Method and system for automatically creating maintenance work order in combination with equipment fault prediction

Abstract

The invention provides a maintenance work order automatic creation method and system combined with equipment fault prediction, and relates to the field of data processing systems or methods for prediction purposes, and the method comprises the steps: carrying out the matching of corresponding equipment information based on a fault prediction result outputted by a fault prediction model; according to the fault prediction result and the equipment information, resources needed by maintenance of each piece of equipment are determined; generating a preliminary maintenance work order draft according to the work order template and the resources required for maintenance, and performing priority ranking according to the predicted severity level to obtain a priority sequence; matching the current human resource and the current accessory resource to a corresponding preliminary maintenance work order draft according to the priority sequence to obtain a preliminary maintenance work order; and generating a formal maintenance work order based on an audit or modification result of the user. By implementing the method, the interference intervention of artificial resource allocation on the overall efficiency in the process of automatically creating the maintenance work order can be reduced by automatically allocating the maintenance resources, so that the overall efficiency of creating the maintenance work order can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing systems or methods for prediction purposes, and more particularly to a method and system for automatically creating maintenance work orders in combination with equipment failure prediction. Background Art

[0002] In modern industrial maintenance management, timely prevention and treatment of equipment failures are the key to improving production efficiency and reducing operating costs. Especially in the fields of urban rail transit equipment management, large industrial facility maintenance and intelligent building facility monitoring, equipment status monitoring and predictive maintenance have become one of the key measures to improve equipment operation reliability.

[0003] In the related technology, a fault prediction model is generally constructed based on the historical status data of the equipment, and then the real-time status data of the current equipment is input into the fault prediction model to obtain the fault prediction result of the equipment. Then, relevant technical personnel allocate resources based on the fault prediction result and generate a maintenance work order.

[0004] However, the traditional method of creating maintenance work orders generally requires relevant technicians to allocate existing inventory resources and human resources based on fault prediction results, which affects the speed of automated creation of work orders and results in low efficiency of the automated creation process of maintenance work orders. Summary of the invention

[0005] The present application provides a method and system for automatically creating maintenance work orders in combination with equipment fault prediction, which is used to address the problem that the traditional maintenance work order creation method requires relevant technicians to allocate maintenance resources based on fault prediction results, resulting in low efficiency in the automatic creation process of maintenance work orders.

[0006] In a first aspect, the present application provides a method for automatically creating a maintenance work order in combination with equipment failure prediction, which is applied to a work order creation system, and the method includes: Obtaining a fault prediction result output by a fault prediction model, the fault prediction result including a device ID, a predicted fault type, a predicted severity level, and a recommended response time, the fault prediction model being trained based on historical operation data of the device and corresponding historical fault data; Match the corresponding equipment information from the equipment archive database according to the equipment ID, the equipment information includes the equipment model specification, installation location, maintenance record and corresponding spare parts inventory data; Determine the maintenance resources required for each device ID according to the fault prediction result and the device information, the maintenance resources including human resources, tools and material lists; Generate a preliminary maintenance work order draft corresponding to each device ID based on the work order template selected by the user and the maintenance resource, and the work order template is stored in the work order template library; Prioritize the preliminary maintenance work order draft according to the predicted severity level to obtain a priority sequence; Matching the current human resources and the current spare parts resources to the corresponding draft of the preliminary maintenance work order according to the priority sequence to obtain a preliminary maintenance work order; Based on the user's review or modification results of the preliminary maintenance work order, a formal maintenance work order is generated.

[0007] Through the above embodiments, the work order creation system automatically retrieves and matches the corresponding faulty equipment information and maintenance resource information by obtaining the fault prediction results output by the fault prediction model based on the equipment operation data, and then automatically generates a draft of the maintenance work order, and then prioritizes the matching of maintenance resources for the equipment with higher priority in the draft of the maintenance work order, and directly generates the final formal maintenance work order after the user reviews and modifies it. This method reduces the interference of manual resource allocation on the overall efficiency during the creation of maintenance work orders by automatically allocating maintenance resources, thereby improving the overall efficiency of maintenance work order creation.

[0008] In some embodiments, before the step of obtaining the fault prediction result output by the fault prediction model, the step further includes: Obtain historical operation data and corresponding historical fault data of the equipment and construct a data set, which includes a training set and a test set; The data set is used to train and test the machine learning model to obtain a fault prediction model, which outputs the fault prediction result corresponding to the device based on the input device operation data.

[0009] Through the above embodiment, the work order creation system trains the fault prediction model through historical operation data and historical fault data, and can more accurately predict the possible fault conditions of the equipment in the future, so as to facilitate the subsequent rapid generation of maintenance work orders based on the prediction results.

[0010] In some embodiments, the step of matching the current human resources and the current parts resources to the corresponding preliminary maintenance work order draft according to the priority sequence to obtain the preliminary maintenance work order specifically includes: Get current spare parts inventory and available human resources in real time; Allocate the corresponding resources required for the maintenance in order from high to low priority until the resources are insufficient, and obtain a resource allocation result. The insufficient resources means that the spare parts inventory or the available human resources cannot support the resources required for the maintenance corresponding to the current priority; The preliminary maintenance work order draft is filled in according to the resource division result to obtain a preliminary maintenance work order.

[0011] Through the above embodiment, the work order creation system obtains the current inventory information and human resource information in real time, and then allocates them in sequence according to the priority according to the resource requirements of each priority level to generate a preliminary maintenance work order, so that relevant staff can prioritize the maintenance of equipment with higher severity levels based on the generated maintenance work order, thereby optimizing resource allocation. At the same time, the automatic allocation process of maintenance resources improves the efficiency of automated creation of maintenance work orders.

[0012] In some embodiments, after the step of generating a formal maintenance work order based on the user's review or modification result of the preliminary maintenance work order, the process further includes: Determining the consumption trend of each resource workpiece according to the maintenance required resources recorded within the first preset time period; Determining a price average based on the historical workpiece market prices of each inventory component recorded within a second preset time period; Determine whether the current market price is appropriate based on the floating threshold set by the user and the price average; If yes, a purchase list is generated directly; If not, determine whether to generate a purchase list based on the inventory information.

[0013] Through the above embodiments, the work order creation system monitors resource consumption trends and market prices, intelligently determines whether to generate a purchase list, effectively controls maintenance costs, ensures timely replenishment of resources, avoids maintenance delays due to resource shortages, and thus enhances the economy and response speed of the entire maintenance system.

[0014] In some embodiments, the step of determining whether to generate a purchase list based on the inventory information specifically includes: If it is detected that the current inventory resources exceed the preset threshold, procurement will be suspended; If it is detected that the current inventory resources are lower than the preset threshold, a purchase list of the minimum quantity is generated based on the maintenance resources.

[0015] Through the above embodiment, the work order creation system determines whether to purchase by setting an inventory threshold. If the market price is high when purchase is necessary, the minimum purchase quantity is selected, thereby reducing the purchase cost while ensuring sufficient maintenance resources.

[0016] In some embodiments, after the step of generating a formal maintenance work order based on the user's review or modification result of the preliminary maintenance work order draft, the step further includes: Obtain the importance level and predicted failure frequency of each device, the importance level is marked by the user in the formal maintenance work order; The failure prediction period of each device is determined based on the importance level and the predicted failure frequency.

[0017] Through the above embodiment, the work order creation system obtains the importance level of the equipment and the predicted fault frequency, and regularly updates the fault prediction cycle. This method improves the management efficiency of maintenance work orders, makes the maintenance plan more consistent with the actual use status and importance of the equipment, helps to prioritize the maintenance of key equipment, and thus improves the stability and reliability of the entire system.

[0018] In some embodiments, after the step of filling in the preliminary maintenance work order draft according to the resource division result to obtain the preliminary maintenance work order, the step further includes: Determine the available maintenance team closest to the installation location and the corresponding expected arrival time on site based on the equipment information and the resources required for the maintenance; Determine the estimated working hours based on the historical work records of the available maintenance team; The available maintenance team, the expected on-site arrival time and the estimated working time are entered into the corresponding template position of the preliminary maintenance work order.

[0019] Through the above embodiment, the work order creation system selects the most suitable maintenance team and determines the maintenance time according to the equipment information and the resources required for maintenance, which can minimize the response time and maintenance time, help the maintenance team to operate efficiently, quickly resolve equipment failures, greatly improve the timeliness of maintenance operations and reduce equipment downtime.

[0020] In a second aspect, the present application provides a work order creation system, the work order creation system comprising: one or more processors and a memory; The memory is coupled to the one or more processors, and the memory is used to store computer program code, which includes computer instructions. The one or more processors call the computer instructions so that the work order creation system can implement a method for automatically creating maintenance work orders combined with equipment fault prediction provided in the above embodiment, which will not be repeated here.

[0021] In a third aspect, the present application provides a computer-readable storage medium comprising instructions. When the instructions are executed on a work order creation system, the work order creation system can implement a method for automatically creating maintenance work orders combined with equipment fault prediction provided in the above-mentioned embodiment, which will not be repeated here.

[0022] In a fourth aspect, the present application provides a computer program product. When the computer program product runs on a work order creation system, the work order creation system can implement a method for automatically creating maintenance work orders combined with equipment fault prediction provided in the above-mentioned embodiment, which will not be repeated here.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The work order creation system matches the maintenance resources required by the equipment by comprehensively utilizing the fault prediction results of the fault prediction model and real-time inventory data, and then automatically generates maintenance work orders according to the predicted severity level of the equipment, thereby improving the efficiency and accuracy of maintenance work order creation, reducing manual intervention, and ensuring the timeliness and accuracy of maintenance response, thereby improving the operational reliability and maintenance efficiency of the equipment.

[0024] 2. The work order creation system can automatically decide whether to generate a purchase list by intelligently monitoring resource consumption trends and market price changes, effectively controlling maintenance costs. In addition, the system can adjust procurement behavior based on actual inventory resources and market conditions. For example, when resources are below the threshold and market prices are high, only the minimum necessary quantity will be purchased, thereby optimizing resource allocation and reducing resource waste. At the same time, it ensures timely replenishment of resources and avoids maintenance delays.

[0025] 3. The work order creation system not only selects the most suitable maintenance team and predicts a reasonable maintenance time, but also intelligently updates the fault prediction cycle based on the importance level of the equipment and the predicted fault frequency. This method closely matches the maintenance plan with the actual use status and importance of the equipment, improves the pertinence and efficiency of maintenance, and significantly optimizes the maintenance management of key equipment, thereby improving the overall stability and reliability of the system, reducing equipment downtime, and improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flowchart of a method for automatically creating a maintenance work order in combination with equipment failure prediction in an embodiment of the present application; Figure 2 It is another flowchart diagram of a method for automatically creating a maintenance work order in combination with equipment failure prediction in an embodiment of the present application; Figure 3 It is a schematic diagram of the physical device structure of the work order creation system in the embodiment of the present application. DETAILED DESCRIPTION

[0027] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0028] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0029] For ease of understanding, the following is a flow chart of the method provided by this embodiment. Figure 1 The figure is a flow chart of a method for automatically creating a maintenance work order in combination with equipment failure prediction in an embodiment of the present application.

[0030] S101. Obtain a fault prediction result output by a fault prediction model.

[0031] The work order creation system obtains the historical operation data of the equipment by collecting and organizing the operation logs, maintenance records and other information of the equipment, and then obtains the historical fault data of the equipment based on the fault report of the equipment. The work order creation system uses the historical operation data and historical fault data after preprocessing (such as cleaning and standardization) to form a data set and train the fault prediction model, so that after the training is completed, the model can analyze the current operation data of the equipment and predict the possible fault type, severity and recommended response time of the equipment.

[0032] Among them, the training fault prediction model can select decision trees, neural networks or support vector machines and other algorithms for framework construction. The specific choice depends on the accuracy requirements of the prediction and the availability of computing resources, which is not limited here.

[0033] S102: Match corresponding device information from a device archive database according to the device ID.

[0034] Among them, the equipment archive database usually contains information such as the equipment model, specifications, installation location, historical maintenance records, and spare parts inventory status.

[0035] Specifically, after obtaining the fault prediction result (including the device ID, predicted fault type, predicted severity level and recommended response time) corresponding to a certain device ID through the fault prediction model, the work order creation system uses the device ID as a key index to quickly retrieve all necessary information about the relevant device. Optionally, the work order creation system can use the advanced query function of the database management system (DBMS) to query the device information, including but not limited to indexing and full-text search technology, and data association analysis technology.

[0036] S103: Determine the resources required for maintenance of each device ID based on the fault prediction result and the device information.

[0037] After obtaining the equipment failure prediction results output by the fault prediction model, the work order creation system determines the various resources required to repair the equipment based on the actual information of the equipment. Specifically, the work order creation system searches the preset maintenance resource matching table for an applicable preliminary maintenance plan based on the predicted fault type and severity level. The plan specifies the personnel configuration, tool list, and spare parts materials usually required to handle this type of fault. Next, the work order creation system retrieves the equipment archive database to obtain the detailed specifications, location, historical maintenance records, and other information of the equipment, and compares and corrects it with the plan given in the maintenance resource matching table, and finally obtains the maintenance resources required for each equipment ID.

[0038] In addition, the work order creation system obtains the current inventory information in real time, and checks whether the required spare parts and tools are in sufficient stock against the determined maintenance resource plan. If the existing inventory cannot meet the maintenance needs, the system will prompt to generate a procurement plan, but at the same time it will weigh the urgency and substitutability of resources, and if necessary, it will cut the original plan, reduce resource usage, or give priority to ensuring the maintenance conditions of the equipment with the highest fault level.

[0039] S104: Generate a preliminary maintenance work order draft corresponding to each device ID based on the work order template and device information selected by the user.

[0040] After determining the maintenance resources required for each faulty device, the work order creation system automatically fills in the equipment information and resource list according to the user's preset work order template to generate a preliminary work order draft. Among them, the work order template is a fixed document format that specifies the various information items that need to be included in the maintenance work order, such as equipment model, fault phenomenon, recommended maintenance measures, required working hours, material cost estimates, etc. Users can customize the content of the template according to the internal workflow and management needs of the enterprise.

[0041] Specifically, the work order creation system first identifies the type of template currently selected by the user and reads the required information items contained therein. Then, the system extracts and calculates relevant data from the equipment archive database and the previously determined maintenance resource plan in sequence, and fills them into the corresponding columns of the template in sequence. For example, the name, model, code, installation location, etc. of the equipment are automatically written in the "Faulty Equipment" column; the predicted fault type, severity level, expected time of occurrence, etc. are automatically written in the "Fault Description" column; the previously matched personnel configuration, tool and spare parts list, etc. are listed in the "Recommended Maintenance Measures" column, and there is no limitation here.

[0042] In addition, the work order creation system can also call the corresponding work order sub-template for different equipment types and fault levels. For example, for electrical equipment, the system may additionally fill in detailed information such as the power supply circuit diagram and the location of the protection switch; for high-temperature equipment, the system may emphasize precautions such as anti-scalding and anti-explosion, etc., which are not limited here.

[0043] After filling in the required information, the work order creation system will generate a complete maintenance work order draft document (preliminary maintenance work order draft).

[0044] S105. Prioritize the preliminary maintenance work order drafts according to the predicted severity levels to obtain a priority sequence.

[0045] After the work order creation system obtains the predicted fault severity level of each device through the fault prediction model, it further sorts all preliminary maintenance work order drafts according to this severity level. Specifically, the work order creation system extracts the fault severity level field in each work order draft and converts it into a numerical priority score. For example, the priority of a "serious" level fault can be set to 1, a "general" level to 2, and a "minor" level to 3, where the smaller the number, the higher the priority. Then, the system uses a sorting algorithm, such as quick sort or merge sort, to sort all work orders in descending order according to the priority score to form a priority sequence. The work order at the front of the sequence will be the first to receive support from maintenance resources.

[0046] S106. Match the current human resources and the current spare parts resources to the corresponding preliminary maintenance work order draft according to the priority sequence to obtain the preliminary maintenance work order.

[0047] After the priority sequence of maintenance work orders is generated, the work order creation system starts from the highest priority and checks whether the maintenance resources required for each preliminary maintenance work order draft can be met. If they are met, resources are automatically allocated and the corresponding preliminary maintenance work order is generated. At the same time, it determines whether the maintenance resources of the next priority can be met; if they are not met, resource allocation is stopped and an early warning reminder of insufficient resources is issued.

[0048] S107. Generate a formal maintenance work order based on the user's review or modification results of the preliminary maintenance work order.

[0049] After the initial maintenance work order is generated, the relevant management personnel can view and adjust it on the work order creation system. The work order creation system reads the user's direct modifications to a work order, such as adjustments to the maintenance personnel arrangement, spare parts selection, etc. The system will extract the modification details, overwrite the original plan in the draft, and generate a formal maintenance work order. In addition, the system can also identify and analyze user comments through natural language understanding technology, such as "high working hours" and "consider replacing materials", and then fine-tune the original plan accordingly, or give modification suggestions for user reference.

[0050] Through the above embodiments, the work order creation system automatically retrieves and matches the corresponding faulty equipment information and maintenance resource information by obtaining the fault prediction results output by the fault prediction model based on the equipment operation data, and then automatically generates a draft maintenance work order, and then prioritizes the matching of maintenance resources for the equipment with higher priority in the draft maintenance work order, and directly generates the final formal maintenance work order after the user reviews and modifies it. This method reduces the interference of manual resource allocation on the overall efficiency during the maintenance work order creation process by automatically allocating maintenance resources, thereby improving the overall efficiency of maintenance work order creation.

[0051] S108. Obtain the importance level and predicted failure frequency of each device.

[0052] The work order creation system determines the importance level of each device by collecting the equipment importance level information marked by technicians in each formal maintenance work order. Among them, the evaluation of the equipment importance level is usually a comprehensive evaluation by field engineers based on factors such as the production tasks undertaken by the equipment and the correlation with other equipment, which is not limited here.

[0053] In addition, the work order creation system can analyze the historical failure of the equipment through machine learning algorithms and predict the frequency of failures in the future. For example, if the system detects that a pump has experienced 5 failures in the past year and the failure intervals are gradually shortening, it can be inferred that the next failure may occur within 3 months. The system can also group equipment of the same model or in the same process environment, comprehensively consider the failure patterns of other equipment in the group, predict the performance of a single device, and improve the confidence of the prediction.

[0054] S109. Determine the fault prediction period of each device according to the importance level and the predicted fault frequency.

[0055] After determining the importance level and predicted failure frequency of each device, the work order creation system dynamically adjusts the operating cycle of its fault prediction model to strengthen or weaken the frequency of monitoring in a targeted manner. Specifically, for devices marked as highly important, the system defaults to the shortest prediction cycle, such as once a day; while for devices with the lowest importance, the prediction cycle is automatically relaxed to once a month. On this basis, the system can further fine-tune the prediction cycle by comparing the predicted value of the device's failure frequency. If frequent failures are expected, the cycle can be shortened; if there is no risk of failure for a long time, the cycle can be extended. After adaptive adjustment, each device will receive a corresponding failure prediction schedule.

[0056] In the above embodiment, the work order creation system obtains the importance level of the equipment and the predicted fault frequency, and regularly updates the fault prediction period. This method improves the management efficiency of maintenance work orders, makes the maintenance plan more consistent with the actual use status and importance of the equipment, helps to prioritize the maintenance of key equipment, and thus improves the stability and reliability of the entire system.

[0057] The following is a more detailed description of the process of the method provided by this embodiment. Figure 2 As shown, it is another flowchart of a method for automatically creating a maintenance work order combined with equipment failure prediction in an embodiment of the present application.

[0058] S201. Obtain historical operation data and corresponding historical fault data of a device and construct a data set.

[0059] The work order creation system collects the historical operation status data of the equipment through various sensors installed on the equipment (such as temperature sensors, vibration sensors, pressure sensors, etc.). Of course, it can also directly read the collected historical operation data from the operation log, which is not limited here. In addition, the work order creation system can also extract key information such as the time, type, severity, and cause analysis of each fault from the equipment's maintenance record to obtain historical fault data.

[0060] Next, the work order creation system matches the historical operation data with the historical fault data and converts them into a standardized data set that can be processed by the machine learning algorithm. Optionally, the operation data within a certain time range (such as one month) is used as a sample. If a fault occurs within the corresponding time period, it is marked as a positive sample, otherwise it is marked as a negative sample. At the same time, the sample data is cleaned, outliers are removed, and the numerical amplitudes of different features are adjusted to the same level using normalization and standardization.

[0061] S202. Use the data set to train and test the machine learning model to obtain a fault prediction model.

[0062] The work order creation system divides the data set constructed in step S201 into a training set and a test set. Then, a fault prediction model is constructed based on the machine learning algorithm selected by the user. The optional machine learning algorithms include but are not limited to logistic regression, decision tree, random forest, support vector machine, neural network, etc., which are not limited here. The fault prediction model is trained using the training set, and the model is tested using the test set. The model parameters that meet the preset performance evaluation indicators on the test set are selected to generate the final fault prediction model.

[0063] S203: Obtain a fault prediction result output by the fault prediction model.

[0064] This step is the same as step S101 and will not be repeated here.

[0065] S204. Allocate the corresponding resources required for maintenance in order from high to low priority until the resources are insufficient, thereby obtaining a resource allocation result.

[0066] After obtaining the fault prediction results, the work order creation system matches the corresponding maintenance resource requirements in the preset standard maintenance solution library according to the predicted fault type and severity. These resources usually include spare parts, tools, manpower, etc. required for maintenance. Then, the system checks the current resource reserves and prioritizes the preliminary maintenance work order drafts according to the severity of the fault. For the most serious faults predicted, the system prioritizes the allocation of maintenance resources to ensure that these key equipment can be repaired in a timely manner.

[0067] The system matches maintenance resources to each work order in descending order of priority until the inventory or human resources are insufficient to support the maintenance needs of the current work order. In this case, the system temporarily suspends the allocation of resources for subsequent work orders and triggers the procurement process to replenish maintenance materials. After the resources are sufficient again, the system continues to allocate resources to the remaining work orders according to priority.

[0068] Furthermore, when the system obtains a new preliminary maintenance work order draft based on the new fault prediction result, if there are still some remaining work orders that have not been assigned, the preliminary maintenance work order drafts of the two will be merged, and then the priority and subsequent resource allocation will be re-sorted according to the severity of the fault.

[0069] S205. Fill in a preliminary maintenance work order draft based on the resource division result to obtain a preliminary maintenance work order.

[0070] When the work order creation system has completed the priority allocation of maintenance resources, it will automatically fill in the specific implementation plan for each work order based on the resource division results to form a preliminary work order draft. Specifically, the system first identifies the type of maintenance task. For example, for the wear of the pump seal, the system classifies it as mechanical seal maintenance. Next, the system extracts the general solution template under this category in the knowledge base, which includes the main steps of maintenance, such as disassembling the pump body, replacing the seal, reassembling and resetting, trial operation inspection, etc., as well as the key control points and precautions for each step.

[0071] Then, the system adds specific technical details based on the general solution according to the severity of the fault and the special requirements of the equipment. For example, if the displacement of the faulty pump is large, the system will specifically mark the need to use heavy lifting tools in the disassembly steps and require strict compliance with the standard lifting process to ensure safety.

[0072] After clarifying the specific work content, the system reads the spare parts model, quantity, special tool list, personnel composition of the execution team, estimated working hours and other elements configured for this task from the maintenance resource division results, and fills them into the corresponding fields of the preliminary maintenance work order draft. After filling in, the system generates a complete preliminary maintenance work order and submits it to the relevant supervisor for review.

[0073] In the above embodiment, the work order creation system obtains the current inventory information and human resource information in real time, and then allocates them in sequence according to the priority in combination with the resource requirements of each priority level to generate a preliminary maintenance work order, so that relevant staff can prioritize the maintenance of equipment with higher severity levels based on the generated maintenance work order, thereby optimizing resource allocation. At the same time, the automatic allocation process of maintenance resources improves the efficiency of automated creation of maintenance work orders.

[0074] S206: Determine the consumption trend of each resource workpiece according to the maintenance required resources recorded within the first preset time period.

[0075] The work order creation system analyzes the maintenance work orders over a period of time (such as the past month) and counts the actual consumption of various resource artifacts (such as spare parts, tools, etc.) required for maintenance. The system arranges these data in chronological order and uses time series analysis methods such as moving average method and exponential smoothing method to predict the demand trend of each artifact in the future.

[0076] S207: Determine a price average based on the historical workpiece market prices of each inventory component recorded within a second preset time period.

[0077] The work order creation system collects the actual purchase prices of various maintenance workpieces in the market over a period of time (such as the past six months), removes possible outliers, and calculates the arithmetic mean as the average price. This mean represents the reasonable price of the workpiece under the general market conditions and can be used as a benchmark for subsequent price judgments. Of course, the set value can also be directly determined as the benchmark for subsequent price judgments based on user needs, which is not limited here.

[0078] S208. Determine whether the current market price is appropriate based on the floating threshold and price average set by the user.

[0079] The work order creation system allows users to set a price fluctuation threshold, such as plus or minus 10%. Then, the system compares the supplier's real-time quotation with the price average in step S206. If the deviation is within the threshold range, the price is determined to be acceptable, and the process goes to step S212 to directly generate a purchase list; otherwise, the system will issue a price abnormality warning and go to step S209 to further determine whether to generate a purchase list based on inventory information.

[0080] S209: Determine whether to generate a purchase list based on the inventory information.

[0081] The system obtains the inventory quantity of various maintenance workpieces and the maintenance resources determined in step S205 in real time to determine whether to generate a purchase list at present. Specifically, if it is detected that the inventory quantity cannot meet the maintenance resources, it is determined that a purchase list needs to be generated at present and the process proceeds to step S211. On the contrary, if it is detected that the inventory quantity can meet the maintenance resources, it is determined that a purchase list does not need to be generated at present and the process proceeds to step S210.

[0082] S210. Suspend procurement.

[0083] When the work order creation system confirms that there is no need to generate a purchase list at present based on the judgment and analysis of the above steps S207-S209, the work order creation system issues an instruction to suspend procurement to the procurement department.

[0084] S211. Determine the minimum purchase quantity of maintenance resources.

[0085] When the work order creation system determines in step S209 that a purchase list needs to be generated, the work order creation system establishes an inventory management model based on parameter information such as the historical demand and predicted demand for the workpiece, the current inventory, and the supplier's minimum order quantity, and performs simulation calculations in combination with real-time data to obtain the optimal minimum purchase quantity.

[0086] S212. Directly generate a purchase list.

[0087] When the work order creation system completes the calculation of the purchase quantity, it directly generates a purchase list based on the determined varieties and quantities for the purchasing department to execute.

[0088] In the above embodiment, the work order creation system monitors resource consumption trends and market prices, intelligently determines whether to generate a purchase list, effectively controls maintenance costs, ensures timely replenishment of resources, avoids maintenance delays due to resource shortages, and thus enhances the economy and response speed of the entire maintenance system.

[0089] S213: Determine the available maintenance team closest to the installation location and the corresponding expected arrival time on site based on the equipment information and the resources required for maintenance.

[0090] The work order creation system extracts detailed geographic location information of the faulty equipment from the equipment archive database, including the factory area, workshop, equipment number, etc. Then, the system queries the maintenance team management system to obtain the current location of all maintenance personnel (which can be updated in real time through the positioning function of the mobile terminal), skills, expertise, idle status and other information.

[0091] Based on the equipment location and personnel distribution, the work order creation system uses the shortest path algorithm, such as the Dijkstra algorithm or the A* search algorithm, to calculate the shortest distance and estimated time for each maintenance team to reach the installation location of the faulty equipment from the current location. The system then compares and selects the personnel with the highest skill match and the least tasks at hand from the maintenance teams closest to the faulty equipment, and assigns them as the execution team for the maintenance work order. At the same time, the system generates the expected arrival time of the team and fills it into the corresponding field of the draft work order.

[0092] S214. Determine the estimated working time based on the historical work records of the available maintenance team.

[0093] The work order creation system accesses the enterprise's equipment management system and human resource management system to extract historical maintenance records of the same or similar models of equipment as the current fault. For example, for a pump bearing wear fault, if it is handled by a maintenance worker with an intermediate technical level, the average time is 2 hours; if it is handled by a senior technician, the average time can be shortened to 1.5 hours.

[0094] Next, the system uses big data analysis technologies, such as association rule mining and decision trees, to establish a maintenance time prediction model under the composite conditions of multiple characteristic parameters such as fault type, fault severity and maintenance team skill level. When a new maintenance task appears, the system quickly matches the most relevant historical maintenance cases based on the determined fault diagnosis results and execution team information, extracts their average time, and then makes fine adjustments based on the current specific situation to obtain an estimated maintenance work duration.

[0095] Among them, the work order creation system can extract training samples from the historical maintenance work order database. Each sample contains various features that affect the maintenance time, such as the type of faulty equipment, the severity of the fault, the keywords describing the fault, the skill level of the maintenance team, etc., as well as the corresponding actual maintenance time (training label). Use the training samples to train the maintenance time prediction model. Input the characteristic parameters such as the fault type, fault severity and the skill level of the maintenance team into the model, and input the corresponding expected working time.

[0096] It should be noted that the optional algorithm framework of the model includes but is not limited to linear regression, decision tree regression, support vector regression, neural network, etc., which are not limited here.

[0097] S215. Enter the available maintenance team, expected arrival time on site and estimated working time into the corresponding template position of the preliminary maintenance work order.

[0098] In the knowledge base of the work order creation system, managers usually pre-design several general templates for maintenance work orders, stipulating the information items that must be included and can be optionally included in different types of maintenance tasks. When the system determines the specific execution team, expected arrival time and working time of this maintenance task, it will activate the work order template with the highest matching degree (such as the standard maintenance template for mechanical equipment) and fill in the relevant information in the corresponding information items. The filling process is completely completed automatically by the system, ensuring the standardization and unification of the work order format and content. After filling, the system generates a preliminary maintenance work order for the faulty equipment and submits it to the relevant management personnel for review.

[0099] In the above embodiment, the work order creation system selects the most suitable maintenance team and determines the maintenance time based on the equipment information and maintenance resources, which can minimize the response time and maintenance time, help the maintenance team to operate efficiently, quickly resolve equipment failures, greatly improve the timeliness of maintenance operations and reduce equipment downtime.

[0100] The work order creation system of the embodiment of the present invention is applied to electronic equipment. Figure 3 A schematic diagram of the architecture of an electronic device suitable for implementing an embodiment of the present invention is shown.

[0101] It should be noted that Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0102] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructions (computer programs), or by controlling related hardware through instructions (computer programs), and the instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. The electronic device of this embodiment includes a storage medium and a processor, wherein a plurality of instructions are stored in the storage medium, and the instructions can be loaded by the processor to execute any step of the method provided in the embodiment of the present invention.

[0103] Specifically, the storage medium and the processor are electrically connected directly or indirectly to realize data transmission or interaction. For example, these elements can be electrically connected to each other through one or more signal lines. The storage medium stores computer execution instructions for implementing the data access control method, including at least one software function module that can be stored in the storage medium in the form of software or firmware. The processor executes various functional applications and data processing by running the software program and module stored in the storage medium. The storage medium can be, but is not limited to, random access storage medium (Random Access Memory, referred to as: RAM), read-only storage medium (Read Only Memory, referred to as: ROM), programmable read-only storage medium (Programmable Read-Only Memory, referred to as: PROM), erasable read-only storage medium (Erasable Programmable Read-Only Memory, referred to as: EPROM), electrically erasable read-only storage medium (Electric Erasable Programmable Read-Only Memory, referred to as: EEPROM), etc. Among them, the storage medium is used to store programs, and the processor executes the program after receiving the execution instruction.

[0104] Furthermore, the software programs and modules in the above-mentioned storage medium may also include an operating system, which may include various software components and / or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide an operating environment for other software components. The processor may be an integrated circuit chip having signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc., which may implement or execute the various methods, steps, and logic flow diagrams disclosed in this embodiment. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0105] Since the instructions stored in the storage medium can execute the steps in any method provided in the embodiments of the present invention, the beneficial effects of any method provided in the embodiments of the present invention can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0106] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A maintenance work order automatic creation method combined with equipment failure prediction, applied to a work order creation system, characterized in that: The method comprises: Obtaining a fault prediction result output by a fault prediction model, wherein the fault prediction result includes a device ID, a predicted fault type, a predicted severity level, and a recommended response time, wherein the fault prediction model is trained based on historical operation data of the device and corresponding historical fault data; Matching corresponding equipment information from the equipment archive database according to the equipment ID, the equipment information including equipment model specifications, installation location, maintenance records and corresponding parts inventory data; Determine the maintenance resources required for each device ID according to the fault prediction result and the device information, wherein the maintenance resources required include human resources, tools and material lists; Generate a preliminary maintenance work order draft corresponding to each device ID according to the work order template selected by the user and the resources required for the maintenance, wherein the work order template is stored in a work order template library; Prioritizing the preliminary maintenance work order drafts according to the predicted severity levels to obtain a priority sequence; Matching current human resources and current spare parts resources to the corresponding draft of the preliminary maintenance work order according to the priority sequence to obtain a preliminary maintenance work order; Based on the user's review or modification results of the preliminary maintenance work order, a formal maintenance work order is generated.

2. The method according to claim 1, characterized in that Before the step of obtaining the fault prediction result output by the fault prediction model, the method further includes: Acquire historical operation data and corresponding historical fault data of the equipment and construct a data set, wherein the data set includes a training set and a test set; The data set is used to train and test the machine learning model to obtain a fault prediction model, which outputs a fault prediction result corresponding to the device based on the input device operation data.

3. The method according to claim 1, characterized in that The step of matching the current human resources and the current parts resources to the corresponding preliminary maintenance work order draft according to the priority sequence to obtain the preliminary maintenance work order specifically includes: Get current spare parts inventory and available human resources in real time; Allocate the corresponding maintenance resources in descending order according to the priority until the resources are insufficient, and obtain a resource division result, wherein the insufficient resources means that the spare parts inventory or the available human resources cannot support the maintenance resources corresponding to the current priority; Fill in the draft of the preliminary maintenance work order according to the resource division result to obtain a preliminary maintenance work order.

4. The method according to claim 1, characterized in that: After the step of generating a formal maintenance work order based on the user's review or modification result of the preliminary maintenance work order, the method further includes: Determining the consumption trend of each resource workpiece according to the maintenance required resources recorded within the first preset time period; Determining a price average based on the historical workpiece market prices of each inventory component recorded within a second preset time period; Determine whether the current market price is appropriate based on the floating threshold set by the user and the price average; If yes, a purchase list is generated directly; If not, it is determined whether a purchase list is currently generated based on the inventory information.

5. The method according to claim 4, characterized in that The step of determining whether to generate a purchase list currently based on the inventory information specifically includes: If it is detected that the current inventory resources exceed the preset threshold, procurement will be suspended; If it is detected that the current inventory resources are lower than the preset threshold, a purchase list of minimum quantity is generated according to the resources required for maintenance.

6. The method according to claim 1, characterized in that After the step of generating a formal maintenance work order based on the user's review or modification result of the preliminary maintenance work order draft, the method further includes: Obtaining the importance level and predicted failure frequency of each device, wherein the importance level is marked by the user in the formal maintenance work order; The failure prediction period of each device is determined according to the importance level and the predicted failure frequency.

7. The method according to claim 3, characterized in that After the step of filling in the preliminary maintenance work order draft according to the resource division result to obtain the preliminary maintenance work order, the method further includes: Determine the available maintenance team closest to the installation location and the corresponding expected arrival time on site based on the equipment information and the resources required for maintenance; Determine the estimated working hours based on the historical work records of the available maintenance team; The available maintenance team, the expected on-site arrival time and the estimated working time are entered into corresponding template positions of the preliminary maintenance work order.

8. A work order creation system, characterized in that: The work order creation system includes: one or more processors and memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the work order creation system to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a work order creation system, the work order creation system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a work order creation system, the work order creation system is enabled to execute the method according to any one of claims 1 to 7.

Images