Full life cycle shield tunneling parameter prediction method and device |
| CN115617554A (en) * | 2022-10-09 | 2023-01-17 | 阿里云计算有限公司 | System fault prediction method, device, equipment and medium based on time perception |
| CN115758225A (en) * | 2023-01-06 | 2023-03-07 | 中建科技集团有限公司 | Fault prediction method and device based on multi-mode data fusion and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102092185B1 (en) | Platform for analyzing electric motor health and analysis method using the same | |
| US6947797B2 (en) | Method and system for diagnosing machine malfunctions | |
| EP1254402B1 (en) | Method and system for analyzing continuous parameter data for diagnostics and repairs | |
| CN106598791B (en) | Industrial equipment fault preventive identification method based on machine learning | |
| CN1991652A (en) | Automatic remote monitoring and diagnostics system and communication method for communicating between a programmable logic controller and a central unit | |
| CN116596322B (en) | Property equipment management method and system based on big data visualization | |
| KR20190021560A (en) | Failure prediction system using big data and failure prediction method | |
| US20170169342A1 (en) | System and method for diagnosing at least one component requiring maintenance in an appliance and/or installation | |
| CN115225463B (en) | Hardware fault monitoring method and system based on IT operation and maintenance | |
| US20040073843A1 (en) | Diagnostics using information specific to a subsystem | |
| Calabrese et al. | An event based machine learning framework for predictive maintenance in industry 4.0 | |
| CN117474357A (en) | Power distribution room operation and maintenance management method and system based on deep learning | |
| CN111367909A (en) | Health management method and system of intelligent manufacturing equipment | |
| Devaney et al. | Case-Based Reasoning for Gas Turbine Diagnostics. | |
| CN117592975A (en) | Operation and maintenance decision processing method and system for electromechanical equipment of expressway based on cloud computing | |
| Zappalá et al. | 2.11-Wind Turbine Reliability-Maintenance Strategies | |
| CN116975639A (en) | Abnormality prevention and control system and method for equipment | |
| CN116992346A (en) | Enterprise production data processing system based on artificial intelligence big data analysis | |
| CN116402219A (en) | Full life cycle operation and maintenance strategy method and device based on prediction model | |
| Beduschi et al. | Optimizing rotating equipment maintenance through machine learning algorithm | |
| JP2019191880A (en) | Equipment management support system | |
| Kumar et al. | An expert system for predictive maintenance of mining excavators and its various forms in open cast mining | |
| KR102667861B1 (en) | heavy electrical equipment treatment apparatus using deep learning-based prediction model and method therefor | |
| CN117272844B (en) | Method and system for predicting service life of distribution board | |
| Karami et al. | Smart predictive maintenance strategy based on cyber-physical systems for centrifugal pumps: A bearing vibration analysis |
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 |