Intelligent decision support method and system for big data real-time analysis

Abstract

The invention relates to the technical field of intelligence, in particular to an intelligent decision support method and system for big data real-time analysis. The method comprises the following steps: acquiring equipment operation state data, equipment historical maintenance data and equipment maintenance supply data in real time, and performing data transmission preprocessing optimization and fault potential risk assessment to obtain equipment fault historical maintenance potential risk factors; performing equipment fault prediction and task emergency analysis on the equipment operation standard data to obtain an equipment fault maintenance task emergency degree; carrying out fault maintenance decision support analysis on the equipment fault maintenance task point to generate an equipment fault maintenance decision strategy; and based on the equipment fault maintenance decision strategy and in combination with a preset decision model, carrying out maintenance feedback optimization on the corresponding equipment with faults so as to execute corresponding equipment fault maintenance decision dynamic optimization and improvement operation. According to the invention, an intelligent decision-making basis can be provided for equipment maintenance strategy making and maintenance resource allocation.

Description

Technical Field

[0001] This invention relates to the field of intelligent technology, and in particular to an intelligent decision support method and system for real-time big data analysis. Background Technology

[0002] In terms of maintenance strategy formulation, the past mainly relied on the experience and judgment of maintenance personnel and simple equipment fault manuals. For example, when equipment malfunctions, maintenance personnel typically determine the maintenance plan based on their accumulated maintenance experience and by referring to typical fault cases in the fault manual. With the development of big data technology, although a large amount of data has been accumulated in the field of equipment maintenance, there is currently a lack of an effective method to systematically and efficiently analyze equipment maintenance-related big data in real time and transform the analysis results into intelligent decision support. However, traditional methods mostly rely on regular equipment inspections and simple monitoring of equipment operating parameters. This involves periodically checking the appearance and operating sounds of equipment for fault diagnosis, and monitoring thresholds for a few key operating parameters (such as temperature and pressure) to determine the equipment status. However, this approach cannot capture subtle changes and potential fault hazards during equipment operation in a timely manner, leading to difficulties in carrying out maintenance work and seriously affecting the efficiency of equipment maintenance. Summary of the Invention

[0003] Therefore, it is necessary for the present invention to provide an intelligent decision support method and system for real-time big data analysis to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above objectives, an intelligent decision support method for real-time big data analysis includes the following steps: Step S1: Real-time acquisition of equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data; and optimization of data transmission preprocessing for the equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data to obtain equipment operation standard data, historical maintenance standard data, and maintenance supply standard data. Step S2: Based on historical maintenance standard data, conduct a fault potential risk assessment on the equipment operation standard data to obtain the equipment fault historical maintenance potential risk factors; based on the equipment fault historical maintenance potential risk factors, conduct equipment fault prediction on the equipment operation standard data to obtain the equipment fault maintenance prediction results. Step S3: Perform task urgency analysis on the corresponding equipment failure maintenance task points within the equipment failure maintenance prediction results to obtain the urgency level of the equipment failure maintenance task; based on the urgency level of the equipment failure maintenance task and maintenance supply standard data, perform failure maintenance decision support analysis on the corresponding equipment failure maintenance task points to generate equipment failure maintenance decision strategies. Step S4: Based on the equipment fault maintenance decision-making strategy and combined with the preset decision-making model, perform maintenance feedback optimization on the corresponding faulty equipment to execute the corresponding equipment fault maintenance decision dynamic optimization and improvement operation.

[0005] Furthermore, step S1 includes the following steps: Step S11: By installing corresponding vibration sensors, temperature sensors, pressure sensors and current sensors on the equipment, the vibration amplitude, temperature change, pressure fluctuation and current value of the equipment during operation are monitored in real time to obtain equipment operation status data. Step S12: Obtain historical maintenance data of the equipment by collecting historical maintenance data such as maintenance operation records, maintenance time and spare parts replacement information of maintenance personnel in the maintenance management record system in real time; Step S13: Obtain equipment maintenance supply data by collecting real-time data on the quantity of spare parts in stock, the procurement cycle of spare parts, and the supply capacity of spare parts for the equipment. Step S14: Based on the Industrial Internet of Things and combined with high-speed data transmission protocols, transmit equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data to the equipment maintenance data processing center in real time in the shortest possible time. Step S15: Use the equipment maintenance data processing center to perform noise reduction, error correction, and deduplication on equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data. At the same time, use real-time median interpolation combined with data mining technology to supplement the corresponding missing data points. And according to the equipment data standard, the original data corresponding to different formats and different sources are standardized and converted to obtain equipment operation standard data, historical maintenance standard data, and maintenance supply standard data.

[0006] Furthermore, step S2 includes the following steps: Step S21: Perform equipment operation fault analysis on the standard equipment operation data to identify potential fault nodes in equipment operation; Step S22: Based on historical maintenance standard data, conduct a potential risk assessment of the equipment operating parameters corresponding to suspected equipment operation fault nodes to obtain potential risk factors of historical equipment fault maintenance, including potential factors of equipment fault operation disassembly, potential factors of equipment fault maintenance duration, and potential factors of equipment fault replacement compatibility. Step S23: By assigning corresponding equipment fault weights to each equipment operating parameter corresponding to the suspected equipment operation fault node, and using the equipment fault degree calculation formula based on the equipment fault history maintenance potential risk factors and the equipment fault weights corresponding to each equipment operating parameter, the equipment operating parameter corresponding to the suspected equipment operation fault node is used to perform fault quantification calculation to obtain the equipment fault degree. Step S24: Compare and judge the degree of equipment failure according to the preset equipment failure threshold. If the degree of equipment failure at the node is greater than or equal to the preset equipment failure threshold, it is considered that there is an equipment failure at the node and it is designated as a maintenance task point. If the degree of equipment failure at the node is less than the preset equipment failure threshold, it is considered that there is no equipment failure at the node and the next node is judged. This process continues until all suspected equipment failure nodes have been judged, and the equipment failure maintenance prediction result is obtained.

[0007] Furthermore, step S21 includes the following steps: The equipment operation parameters corresponding to the equipment operation standard data are time-series synchronized in the time dimension to obtain the corresponding equipment operation data in the same time dimension. The time-series change trend of equipment operation data under the same time dimension is plotted to generate the change trend map of equipment operation parameters under the same time coordinate system; Based on the corresponding operational fault abnormality threshold, the trend chart of equipment operation parameters under the same time coordinate system is analyzed to determine operational faults. If there is one or more corresponding equipment operation parameters that are greater than or equal to the corresponding operational fault abnormality threshold, the corresponding time node is determined as a suspected operational fault node, so as to obtain the suspected equipment operation fault node.

[0008] Furthermore, step S22 includes the following steps: By obtaining the corresponding maintenance operation records in the historical maintenance standard data, the complexity of the corresponding equipment maintenance operation and the technical difficulty required for maintenance operation disassembly are obtained. Based on the complexity of the equipment maintenance operation and the technical difficulty required for maintenance operation disassembly, the operation potential factors of the equipment operation parameters corresponding to the suspected equipment operation fault nodes are evaluated to obtain the potential factors for equipment fault operation disassembly. By performing a maintenance cycle distribution analysis on the corresponding maintenance time within the historical maintenance standard data, the historical maintenance time cycle distribution of the equipment is obtained. Based on the historical maintenance time cycle distribution of equipment, the maintenance time distribution potential factors of the equipment operation parameters corresponding to the suspected nodes of equipment operation failure are evaluated to obtain the potential factors of equipment failure maintenance duration. Based on the replacement spare parts information in the historical maintenance standard data, the equipment operating parameters corresponding to the suspected equipment failure nodes are evaluated for potential replacement factors to obtain equipment failure replacement compatibility potential factors.

[0009] Furthermore, the assessment of potential replacement factors for equipment operating parameters at suspected fault points based on replacement spare parts information within historical maintenance standard data includes the following steps: The types of replacement parts and the frequency of equipment replacement can be obtained by referring to the replacement parts information in the historical maintenance standard data. Based on the types of spare parts that can be replaced, a spare parts operation compatibility analysis is performed on the corresponding equipment to obtain the operation compatibility probability between the equipment and the replaced spare parts. Based on the equipment replacement frequency and the operational compatibility probability between the equipment and the replacement spare parts, the equipment operation parameters corresponding to the suspected equipment failure nodes are evaluated to obtain the equipment failure replacement compatibility potential factors.

[0010] Furthermore, the specific formula for calculating the degree of equipment failure mentioned in step S23 is as follows: ; In the formula, Depending on the degree of equipment failure, For suspected equipment malfunction nodes The corresponding vibration amplitude value at that location, For vibration amplitude fault weights, For suspected equipment malfunction nodes The corresponding temperature change value at that location, For temperature change fault weights, For suspected equipment malfunction nodes The corresponding pressure fluctuation value, For pressure fluctuation fault weights, For suspected equipment malfunction nodes The corresponding current value at that location, For current fault weights, To identify potential factors contributing to equipment malfunctions. Replace compatibility potential factors for equipment malfunctions. Potential factors affecting equipment failure repair time, The time required for equipment malfunction repair. This is a correction factor for the degree of equipment failure.

[0011] Furthermore, step S3 includes the following steps: Step S31: Obtain the corresponding equipment fault type, equipment fault duration, and equipment fault location through the corresponding equipment fault repair task point in the equipment fault repair prediction result. Step S32: Based on the equipment failure type, equipment failure duration, and equipment failure location, perform a task urgency analysis on the corresponding equipment failure repair task points to obtain the urgency level of the equipment failure repair task. Step S33: Sort the corresponding equipment fault repair tasks according to the urgency of the equipment fault repair tasks to generate an urgent priority sequence of equipment fault repair tasks. Step S34: Based on the spare parts inventory quantity, spare parts procurement cycle, and spare parts supply capacity within the maintenance supply standard data, perform fault maintenance decision support analysis on the priority equipment fault maintenance task points within the emergency priority task sequence for equipment fault maintenance. Recommend the optimal fault maintenance strategy based on the corresponding spare parts inventory quantity, spare parts procurement cycle, and spare parts supply capacity, including maintenance personnel allocation, spare parts inventory usage, and fault maintenance resource allocation, and generate equipment fault maintenance decision strategies.

[0012] Furthermore, step S4 includes the following steps: Step S41: Based on the equipment fault maintenance decision strategy, perform initial equipment maintenance on the corresponding faulty equipment to generate the corresponding equipment fault maintenance execution process; Step S42: By deploying real-time monitoring points in the corresponding equipment fault repair execution process, the corresponding repair time, repair cost, equipment repair efficiency and repair quality after the repair decision is executed are collected in real time to obtain equipment fault repair feedback data. Step S43: Input the equipment failure maintenance feedback data into the preset decision model to use the online learning algorithm to optimize the maintenance feedback of the corresponding faulty equipment. If it is found that the actual maintenance time corresponding to a certain maintenance decision strategy exceeds the expectation, the model automatically analyzes the reasons to adjust the maintenance resource allocation strategy. If it is found that a certain maintenance decision strategy leads to resource waste or shortage, the model re-optimizes the constraints corresponding to resource allocation to achieve dynamic optimization and continuous improvement of maintenance decisions, so as to execute the corresponding dynamic optimization and improvement operation of equipment failure maintenance decisions.

[0013] Furthermore, the present invention also provides an intelligent decision support system for real-time big data analysis, used to execute the intelligent decision support method for real-time big data analysis as described above. The intelligent decision support system for real-time big data analysis includes: The equipment big data real-time acquisition module is used to acquire equipment operating status data, equipment historical maintenance data, and equipment maintenance supply data in real time. It also performs data transmission preprocessing optimization on the equipment operating status data, equipment historical maintenance data, and equipment maintenance supply data to obtain equipment operating standard data, historical maintenance standard data, and maintenance supply standard data. The equipment failure risk prediction module is used to assess the potential failure risk of equipment operation standard data based on historical maintenance standard data to obtain the historical maintenance potential risk factors of equipment failure; and to predict equipment failure based on the historical maintenance potential risk factors of equipment failure and the equipment operation standard data to obtain the equipment failure maintenance prediction result. The equipment failure maintenance decision analysis module is used to perform task urgency analysis on the corresponding equipment failure maintenance task points within the equipment failure maintenance prediction results to obtain the urgency level of the equipment failure maintenance task; based on the urgency level of the equipment failure maintenance task and maintenance supply standard data, it performs failure maintenance decision support analysis on the corresponding equipment failure maintenance task points to generate equipment failure maintenance decision strategies. The equipment maintenance feedback optimization module is used to optimize the maintenance feedback of corresponding faulty equipment based on the equipment fault maintenance decision-making strategy and in combination with the preset decision-making model, so as to execute the corresponding equipment fault maintenance decision dynamic optimization and improvement operation.

[0014] The beneficial effects of this invention are: 1. The intelligent decision support method for real-time big data analysis proposed in this invention, compared with the prior art, has the following advantages: it can ensure the real-time and efficient acquisition of equipment operating status, historical maintenance records, and maintenance supply chain related data. This data provides a solid foundation for subsequent analysis and decision-making. By preprocessing and optimizing this data, noise and inconsistencies in the original data can be eliminated, data formats can be unified, and data cleaning can be performed to improve data quality and accuracy. In particular, the optimization of equipment operating status data transmission enables real-time equipment monitoring data to be transmitted to the system with no or low latency, providing timely information for subsequent fault prediction and maintenance decisions. The standardization of historical maintenance data helps to establish historical models of equipment faults, thereby identifying potential fault modes and patterns and helping to determine whether there is a correlation between equipment operation and historical maintenance. The standardization of maintenance supply standard data can also optimize the scheduling of maintenance resources, enabling maintenance resources and services to be accurately matched with equipment needs. This allows for the timely capture of subtle changes and potential fault hazards during equipment operation, thereby improving the accuracy and reliability of subsequent fault prediction and decision-making. Secondly, by analyzing historical maintenance standard data, we can delve into the patterns and characteristics of past failures, assess the potential risks of each piece of equipment failure, and derive specific risk factors based on in-depth analysis of historical maintenance data. These factors provide key information for predictive models, helping the system to more accurately predict equipment failures. This process also effectively improves the accuracy of failure prediction, avoiding the blindness and inefficiency of traditional manual inspection methods, and prompting managers to intervene early. Thirdly, task urgency analysis helps to prioritize the identification of failure maintenance tasks that have a significant impact on production. Each failure maintenance task has a different level of urgency; some failures require immediate repair, while others can be resolved in subsequent maintenance. Through urgency analysis, these tasks can be categorized and managed, ensuring that the most urgent failures are addressed first, avoiding production stoppages or greater losses due to maintenance delays. Meanwhile, by combining maintenance supply standard data, this process helps optimize the scheduling and allocation of maintenance resources. The decision-making model can recommend the most suitable maintenance plan based on existing maintenance supply data, avoiding the impact of resource conflicts on maintenance efficiency, and thus proposing the most suitable maintenance plan. The intelligence and systematization of this strategy can greatly reduce the bias of human decision-making, improve decision-making efficiency, and ensure the timeliness and effectiveness of equipment maintenance work.Finally, by combining a pre-set decision-making model, maintenance strategies can be continuously adjusted based on real-time feedback information. For example, during the execution of fault repair tasks, the system will adjust maintenance strategies in a timely manner based on feedback data such as actual repair results, repair time, and equipment recovery status, and optimize subsequent maintenance plans. This not only better adapts to changes in actual production conditions, but also optimizes the decision-making model based on feedback, improving the execution and efficiency of maintenance strategies. The dynamic optimization process can avoid the limitations brought by static decision-making models, improve the flexibility and adaptability of equipment maintenance, and thus enhance equipment maintenance efficiency and the level of intelligence in equipment management.

[0015] 2. The intelligent decision support system for real-time big data analysis proposed in this invention is composed of an equipment big data real-time acquisition module, an equipment fault risk prediction module, an equipment fault maintenance decision analysis module, and an equipment maintenance feedback optimization module. It can realize the intelligent decision support method for real-time big data analysis described in this invention. It is used to combine the operations between the computer programs running on each module to realize the intelligent decision support method for real-time big data analysis. The internal structure of the system cooperates with each other, which can greatly reduce repetitive work and manpower input, and can quickly and effectively provide a more accurate and efficient intelligent decision support process for real-time big data analysis, thereby simplifying the operation process of the intelligent decision support system for real-time big data analysis. Attached Figure Description

[0016] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a flowchart illustrating the steps of the intelligent decision support method for real-time big data analysis of the present invention. Figure 2 for Figure 1 A detailed flowchart of step S1; Figure 3 for Figure 1 A detailed flowchart of step S2. Detailed Implementation

[0017] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0018] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0019] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0020] To achieve the above objectives, please refer to Figures 1 to 3 This invention provides an intelligent decision support method for real-time big data analysis, the method comprising the following steps: Step S1: Real-time acquisition of equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data; and optimization of data transmission preprocessing for the equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data to obtain equipment operation standard data, historical maintenance standard data, and maintenance supply standard data. Step S2: Based on historical maintenance standard data, conduct a fault potential risk assessment on the equipment operation standard data to obtain the equipment fault historical maintenance potential risk factors; based on the equipment fault historical maintenance potential risk factors, conduct equipment fault prediction on the equipment operation standard data to obtain the equipment fault maintenance prediction results. Step S3: Perform task urgency analysis on the corresponding equipment failure maintenance task points within the equipment failure maintenance prediction results to obtain the urgency level of the equipment failure maintenance task; based on the urgency level of the equipment failure maintenance task and maintenance supply standard data, perform failure maintenance decision support analysis on the corresponding equipment failure maintenance task points to generate equipment failure maintenance decision strategies. Step S4: Based on the equipment fault maintenance decision-making strategy and combined with the preset decision-making model, perform maintenance feedback optimization on the corresponding faulty equipment to execute the corresponding equipment fault maintenance decision dynamic optimization and improvement operation.

[0021] In the embodiments of this invention, please refer to Figure 1The diagram shown is a flowchart illustrating the steps of the intelligent decision support method for real-time big data analysis according to the present invention. In this example, the intelligent decision support method for real-time big data analysis includes the following steps: Step S1: Real-time acquisition of equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data; and optimization of data transmission preprocessing for the equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data to obtain equipment operation standard data, historical maintenance standard data, and maintenance supply standard data. In this embodiment of the invention, various sensors installed on the equipment, such as vibration sensors, temperature sensors, pressure sensors, and current sensors, collect real-time equipment operating status data multiple times per second. This data covers information such as vibration amplitude, temperature changes, pressure fluctuations, and current values ​​during equipment operation. Historical equipment maintenance data, including maintenance personnel's operation records, maintenance time, and spare parts replacement information, is retrieved from the maintenance management system database. Simultaneously, equipment maintenance supply data, such as spare parts inventory quantity, spare parts procurement cycle, and spare parts supply capacity, is obtained from the spare parts inventory management system and the procurement system. Before data transmission, data cleaning algorithms are used to denoise, correct errors, and remove duplicates from this data. For example, obviously abnormal temperature values ​​(exceeding the normal operating temperature range) in the equipment operating status data are corrected or removed; errors in time recordings in the historical equipment maintenance data are corrected; and duplicate spare parts inventory records in the equipment maintenance supply data are removed. Data interpolation methods are then used to supplement missing data. For example, for occasionally missing pressure values ​​in the equipment operating status data, linear interpolation is used to estimate and fill the missing values ​​based on pressure values ​​at previous and subsequent time points. Finally, based on the pre-established equipment data standards, data from different formats and sources are converted into a unified format, ultimately yielding equipment operation standard data, historical maintenance standard data, and maintenance supply standard data.

[0022] Step S2: Based on historical maintenance standard data, conduct a fault potential risk assessment on the equipment operation standard data to obtain the equipment fault historical maintenance potential risk factors; based on the equipment fault historical maintenance potential risk factors, conduct equipment fault prediction on the equipment operation standard data to obtain the equipment fault maintenance prediction results. In this embodiment of the invention, a potential fault risk assessment model is constructed, and the maintenance operation records and spare parts replacement information in the historical maintenance standard data are correlated with various parameters in the equipment operation standard data. For example, the changes in relevant parameters (such as pressure, current, etc. related to the function of the spare parts) in the current operating status data of equipment with frequent replacement of a certain type of spare parts in the past are analyzed. If it is found that a certain equipment has replaced a certain key component multiple times in the past maintenance, and the parameters corresponding to the component fluctuate greatly during the current operation, a high risk score is assigned in the assessment model. Taking into account multiple factors, a potential fault risk score is calculated for each parameter in the equipment operation standard data, thereby obtaining the equipment fault historical maintenance potential risk factor. Based on the equipment fault historical maintenance potential risk factor, fault prediction algorithms, such as decision tree algorithms and neural network algorithms based on machine learning, are used to analyze the equipment operation standard data. The changing trend of equipment operation parameters and historical fault modes are used as input features to predict the type, time and location of future faults of the equipment, and finally generate the equipment fault maintenance prediction result.

[0023] Step S3: Perform task urgency analysis on the corresponding equipment failure maintenance task points within the equipment failure maintenance prediction results to obtain the urgency level of the equipment failure maintenance task; based on the urgency level of the equipment failure maintenance task and maintenance supply standard data, perform failure maintenance decision support analysis on the corresponding equipment failure maintenance task points to generate equipment failure maintenance decision strategies. In this embodiment of the invention, for each equipment failure maintenance task point determined from the equipment failure maintenance prediction results, an urgency analysis is conducted based on factors such as the severity of the failure, the scope of its impact on normal equipment operation, and the resulting losses. For example, if an equipment failure may lead to production line shutdown and cause significant economic losses, the urgency level of that task point is determined to be high; if the failure only affects part of the equipment's function and has a minor impact on overall operation, the urgency level is determined to be low. Using methods such as the Analytic Hierarchy Process (AHP), multiple factors are comprehensively considered to determine a specific urgency value for each task point. Combining the urgency level of the equipment failure maintenance task with maintenance supply standard data, a failure maintenance decision support analysis is performed for each task point. If a task point has a high urgency level and sufficient spare parts inventory, maintenance personnel are prioritized for maintenance, and spare parts are used for replacement. If spare parts inventory is insufficient but the procurement cycle is short, maintenance personnel can be prepared first, and the spare parts procurement process can be initiated to ensure timely supply of spare parts. Based on different situations, an equipment failure maintenance decision-making strategy is formulated, including maintenance personnel allocation, spare parts usage and procurement plans, maintenance steps, and time arrangements.

[0024] Step S4: Based on the equipment fault maintenance decision-making strategy and combined with the preset decision-making model, perform maintenance feedback optimization on the corresponding faulty equipment to execute the corresponding equipment fault maintenance decision dynamic optimization and improvement operation.

[0025] In this embodiment of the invention, during the execution of equipment failure maintenance decision-making strategies, data such as maintenance time, maintenance personnel operation records, spare parts usage, and post-repair equipment operating status data are collected in real time. This data is input into a preset decision-making model, which can be a rule-based expert system model or a machine learning-based intelligent model. The model compares and analyzes the input data with preset standards and targets. For example, it compares the actual maintenance time with the expected maintenance time. If the actual maintenance time is too long, it analyzes whether the problem is due to maintenance personnel skill issues, spare parts supply issues, or unreasonable maintenance procedures. If a spare part is found to have a similar failure shortly after maintenance, it assesses whether the problem is due to spare part quality issues or installation operation issues. Based on the analysis results, the equipment failure maintenance decision-making strategy is adjusted and optimized, such as reallocating maintenance personnel, changing spare parts suppliers, or improving maintenance operation procedures. This dynamic optimization and improvement of equipment failure maintenance decisions is carried out to improve the efficiency and quality of equipment maintenance and reduce the probability of future failures.

[0026] Furthermore, step S1 includes the following steps: Step S11: By installing corresponding vibration sensors, temperature sensors, pressure sensors and current sensors on the equipment, the vibration amplitude, temperature change, pressure fluctuation and current value of the equipment during operation are monitored in real time to obtain equipment operation status data. Step S12: Obtain historical maintenance data of the equipment by collecting historical maintenance data such as maintenance operation records, maintenance time and spare parts replacement information of maintenance personnel in the maintenance management record system in real time; Step S13: Obtain equipment maintenance supply data by collecting real-time data on the quantity of spare parts in stock, the procurement cycle of spare parts, and the supply capacity of spare parts for the equipment. Step S14: Based on the Industrial Internet of Things and combined with high-speed data transmission protocols, transmit equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data to the equipment maintenance data processing center in real time in the shortest possible time. Step S15: Use the equipment maintenance data processing center to perform noise reduction, error correction, and deduplication on equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data. At the same time, use real-time median interpolation combined with data mining technology to supplement the corresponding missing data points. And according to the equipment data standard, the original data corresponding to different formats and different sources are standardized and converted to obtain equipment operation standard data, historical maintenance standard data, and maintenance supply standard data.

[0027] As an embodiment of the present invention, reference is made to... Figure 2 As shown, Figure 1 A detailed flowchart of step S1 is shown below. In this embodiment, step S1 includes the following steps: Step S11: By installing corresponding vibration sensors, temperature sensors, pressure sensors and current sensors on the equipment, the vibration amplitude, temperature change, pressure fluctuation and current value of the equipment during operation are monitored in real time to obtain equipment operation status data. In this embodiment of the invention, high-precision vibration sensors, temperature sensors, pressure sensors, and current sensors are installed at key locations on the equipment, such as the engine casing, near the motor windings, and key nodes in the hydraulic pipelines. The vibration sensors are piezoelectric vibration sensors, which collect vibration signals during equipment operation at a frequency of 100 times per second. Vibration amplitude data is obtained by measuring the acceleration, velocity, and displacement of the vibration. The temperature sensors are thermocouple temperature sensors, which monitor temperature changes of equipment components in real time and record temperature values ​​every 5 seconds. The pressure sensors are piezoresistive pressure sensors, installed on the hydraulic system pipelines, continuously monitoring pressure fluctuations and collecting pressure data once per second. The current sensors are Hall effect current sensors, connected in series in the equipment's circuitry, measuring current values ​​in real time and recording current data once per second. The data collected by these sensors are integrated to obtain the final equipment operating status data.

[0028] Step S12: Obtain historical maintenance data of the equipment by collecting historical maintenance data such as maintenance operation records, maintenance time and spare parts replacement information of maintenance personnel in the maintenance management record system in real time; In this embodiment of the invention, a dedicated module is set up in the maintenance management record system to record the operations of maintenance personnel. When maintenance personnel repair equipment, each maintenance operation step is recorded in detail in the system, such as disassembly, inspection, and replacement of parts. At the same time, the system automatically records the start and end time of maintenance, accurate to the second. For replaced spare parts, maintenance personnel enter information such as the name, model, manufacturer, and replacement time of the spare parts into the system. The system stores this data in the form of a database. Each time a maintenance task is completed, a complete maintenance record is generated. By periodically retrieving these records from the database, the maintenance historical data in the maintenance management record system is collected in real time. After sorting and classifying, the equipment historical maintenance data is finally obtained.

[0029] Step S13: Obtain equipment maintenance supply data by collecting real-time data on the quantity of spare parts in stock, the procurement cycle of spare parts, and the supply capacity of spare parts for the equipment. In this embodiment of the invention, a spare parts inventory management system is established. This system is connected to the warehouse's inventory management equipment, which uses barcode scanners and electronic tag readers to read the inventory quantity information of spare parts in real time. When spare parts are put into or taken out of the warehouse, the system automatically updates the inventory quantity. For the spare parts procurement cycle, by connecting with the procurement department's system, information such as the procurement application time, supplier confirmation time, delivery time and arrival time of each spare part is obtained, and the procurement cycle is calculated. The spare parts supply capacity is evaluated by analyzing factors such as the supplier's production capacity, delivery records and transportation methods. This information is collected periodically, and the spare parts inventory quantity, procurement cycle and supply capacity data are integrated to finally obtain equipment maintenance supply data.

[0030] Step S14: Based on the Industrial Internet of Things and combined with high-speed data transmission protocols, transmit equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data to the equipment maintenance data processing center in real time in the shortest possible time. In this embodiment of the invention, an industrial Internet of Things (IoT) network is constructed to connect devices such as sensors, maintenance management record systems, and spare parts inventory management systems on the equipment to the network. High-speed data transmission protocols, such as industrial Ethernet or 5G communication protocols, are used to ensure rapid data transmission. For equipment operating status data, the data collected by the sensors is directly transmitted to the server of the data processing center through the network. The historical maintenance data and equipment maintenance supply data are sent to the data processing center by their respective systems through the network interface. The data processing center is equipped with a dedicated receiving module to receive these data in real time and perform preliminary analysis and storage of the data to ensure that the latest data information is obtained in the shortest possible time.

[0031] Step S15: Use the equipment maintenance data processing center to perform noise reduction, error correction, and deduplication on equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data. At the same time, use real-time median interpolation combined with data mining technology to supplement the corresponding missing data points. And according to the equipment data standard, the original data corresponding to different formats and different sources are standardized and converted to obtain equipment operation standard data, historical maintenance standard data, and maintenance supply standard data.

[0032] In this embodiment of the invention, the equipment maintenance data processing center uses data cleaning algorithms to process equipment operating status data, historical equipment maintenance data, and equipment maintenance supply data. For equipment operating status data, filtering algorithms are used to remove noise interference, such as removing high-frequency noise from vibration sensor data. Logical verification and statistical analysis methods are used to correct data errors, such as checking whether maintenance time records conform to logical order. Data is deduplicated using hash algorithms to ensure data uniqueness. For missing data points, real-time median interpolation is used, combined with data mining techniques to analyze data trends and correlations, and missing values ​​are supplemented. For data of different formats and sources, they are converted into a unified format according to equipment data standards, such as unifying the time format to "YYYY-MM-DD HH:MM:SS" and standardizing the spare parts model format, etc., finally obtaining standard equipment operating data, historical maintenance data, and maintenance supply data.

[0033] Furthermore, step S2 includes the following steps: Step S21: Perform equipment operation fault analysis on the standard equipment operation data to identify potential fault nodes in equipment operation; Step S22: Based on historical maintenance standard data, conduct a potential risk assessment of the equipment operating parameters corresponding to suspected equipment operation fault nodes to obtain potential risk factors of historical equipment fault maintenance, including potential factors of equipment fault operation disassembly, potential factors of equipment fault maintenance duration, and potential factors of equipment fault replacement compatibility. Step S23: By assigning corresponding equipment fault weights to each equipment operating parameter corresponding to the suspected equipment operation fault node, and using the equipment fault degree calculation formula based on the equipment fault history maintenance potential risk factors and the equipment fault weights corresponding to each equipment operating parameter, the equipment operating parameter corresponding to the suspected equipment operation fault node is used to perform fault quantification calculation to obtain the equipment fault degree. Step S24: Compare and judge the degree of equipment failure according to the preset equipment failure threshold. If the degree of equipment failure at the node is greater than or equal to the preset equipment failure threshold, it is considered that there is an equipment failure at the node and it is designated as a maintenance task point. If the degree of equipment failure at the node is less than the preset equipment failure threshold, it is considered that there is no equipment failure at the node and the next node is judged. This process continues until all suspected equipment failure nodes have been judged, and the equipment failure maintenance prediction result is obtained.

[0034] As an embodiment of the present invention, reference is made to... Figure 3 As shown, Figure 1 A detailed flowchart of step S2 is shown below. In this embodiment, step S2 includes the following steps: Step S21: Perform equipment operation fault analysis on the standard equipment operation data to identify potential fault nodes in equipment operation; In this embodiment of the invention, standard equipment operation data is extracted from the equipment operation database. This data covers various operating parameters of the equipment, such as temperature, pressure, vibration amplitude, current value, as well as information such as operating time and workload. Data analysis algorithms are used to monitor and analyze these parameters in real time, setting normal ranges and trend standards for each operating parameter. For example, the normal operating temperature range of a certain piece of equipment is 50℃-80℃. When the temperature data exceeds this range, or the rate of temperature change is abnormal, that time point is marked as the corresponding fault point. Simultaneously, the correlation between multiple parameters is comprehensively considered. For example, when the pressure increases and the current value also increases abnormally, that time point is further confirmed as a suspected fault node in equipment operation. Through this analysis, suspected fault nodes in equipment operation are screened from the standard equipment operation data.

[0035] Step S22: Based on historical maintenance standard data, conduct a potential risk assessment of the equipment operating parameters corresponding to suspected equipment operation fault nodes to obtain potential risk factors of historical equipment fault maintenance, including potential factors of equipment fault operation disassembly, potential factors of equipment fault maintenance duration, and potential factors of equipment fault replacement compatibility. In this embodiment of the invention, by retrieving historical maintenance standard data, which includes detailed records of past equipment maintenance such as maintenance operation steps, maintenance time, and information on replaced spare parts, the operating parameters at suspected equipment malfunction points are analyzed in relation to historical maintenance records. When calculating potential factors for equipment malfunction operation disassembly, the number and complexity of operation steps for similar malfunctions in historical maintenance are used for evaluation. If handling this type of malfunction historically required complex disassembly steps and professional skills, then the factor value is high. The potential factor for equipment malfunction maintenance time is calculated by referring to the average time for repairing similar malfunctions in history. If this type of malfunction usually takes a long time to repair, then the factor value is high. The potential factor for equipment malfunction replacement compatibility is calculated based on the compatibility of replaced spare parts in history, such as the universality of spare parts and their matching degree with the equipment. If the spare parts replacement compatibility is poor, then the factor value is high. Through these analyses and calculations, the potential risk factors for historical equipment malfunction maintenance are finally obtained.

[0036] Step S23: By assigning corresponding equipment fault weights to each equipment operating parameter corresponding to the suspected equipment operation fault node, and using the equipment fault degree calculation formula based on the equipment fault history maintenance potential risk factors and the equipment fault weights corresponding to each equipment operating parameter, the equipment operating parameter corresponding to the suspected equipment operation fault node is used to perform fault quantification calculation to obtain the equipment fault degree. In this embodiment of the invention, based on the equipment's design requirements and actual operating experience, a corresponding equipment fault weight is assigned to each equipment operating parameter at a suspected fault node. For example, the vibration amplitude is assigned a weight of 0.3; temperature changes and pressure fluctuations are assigned a lower weight of 0.1, while the corresponding current value is assigned a corresponding weight of 0.5. An equipment fault degree calculation formula is constructed, and the actual value of each equipment operating parameter, the corresponding equipment fault weight, and the previously obtained equipment fault history maintenance potential risk factor are substituted into the formula for calculation to obtain the equipment fault degree at that node. In addition, this equipment fault degree calculation formula can also use any fault degree detection method in the art to replace the fault quantification calculation process. For example, equipment fault degree = Σ (equipment operating parameter value × equipment fault weight) × equipment fault history maintenance potential risk factor, and is not limited to this equipment fault degree calculation formula.

[0037] Step S24: Compare and judge the degree of equipment failure according to the preset equipment failure threshold. If the degree of equipment failure at the node is greater than or equal to the preset equipment failure threshold, it is considered that there is an equipment failure at the node and it is designated as a maintenance task point. If the degree of equipment failure at the node is less than the preset equipment failure threshold, it is considered that there is no equipment failure at the node and the next node is judged. This process continues until all suspected equipment failure nodes have been judged, and the equipment failure maintenance prediction result is obtained.

[0038] In this embodiment of the invention, by pre-setting an equipment failure threshold, which is determined comprehensively based on factors such as equipment performance requirements, safety standards, and maintenance costs, for example, setting it to 30, the equipment failure severity of each suspected equipment failure node calculated previously is compared with the preset equipment failure threshold. If the equipment failure severity of a node is 49.2, which is greater than 30, then it is determined that there is an equipment failure in that node, and the node is recorded as a maintenance task point. If the equipment failure severity of a node is 20, which is less than 30, then it is determined that there is no equipment failure in that node. Then, the same comparison and judgment operation is performed on the next suspected equipment failure node until all suspected equipment failure nodes have been judged, and finally the equipment failure maintenance prediction result is obtained, and the task time node that needs to be maintained is determined.

[0039] Furthermore, step S21 includes the following steps: The equipment operation parameters corresponding to the equipment operation standard data are time-series synchronized in the time dimension to obtain the corresponding equipment operation data in the same time dimension. In this embodiment of the invention, standard equipment operation data is extracted from the equipment operation database. This data includes various equipment operation parameters such as vibration amplitude, temperature, pressure, and current. These parameters are collected at different times. A timestamp matching algorithm is used to add precise timestamp information to each parameter data. Taking a certain industrial equipment as an example, its temperature and pressure data are collected at different intervals. The timestamps of the two are compared, and data with similar timestamps are merged. A time error threshold is set, for example, data with a time error within ±1 second are considered as data at the same time point. In this way, the data of different parameters are synchronized in the time dimension, and finally the corresponding equipment operation data in the same time dimension are obtained, ensuring the accuracy of subsequent analysis.

[0040] Preferably, the equipment operation data corresponding to the same time dimension are plotted to generate a trend diagram of equipment operation parameters corresponding to the same time coordinate system. In this embodiment of the invention, data visualization tools, such as the Matplotlib library in Python, are used to process equipment operation data in the same time dimension. Time is used as the horizontal axis, and equipment operation parameters (such as temperature and pressure) are used as the vertical axis. Taking a certain engine as an example, for the synchronized temperature and pressure data, the time points are arranged in sequence, and the temperature and pressure values ​​corresponding to each time point are plotted on the chart. By connecting these data points, a continuous curve is formed, thereby generating a trend chart of equipment operation parameters in the same time coordinate system. This allows for a direct observation of the changes in equipment operation parameters over time, providing a basis for subsequent fault diagnosis.

[0041] Preferably, based on the corresponding abnormal threshold for operational faults, the trend chart of equipment operating parameters under the same time coordinate system is analyzed to determine operational faults. If there is one or more corresponding equipment operating parameters that are greater than or equal to the corresponding abnormal threshold for operational faults, then the corresponding time node is determined as a suspected node for operational faults, so as to obtain suspected nodes for equipment operational faults.

[0042] In this embodiment of the invention, by pre-setting abnormal thresholds for equipment operating parameters, such as setting the normal operating temperature range of a certain equipment to 50-80 degrees Celsius and setting the abnormal temperature threshold to 100 degrees Celsius, these thresholds are compared and analyzed with the trend chart of equipment operating parameters under the same time coordinate system. Using data query and comparison algorithms, each data point on the trend chart is traversed. When it is found that the equipment operating parameter (such as temperature) corresponding to a certain time point is greater than or equal to the set abnormal threshold, that time point is marked as a suspected node of operating failure. For example, if the trend chart shows that the equipment temperature reaches 105 degrees Celsius at a certain moment, exceeding the abnormal threshold of 100 degrees Celsius, then that moment is a suspected node of operating failure. By performing such analysis on all operating parameters, the thresholds for other equipment operating parameters vary depending on factors such as equipment type, working environment, and process requirements. For example, the pressure fluctuation of hydraulic equipment is ±2MPa, and that of pneumatic systems is ±0.03MPa. Furthermore, for motors, fans, etc., the vibration amplitude is usually measured by vibration intensity, generally at a speed of 1500 r / min. For motors with a vibration intensity exceeding 4.5 mm / s, it is necessary to pay attention to whether there are problems such as bearing wear or rotor imbalance. For motors with a speed of 3000 r / min, a vibration intensity exceeding 1 mm / s indicates a potential fault. As for the current threshold, for three-phase asynchronous motors, the current generally does not exceed ±10% of the rated current when operating under rated load. For example, for a motor with a rated current of 10A, when the operating current exceeds 11A or is lower than 9A, there are problems such as abnormal load, power supply voltage imbalance, or motor winding fault. Finally, all suspected fault nodes in equipment operation are obtained, providing key information for subsequent fault diagnosis and maintenance.

[0043] Furthermore, step S22 includes the following steps: By obtaining the corresponding maintenance operation records in the historical maintenance standard data, the complexity of the corresponding equipment maintenance operation and the technical difficulty required for maintenance operation disassembly are obtained. Based on the complexity of the equipment maintenance operation and the technical difficulty required for maintenance operation disassembly, the operation potential factors of the equipment operation parameters corresponding to the suspected equipment operation fault nodes are evaluated to obtain the potential factors for equipment fault operation disassembly. In this embodiment of the invention, maintenance operation records are retrieved from historical maintenance standard data. These records detail the specific operation procedures for each equipment maintenance. Data analysis tools are used to analyze these records, determining the complexity of the equipment maintenance operation based on factors such as the number of operation steps, the level of precision, and the required professional skills. For example, if the maintenance operation of a certain piece of equipment involves the coordinated operation of multiple systems and has numerous steps, its complexity is high. Simultaneously, the technical difficulty required for disassembling the maintenance operation is assessed based on factors such as the use of special tools and the requirement for professional knowledge. For suspected equipment malfunctions, the equipment operating parameters are correlated with the maintenance operation records, and an evaluation model is established to quantify the potential impact of operation disassembly on equipment operation, thereby obtaining the potential factors for equipment malfunction operation disassembly. ,in Due to the complexity of equipment maintenance operations, The specific numerical values ​​corresponding to the technical difficulty required for disassembly and repair operations.

[0044] Preferably, a maintenance cycle distribution analysis is performed on the maintenance time corresponding to the historical maintenance standard data to obtain the historical maintenance time cycle distribution of the equipment; In this embodiment of the invention, by extracting the maintenance time information of all equipment from the historical maintenance standard data, including the start and end times of each maintenance, and using time series analysis tools, these maintenance times are arranged in chronological order, and time intervals are set, such as monthly units. The number of equipment maintenances in each time interval is counted. For example, the number of equipment maintenances in each month over the past three years is counted to obtain a series of data points. By drawing bar charts or line charts, the distribution of the number of equipment maintenances in different time intervals is displayed intuitively, thereby obtaining the historical maintenance time cycle distribution of the equipment. If it is found that the number of maintenances of a certain piece of equipment increases significantly in a specific month of each year, it indicates that the equipment is more prone to failure during these time periods, and there is a certain maintenance time cycle pattern. Finally, the historical maintenance time cycle distribution of the equipment is obtained.

[0045] Preferably, based on the historical maintenance time cycle distribution of the equipment, the maintenance time distribution potential factors of the equipment operating parameters corresponding to the suspected fault nodes of the equipment are evaluated to obtain the potential factors of equipment fault maintenance duration. In this embodiment of the invention, based on the previously obtained historical maintenance time cycle distribution of the equipment and combined with the equipment operating parameters at suspected fault nodes, the process first determines whether the time of occurrence of the suspected node falls within a high maintenance frequency period in the historical maintenance time cycle distribution. If it falls within a high maintenance frequency period, a higher time correlation coefficient is assigned; if it falls within a low maintenance frequency period, a lower time correlation coefficient is assigned. Simultaneously, factors related to fault severity in the equipment operating parameters are considered, such as the degree to which parameters like operating temperature and pressure exceed normal ranges. These parameters are then quantified and scored using an evaluation formula. The time correlation coefficient and fault severity score are assigned certain weights (e.g., the time correlation coefficient weight is 0.4, and the fault severity score weight is 0.6). By calculating the weighted sum of the two, the potential factor for equipment fault maintenance duration is obtained. For example, if a suspected node occurs within a high maintenance frequency period with a time correlation coefficient of 0.8 and a fault severity score of 6, the potential factor for equipment fault maintenance duration is 0.8 × 0.4 + 6 × 0.6 = 3.92. The final potential factor for equipment fault maintenance duration is thus obtained.

[0046] Preferably, based on the replacement spare parts information corresponding to the historical maintenance standard data, the equipment operating parameters corresponding to the suspected equipment failure nodes are evaluated for replacement potential factors to obtain equipment failure replacement compatibility potential factors.

[0047] In this embodiment of the invention, by extracting replacement spare parts information from historical maintenance standard data, including the type of replaced spare parts, their specifications, and the replacement time, the spare parts replacement situation at suspected equipment failure nodes is analyzed based on the equipment operating parameters. The compatibility probability between the equipment and the replaced spare parts is assessed based on factors such as the spare parts' versatility and compatibility with the equipment, and a compatibility probability value is set, ranging from 0 to 1. Simultaneously, the replacement frequency of the spare parts in historical maintenance is statistically analyzed, i.e., the number of replacements per unit time. An evaluation model is established, assigning certain weights to the compatibility probability and replacement frequency (e.g., a compatibility probability weight of 0.7 and a replacement frequency weight of 0.3). By calculating the weighted sum of the two, the potential compatibility factor for equipment failure replacement is obtained. For example, if the compatibility probability between a spare part and the equipment at a suspected node is 0.9 and the replacement frequency is 5 times per year, then the potential compatibility factor for equipment failure replacement is 0.9 × 0.7 + 5 × 0.3 = 2.33. The final potential compatibility factor for equipment failure replacement is thus obtained.

[0048] Furthermore, the assessment of potential replacement factors for equipment operating parameters at suspected fault points based on replacement spare parts information within historical maintenance standard data includes the following steps: The types of replacement parts and the frequency of equipment replacement can be obtained by referring to the replacement parts information in the historical maintenance standard data. In this embodiment of the invention, historical maintenance standard data is extracted from a historical maintenance database that records detailed information about each equipment maintenance. Data filtering tools are used to filter information related to spare parts replacement from massive amounts of data. For each spare parts replacement record, the specific name and model of the replaced spare parts are extracted to determine the type of spare parts to be replaced. Simultaneously, the number of times each spare part is replaced within a certain time period (e.g., one year) is calculated. Dividing the number of replacements by the time period yields the equipment replacement frequency. For example, in the equipment maintenance records of a factory, filtering reveals that a certain model of motor was replaced 10 times in the past year, thus identifying this motor as one of the spare parts to be replaced, with a replacement frequency of 10 times per year. Finally, the corresponding type of equipment spare parts and the equipment replacement frequency are obtained.

[0049] Preferably, a spare parts operation compatibility analysis is performed on the corresponding equipment based on the type of spare parts to obtain the operation compatibility probability between the equipment and the spare parts. In this embodiment of the invention, a spare parts operation compatibility analysis model is constructed. This model comprehensively considers the technical parameters of the equipment and the specifications of the spare parts. For each type of spare parts to be replaced, the technical parameters of the equipment, such as rated power, operating voltage, and interface type, as well as the corresponding specifications of the spare parts, are collected. By comparing the degree of matching between the two parameters, an operation compatibility score is calculated. For example, if the rated power of the equipment is 500 watts and the rated power of the spare parts is between 490 and 510 watts, then the compatibility in terms of power parameters is considered to be high. The compatibility scores of all parameters are weighted and averaged to obtain a comprehensive compatibility score. Then, based on the actual operation compatibility under the same or similar parameter matching conditions in historical data, the comprehensive compatibility score is converted into an operation compatibility probability. For example, through a large amount of historical data statistics, it is found that when the comprehensive compatibility score is above 80 points, the actual operation compatibility ratio is 90%. Therefore, the operation compatibility probability of the equipment and the spare parts corresponding to 80 points is set to 90%, and finally the operation compatibility probability between the equipment and the replaced spare parts is obtained.

[0050] Preferably, the potential replacement factor is evaluated for the equipment operating parameters corresponding to the suspected equipment failure node based on the equipment replacement frequency and the operational compatibility probability between the equipment and the replacement spare parts, so as to obtain the potential replacement compatibility factor for equipment failure.

[0051] In this embodiment of the invention, by monitoring equipment operating parameters in real time through sensors during equipment operation, suspected fault nodes are identified. For these suspected nodes, the equipment replacement frequency and the operational compatibility probability between the equipment and the replacement spare parts are used as evaluation factors. First, weights are assigned to the equipment replacement frequency and the operational compatibility probability, such as a weight of 0.6 for the equipment replacement frequency and a weight of 0.4 for the operational compatibility probability. For each suspected node, the replacement frequency and operational compatibility probability of the spare parts involved at that node are substituted into the evaluation formula: Equipment Fault Replacement Compatibility Potential Factor = Equipment Replacement Frequency × Weight 1 + Operational Compatibility Probability × Weight 2. For example, if the replacement frequency of spare parts at a suspected node is 8 times per year and the operational compatibility probability is 85%, then the Equipment Fault Replacement Compatibility Potential Factor = 8 × 0.6 + 0.85 × 0.4 = 5.14. By performing this calculation on all suspected nodes, the corresponding Equipment Fault Replacement Compatibility Potential Factor is finally obtained.

[0052] Furthermore, the specific formula for calculating the degree of equipment failure mentioned in step S23 is as follows: ; In the formula, Depending on the degree of equipment failure, For suspected equipment malfunction nodes The corresponding vibration amplitude value at that location, For vibration amplitude fault weights, For suspected equipment malfunction nodes The corresponding temperature change value at that location, For temperature change fault weights, For suspected equipment malfunction nodes The corresponding pressure fluctuation value, For pressure fluctuation fault weights, For suspected equipment malfunction nodes The corresponding current value at that location, For current fault weights, To identify potential factors contributing to equipment malfunctions. Replace compatibility potential factors for equipment malfunctions. Potential factors affecting equipment failure repair time, The time required for equipment malfunction repair. This is a correction factor for the degree of equipment failure.

[0053] This invention, through the use of a specific mathematical model and verification, yields a formula for calculating the degree of equipment failure. This formula quantifies the failure of equipment operating parameters corresponding to suspected failure points. By comprehensively considering multiple operating parameters (such as vibration amplitude, temperature change, pressure fluctuation, and current value) along with relevant failure weights and potential risk factors, it quantifies the complex failure assessment process. This quantification method provides more accurate and quantitative data support for failure analysis, making equipment failure judgment more objective and reliable. The formula considers the impact of multiple factors on equipment failure from multiple perspectives, such as changes in parameters like vibration, temperature, pressure, and current. Each parameter is assigned a corresponding weight according to its different degrees of influence in the failure occurrence. This multi-dimensional comprehensive analysis can more comprehensively reflect the operating status of the equipment and avoid misjudgments caused by single indicators. Potential risk factors (such as potential factors for operation and disassembly, maintenance time, and failure replacement compatibility) are introduced into the formula, further improving the accuracy of failure degree assessment. The consideration of these potential factors allows the formula to reflect not only immediate failure performance but also historical failures and potential risks during maintenance, providing a more in-depth analysis for equipment maintenance. The correction coefficients and time factor in this formula effectively adjust and modify the calculation of fault severity to adapt to actual fault conditions. They help correct for the influence of possible external factors, making the calculation results more consistent with actual fault situations encountered in operation. Furthermore, the time factor allows the impact of fault repair cycles to be taken into account, improving the accuracy of fault prediction. By quantifying faults in equipment operating parameters and comparing them with preset equipment fault thresholds, the formula can effectively identify potential fault nodes. This ability to detect faults in advance facilitates preventative maintenance, avoiding production downtime or more serious losses due to undetected faults. In summary, this formula fully considers the severity of equipment faults. Suspected equipment malfunction nodes The corresponding vibration amplitude value Vibration amplitude fault weight Suspected equipment malfunction nodes The corresponding temperature change value Fault weights due to temperature changes Suspected equipment malfunction nodes The corresponding pressure fluctuation value Pressure fluctuation fault weight Suspected equipment malfunction nodes The corresponding current value Current fault weight Potential factors for equipment failure and operation dismantling Equipment malfunction replacement compatibility potential factors Potential factors affecting equipment failure repair time The length of time corresponding to equipment failure repair Correction coefficient for equipment failure severity According to the degree of equipment failure The interrelationships between the above parameters constitute a functional relationship. This formula enables the quantitative calculation of equipment operating parameters corresponding to suspected fault points, and simultaneously, through a correction coefficient for the degree of equipment fault. The introduction of this feature allows for adjustments based on errors that occur during the calculation process, thereby improving the accuracy and applicability of the equipment failure severity calculation formula.

[0054] Furthermore, step S3 includes the following steps: Step S31: Obtain the corresponding equipment fault type, equipment fault duration, and equipment fault location through the corresponding equipment fault repair task point in the equipment fault repair prediction result. In this embodiment of the invention, relying on an equipment fault monitoring system, the system collects and analyzes equipment operation data in real time, outputs equipment fault repair prediction results, and in the results, for each equipment fault repair task point, uses a data query tool to retrieve detailed information from the database. For example, for a certain task point, by inputting the task point number, the system accurately extracts the corresponding equipment fault type from the equipment fault information database, such as engine fault, circuit fault, etc.; obtains the equipment fault duration, which is obtained by the fault monitoring system from the time the fault is detected; and determines the equipment fault location, such as a certain cylinder of the engine, a certain line node of the circuit, etc., and finally obtains the corresponding equipment fault type, equipment fault duration, and equipment fault location.

[0055] Step S32: Based on the equipment failure type, equipment failure duration, and equipment failure location, perform a task urgency analysis on the corresponding equipment failure repair task points to obtain the urgency level of the equipment failure repair task. In this embodiment of the invention, a task urgency assessment model is constructed, using equipment failure type, failure duration, and failure location as input parameters. For failure type, different urgency weights are pre-set, such as high weights for failures involving safety-critical systems and low weights for failures involving ordinary components. Regarding failure duration, a standard duration is set, with the urgency increasing the longer the duration exceeds the standard duration. If the failure location affects the operation of the core functions of the equipment, the urgency also increases accordingly. For example, if an aircraft engine fails (high failure type weight), has been failing for 24 hours (far exceeding the standard duration), and the failure location is the combustion chamber (affecting core functions), the model calculates that the urgency of the equipment failure repair task point is high. By performing this calculation for each task point, that is, multiplying the corresponding failure degree, failure duration, and failure location anomaly measurement with the corresponding weights to obtain the corresponding urgency, the urgency of the equipment failure repair task at each task time node is finally obtained.

[0056] Step S33: Sort the corresponding equipment fault repair tasks according to the urgency of the equipment fault repair tasks to generate an urgent priority sequence of equipment fault repair tasks. In this embodiment of the invention, a sorting algorithm, such as quicksort, is used to sort equipment fault repair tasks from highest to lowest urgency. First, the urgency values ​​of all tasks are extracted to form a numerical sequence. The quicksort algorithm selects a pivot value and divides the sequence into two parts: the values ​​on the left are less than the pivot value, and the values ​​on the right are greater than the pivot value. Then, the left and right parts are recursively sorted. For example, if there are 5 equipment fault repair tasks with urgency values ​​of 8, 3, 6, 9, and 2, after quicksort, the order from highest to lowest urgency is 9, 8, 6, 3, 2. The corresponding tasks are also sorted accordingly, ultimately generating a priority sequence for equipment fault repair tasks, ensuring that tasks with higher urgency are processed first.

[0057] Step S34: Based on the spare parts inventory quantity, spare parts procurement cycle, and spare parts supply capacity within the maintenance supply standard data, perform fault maintenance decision support analysis on the priority equipment fault maintenance task points within the emergency priority task sequence for equipment fault maintenance. Recommend the optimal fault maintenance strategy based on the corresponding spare parts inventory quantity, spare parts procurement cycle, and spare parts supply capacity, including maintenance personnel allocation, spare parts inventory usage, and fault maintenance resource allocation, and generate equipment fault maintenance decision strategies.

[0058] In this embodiment of the invention, by extracting maintenance supply standard data from the maintenance supply database, including information such as spare parts inventory quantity, spare parts procurement cycle, and spare parts supply capacity, decision support analysis is performed on priority task points in the emergency priority task sequence for equipment failure maintenance, based on this data. For example, if a priority task point needs to replace a certain spare part, the spare parts inventory quantity is checked first. If the inventory is sufficient, it is taken directly from the inventory. If the inventory is insufficient but the spare parts procurement cycle is short and the supply capacity is strong, the procurement process can be started immediately, and maintenance personnel can be dispatched to wait for the spare parts to arrive before carrying out maintenance. Based on different situations, the skills and expertise of maintenance personnel are comprehensively considered, and personnel are rationally allocated to determine the optimal failure maintenance strategy, such as assigning personnel skilled in electrical maintenance to handle circuit failure tasks. These strategies are compiled into equipment failure maintenance decision strategies to provide guidance for actual maintenance work.

[0059] Furthermore, step S4 includes the following steps: Step S41: Based on the equipment fault maintenance decision strategy, perform initial equipment maintenance on the corresponding faulty equipment to generate the corresponding equipment fault maintenance execution process; In this embodiment of the invention, after determining the type of equipment failure, work is carried out according to a pre-defined equipment failure maintenance decision strategy. For example, for equipment with an engine failure, the maintenance decision strategy stipulates that the faulty component must be disassembled first. The maintenance personnel follow the detailed operation manual and use professional disassembly tools, such as wrenches and screwdrivers, to gradually remove the connecting components related to the faulty engine, recording the disassembly sequence and the position of each component. Then, according to the strategy requirements, the disassembled engine is initially inspected. Using fault detection instruments, such as an engine fault diagnostic instrument, the fault code is read and the specific fault point is determined. These maintenance operation steps are recorded in sequence to generate an equipment failure maintenance execution process. There are clear records from fault confirmation to component disassembly and inspection.

[0060] Step S42: By deploying real-time monitoring points in the corresponding equipment fault repair execution process, the corresponding repair time, repair cost, equipment repair efficiency and repair quality after the repair decision is executed are collected in real time to obtain equipment fault repair feedback data. In this embodiment of the invention, sensors and data acquisition devices are deployed as real-time monitoring points at key nodes in the equipment fault repair process. At the start of repair, a time recording device is activated to accurately record the time when the repair personnel begin their operation. During the replacement of parts, cost information of the parts used is collected in real time through electronic tags and an inventory management system. Equipment operation monitoring sensors are used to monitor the operating parameters of the equipment during the repair process in real time, thereby evaluating repair efficiency. For example, the operating speed and power of the equipment are compared with normal standards. Regarding repair quality, in the testing phase after repair, professional quality testing instruments, such as precision measuring instruments, are used to test the performance of the repaired equipment. The repair time, repair cost, equipment repair efficiency, and repair quality data collected at various monitoring points are summarized to finally form equipment fault repair feedback data.

[0061] Step S43: Input the equipment failure maintenance feedback data into the preset decision model to use the online learning algorithm to optimize the maintenance feedback of the corresponding faulty equipment. If it is found that the actual maintenance time corresponding to a certain maintenance decision strategy exceeds the expectation, the model automatically analyzes the reasons to adjust the maintenance resource allocation strategy. If it is found that a certain maintenance decision strategy leads to resource waste or shortage, the model re-optimizes the constraints corresponding to resource allocation to achieve dynamic optimization and continuous improvement of maintenance decisions, so as to execute the corresponding dynamic optimization and improvement operation of equipment failure maintenance decisions.

[0062] In this embodiment of the invention, equipment failure maintenance feedback data is input into a preset decision model based on machine learning. This model employs an online learning algorithm. If the data shows that the actual maintenance time under a certain maintenance decision strategy exceeds expectations—for example, the maintenance of a complex piece of machinery was originally expected to be completed in 5 hours but actually took 8 hours—the model analyzes the time data of each stage of the maintenance process and finds that a certain maintenance procedure is waiting for parts to be supplied for too long. At this time, the model automatically adjusts the maintenance resource allocation strategy, communicates with parts suppliers to speed up the supply, or looks for alternative parts in the inventory. If resource waste is found, such as a certain maintenance strategy using too many high-cost parts without significantly improving maintenance quality, the model re-optimizes the resource allocation constraints to reduce parts costs while ensuring maintenance quality. By continuously inputting new feedback data, the model continuously optimizes maintenance decisions to perform dynamic optimization and improvement of equipment failure maintenance decisions.

[0063] Furthermore, the present invention also provides an intelligent decision support system for real-time big data analysis, used to execute the intelligent decision support method for real-time big data analysis as described above. The intelligent decision support system for real-time big data analysis includes: The equipment big data real-time acquisition module is used to acquire equipment operating status data, equipment historical maintenance data, and equipment maintenance supply data in real time. It also performs data transmission preprocessing optimization on the equipment operating status data, equipment historical maintenance data, and equipment maintenance supply data to obtain equipment operating standard data, historical maintenance standard data, and maintenance supply standard data. The equipment failure risk prediction module is used to assess the potential failure risk of equipment operation standard data based on historical maintenance standard data to obtain the historical maintenance potential risk factors of equipment failure; and to predict equipment failure based on the historical maintenance potential risk factors of equipment failure and the equipment operation standard data to obtain the equipment failure maintenance prediction result. The equipment failure maintenance decision analysis module is used to perform task urgency analysis on the corresponding equipment failure maintenance task points within the equipment failure maintenance prediction results to obtain the urgency level of the equipment failure maintenance task; based on the urgency level of the equipment failure maintenance task and maintenance supply standard data, it performs failure maintenance decision support analysis on the corresponding equipment failure maintenance task points to generate equipment failure maintenance decision strategies. The equipment maintenance feedback optimization module is used to optimize the maintenance feedback of corresponding faulty equipment based on the equipment fault maintenance decision-making strategy and in combination with the preset decision-making model, so as to execute the corresponding equipment fault maintenance decision dynamic optimization and improvement operation.

[0064] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0065] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. An intelligent decision support method for real-time big data analysis, characterized in that, Includes the following steps: Step S1: Real-time acquisition of equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data; and optimization of data transmission preprocessing for the equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data to obtain equipment operation standard data, historical maintenance standard data, and maintenance supply standard data. Step S2: Based on historical maintenance standard data, conduct a fault potential risk assessment on the equipment operation standard data to obtain the equipment fault historical maintenance potential risk factors; Based on the potential risk factors of equipment failure history maintenance, equipment failure prediction is performed on the standard data of equipment operation to obtain equipment failure maintenance prediction results. Step S3: Perform a task urgency analysis on the corresponding equipment failure maintenance task points within the equipment failure maintenance prediction results to obtain the urgency level of the equipment failure maintenance task. Based on the urgency of equipment failure repair tasks and maintenance supply standard data, a failure repair decision support analysis is performed on the corresponding equipment failure repair task points to generate equipment failure repair decision strategies. Step S4: Based on the equipment fault maintenance decision-making strategy and combined with the preset decision-making model, perform maintenance feedback optimization on the corresponding faulty equipment to execute the corresponding equipment fault maintenance decision dynamic optimization and improvement operation.

2. The intelligent decision support method for real-time big data analysis according to claim 1, characterized in that, Step S1 includes the following steps: Step S11: By installing corresponding vibration sensors, temperature sensors, pressure sensors and current sensors on the equipment, the vibration amplitude, temperature change, pressure fluctuation and current value of the equipment during operation are monitored in real time to obtain equipment operation status data. Step S12: Obtain historical maintenance data of the equipment by collecting historical maintenance data such as maintenance operation records, maintenance time, and replacement parts information of maintenance personnel in the maintenance management record system in real time. Step S13: Obtain equipment maintenance supply data by collecting real-time data on the quantity of spare parts in stock, the procurement cycle of spare parts, and the supply capacity of spare parts for the equipment. Step S14: Based on the Industrial Internet of Things and combined with high-speed data transmission protocols, transmit equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data to the equipment maintenance data processing center in real time in the shortest possible time. Step S15: Use the equipment maintenance data processing center to perform noise reduction, error correction, and deduplication on equipment operation status data, equipment historical maintenance data, and equipment maintenance supply data. At the same time, use real-time median interpolation combined with data mining technology to supplement the corresponding missing data points. And according to the equipment data standard, the original data corresponding to different formats and different sources are standardized and converted to obtain equipment operation standard data, historical maintenance standard data, and maintenance supply standard data.

3. The intelligent decision support method for real-time big data analysis according to claim 2, characterized in that, Step S2 includes the following steps: Step S21: Perform equipment operation fault analysis on the standard equipment operation data to identify potential fault nodes in equipment operation; Step S22: Based on historical maintenance standard data, conduct a potential risk assessment of the equipment operating parameters corresponding to suspected equipment operation fault nodes to obtain potential risk factors of historical equipment fault maintenance, including potential factors of equipment fault operation disassembly, potential factors of equipment fault maintenance duration, and potential factors of equipment fault replacement compatibility. Step S23: By assigning corresponding equipment fault weights to each equipment operating parameter corresponding to the suspected equipment operation fault node, and using the equipment fault degree calculation formula based on the equipment fault history maintenance potential risk factors and the equipment fault weights corresponding to each equipment operating parameter, the equipment operating parameter corresponding to the suspected equipment operation fault node is used to perform fault quantification calculation to obtain the equipment fault degree. Step S24: Compare and judge the degree of equipment failure according to the preset equipment failure threshold. If the degree of equipment failure at the node is greater than or equal to the preset equipment failure threshold, it is considered that there is an equipment failure at the node and it is designated as a maintenance task point. If the degree of equipment failure at the node is less than the preset equipment failure threshold, it is considered that there is no equipment failure at the node and the next node is judged. This process continues until all suspected equipment failure nodes have been judged, and the equipment failure maintenance prediction result is obtained.

4. The intelligent decision support method for real-time big data analysis according to claim 3, characterized in that, Step S21 includes the following steps: The equipment operation parameters corresponding to the equipment operation standard data are time-series synchronized in the time dimension to obtain the corresponding equipment operation data in the same time dimension. The time-series change trend of equipment operation data under the same time dimension is plotted to generate the change trend map of equipment operation parameters under the same time coordinate system; Based on the corresponding operational fault abnormality threshold, the trend chart of equipment operation parameters under the same time coordinate system is analyzed to determine operational faults. If there is one or more corresponding equipment operation parameters that are greater than or equal to the corresponding operational fault abnormality threshold, the corresponding time node is determined as a suspected operational fault node, so as to obtain the suspected equipment operation fault node.

5. The intelligent decision support method for real-time big data analysis according to claim 3, characterized in that, Step S22 includes the following steps: By obtaining the corresponding maintenance operation records in the historical maintenance standard data, the complexity of the corresponding equipment maintenance operation and the technical difficulty required for maintenance operation disassembly are obtained. Based on the complexity of the equipment maintenance operation and the technical difficulty required for maintenance operation disassembly, the operation potential factors of the equipment operation parameters corresponding to the suspected equipment operation fault nodes are evaluated to obtain the potential factors for equipment fault operation disassembly. By performing a maintenance cycle distribution analysis on the corresponding maintenance time within the historical maintenance standard data, the historical maintenance time cycle distribution of the equipment is obtained. Based on the historical maintenance time cycle distribution of equipment, the maintenance time distribution potential factors of the equipment operation parameters corresponding to the suspected nodes of equipment operation failure are evaluated to obtain the potential factors of equipment failure maintenance duration. Based on the replacement spare parts information in the historical maintenance standard data, the equipment operating parameters corresponding to the suspected equipment failure nodes are evaluated for potential replacement factors to obtain equipment failure replacement compatibility potential factors.

6. The intelligent decision support method for real-time big data analysis according to claim 5, characterized in that, The assessment of potential replacement factors for equipment operating parameters at suspected fault points based on replacement spare parts information within historical maintenance standard data includes the following steps: The types of replacement parts and the frequency of equipment replacement can be obtained by referring to the replacement parts information in the historical maintenance standard data. Based on the types of spare parts that can be replaced, a spare parts operation compatibility analysis is performed on the corresponding equipment to obtain the operation compatibility probability between the equipment and the replaced spare parts. Based on the equipment replacement frequency and the operational compatibility probability between the equipment and the replacement spare parts, the equipment operation parameters corresponding to the suspected equipment failure nodes are evaluated to obtain the equipment failure replacement compatibility potential factors.

7. The intelligent decision support method for real-time big data analysis according to claim 3, characterized in that, The specific formula for calculating the degree of equipment failure mentioned in step S23 is as follows: ； In the formula, Depending on the degree of equipment failure, For suspected equipment malfunction nodes The corresponding vibration amplitude value at that location, For vibration amplitude fault weights, For suspected equipment malfunction nodes The corresponding temperature change value at that location, For temperature change fault weights, For suspected equipment malfunction nodes The corresponding pressure fluctuation value, For pressure fluctuation fault weights, For suspected equipment malfunction nodes The corresponding current value at that location, For current fault weights, To identify potential factors contributing to equipment malfunctions. Replace compatibility potential factors for equipment malfunctions. Potential factors affecting equipment failure repair time, The time required for equipment malfunction repair. This is a correction factor for the degree of equipment failure.

8. The intelligent decision support method for real-time big data analysis according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Obtain the corresponding equipment fault type, equipment fault duration, and equipment fault location through the corresponding equipment fault repair task point in the equipment fault repair prediction result. Step S32: Based on the equipment failure type, equipment failure duration, and equipment failure location, perform a task urgency analysis on the corresponding equipment failure repair task points to obtain the urgency level of the equipment failure repair task. Step S33: Sort the corresponding equipment fault repair tasks according to the urgency of the equipment fault repair tasks to generate an urgent priority sequence of equipment fault repair tasks. Step S34: Based on the spare parts inventory quantity, spare parts procurement cycle, and spare parts supply capacity within the maintenance supply standard data, perform fault maintenance decision support analysis on the priority equipment fault maintenance task points within the emergency priority task sequence for equipment fault maintenance. Recommend the optimal fault maintenance strategy based on the corresponding spare parts inventory quantity, spare parts procurement cycle, and spare parts supply capacity, including maintenance personnel allocation, spare parts inventory usage, and fault maintenance resource allocation, and generate equipment fault maintenance decision strategies.

9. The intelligent decision support method for real-time big data analysis according to claim 1, characterized in that, Step S4 includes the following steps: Step S41: Based on the equipment fault maintenance decision strategy, perform initial equipment maintenance on the corresponding faulty equipment to generate the corresponding equipment fault maintenance execution process; Step S42: By deploying real-time monitoring points in the corresponding equipment fault repair execution process, the corresponding repair time, repair cost, equipment repair efficiency and repair quality after the repair decision is executed are collected in real time to obtain equipment fault repair feedback data. Step S43: Input the equipment failure maintenance feedback data into the preset decision model to use the online learning algorithm to optimize the maintenance feedback of the corresponding faulty equipment. If it is found that the actual maintenance time corresponding to a certain maintenance decision strategy exceeds the expectation, the model automatically analyzes the reasons to adjust the maintenance resource allocation strategy. If it is found that a certain maintenance decision strategy leads to resource waste or shortage, the model re-optimizes the constraints corresponding to resource allocation to achieve dynamic optimization and continuous improvement of maintenance decisions, so as to execute the corresponding dynamic optimization and improvement operation of equipment failure maintenance decisions.

10. An intelligent decision support system for real-time big data analysis, characterized in that, The intelligent decision support system for performing real-time big data analysis as described in claim 1 includes: The equipment big data real-time acquisition module is used to acquire equipment operating status data, equipment historical maintenance data, and equipment maintenance supply data in real time. It also performs data transmission preprocessing optimization on the equipment operating status data, equipment historical maintenance data, and equipment maintenance supply data to obtain equipment operating standard data, historical maintenance standard data, and maintenance supply standard data. The equipment failure risk prediction module is used to assess the potential failure risk of equipment operation standard data based on historical maintenance standard data to obtain the historical maintenance potential risk factors of equipment failure; and to predict equipment failure based on the historical maintenance potential risk factors of equipment failure and the equipment operation standard data to obtain the equipment failure maintenance prediction result. The equipment failure maintenance decision analysis module is used to perform task urgency analysis on the corresponding equipment failure maintenance task points within the equipment failure maintenance prediction results to obtain the urgency level of the equipment failure maintenance task; based on the urgency level of the equipment failure maintenance task and maintenance supply standard data, it performs failure maintenance decision support analysis on the corresponding equipment failure maintenance task points to generate equipment failure maintenance decision strategies. The equipment maintenance feedback optimization module is used to optimize the maintenance feedback of corresponding faulty equipment based on the equipment fault maintenance decision-making strategy and in combination with the preset decision-making model, so as to execute the corresponding equipment fault maintenance decision dynamic optimization and improvement operation.

Images