Fault handling scheme determination method, fault handling scheme recommendation system and storage medium

Abstract

The invention discloses a fault handling scheme determination method, a fault handling scheme recommendation system and a storage medium, relates to the technical field of intelligent business process management, and discloses a fault handling scheme determination method comprising the following steps: obtaining multi-dimensional constraint information in a production environment to which a fault diagnosis process belongs, calculating a historical utility index set of a plurality of to-be-treated schemes corresponding to the fault diagnosis process; by taking the multi-dimensional constraint information as a constraint condition and the historical utility index set as an evaluation factor, determining a sorting priority of the plurality of to-be-processed schemes; and determining the to-be-processed scheme with the highest ranking priority under a preset constraint condition as a target processing scheme of the fault diagnosis process. On the basis, the target disposal scheme can strictly meet the actual constraint requirement of the current production environment, and can also support the utility index subjected to historical verification to guarantee the disposal effect.

Description

Technical Field

[0001] This application relates to the field of intelligent business process management technology, and in particular to a method for determining fault handling solutions, a fault handling solution recommendation system, and a storage medium. Background Technology

[0002] When production equipment malfunctions, the recommendation mechanism of mainstream fault handling solutions often simplifies the process into a static information retrieval or logical reasoning problem, such as selecting the most similar historical handling solution based on a historical fault database, or generating handling suggestions based on knowledge graph paths.

[0003] However, static case matching or rule reasoning cannot adapt to factors such as equipment aging, operating condition fluctuations, and raw material batch changes in production scenarios, resulting in the output disposal cases being out of touch with the actual product situation.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of this application is to provide a method for determining fault handling solutions, a fault handling solution recommendation system, and a storage medium, aiming to solve the technical problem that the current output handling solutions are out of sync with the actual product conditions.

[0006] To achieve the above objectives, this application proposes a method for determining a fault handling solution, the method comprising: Obtain multi-dimensional constraint information of the production environment to which the fault diagnosis process belongs, and calculate the historical utility index set of multiple solutions to be handled corresponding to the fault diagnosis process; Using the multidimensional constraint information as constraints and the historical utility index set as evaluation factors, the ranking priority of multiple proposed solutions is determined. The solution with the highest priority under preset constraints is determined as the target solution in the fault diagnosis process.

[0007] In one embodiment, after the step of determining the disposal plan with the highest priority under preset constraints as the target disposal plan in the fault diagnosis process, the method for determining the fault disposal plan further includes: Obtain a recommendation report of the target treatment plan, the recommendation report including at least the ranking result and ranking basis of the ranking priority, as well as the target treatment plan and its basic information; Output the recommendation report.

[0008] In one embodiment, the step of determining the ranking priority of multiple proposed solutions using the multidimensional constraint information as constraints and the historical utility index set as evaluation factors includes: Using the multidimensional constraint information as constraints and the historical utility index set as evaluation factors, a multidimensional priority evaluation model is constructed. Invalid solutions are screened out from the solutions to be dealt with based on the multi-dimensional priority evaluation model, and a comprehensive score result of multiple solutions to be dealt with is calculated by weighting according to the scoring function constructed based on the constraints and the evaluation factors. The ranking priority of the multiple solutions to be dealt with after filtering out invalid solutions is generated based on the comprehensive scoring results.

[0009] In one embodiment, after the step of constructing a multi-dimensional priority evaluation model using the multi-dimensional constraint information as constraints and the historical utility index set as evaluation factors, the method for determining the fault handling plan further includes: Based on the fault diagnosis information corresponding to the fault diagnosis process, determine the fault urgency and / or production environment status associated with the fault diagnosis process. Based on the fault urgency and / or the production environment status, update the weights of the multidimensional constraint information and the weights of the historical utility index set in the scoring function.

[0010] In one embodiment, the step of calculating the historical utility index set of multiple pending solutions corresponding to the fault diagnosis process includes: Among the multiple proposed solutions, the historical average repair time and historical execution success rate of any proposed solution in the single-dimensional information of the multidimensional constraint information are obtained. By associating the historical average repair time and the historical execution success rate under the same single-dimensional information, the historical utility index of the solution to be dealt with under the same single-dimensional information is obtained; Based on the historical utility indicators and the multidimensional constraint information, the historical utility indicator set is constructed.

[0011] In one embodiment, before the step of determining the disposal plan with the highest priority under preset constraints as the target disposal plan in the fault diagnosis process, the method for determining the fault disposal plan further includes: In response to the filtering instructions of the multiple proposed solutions, determine the filtering information associated with the filtering instructions; Set the filtering information as the preset constraint.

[0012] In one embodiment, before the steps of obtaining multi-dimensional constraint information of the production environment to which the fault diagnosis process belongs, and calculating the historical utility indicators of multiple pending solutions corresponding to the fault diagnosis process, the method for determining the fault handling solution further includes: If the fault diagnosis process is triggered, the received fault diagnosis information is obtained; Based on the fault diagnosis information, multiple solutions to be handled are matched in the fault knowledge base.

[0013] In one embodiment, before the step of determining the disposal plan with the highest priority under preset constraints as the target disposal plan in the fault diagnosis process, the method for determining the fault disposal plan further includes: If there are conflicting constraints in the multidimensional constraint information, determine the target historical utility index associated with the conflicting constraint. The ranking priority of the multiple proposed solutions is updated based on the target historical utility index.

[0014] Furthermore, to achieve the above objectives, this application also proposes a fault handling scheme recommendation system, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the fault handling scheme determination method as described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the fault handling scheme determination method as described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: First, multi-dimensional constraint information of the production environment to which the fault diagnosis process belongs is obtained, and the historical utility index set of multiple solutions to be handled corresponding to the fault diagnosis process is calculated. Then, the ranking priority of each solution to be handled is determined by using the multi-dimensional constraint information as the constraint condition and the historical utility index set as the evaluation factor. Finally, the solution with the highest ranking priority under the preset constraint condition is selected as the target solution. This constructs a dual-core linkage decision logic of actual scenario constraints and solution utility, so that the target solution can not only strictly fit the actual constraint requirements of the current production environment, but also rely on historically verified utility indicators to ensure the handling effect. This avoids decision-making biases that only consider constraints and ignore the actual application value of the solution or rely solely on historical data and deviate from the actual situation on site. It solves the problems of poor solution adaptability and insufficient reliability caused by single-dimensional decision-making and the separation of constraints and utility in existing fault handling technologies. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a system architecture diagram of the fault handling recommendation system for this application; Figure 2 A flowchart illustrating the first embodiment of the method for determining a fault handling solution in this application; Figure 3 A flowchart illustrating the second embodiment of the method for determining a fault handling solution in this application; Figure 4 This is a simplified flowchart illustrating the method for determining a fault handling solution obtained by combining various embodiments of this application. Figure 5 This is a schematic diagram of the hardware operating environment involved in the fault handling scheme determination method in the embodiments of this application.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] The main solution of this application embodiment is: to obtain multi-dimensional constraint information of the production environment to which the fault diagnosis process belongs, and to calculate the historical utility index set of multiple solutions to be handled corresponding to the fault diagnosis process; Using the multidimensional constraint information as constraints and the historical utility index set as evaluation factors, the ranking priority of multiple proposed solutions is determined. The solution with the highest priority under preset constraints is determined as the target solution in the fault diagnosis process.

[0023] In this embodiment, for ease of description, the fault handling solution recommendation system will be used as the execution subject in the following description.

[0024] Because existing technologies cannot adapt to factors such as equipment aging, operating condition fluctuations, and raw material batch changes in production scenarios, the output disposal cases are out of touch with the actual product conditions.

[0025] Based on this, this application provides a solution that constructs a dual-core linkage decision-making logic of actual scenario constraints and solution utility. This enables the target disposal solution to not only strictly conform to the actual constraints of the current production environment, but also to rely on historically verified utility indicators to ensure the disposal effect. This avoids decision-making biases that only consider constraints and ignore the actual application value of the solution or rely solely on historical data and deviate from the actual situation on site. It solves the problems of poor solution adaptability and insufficient reliability caused by single-dimensional decision-making and the separation of constraints and utility in existing fault handling technologies.

[0026] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific embodiments.

[0027] In this embodiment, the system architecture of the fault handling solution recommendation system is as follows: Figure 1 As shown, the system includes a constraint perception and acquisition module, a solution retrieval module, a historical utility analysis module, a multi-constraint optimization engine, an interpretable report generator, and a knowledge base and database. The constraint perception and acquisition module serves as the interface between the system and external real-time data systems (ERP, MES, WMS, APS systems), dynamically acquiring and structuring the required constraint information. The solution retrieval module retrieves an initial set of candidate solutions from the knowledge base based on the input fault information. The historical utility analysis module links to the maintenance history database, calculating and maintaining historical performance indicators for various types of solutions. The multi-constraint optimization engine, as the core computing unit of the system, incorporates multi-constraint optimization models such as mixed-integer programming models and constraint satisfaction problem solvers, responsible for calculating the global optimal solution and outputting reports to maintenance personnel / decision-makers. The interpretable report generator transforms the mathematical solution results of the optimization engine into easily understandable recommendation reports containing natural language descriptions and structured data, and transmits this report synchronously when the disposal plan is transmitted to the maintenance personnel / decision-makers. The knowledge base and database store standard fault-solution mappings, historical cases, resource data, and other data.

[0028] Based on this, embodiments of this application provide a method for determining a fault handling solution, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the method for determining a fault handling solution in this application.

[0029] In this embodiment, the method for determining the fault handling plan includes steps S10 to S30: Step S10: Obtain multi-dimensional constraint information of the production environment to which the fault diagnosis process belongs, and calculate the historical utility index set of multiple solutions to be handled corresponding to the fault diagnosis process.

[0030] The aforementioned multidimensional constraint information refers to the set of multidimensional technical constraints affecting the execution of fault handling solutions in the production scenario corresponding to the fault diagnosis process. This multidimensional constraint information includes at least spare parts inventory status information, available maintenance personnel skills and working hours information, and current production task priority information. Specifically, spare parts inventory status information includes the real-time inventory quantity, specification compatibility, storage location, and allocation cycle of maintenance spare parts; available maintenance personnel skills and working hours information includes the professional skill type, skill level, current working hours occupancy, remaining available working hours, and available arrival time of on-duty maintenance personnel; and current production task priority information includes the delivery node, batch importance, downtime impact scope, and capacity target weight of fault-related production tasks.

[0031] The historical utility index set refers to a set of quantitative indicators calculated based on past execution data of the solutions to be addressed, including the historical average repair time and historical execution success rate. The historical average repair time reflects the efficiency of the solution's handling, while the historical execution success rate reflects the reliability of the solution. Each solution to be addressed corresponds to one historical utility index, and the historical utility indices corresponding to multiple solutions form an index set. Optionally, each solution to be addressed may also correspond to multiple different historical utility indices based on different constraints.

[0032] In this embodiment, when the fault diagnosis process is triggered, the fault handling solution recommendation system collects production environment data in real time through Internet of Things (IoT) sensors. It establishes communication connections with the production line's programmable logic controller (PLC) and manufacturing execution system (MES) to read the inventory status information of spare parts required for fault handling, including inventory quantity, specifications, storage location, and availability. Simultaneously, it retrieves the human resource management ledger from the MES system, extracts the list of on-duty maintenance personnel, and filters out personnel with the corresponding fault handling skills. It also simultaneously obtains their current workload, remaining available hours, and on-call time, among other maintenance personnel skill and workload information. Finally, it extracts the current production task priority information from the production planning management system, including the delivery node, batch priority, potential upstream and downstream processes affected by the downtime, and capacity targets of the fault-related production tasks. After obtaining the multi-dimensional constraint information, this information needs to be deduplicated and standardized to generate a structured multi-dimensional constraint information set, ensuring data accuracy and completeness and providing reliable input for subsequent constraint verification.

[0033] Simultaneously or subsequently, upon obtaining multidimensional constraint information, the system can also calculate a set of historical utility indicators for multidimensional solutions to be handled corresponding to the fault diagnosis process. Specifically, when triggering the fault diagnosis process, the recommendation system filters out multiple solutions to be handled based on the fault diagnosis information, performing initial filtering of invalid solutions and retaining only those that meet the requirements. Therefore, when triggering the fault diagnosis process, the system can obtain received fault diagnosis information, which includes at least standardized fault modes and affected equipment. This information can be obtained through various methods such as voice input, text input, and image input. After obtaining the fault diagnosis information, multiple solutions to be handled are matched against the fault knowledge base. For each solution, its effective execution records are statistically analyzed, the historical execution success rate and the repair time for each successful handling are calculated, and finally, these two indicators are organized into a structured set of historical utility indicators and stored in association with the corresponding solutions to be handled.

[0034] For example, if a robotic arm on the production line experiences a positioning deviation fault, the multi-dimensional constraint information obtained includes the following: spare parts inventory status information: two compatible positioning sensors are in stock, with fully matched specifications, stored in the workshop spare parts warehouse and readily available; available maintenance personnel skills and workload information includes one experienced maintenance personnel with robotic arm calibration skills on duty, currently with no available time and sufficient remaining time, ready to start immediately; current production task priority information indicates the associated batch is an urgent order with only 4 hours remaining until delivery, allowing for partial shutdown but not a complete shutdown affecting upstream and downstream processes. Simultaneously, for the aforementioned robotic arm positioning deviation fault, three candidate solutions are selected, with the following historical utility metrics: Solution A (historical execution success rate 92%, historical average repair time 45 minutes), Solution B (historical execution success rate 88%, historical average repair time 20 minutes), and Solution C (historical execution success rate 75%, historical average repair time 10 minutes).

[0035] It should be noted that the above parameters are for illustrative purposes only and are not intended to limit this application.

[0036] Step S20: Using multidimensional constraint information as constraints and historical utility index set as evaluation factors, determine the ranking priority of multiple disposal options.

[0037] In this embodiment, multi-dimensional constraint information is used as the constraint condition, combined with historical utility indicators to optimize and rank the proposed solutions. This upgrades the proposed solutions from feasibility matching to globally optimal decision matching that conforms to actual production conditions. Therefore, it is necessary to establish a linkage evaluation logic between constraints and utility, clarify the evaluation weights and rules of each indicator, and ensure that the priority ranking has a unified and repeatable calculation basis to avoid confusion in the evaluation logic. By quantitatively calculating the constraint fit of each solution, historical utility is transformed into comparable scores, thereby clarifying the priority of multiple proposed solutions and providing a basis for subsequent target solution selection.

[0038] In this embodiment, the fault diagnosis information does not include the core content of multidimensional constraints. Among the multiple solutions to be addressed selected based on this information, there are solutions that are "technically compatible but not feasible on-site." Therefore, it is necessary to first filter out obviously infeasible solutions through constraints, and then find the optimal solution for the remaining feasible solutions through a scoring function constructed from evaluation factors.

[0039] Optionally, solution filtering based on multi-dimensional constraint information retains a pool of feasible solutions with an executable basis. However, this does not reflect the differences in feasibility or optimal solutions between solutions. Therefore, it is necessary to combine a scoring function that integrates constraints and evaluation factors to find the optimal solution. For example, solutions A and B for robotic arm failure both meet the requirements of spare parts, personnel, and task constraints after constraint filtering. Although solution B's constraint satisfaction score of 85 is lower than solution A's 90, after weighting, solution B is more suitable for the on-site needs of partial downtime and urgent orders, thus avoiding the one-sidedness of ranking solely based on utility indicators (success rate, time).

[0040] Optionally, multiple solutions can be scored directly based on a scoring function constructed from constraints and evaluation factors. Understandably, solutions that are "technically compatible but not feasible on-site" will typically receive lower scores than normal after scoring.

[0041] Based on this, when determining the priority of solutions to be addressed, obviously infeasible solutions are first filtered out by constraints. Then, for the remaining feasible solutions, the optimal solution is found through a scoring function that integrates constraints and evaluation factors. Specifically, in determining the priority of multiple solutions, the score = constraint fit (percentage A%) + historical utility score (percentage 1 - A%), where A can be set based on actual needs.

[0042] It's important to note that the ranking priority is related to the constraint information of each dimension in the multi-dimensional constraints. The weight of different constraint dimensions in actual production scenarios changes dynamically with on-site needs. Therefore, for the same set of solutions to be addressed, different priority ranking results will be obtained when different constraint dimensions are used as the core screening requirements. For example, in a robotic arm failure scenario, if the core issue on-site is "tight staffing schedules," then when staffing constraints are the primary screening requirement, the weight of this condition is increased, and the ranking result will prioritize the solution with the highest staffing availability, resulting in a ranking (A, B, C, D). If the core issue on-site changes to "insufficient spare parts inventory," then when spare parts constraints are the primary screening requirement, the ranking result will prioritize the solution with the highest spare parts availability, resulting in a ranking (B, A, D, C).

[0043] Step S30: Determine the solution to be handled with the highest priority under preset constraints, and use it as the target solution for the fault diagnosis process.

[0044] The aforementioned target handling plan refers to the optimal fault handling plan that is finally determined and adapted to the current fault diagnosis process and production environment.

[0045] In this embodiment, after the fault handling solution recommendation system confirms that the highest priority solution has passed the verification, it takes the solution as the target handling solution and extracts detailed execution steps, required resource list, operation specifications, precautions and other information of the solution to generate standardized handling instructions and processing list for subsequent solution issuance and solution selection.

[0046] In this embodiment, the system can respond in real time to changes in inventory, personnel scheduling, order insertion, and other on-site changes, and recalculate the optimal solution, realizing flexible decision-making based on real-time situational awareness. This is a capability that static case matching systems cannot possess, thereby solving the problem of the current output disposal plan being out of sync with the actual product situation.

[0047] Optionally, when conflicts exist in multidimensional constraint information, it is necessary to determine the target historical utility index associated with the conflicting constraint items and update the ranking priority of multiple pending solutions based on the target historical utility index. Specifically, when conflicts exist in multidimensional constraint information, such as the conflict between insufficient spare parts inventory and urgent production tasks, the historical utility index corresponding to each pending solution under this dimension can be extracted. The weights of the conflicting constraint dimension and the historical utility index in the scoring function can be dynamically adjusted. In the case of urgent production, the weight of historical repair time is increased and the weight of resource cost constraints is reduced. Then, the comprehensive score of each solution is calculated based on the adjusted weights, thereby updating the ranking priority to ensure optimal global efficiency in conflict scenarios.

[0048] This embodiment provides a method for determining fault handling solutions. It uses at least three types of multi-dimensional constraints—spare parts inventory, maintenance personnel, and production task priorities—as scenario-based dynamic constraints, and historical utility indicators as quantitative evaluation factors. By establishing a linkage evaluation logic between the two types of information, the priority of the solutions to be handled is determined. Then, a secondary verification focusing on the rigid requirements of the three types of constraints is used to filter out the target solutions, forming a complete technical closed loop. This ensures that the target solutions align with the actual dynamic conditions of the industrial production site, and relies on historical utility to ensure the efficiency and reliability of the solutions. It effectively solves the problem of traditional fault handling decisions being detached from actual site conditions or ignoring historical application effects, significantly improving the rationality and efficiency of fault handling, and is adaptable to the fault handling needs of various types of industrial production scenarios.

[0049] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 After step S30, the method for determining the fault handling plan further includes steps S40 to S50. Step S40: Obtain a recommended report of the target treatment plan.

[0050] Step S50: Output the recommendation report.

[0051] The aforementioned explanatory report should include at least the ranking results and basis for prioritization, as well as the target disposal plan and its basic information. Specifically, as a document that provides a structured explanation of the target disposal plan and decision-making process, the explanatory report should include at least three parts: first, the ranking results of prioritization, i.e., the priority order of all candidate plans and their corresponding comprehensive scores; second, the basis for prioritization, i.e., the composition of the multi-dimensional constraint satisfaction score, the quantification results of historical utility indicators, and the evaluation rules and weight allocation explanation; and third, the target disposal plan and its basic information, which includes the plan name, core execution steps, a list of required resources, an estimated disposal time, and the chain of reasoning supporting the recommendation.

[0052] It should be noted that the current method of recommending troubleshooting solutions only provides the recommendation result and cannot clearly explain "why this solution is recommended instead of that solution". As a result, maintenance personnel, especially experienced experts, find it difficult to understand and trust the recommendation logic, resulting in a low system adoption rate.

[0053] In this embodiment, in order to solve the black box decision-making problem, a structured explanation report can be used to clearly present the decision-making logic, enabling maintenance personnel to understand the basis for the recommended solution, improving the credibility and adoption rate of the system's decision-making, and providing traceable evidence for subsequent solution review.

[0054] Therefore, after obtaining the target handling solution, the fault handling solution recommendation system can use an interpretable report generator to transform the mathematical results of the optimization model into a logically clear reasoning chain, explicitly informing users "why A is recommended instead of B," as well as the potential risks and subsequent suggestions of the solution, thereby improving the credibility of the system and users' willingness to adopt it. Specifically, the interpretable report generator of the fault handling solution recommendation system automatically associates with the preceding decision data, extracts the ranking results and the comprehensive scores of each solution, sorts out the score composition, and then retrieves the evaluation rules such as weight allocation, constraint satisfaction thresholds, scoring formulas, etc., as well as the multi-dimensional constraint information and historical utility index set used in the ranking. It then clarifies the ranking basis and translates it into plain technical language. Finally, it extracts the basic information of the target handling solution and integrates it into a standardized interpretive report, which is output on the display terminal or pushed to the maintenance personnel's client. This application does not limit the output format.

[0055] For example, taking a robotic arm malfunction as an example, under the preset conditions, the ranking result is Scheme B > Scheme A > Scheme C, with comprehensive scores of 84.9, 81.4, and 80 points respectively. The core content of the interpretable recommendation report output at this time is as follows: The recommended solution is Solution B; its comprehensive utility score is 84.9 points; the estimated resource list is no additional spare parts required, senior maintenance personnel A can be dispatched, and no special testing equipment is required; the estimated time is 20 minutes; the recommendation reasoning chain is as follows: This ranking adopts the evaluation rule of "constraint satisfaction weight 50% + historical utility index weight 50%", where the historical utility index includes historical execution success rate (sub-weight 60%) and average repair time (sub-weight 40%). Solution B's constraint satisfaction score is 85 points, which is slightly lower than Solution A's 90 points, but Solution B's historical execution success rate is 98%, the average repair time is only 18 minutes, and the historical utility score is 0.848, which is significantly higher than Solution A's 0.782. After weighted calculation, the comprehensive score is higher than other solutions; at the same time, Solution B does not require additional spare parts, can directly adapt to the current on-site constraints of tight spare parts inventory, and the estimated time of 20 minutes is completely in line with the task requirements of expedited order semi-shutdown production, and will not have an additional impact on production line capacity. The potential risks and subsequent recommendations are as follows: Before performing parameter calibration, the robotic arm should be powered off and left stationary to avoid mechanical malfunctions during parameter adjustment. After calibration, it is recommended to conduct three no-load test runs to confirm that the accuracy meets the standards before putting it into formal production.

[0056] This embodiment provides a method for determining fault handling solutions. After accurately screening fault handling solutions by relying on the linkage evaluation of multi-dimensional constraints and historical utility, an easy-to-understand recommendation report is generated through the ranking results and ranking criteria. This clearly presents the reasoning chain, core basis, and potential risks of the solution recommendation, solves the black-box decision-making problem of optimization models, significantly improves the transparency and credibility of system decisions, enhances the willingness of maintenance personnel to adopt solutions, effectively improves fault handling efficiency, ensures the stability and continuity of production processes, and adapts to the fault handling needs of various types of intelligent manufacturing scenarios.

[0057] Based on any embodiment of this application, in the third embodiment of this application, the content that is the same as or similar to the above embodiments can be referred to the above description, and will not be repeated hereafter. Based on this, step S20 includes steps S21 to S23: Step S21: Using multidimensional constraint information as constraints and historical utility index set as evaluation factors, construct a multidimensional priority evaluation model.

[0058] Step S22: Based on the multi-dimensional priority evaluation model, invalid solutions are screened out from the solutions to be dealt with, and the comprehensive score of multiple solutions to be dealt with is calculated by weighting according to the scoring function constructed based on the constraints and evaluation factors.

[0059] Step S23: Generate the sorting priority of multiple solutions to be dealt with after eliminating invalid solutions based on the comprehensive scoring results.

[0060] In this embodiment, a multi-dimensional priority evaluation model is constructed with the goal of maximizing the overall utility score. Multi-dimensional constraint information is used as the constraint condition, and historical utility indicators are used as the evaluation factors to optimize and rank the set of candidate solutions. This allows for a quantitative evaluation of which solution has the lowest overall cost, shortest time, and highest success rate among multiple similar cases.

[0061] Specifically, the multi-dimensional priority evaluation model can be a mixed integer programming model, a constraint satisfaction problem solver, or a machine learning model such as a decision tree, random forest, hybrid intelligent model, reinforcement learning model, and artificial intelligence model.

[0062] To avoid the interference of invalid solutions in the subsequent ranking of solutions, the model needs to first screen out invalid solutions. Then, through a scoring function constructed using constraints and evaluation factors, the model calculates the weighted scores of the solutions under all constraints. A single constraint cannot cover the actual feasibility boundary of a solution and can easily filter out invalid solutions such as "having spare parts but no suitable personnel," which interfere with the ranking. Simply mixing multiple constraints will lose the accurate evaluation basis of a single-dimensional constraint, failing to identify the shortcomings of the solution and making it difficult to support the reasoning chain for subsequent dynamic weight adjustments and interpretable reports. By calculating all constraints, a standardized single-dimensional data foundation can be provided for weighted scoring. By adapting weight allocation to different on-site needs, the model achieves a decision-making upgrade from single-dimensional optimization to global optimization, ensuring that the ranking results align with the dynamic production conditions of intelligent manufacturing scenarios.

[0063] During the calculation process, the constraint satisfaction of the proposed solutions can be calculated. Then, the weights of historical utility indicators are set, and a comprehensive scoring method is established based on these weights. Finally, the ranking priority of multiple proposed solutions is determined through a scoring system. Specifically, the multi-dimensional constraint information is broken down into multiple sub-indicators, each corresponding to a weight of 1 / N, where N is the number of sub-indicators. The constraint satisfaction of each proposed solution is then calculated. Subsequently, the weights of historical utility indicators are set, such as historical execution success rate accounting for 60% and historical average repair time accounting for 40%. Based on the weighted scoring formula: Comprehensive Score = Constraint Satisfaction × 50% + (Historical Execution Success Rate × 60% + Historical Average Repair Time Reverse Score × 40%) × 50%. That is, Comprehensive Score = Constraint Condition Score × A% + Historical Utility Score × (1-A)%. And Historical Utility Score = Historical Execution Success Rate × B% + Historical Average Repair Time Reverse Score × C%, where B% + C% = 100%.

[0064] For example, in the case of three possible solutions to a robotic arm malfunction, the calculation results are as follows: Solution A (constraint satisfaction score 90, utility score 0.92×0.6+0.4×0.4=0.728, overall score 90×0.5+0.728×100×0.5=81.4), Solution B (constraint satisfaction score 85, utility score 0.88×0.6+0.8×0.4=0.848, overall score 85×0.5+0.848×100×0.5=84.9), and Solution C (constraint satisfaction score 75, utility score 0.75×0.6+1.0×0.4=0.85, overall score 75×0.5+0.85×100×0.5=80). The final priority ranking is Solution B > Solution A > Solution C.

[0065] Optionally, the weights of multidimensional constraint information and historical utility indicators can be dynamically adjusted based on the actual urgency of the fault and production environment parameters. For example, when the fault urgency is high, the weight of the historical average repair time indicator is increased, while the weight of resource cost constraints is decreased. When the production environment is in a non-peak capacity period, the weight of resource utilization utility indicators can be increased to balance fault handling efficiency and production resource costs. Therefore, before step S22, the fault urgency and / or production environment status associated with the fault diagnosis process can be determined based on the fault diagnosis information corresponding to the fault diagnosis process. Then, based on the fault urgency and / or production environment status, the weights of the multidimensional constraint information and the weights of the historical utility indicator set in the scoring function are updated.

[0066] For example, the initial scoring function weights are set as follows: 40% for multidimensional constraint information and 60% for historical utility index set. Then, based on fault diagnosis information, it is determined that the robotic arm is associated with an urgent parts order for delivery that day, indicating a high degree of urgency. Furthermore, the production line is operating at peak capacity, and a one-minute downtime would result in significant order losses. At this point, the system automatically updates the weights, increasing the weight of historical average repair time from 30% to 50% and decreasing the weight of historical execution success rate to 10%. Simultaneously, the weight of resource cost constraints in the multidimensional constraint information is reduced from 20% to 5%, while the weight of production task matching constraints is increased to 35%. After these adjustments, the solution with the shorter repair time exhibits a further significant advantage over other solutions in terms of overall scoring. Even if the spare parts cost of this solution is slightly higher than others, it can still become the optimal recommendation due to its core advantage of "short time consumption," meeting the urgent handling needs of urgent orders. The weight adjustments for other situations, such as non-peak capacity periods, are similar and will not be elaborated upon here.

[0067] This embodiment provides a method for determining fault handling solutions. By first filtering out invalid solutions that do not meet rigid constraints, it avoids interference from solutions without feasible execution basis in subsequent ranking, ensuring the efficiency of scoring calculation and the validity of the benchmark. Next, a weighted integration of all flexible constraint dimensions, combined with historical utility indicators, achieves a globally optimal evaluation of the solutions. This avoids decision-making bias caused by single constraints or simple mixed constraints, clearly traces the contribution of each constraint dimension to the scoring results, lays the foundation for generating interpretable reports, and improves the accuracy, adaptability, and credibility of fault handling solution recommendations.

[0068] Based on any embodiment of this application, in the fourth embodiment of this application, the same or similar content as the above embodiments can be referred to the above description, and will not be repeated hereafter. On this basis, when calculating the historical utility index set, the historical average repair time and historical execution success rate of any one of the multiple solutions to be dealt with can be obtained in terms of the single-dimensional information of the multi-dimensional constraint information. The two core performance indicators, historical average repair time and historical execution success rate, can be accurately bound to the single-dimensional information of the multi-dimensional constraints. This makes the historical data no longer an abstract value detached from the actual production scenario, but a quantitative basis that can directly match specific constraint dimensions such as spare parts, personnel, and production tasks. This provides a standardized and traceable evaluation benchmark for subsequent comparison of solution performance under different constraint dimensions, and can also support the dynamic weight adjustment needs when the urgency of the fault changes or the production environment changes.

[0069] Next, by associating the historical average repair time and historical execution success rate under the same single-dimensional information, historical utility indicators for the proposed solutions under the same single-dimensional information are obtained. Finally, based on these historical utility indicators and multi-dimensional constraint information, a set of historical utility indicators is constructed. By linking the two core performance indicators—historical average repair time and historical execution success rate—to the single-dimensional information of multi-dimensional constraints one by one, historical utility is no longer abstract data detached from real-world scenarios, but rather a quantitative basis that accurately matches specific constraints such as spare parts, personnel, and production tasks. This is achieved by integrating the single-dimensional utility indicators into a set of indicators. Calculating the historical utility indicators of the proposed solutions under different constraint conditions provides effective data support for subsequent data filtering and report generation.

[0070] For example, regarding a robotic arm positioning deviation fault, the available maintenance personnel in the current multi-dimensional constraints are "senior maintenance personnel M with robotic arm calibration skills," the spare part is "compatible positioning sensor," and the solutions to be addressed are solution B (equipment parameter calibration) and solution A (equipment replacement). When performed by maintenance personnel M, solution B has a historical success rate of 93% and a historical average repair time of 18 minutes. However, when performed by ordinary maintenance personnel N, solution B has a historical success rate of 78% and a historical average repair time of 35 minutes. Similarly, when replacing the faulty component, when performed by maintenance personnel M, the historical success rate is 95% and the historical average repair time is 40 minutes. When performed by ordinary maintenance personnel N, the historical success rate is 85% and the historical average repair time is 55 minutes. It can be seen that the utility of different maintenance personnel handling the same solution differs, i.e., the historical utility indicators are different under different constraints. Therefore, for the same solution to be addressed, there are multiple different sets of historical utility indicators. When calculating priorities based on the historical utility indicator sets, selection needs to be based on the actual constraints.

[0071] For example, to help understand the implementation flow of the fault handling solution determination method obtained by combining the above embodiments, please refer to... Figure 4 , Figure 4 A simplified flowchart illustrating a method for determining a fault handling solution is provided, specifically: Upon startup, the user / administrator inputs standardized fault diagnosis information into the system. Based on this information, the system retrieves information from the knowledge base and generates a set of candidate solutions {S1, S2, ..., S...}. n The parallel processing phase then begins, simultaneously completing two key data acquisition and calculation tasks: acquiring multi-dimensional dynamic constraint information C in parallel to obtain rigid / flexible constraints under the current production scenario; and simultaneously calculating the historical utility index U for each solution in parallel. For each candidate solution Si, the historical execution success rate, historical average repair time, and other performance data are extracted to form the historical utility index U(Si) of that solution.

[0072] Subsequently, based on the above data, a multi-constraint optimization model was constructed, clarifying the objective and constraints: Objective function: MaximizeScore(Si)=f(U(Si),C), which means maximizing the comprehensive score Score(Si) of each candidate solution Si. The score is calculated by combining the historical utility index U(Si) of the solution and the current multidimensional constraint information C.

[0073] Constraint: Subjecttog(Si, C) ≤ 0.

[0074] This function is used to determine the feasibility of solution Si under the current constraint C. Solutions that do not meet the constraint will be directly determined as infeasible and excluded from the candidate pool. If none of them meet the constraint, the optimal solution will be selected from the pool.

[0075] Next, the global optimal solution sequence is solved. The solver is invoked to calculate the multi-constraint optimization model, outputting the global optimal solution sequence that satisfies the constraints, i.e., the priority ranking result of all feasible solutions. In the optimal recommendation report generation stage, an optimal recommendation report is generated based on the optimal solution sequence. The core content of this report includes: the preferred solution S. k Its overall score: S k This is the optimal solution in the ranking, and the required resource list is as follows: for example, "Spare Part A". 2. Technical staff member Wang Wu spent 2 hours clarifying the resource requirements for implementing the plan; Estimated time: For example, "4.5 hours (based on historical average)," estimated based on repair time data in historical utility index U(Si); the reasoning is used to explain why the solution is the optimal recommendation, and the matching logic between the associated constraint C and historical utility U(Si).

[0076] Finally, the optimal recommendation report is output, and the entire fault handling solution recommendation process is completed.

[0077] Based on any embodiment of this application, in the fourth embodiment of this application, the content that is the same as or similar to the above embodiments can be referred to the above description, and will not be repeated hereafter. On this basis, under different constraints, the priority of the solutions to be handled varies. Under normal circumstances, the fault handling solution recommendation system ranks the solutions to be handled based on preset constraints, and this result is usually the optimal result.

[0078] Therefore, while displaying multiple pending solutions and their corresponding priority scores on the interface, the system can also output corresponding filtering conditions. That is, before step S30, the system can respond to filtering instructions for multiple pending solutions, determine the filtering information associated with the filtering instruction, and then set the filtering information as a preset constraint. For example, when on-site maintenance personnel discover that the current spare parts inventory is critically low, they can trigger the "Spare Parts Constraint Priority" filtering instruction on the system interface. The system will then automatically increase the weight of the spare parts satisfaction dimension to above a preset threshold, and use this as the core constraint to reorder the priority scores of all feasible solutions, outputting a new ranking result centered on spare parts availability (such as B, A, D, C). If maintenance personnel subsequently discover temporary adjustments to the personnel schedule, they can switch to triggering the "Personnel Constraint Priority" filtering instruction. The system will then dynamically adjust the weight of the personnel availability rate, outputting a ranking result centered on personnel suitability (such as A, B, C, D), allowing maintenance personnel to flexibly obtain targeted solution recommendations based on real-time changes on-site, improving the efficiency and accuracy of fault handling.

[0079] This application provides a fault handling scheme recommendation system, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the fault handling scheme determination method in the first embodiment described above.

[0080] The following is for reference. Figure 5 It shows a schematic diagram of a fault handling scheme recommendation system suitable for implementing the embodiments of this application. Figure 5 The fault handling solution recommendation system shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0081] like Figure 5As shown, the fault handling solution recommendation system may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The random access memory 1004 also stores various programs and data required for the operation of the fault handling solution recommendation system. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the fault handling system recommendation system to communicate wirelessly or wiredly with other devices to exchange data. Although a fault handling system recommendation system with various systems is shown in the figure, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0082] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0083] The fault handling solution recommendation system provided in this application, employing the fault handling solution determination method in the above embodiments, can solve the technical problem of the disconnect between the currently output handling solution and the actual product condition. Compared with the prior art, the beneficial effects of the fault handling solution recommendation system provided in this application are the same as those of the fault handling solution determination method provided in the above embodiments, and other technical features of this fault handling solution recommendation system are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0084] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0085] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0086] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the fault handling scheme determination method in the above embodiments.

[0087] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory (EPROM, or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, radio frequency (RF), etc., or any suitable combination thereof.

[0088] The aforementioned computer-readable storage medium may be included in the fault handling solution recommendation system; or it may exist independently and not be assembled into the fault handling solution recommendation system.

[0089] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by the fault handling solution recommendation system, the fault handling solution recommendation system: obtains multi-dimensional constraint information of the production environment to which the fault diagnosis process belongs, and calculates the historical utility index set of multiple solutions to be handled corresponding to the fault diagnosis process. Using the multidimensional constraint information as constraints and the historical utility index set as evaluation factors, the ranking priority of multiple proposed solutions is determined. The solution with the highest priority under preset constraints is determined as the target solution in the fault diagnosis process.

[0090] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0091] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0092] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0093] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described method for determining a fault handling solution, thereby solving the technical problem of a disconnect between the currently output handling solution and the actual product condition. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the fault handling solution determination method provided in the above embodiments, and will not be repeated here.

[0094] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for determining a fault handling plan, characterized in that, The method for determining the fault handling plan includes: Obtain multi-dimensional constraint information of the production environment to which the fault diagnosis process belongs, and calculate the historical utility index set of multiple solutions to be handled corresponding to the fault diagnosis process; Using the multidimensional constraint information as constraints and the historical utility index set as evaluation factors, the ranking priority of multiple proposed solutions is determined. The solution with the highest priority under preset constraints is determined as the target solution in the fault diagnosis process.

2. The method for determining a fault handling solution as described in claim 1, characterized in that, After the step of determining the highest priority solution under preset constraints as the target solution for the fault diagnosis process, the method for determining the fault solution further includes: Obtain a recommendation report of the target treatment plan, the recommendation report including at least the ranking result and ranking basis of the ranking priority, as well as the target treatment plan and its basic information; Output the recommendation report.

3. The recommended method of the fault handling scheme as described in claim 1, characterized in that, The step of determining the ranking priority of multiple proposed solutions using the multidimensional constraint information as constraints and the historical utility index set as evaluation factors includes: Using the multidimensional constraint information as constraints and the historical utility index set as evaluation factors, a multidimensional priority evaluation model is constructed. Invalid solutions are screened out from the solutions to be dealt with based on the multi-dimensional priority evaluation model, and a comprehensive score result of multiple solutions to be dealt with is calculated by weighting according to the scoring function constructed based on the constraints and the evaluation factors. The ranking priority of the multiple solutions to be dealt with after filtering out invalid solutions is generated based on the comprehensive scoring results.

4. The method for determining a fault handling solution as described in claim 3, characterized in that, Following the step of constructing a multi-dimensional priority evaluation model using the multi-dimensional constraint information as constraints and the historical utility index set as evaluation factors, the method for determining the fault handling plan further includes: Based on the fault diagnosis information corresponding to the fault diagnosis process, determine the fault urgency and / or production environment status associated with the fault diagnosis process. Based on the fault urgency and / or the production environment status, update the weights of the multidimensional constraint information and the weights of the historical utility index set in the scoring function.

5. The method for determining a fault handling solution as described in claim 1, characterized in that, The steps for calculating the historical utility index set of multiple pending solutions corresponding to the fault diagnosis process include: Among the multiple proposed solutions, obtain the historical average repair time and historical execution success rate of any one of the single-dimensional information of the multidimensional constraint information for the proposed solution; By associating the historical average repair time and the historical execution success rate under the same single-dimensional information, the historical utility index of the solution to be dealt with under the same single-dimensional information is obtained; Based on the historical utility indicators and the multidimensional constraint information, the historical utility indicator set is constructed.

6. The method for determining a fault handling plan as described in claim 1, characterized in that, Before the step of determining the highest-priority proposed solution under preset constraints as the target proposed solution in the fault diagnosis process, the method for determining the fault proposed solution further includes: In response to the filtering instructions of the multiple proposed solutions, determine the filtering information associated with the filtering instructions; Set the filtering information as the preset constraint.

7. The method for determining a fault handling plan as described in claim 1, characterized in that, Before the steps of obtaining multi-dimensional constraint information of the production environment to which the fault diagnosis process belongs, and calculating the historical utility indicators of multiple pending solutions corresponding to the fault diagnosis process, the method for determining the fault handling solution further includes: If the fault diagnosis process is triggered, the received fault diagnosis information is obtained; Based on the fault diagnosis information, multiple solutions to be handled are matched in the fault knowledge base.

8. The method for determining a fault handling solution as described in claim 1, characterized in that, Before the step of determining the highest-priority proposed solution under preset constraints as the target proposed solution in the fault diagnosis process, the method for determining the fault proposed solution further includes: If there are conflicting constraints in the multidimensional constraint information, determine the target historical utility index associated with the conflicting constraint. The ranking priority of the multiple proposed solutions is updated based on the target historical utility index.

9. A fault handling solution recommendation system, characterized in that, The fault handling solution recommendation system includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the fault handling solution determination method as described in any one of claims 1 to 8.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the method for determining a fault handling scheme as described in any one of claims 1 to 8.

Images