Factory equipment asset maintenance management method and device, terminal and storage medium

Abstract

The invention discloses a factory equipment asset maintenance management method and device, a terminal and a storage medium, and the method comprises the steps: building a centralized equipment management platform, obtaining a digital file of each piece of equipment, and collecting the equipment operation data of the current equipment in real time through sensor equipment; key features of the devices are extracted from the device operation data, historical fault information in the digital archive is combined for training to obtain a fault prediction model, and a fault prediction result of each device is obtained according to the fault prediction model and the device operation data; comparing the fault prediction result with a preset health assessment standard to obtain a health assessment result of each device, and generating a maintenance suggestion of each device according to the health assessment result; and converting the maintenance suggestion of each device into a maintenance work order, and updating the digital file of the corresponding device according to the maintenance result of the maintenance work order. According to the method provided by the invention, comprehensive and real-time monitoring of all equipment is realized, and the timeliness and accuracy of equipment maintenance are improved.

Description

Technical Field

[0001] The present application relates to the field of factory equipment asset management, and in particular to a factory equipment asset maintenance management method, device, terminal and storage medium. Background Art

[0002] Factory equipment asset maintenance management is an indispensable part of modern industrial production. With the transformation of manufacturing industry towards intelligence and digitalization, the importance of equipment asset management has become increasingly prominent. At present, more and more companies are beginning to introduce advanced information technology and automation tools to optimize equipment maintenance processes, thereby achieving more efficient and accurate maintenance management.

[0003] In the existing equipment maintenance management model, common methods include regular inspections, preventive maintenance, and post-repair. Among them, regular inspections usually involve manual inspections and manual recording of equipment status. Although some problems can be discovered in a timely manner, it is often difficult to accurately predict potential failures due to the lack of real-time monitoring and data analysis support. Preventive maintenance mainly relies on experience to formulate maintenance plans. Although it can reduce the frequency of sudden failures, it may also lead to over-maintenance or under-maintenance. Post-repair is to deal with failures that have already occurred. This model will not only cause production line interruptions, but may also cause huge economic losses due to frequent downtime.

[0004] However, the above traditional methods generally have problems such as the inability to achieve real-time monitoring, low data utilization, and unscientific maintenance decisions. Especially when facing complex and diverse equipment groups, how to effectively integrate the data resources of various types of equipment and use big data analysis and artificial intelligence technology for fault prediction and health management has become a technical problem that needs to be solved urgently. Therefore, it is particularly necessary to develop an advanced equipment maintenance management system that can integrate multiple functions. Summary of the invention

[0005] In order to solve the above problems, the present application provides a factory equipment asset maintenance management method, device, terminal and storage medium.

[0006] In the first aspect, the present application provides a method for plant equipment asset maintenance management, which adopts the following technical solution: A factory equipment asset maintenance management method comprises the following steps: Establish a centralized equipment management platform, which is connected to all equipment, obtains the digital archive of each equipment, collects the equipment operation data of the current equipment in real time through sensor equipment, and updates it to the digital archive; Extracting key features of the equipment from the equipment operation data, combining them with historical fault information in the digital archive to train a fault prediction model, and obtaining a fault prediction result for each of the equipment based on the fault prediction model and the equipment operation data; Compare the fault prediction result with a preset health assessment standard to obtain a health assessment result of each of the devices, and generate maintenance recommendations for each of the devices based on the health assessment result; The maintenance suggestion for each of the devices is converted into a maintenance work order, the maintenance work order is added to a maintenance task queue for maintenance, and the digital file of the corresponding device is updated according to the maintenance result of the maintenance work order.

[0007] By adopting the above technical solutions, potential faults can be identified in advance through the fault prediction model, which effectively improves the reliability and stability of the equipment. Combining the health assessment standards and generating corresponding maintenance suggestions helps to formulate scientific and reasonable maintenance plans, convert maintenance suggestions into specific maintenance work orders and prioritize them, optimize the allocation and utilization efficiency of maintenance resources, further improve the work efficiency of equipment management and maintenance, and realize comprehensive and real-time monitoring and management of factory equipment.

[0008] Preferably, extracting the key features of the device from the device operation data, combining with the historical fault information in the digital archive to train a fault prediction model, and obtaining the fault prediction result of each device according to the fault prediction model and the device operation data specifically includes the following steps: Preprocessing the device operation data, extracting key features of the device from the preprocessed device operation data according to a feature extraction technology, and obtaining a feature subset of the device from the key features by a preset feature selection method; According to the preset machine learning algorithm, the feature subset and the historical fault information extracted from the digital archive are combined to train a fault prediction model, and the equipment operation data of all the equipment are input into the fault prediction model to obtain the fault prediction results of each equipment.

[0009] By adopting the above technical solution, the fault prediction model obtained by training with the preset machine learning algorithm combined with historical fault information not only takes into account the current equipment operation status, but also integrates past experience and knowledge, so that the model can show high prediction accuracy in many cases. The operation data of all equipment is input into the optimized fault prediction model, which realizes the accurate prediction of possible problems of each equipment in the future.

[0010] Preferably, comparing the fault prediction result with a preset health assessment standard to obtain a health assessment result of each device specifically includes the following steps: Compare the fault prediction results with preset health assessment criteria, the fault prediction results including the failure probability and remaining life of each of the devices, When the fault prediction result is the fault probability, the fault probability is compared with a preset fault probability threshold, and when the fault prediction result exceeds the fault probability threshold, the health assessment result of the current device is a probability failure; When the fault prediction result is the remaining life, the remaining life is compared with a preset remaining life threshold, and when the remaining life is less than the remaining life threshold, the current health assessment result of the device is that the life is unqualified.

[0011] By adopting the above technical solution, by comparing the failure probability and remaining life in the fault prediction results with the preset threshold value, this multi-objective prediction method can provide more comprehensive and accurate information support for the efficient management and maintenance of equipment, which helps to reduce the failure rate, extend the service life of equipment and improve the overall operational efficiency.

[0012] Preferably, after obtaining the health assessment result of each of the devices, the following steps are also included: The devices that have failed the lifespan test are grouped as first devices, and the devices that have failed the probability test are grouped as second devices. Based on the health assessment result, all the devices are prioritized. The priority ranking rule is: Setting the priority of the first device to be higher than the priority of the second device; For the first device that fails both the life span and the probability, assigning a priority according to the failure probability, and giving a higher priority to the first device with a higher failure probability; For the second device, a priority is assigned according to the failure probability, and a second device with a higher failure probability is given a higher priority.

[0013] By adopting the above technical solution, the fault prediction results are classified and prioritized in detail to ensure that those devices with unqualified life problems are handled first, thereby avoiding the risk of production interruption due to sudden equipment failure. For the first device that has both unqualified life and unqualified probability, the priority is further assigned according to the failure probability, so that the equipment that needs more urgent attention can be maintained in time, improving the response speed and resource utilization efficiency. For the second device that only has unqualified probability, the priority is also assigned according to the failure probability, ensuring that all potential risks that may affect production can be effectively controlled. It can effectively improve the efficiency and accuracy of equipment maintenance management.

[0014] Preferably, generating maintenance recommendations for each of the devices based on the health assessment results specifically includes the following steps: Determine the maintenance method of the equipment according to the fault type and equipment characteristics of each equipment, the equipment characteristics are recorded in the digital file, the fault type is determined according to the equipment characteristics, and the maintenance method includes predictive maintenance and post-maintenance; Generate a maintenance plan for each of the devices according to the result of the priority sorting, wherein the maintenance plan includes maintenance time, maintenance items, and maintenance resources; A maintenance suggestion for each of the devices is obtained according to the maintenance plan.

[0015] By adopting the above technical solutions, the maintenance method suitable for each device can be accurately determined according to the failure type and device characteristics of the equipment, effectively improving the maintenance efficiency and accuracy. A maintenance plan is generated based on the results of priority sorting to ensure that high-priority equipment is maintained first, optimize resource allocation, and improve the reliability and stability of the entire system.

[0016] Preferably, converting the maintenance suggestion for each device into a maintenance work order, and adding the maintenance work order to a maintenance task queue for maintenance, specifically comprises the following steps: Generate an estimated completion time based on the maintenance time, generate a maintenance task based on the maintenance item, generate a required resource list based on the maintenance resources, and generate a corresponding maintenance work order based on the estimated completion time, the maintenance task and the required resource list; The maintenance work order is added to a maintenance task queue, and the maintenance work order is allocated according to the required resource list, the device characteristics, and the priority of the device corresponding to the maintenance work order.

[0017] By adopting the above technical solution, the maintenance suggestions for each device are converted into specific maintenance work orders, and they are added to the maintenance task queue in an orderly manner for management and execution. Through the reasonable allocation of maintenance work orders, the allocation strategy of maintenance work orders is optimized, so that high-priority equipment can obtain maintenance support faster, effectively utilize existing resources, improve maintenance efficiency, and thus improve the overall management level of the entire factory equipment assets.

[0018] Preferably, updating the digital file of the corresponding device according to the maintenance result of the maintenance work order specifically includes the following steps: When the real-time status of the maintenance work order is changed to received, the real-time status of the maintenance work order is tracked in real time; When the real-time status of the maintenance work order changes to completed, the maintenance result of the maintenance work order is obtained and reviewed, and the digital file and health assessment result of the current device are updated according to the review result, wherein the digital file includes the historical maintenance record of the device; When the audit result is passed, the real-time status of the maintenance work order is marked as closed, and the maintenance work order is removed from the maintenance task queue.

[0019] By adopting the above technical solutions, we can achieve full tracking and management of maintenance work orders, ensure that each maintenance link is traceable, and strictly review the maintenance results after the maintenance is completed to prevent erroneous information from affecting subsequent health management decisions. Finally, through the closed-loop management of completed business, work efficiency is effectively improved, redundant workload is reduced, and the entire asset management process is more standardized and efficient.

[0020] In the second aspect, the present application provides a factory equipment asset maintenance management device, which adopts the following technical solution: A factory equipment asset maintenance management device includes the following modules: A data acquisition module is used to establish a centralized equipment management platform, which is connected to all the equipment, obtain the digital archive of each of the equipment, collect the equipment operation data of the current equipment in real time through the sensor equipment, and update it to the digital archive; A fault prediction module is used to extract key features of the device from the device operation data, train a fault prediction model based on the historical fault information in the digital archive, and obtain a fault prediction result for each device based on the fault prediction model and the device operation data; A health assessment module, used to compare the fault prediction result with a preset health assessment standard to obtain a health assessment result of each of the devices, and generate maintenance recommendations for each of the devices based on the health assessment result; The work order management module is used to convert the maintenance suggestion of each device into a maintenance work order, add the maintenance work order to the maintenance task queue for maintenance, and update the digital file of the corresponding device according to the maintenance result of the maintenance work order.

[0021] By adopting the above technical solutions, the centralized equipment management platform connects all devices and collects equipment operation data in real time, ensuring comprehensive monitoring and timely updating of equipment status. At the same time, a complete equipment maintenance system is built, which provides the necessary software and technical support for the stable operation of equipment and the improvement of production efficiency, and realizes the centralized management and intelligent maintenance of factory equipment.

[0022] In a third aspect, the present application provides a smart terminal, which adopts the following technical solution: An intelligent terminal includes a memory and a processor, wherein the memory stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by the processor to implement the factory equipment asset maintenance management method as described above.

[0023] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium, wherein at least one instruction, at least one program, code set or instruction set is stored in the computer-readable storage medium, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement the factory equipment asset maintenance management method as described above.

[0024] In summary, this application has at least the following beneficial effects: 1. This application realizes comprehensive and real-time monitoring of all equipment by establishing a centralized equipment management platform to collect and update equipment operation data and digital archives in real time, thereby improving the timeliness and accuracy of equipment maintenance.

[0025] 2. This application utilizes a fault prediction model combined with historical fault information to predict equipment failures in advance and generate health assessment results, thereby avoiding the problem of over-maintenance or under-maintenance caused by lack of foresight in traditional methods and improving equipment reliability.

[0026] 3. This application converts health assessment results into specific maintenance recommendations and generates maintenance work orders by priority, making maintenance work more targeted and efficient, reducing unnecessary downtime and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 is a flow chart of the factory equipment asset maintenance management method of this embodiment; Figure 2 is a flow chart of step S3 of the factory equipment asset maintenance management method of this embodiment; Figure 3 This is an architectural diagram of the factory equipment asset maintenance management device of this embodiment. DETAILED DESCRIPTION

[0028] The present application provides a factory equipment asset maintenance management method, device, terminal and storage medium. In order to make the purpose, technical solution and advantages of the present application clearer, the implementation method of the present application will be further described in detail below.

[0029] The following is a further detailed description of an embodiment of a factory equipment asset maintenance management method of the present application in conjunction with the drawings in the specification.

[0030] A factory equipment asset maintenance management method of the present application, such as Figure 1 As shown, the following steps are included: S1. Establish a centralized equipment management platform. The centralized management platform is connected to all equipment and obtains the digital archive of each equipment. The digital archive includes the basic information, technical parameters and historical maintenance records of the current equipment. The equipment operation data of the current equipment is collected in real time through sensor equipment and updated to the digital archive. The specific steps include the following: S11. Establish a centralized equipment management platform that connects all implemented equipment.

[0031] This platform can be a cloud server or a local server, connected to the equipment in each production workshop in the factory through the network. The main function of the platform is to collect and store the digital archives of each device, which include the basic information, technical parameters and historical maintenance records of the current equipment. The basic information includes the equipment type, equipment model and manufacturer, the technical parameters include power, speed and other parameter data, and the historical maintenance records include the previous maintenance date and maintenance content.

[0032] To achieve this goal, sensor devices are installed on each device to collect real-time equipment operation data of each device, including temperature, pressure and vibration signals, and transmit these data to the central equipment management platform.

[0033] S12. Obtain the digital archive of each device, and collect the device operation data through sensors in real time, and update the collected device operation data into the digital archive.

[0034] S2. Extract key features of the equipment from the equipment operation data, combine them with the historical fault information in the digital archive to train a fault prediction model, and obtain the fault prediction results of each equipment based on the fault prediction model and equipment operation data, which specifically includes the following steps: S21. Preprocess the equipment operation data, including cleaning and normalization, to remove noise and outliers, so as to make the data more representative and convenient for subsequent analysis.

[0035] S22. Extract key features of the equipment from the preprocessed equipment operation data based on feature extraction technology.

[0036] The feature extraction method of this embodiment is to use statistical methods to calculate the mean, variance and peak index of each physical quantity, and select the features closely related to the device status. In addition, advanced methods such as spectrum analysis and phase space reconstruction can also be used to explore hidden patterns and trends.

[0037] S23. The feature subset of the equipment is obtained from the key features by using a preset feature selection method. The most representative feature subset is selected by using evaluation indicators such as correlation coefficient and mutual information to reduce unnecessary dimensions in the subsequent modeling process.

[0038] S24. According to the preset machine learning algorithm, this embodiment adopts a support vector machine (SVM). SVM has a powerful classification capability and can be used for fault type judgment.

[0039] By combining the feature subset and the historical fault information extracted from the digital archives, a fault prediction model is trained. This fault prediction model is actually a multi-objective prediction model that can learn the mapping relationship between the normal operating state and the fault state of the equipment, and can accurately capture the dynamic changes of the equipment state and the diversity of failure modes.

[0040] S25. Input the equipment operation data of all equipment into the fault prediction model. The fault prediction model will output the fault prediction results of each equipment according to the input data.

[0041] The failure prediction results include the failure probability and remaining life of each device; the failure probability indicates the possibility of a device failing within a given time, and the remaining life indicates the predicted time required for the device to completely fail from its current state.

[0042] S3. Compare the fault prediction results with the preset health assessment standards to obtain the health assessment results of each device, and generate maintenance recommendations for each device based on the health assessment results, such as Figure 2 As shown, the specific steps include: S31, comparing the fault prediction result with the preset health assessment standard, specifically comparing the fault probability and the remaining life in the fault prediction result with the health assessment standard.

[0043] S311. When the fault prediction result is a fault probability, the health assessment standard is based on a preset fault probability threshold, and the fault probability is compared with the preset fault probability threshold. When the fault prediction result exceeds the fault probability threshold, the health assessment result of the current device is a probability failure.

[0044] S312. When the fault prediction result is the remaining life, the health assessment standard is based on a preset remaining life threshold, and the remaining life is compared with the preset remaining life threshold. When the remaining life is less than the remaining life threshold, the health assessment result of the current device is that the life is unqualified.

[0045] S313: When the fault prediction result does not exceed the fault probability threshold and the remaining life is not less than the remaining life threshold, the health assessment result of the current device is qualified.

[0046] S32, aggregate the devices with unqualified life span into the first devices, aggregate the devices with only probability unqualified into the second devices, and prioritize all unqualified devices based on the health assessment results. The priority ranking rule is: S321. Set the priority of the first device to be higher than the priority of the second device.

[0047] S322. For first devices that fail both life and probability, assign priorities according to failure probability, and assign higher priorities to first devices with higher failure probability.

[0048] S323. Assign priorities to the second devices according to the failure probability, and give higher priorities to the second devices with higher failure probability.

[0049] S33. Determine the maintenance method for unqualified equipment based on the fault type and equipment characteristics of each equipment. The equipment characteristics are recorded in the digital file. The fault type is determined based on the equipment characteristics. The maintenance method includes predictive maintenance and post-maintenance.

[0050] Failure types include predictable failures and unpredictable failures. Predictable failures usually have certain signs or monitorable status changes before they occur. Their equipment characteristics are mostly critical equipment or complex systems, so predictive maintenance is suitable. Unpredictable failures occur randomly and are difficult to predict. Most of the equipment is non-critical or simple, and the failure has little impact on production. Therefore, it is suitable for post-failure maintenance. That is, maintenance and replacement are performed after the failure occurs. This post-failure maintenance can reduce maintenance costs and avoid unnecessary downtime.

[0051] S34. Generate a maintenance plan for each device based on the priority sorting result, the maintenance plan including maintenance time, maintenance items and maintenance resources; Determine the equipment. For equipment with predictable failures, the maintenance time needs to be before the predicted failure occurs. For equipment with unpredictable failures, the maintenance time needs to be after the predicted failure occurs. Consider the results of priority sorting comprehensively and determine the maintenance time for each equipment. Maintenance items are determined based on the equipment operation data collected by sensors. Maintenance items can be determined based on the equipment operation data, including mechanical maintenance and electrical maintenance.

[0052] Maintenance resources are determined based on maintenance projects.

[0053] S35. Obtain maintenance recommendations for each device based on the maintenance plan.

[0054] Maintenance recommendations are more specific maintenance plans, including maintaining or replacing parts, adjusting equipment parameters, and performing preventive inspections.

[0055] In order to make the above description clearer, a specific simplified embodiment is described below: Assume that a failure prediction is performed on a piece of equipment, and the probability of failure of the equipment within the next month is higher than the preset failure probability threshold. The records in the digital archive show that the equipment occupies an important position in the production process and the equipment characteristics are critical equipment. Therefore, it can be determined that the failure type is a predictable failure.

[0056] Therefore, it was decided to adopt predictive maintenance. Based on the vibration sensor data and historical fault records, it was determined that the fault was related to bearing wear or looseness, so the maintenance project was mechanical maintenance.

[0057] Based on the priority based on failure probability and the current production schedule, maintenance is scheduled to be performed within the next two weeks.

[0058] In response to the problem of bearing wear or looseness, the maintenance project is planned as follows: conduct a comprehensive inspection of the bearings, including appearance, vibration, temperature, etc.; if the bearings are found to be severely worn or loose, replace or tighten them; lubricate and clean the relevant transmission parts to ensure smooth operation of the equipment.

[0059] Allocate maintenance resources based on the above maintenance items: call in experienced mechanical maintenance engineers to be responsible for this maintenance work. Required spare parts include bearings and lubricants. Arrange maintenance tools and equipment: including vibration sensors, temperature meters, etc.

[0060] Generate specific maintenance recommendations: Shut down and disconnect power to ensure the equipment is in a safe state; remove the equipment housing to expose the bearings and transmission components; use vibration sensors and temperature meters to conduct a comprehensive inspection of the bearings; based on the inspection results, decide whether the bearings need to be replaced or tightened; lubricate and clean the transmission components; reinstall the equipment housing and connect the power supply for testing.

[0061] S4. Convert the maintenance suggestion for each device into a maintenance work order, add the maintenance work order to the maintenance task queue for maintenance, and update the digital file of the corresponding device according to the maintenance result of the maintenance work order, which specifically includes the following steps: S41. Generate an estimated completion time based on the maintenance time, generate a maintenance task based on the maintenance item, and generate a required resource list based on the maintenance resources.

[0062] S42: Generate a corresponding maintenance work order based on the estimated completion time, maintenance tasks and required resource list.

[0063] S43. Add the maintenance work order to the maintenance task queue, and assign the maintenance work order based on the required resource list, equipment characteristics, and the priority of the equipment corresponding to the maintenance work order, so that the maintenance work order corresponds to the appropriate maintenance personnel. The maintenance project will also be taken into consideration. For example, mechanical maintenance will correspond to mechanical maintenance engineers, and electrical maintenance will correspond to electrical maintenance engineers.

[0064] During the allocation process, the current workload of the maintenance personnel, task conflicts, and the urgency of the maintenance tasks are taken into consideration to ensure efficient execution of maintenance tasks.

[0065] S44. When the real-time status of the maintenance work order changes to received, it indicates that the maintenance personnel accepts the maintenance work order, and the system tracks the real-time status of the maintenance work order in real time.

[0066] Real-time tracking includes the start time of the maintenance task, execution status (including in progress, completed, pending review), and any related notes.

[0067] S45. When the real-time status of the maintenance work order changes to completed, the maintenance personnel submits the maintenance results, including detailed information such as maintenance time, replaced parts, and maintenance costs. The system obtains the maintenance results of the maintenance work order and conducts an audit.

[0068] The audit process includes re-predicting equipment failures and evaluating health status based on real-time equipment operation data. For equipment with probability failure, the audit is passed when there is no probability failure in the health assessment results. For equipment with unqualified lifespan, the audit requires the replacement of the equipment, or the maintenance results submitted by the maintenance personnel are marked with ignoring the equipment lifespan.

[0069] S46. The digital file and health assessment results of the current equipment are updated based on the audit results. The digital file includes the historical maintenance record of the equipment, and the maintenance results will be updated in real time into the historical maintenance record.

[0070] When the review result is passed, the system will mark the real-time status of the maintenance work order as closed and remove the maintenance work order from the maintenance task queue.

[0071] Based on the same inventive concept as above, the present application also discloses a factory equipment asset maintenance management device, the structure of which is as follows: Figure 3 As shown, the device includes the following modules: The data acquisition module is used to establish a centralized equipment management platform. The centralized management platform is connected to all devices, obtains the digital files of each device, collects the equipment operation data of the current device in real time through sensor devices, and updates it to the digital files; The fault prediction module is used to extract the key features of the equipment from the equipment operation data, combine the historical fault information in the digital archive to train a fault prediction model, and obtain the fault prediction results of each equipment based on the fault prediction model and equipment operation data; The health assessment module is used to compare the fault prediction results with the preset health assessment standards to obtain the health assessment results of each device and generate maintenance recommendations for each device based on the health assessment results; The work order management module is used to convert the maintenance suggestions for each device into a maintenance work order, add the maintenance work order to the maintenance task queue for maintenance, and update the digital file of the corresponding device according to the maintenance results of the maintenance work order.

[0072] In a specific implementation scheme, the fault prediction module includes the following units: The first fault prediction unit is used to pre-process the equipment operation data, extract key features of the equipment from the pre-processed equipment operation data according to the feature extraction technology, and obtain a feature subset of the equipment from the key features through a preset feature selection method; The second fault prediction unit is used to train a fault prediction model based on a preset machine learning algorithm, combining a feature subset and historical fault information extracted from digital archives, and input the equipment operation data of all equipment into the fault prediction model to obtain a fault prediction result for each device.

[0073] In a specific implementation scheme, the health assessment module includes the following units: The first health assessment unit is used to compare the fault prediction result with the preset health assessment standard. The fault prediction result includes the failure probability and remaining life of each device. When the fault prediction result is a fault probability, the fault probability is compared with a preset fault probability threshold. When the fault prediction result exceeds the fault probability threshold, the health assessment result of the current device is a probability failure. When the fault prediction result is the remaining life, the remaining life is compared with a preset remaining life threshold. When the remaining life is less than the remaining life threshold, the health assessment result of the current device is that the life is unqualified.

[0074] The second health assessment unit is used to aggregate the devices with unqualified life span into the first devices, aggregate the devices with only unqualified probability into the second devices, and prioritize all the devices based on the health assessment results. The priority ranking rule is: Setting the priority of the first device to be higher than the priority of the second device; For the first equipment that fails both the life and probability, the priority is assigned according to the failure probability, and the first equipment with a higher failure probability is given a higher priority; For the second device, a priority is assigned according to the failure probability, and a second device with a higher failure probability is given a higher priority.

[0075] The third health assessment unit is used to determine the maintenance method of each device according to the fault type and device characteristics of each device. The device characteristics are recorded in the digital file. The fault type is determined based on the device characteristics. The maintenance method includes predictive maintenance and post-maintenance. Generate a maintenance plan for each device based on the results of priority sorting, which includes maintenance time, maintenance items, and maintenance resources; Get maintenance recommendations for each device based on the maintenance plan.

[0076] In a specific implementation scheme, the work order management module includes the following units: The first work order management unit is used to generate an estimated completion time according to the maintenance time, generate a maintenance task according to the maintenance project, generate a required resource list according to the maintenance resources, and generate a corresponding maintenance work order according to the estimated completion time, the maintenance task and the required resource list; Add maintenance work orders to the maintenance task queue and assign them based on the required resource list, equipment characteristics, and the priority of the equipment to which the maintenance work order corresponds.

[0077] The second work order management unit is used to track the real-time status of the maintenance work order in real time when the real-time status of the maintenance work order is changed to received; When the real-time status of the maintenance work order changes to completed, the maintenance results of the maintenance work order are obtained and reviewed, and the digital files and health assessment results of the current equipment are updated according to the review results. The digital files include the historical maintenance records of the equipment. When the review result is passed, the real-time status of the maintenance work order is marked as closed, and the maintenance work order is removed from the maintenance task queue.

[0078] From the above function introduction, it can be seen that a factory equipment asset maintenance management device in this application has built a complete equipment maintenance system, provided the necessary software and technical support for the stable operation of the equipment and the improvement of production efficiency, and promoted the sustained and rapid development of the economy and society.

[0079] Based on the same inventive concept mentioned above, an embodiment of the present application also discloses a computer-readable storage medium, which stores at least one instruction, at least one program, code set or instruction set, and at least one instruction, at least one program, code set or instruction set can be loaded and executed by a processor to implement the factory equipment asset maintenance management method provided by the above method embodiment.

[0080] Also based on the same inventive concept mentioned above, an embodiment of the present application also discloses a computer-readable storage medium, in which at least one instruction, at least one program, code set or instruction set is stored, and at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor to implement the factory equipment asset maintenance management method as mentioned above.

[0081] A person skilled in the art can understand that all or part of the steps of implementing the above embodiments can be completed by hardware, or can be completed by a program to instruct the relevant hardware, and the program can be stored in a computer-readable storage medium, and the computer-readable storage medium includes, for example: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0082] The above are only optional embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A factory equipment asset maintenance management method, characterized in that: The steps include: Establish a centralized equipment management platform, which is connected to all equipment, obtains the digital archive of each equipment, collects the equipment operation data of the current equipment in real time through sensor equipment, and updates it to the digital archive; Extracting key features of the equipment from the equipment operation data, combining them with historical fault information in the digital archive to train a fault prediction model, and obtaining a fault prediction result for each of the equipment based on the fault prediction model and the equipment operation data; Compare the fault prediction result with a preset health assessment standard to obtain a health assessment result of each of the devices, and generate maintenance recommendations for each of the devices based on the health assessment result; The maintenance suggestion for each of the devices is converted into a maintenance work order, the maintenance work order is added to a maintenance task queue for maintenance, and the digital file of the corresponding device is updated according to the maintenance result of the maintenance work order.

2. The factory equipment asset maintenance management method according to claim 1, characterized in that: Extracting the key features of the device from the device operation data, combining the historical fault information in the digital archive to train a fault prediction model, and obtaining the fault prediction result of each device according to the fault prediction model and the device operation data specifically includes the following steps: Preprocessing the device operation data, extracting key features of the device from the preprocessed device operation data according to a feature extraction technology, and obtaining a feature subset of the device from the key features by a preset feature selection method; According to the preset machine learning algorithm, the feature subset and the historical fault information extracted from the digital archive are combined to train a fault prediction model, and the equipment operation data of all the equipment are input into the fault prediction model to obtain the fault prediction results of each equipment.

3. The factory equipment asset maintenance management method according to claim 1, characterized in that: The step of comparing the fault prediction result with a preset health assessment standard to obtain a health assessment result of each device specifically includes the following steps: Compare the fault prediction results with preset health assessment criteria, the fault prediction results including the failure probability and remaining life of each of the devices, When the fault prediction result is the fault probability, the fault probability is compared with a preset fault probability threshold, and when the fault prediction result exceeds the fault probability threshold, the health assessment result of the current device is a probability failure; When the fault prediction result is the remaining life, the remaining life is compared with a preset remaining life threshold, and when the remaining life is less than the remaining life threshold, the current health assessment result of the device is that the life is unqualified.

4. The factory equipment asset maintenance management method according to claim 3, characterized in that: After obtaining the health assessment result of each device, the following steps are also included: The devices that have failed the lifespan test are grouped as first devices, and the devices that have failed the probability test are grouped as second devices. Based on the health assessment result, all the devices are prioritized. The priority ranking rule is: Setting the priority of the first device to be higher than the priority of the second device; For the first device that fails both the life span and the probability, assigning a priority according to the failure probability, and giving a higher priority to the first device with a higher failure probability; For the second device, a priority is assigned according to the failure probability, and a second device with a higher failure probability is given a higher priority.

5. The factory equipment asset maintenance management method according to claim 4, characterized in that: Generating maintenance suggestions for each of the devices according to the health assessment results specifically includes the following steps: Determine the maintenance method of the equipment according to the fault type and equipment characteristics of each equipment, the equipment characteristics are recorded in the digital file, the fault type is determined according to the equipment characteristics, and the maintenance method includes predictive maintenance and post-maintenance; Generate a maintenance plan for each of the devices according to the result of the priority sorting, wherein the maintenance plan includes maintenance time, maintenance items, and maintenance resources; A maintenance suggestion for each of the devices is obtained according to the maintenance plan.

6. The factory equipment asset maintenance management method according to claim 5, characterized in that: The step of converting the maintenance suggestion for each device into a maintenance work order and adding the maintenance work order to a maintenance task queue for maintenance specifically includes the following steps: Generate an estimated completion time based on the maintenance time, generate a maintenance task based on the maintenance item, generate a required resource list based on the maintenance resources, and generate a corresponding maintenance work order based on the estimated completion time, the maintenance task and the required resource list; The maintenance work order is added to a maintenance task queue, and the maintenance work order is allocated according to the required resource list, the device characteristics, and the priority of the device corresponding to the maintenance work order.

7. The factory equipment asset maintenance management method according to claim 1, characterized in that: The updating of the digital file of the corresponding device according to the maintenance result of the maintenance work order specifically includes the following steps: When the real-time status of the maintenance work order is changed to received, the real-time status of the maintenance work order is tracked in real time; When the real-time status of the maintenance work order changes to completed, the maintenance result of the maintenance work order is obtained and reviewed, and the digital file and health assessment result of the current device are updated according to the review result, wherein the digital file includes the historical maintenance record of the device; When the audit result is passed, the real-time status of the maintenance work order is marked as closed, and the maintenance work order is removed from the maintenance task queue.

8. A factory equipment asset maintenance management device, characterized in that: Includes the following modules: A data acquisition module is used to establish a centralized equipment management platform, which is connected to all the equipment, obtain the digital archive of each of the equipment, collect the equipment operation data of the current equipment in real time through the sensor equipment, and update it to the digital archive; A fault prediction module is used to extract key features of the device from the device operation data, train a fault prediction model based on the historical fault information in the digital archive, and obtain a fault prediction result for each device based on the fault prediction model and the device operation data; A health assessment module, used to compare the fault prediction result with a preset health assessment standard to obtain a health assessment result of each of the devices, and generate maintenance recommendations for each of the devices based on the health assessment result; The work order management module is used to convert the maintenance suggestion of each device into a maintenance work order, add the maintenance work order to the maintenance task queue for maintenance, and update the digital file of the corresponding device according to the maintenance result of the maintenance work order.

9. An intelligent terminal, characterized in that: It includes a memory and a processor, wherein the memory stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by the processor to implement the factory equipment asset maintenance management method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The readable storage medium stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by the processor to implement the factory equipment asset maintenance management method as described in any one of claims 1 to 7.

Images