Equipment operation and maintenance data management method and system

Abstract

The invention discloses an equipment operation and maintenance data management method and system, and relates to the technical field of industrial equipment maintenance, and the method comprises the steps: collecting the operation parameters of industrial equipment to form a collection data group; inputting the collected data set into the support vector machine model, and outputting an equipment abnormal probability value and an equipment residual life prediction value; generating an equipment state grade according to the equipment abnormity probability value, and establishing a maintenance priority matrix through a combination relationship between the equipment state grade and the equipment residual life prediction value; and selecting to-be-maintained equipment according to the maintenance priority matrix, extracting characteristic parameters of the acquisition data set, matching a standard maintenance scheme in the maintenance scheme library, and generating a customized maintenance scheme for the to-be-maintained equipment. According to the method, data driving and an intelligent algorithm are combined, so that the maintenance cost is effectively reduced and the service life of equipment is prolonged while the operation and maintenance efficiency of the equipment is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial equipment maintenance, and particularly to a method and system for managing equipment operation and maintenance data. Background Art

[0002] The operation and maintenance management of industrial equipment has gradually shifted from traditional passive maintenance and planned maintenance to intelligent and predictive maintenance. Existing technologies mainly adopt equipment status evaluation methods based on threshold monitoring and maintenance strategies with fixed cycles. By deploying a sensor network to collect equipment operation data, maintenance rules are formulated in combination with expert experience. At the same time, machine learning technologies have made remarkable progress in equipment fault diagnosis and prediction. Algorithms such as support vector machines and deep learning have been widely applied to equipment health status evaluation and remaining life prediction, providing data support for equipment maintenance decisions.

[0003] However, the existing equipment operation and maintenance management technologies still have the following deficiencies: First, the equipment status evaluation method relies too much on fixed thresholds and empirical rules, making it difficult to adapt to the dynamic changes in equipment operating conditions, resulting in frequent false alarms and missed alarms; Second, the maintenance decision-making lacks a scientific priority division mechanism and fails to comprehensively consider the equipment status level and remaining life prediction results, affecting the reasonable allocation of maintenance resources; Third, standard maintenance plans often fail to meet the personalized needs of different equipment, lacking a mechanism for optimizing and adjusting the plan based on historical data, reducing the maintenance effect; Finally, the processes of collecting, analyzing, and applying equipment operation and maintenance data are fragmented, and a closed-loop data management system has not been formed, affecting the continuous improvement of maintenance efficiency.

[0004] In view of the above problems, the present invention proposes a method and system for managing equipment operation and maintenance data. The present invention realizes equipment status evaluation and life prediction by establishing a support vector machine model, constructs a maintenance priority matrix to guide maintenance decisions, and realizes personalized customization of maintenance plans in a data-driven manner, forming a complete closed-loop equipment operation and maintenance data management system, effectively solving technical problems such as inaccurate equipment status evaluation, lack of scientific basis for maintenance decisions, and low personalization degree of maintenance plans in the prior art. Summary of the Invention

[0005] In view of the problems existing in the existing equipment operation and maintenance data management technologies, such as over-reliance on fixed thresholds for equipment status evaluation, lack of a scientific priority division mechanism for maintenance decisions, insufficient personalization degree of maintenance plans, and incomplete operation and maintenance data management systems, the present invention is proposed.

[0006] Therefore, the problem to be solved by the present invention is how to accurately predict equipment status and life through a support vector machine model, establish a maintenance priority evaluation mechanism, and realize intelligent customization of maintenance plans, and finally form a closed-loop equipment operation and maintenance data management system.

[0007] To solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides a method for managing device operation and maintenance data, which includes collecting operation parameters of industrial devices to form a collection data group; inputting the collection data group into a support vector machine model to output a device anomaly probability value and a predicted value of the remaining life of the device; generating a device status level according to the device anomaly probability value, and establishing a maintenance priority matrix through the combination relationship between the device status level and the predicted value of the remaining life of the device; selecting a device to be maintained according to the maintenance priority matrix, extracting characteristic parameters of the collection data group, matching a standard maintenance plan in a maintenance plan library, and generating a customized maintenance plan for the device to be maintained.

[0009] As a preferred solution of the method for managing device operation and maintenance data of the present invention, wherein: the method for generating the customized maintenance plan is to select the device to be maintained according to the priority level order of the maintenance priority matrix, and give priority to processing high-priority devices; extract characteristic parameters from the collection data group of the device to be maintained, and perform feature matching between the characteristic parameters and the standard maintenance plans in the maintenance plan library, where the maintenance plan library adopts a hierarchical structure; based on the matching results, determine the standard maintenance plan with the best match through feature similarity calculation, and combine the operation history record, maintenance history record and spare part replacement record of the device to be maintained to perform personalized adjustment on the standard maintenance plan to form a customized maintenance plan for the device to be maintained.

[0010] As a preferred solution of the method for managing device operation and maintenance data of the present invention, wherein: generating a device status level according to the device anomaly probability value and establishing a maintenance priority matrix through the combination relationship between the device status level and the predicted value of the remaining life of the device includes: generating a device status level according to the device anomaly probability value, and dividing the device operation status into a normal operation status, a sub-healthy status and a fault warning status through a preset threshold division method; at the same time, dividing the predicted value of the remaining life of the device into a sufficient life interval, a transition life interval and an emergency life interval according to the degree of life consumption; establishing a maintenance priority matrix according to the interval combination of the device status level and the predicted value of the remaining life of the device, where the maintenance priority matrix adopts a three-dimensional structure; determining the maintenance priority level through the cross mapping of the status level and the life interval, and adjusting the priority through a weight coefficient between different dimension combinations.

[0011] As a preferred solution of the device operation and maintenance data management method of the present invention, it further includes: when the device abnormal probability value is less than the first threshold, the device operation state is classified as a normal operation state; if the device is in the normal operation state and belongs to the ample life interval, it is determined as a low-priority maintenance task, and the urgency of the maintenance task is defined as routine maintenance; when the device abnormal probability value is greater than the first threshold and less than the second threshold, the device operation state is classified as a sub-healthy state; if the device is in the sub-healthy state and belongs to the transition life interval, it is determined as a medium-priority maintenance task, and the urgency of the maintenance task is defined as planned handling; when the device abnormal probability value is greater than the second threshold, the device operation state is classified as a fault warning state; if the device is in the fault warning state and belongs to the emergency life interval, it is determined as a high-priority maintenance task, and the urgency of the maintenance task is defined as immediate handling; when the predicted remaining life value of the device is greater than the life threshold A, it belongs to the ample life interval; when the predicted remaining life value of the device is less than the life threshold A and greater than the life threshold B, it belongs to the transition life interval; when the predicted remaining life value of the device is less than the life threshold B, it belongs to the emergency life interval; when the combination of the device state level and the remaining life interval does not match, the priority is adjusted through the weight coefficient.

[0012] As a preferred solution of the device operation and maintenance data management method of the present invention, it includes: inputting the collected data group into the support vector machine model, and outputting the device abnormal probability value and the predicted remaining life value of the device, including: inputting the standardized collected data group into the support vector machine model for analysis and prediction according to the time series structure, wherein the support vector machine model includes a state diagnosis model and a life prediction model; the state diagnosis model constructs the feature space mapping relationship by using the radial basis kernel function, and performs non-linear classification on the sample data in the feature space by minimizing the structural risk criterion, and calculates the device abnormal probability value according to the distance function of the classification hyperplane; the life prediction model adopts the support vector regression structure, selects the ε-insensitive loss function to construct the optimization objective, establishes a regression prediction model by extracting the temperature trend feature, pressure fluctuation feature and vibration spectrum feature in the collected data group, and trains the regression prediction model in combination with the life attenuation law in the historical operation data, and outputs the predicted remaining life value of the device.

[0013] As a preferred solution of the device operation and maintenance data management method of the present invention, the specific formula of the device abnormal probability value is as follows:

[0014]

[0015] Among them, P(x) is the device abnormal probability value, x is the input feature vector, n is the number of support vectors, α i is the Lagrange multiplier, y i is the class label of the i-th support vector, xi is the input feature vector of the i-th support vector, σ is the parameter of the RBF kernel function, λ is the probability conversion coefficient, and μ is the mean of the feature vectors.

[0016] The specific formula for the predicted remaining life value of the device is as follows:

[0017]

[0018] Where R(x) is the predicted remaining life value of the device, R0 is the nominal life of the device, m is the number of degradation features, ω i i is the weight coefficient of the i-th feature, a i is the measured value of the i-th feature, is the ideal value of the i-th feature, θ is the life attenuation coefficient, b is the current value of the key environmental factor, η is the standard value of the environmental factor, and δ is the tolerance coefficient of the environmental factor.

[0019] As a preferred solution of the device operation and maintenance data management method of the present invention, wherein: the method for forming the collected data group is to perform time alignment on the temperature data, pressure data, and vibration data according to the collection timestamps of the operation parameters, and divide the aligned operation parameters into several collected data groups at preset time intervals; perform data preprocessing on the temperature data, pressure data, and vibration data in the collected data group respectively to generate a standardized collected data group.

[0020] In a second aspect, an embodiment of the present invention provides a device operation and maintenance data management system, which includes: a collection module for collecting operation parameters of industrial equipment to form a collected data group; an output module for inputting the collected data group into a support vector machine model and outputting a device anomaly probability value and a predicted remaining life value of the device; a establishment module for generating a device status level according to the device anomaly probability value and establishing a maintenance priority matrix through the combination relationship between the device status level and the predicted remaining life value of the device; a generation module for selecting a device to be maintained according to the maintenance priority matrix, extracting feature parameters of the collected data group, matching standard maintenance plans in the maintenance plan library, and generating a customized maintenance plan for the device to be maintained.

[0021] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and wherein: when the computer program instructions are executed by the processor, the steps of the device operation and maintenance data management method as described in the first aspect of the present invention are implemented.

[0022] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and wherein: when the computer program instructions are executed by the processor, the steps of the device operation and maintenance data management method as described in the first aspect of the present invention are implemented.

[0023] The beneficial effects of the present invention are as follows: By collecting the operating parameters of industrial equipment to form a standardized data set of collected data and inputting it into a support vector machine model for analysis, dual predictions of the abnormal state and remaining life of the equipment are realized; a maintenance priority matrix with a three-dimensional structure is established through the combined relationship between the equipment status level and the predicted remaining life value, achieving precise classification of equipment maintenance tasks; finally, the equipment to be maintained is selected based on the maintenance priority matrix, and the standard maintenance plan is personalized adjusted in combination with the equipment historical records, thus forming a targeted customized maintenance plan. The present invention combines data-driven and intelligent algorithms, while improving the equipment operation and maintenance efficiency, effectively reducing the maintenance cost and extending the service life of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. Among them:

[0025] Figure 1 It is a flowchart of the equipment operation and maintenance data management method in Embodiment 1.

[0026] Figure 2 It is a system block diagram of the equipment operation and maintenance data management method in Embodiment 1. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention will be described in detail below with reference to the drawings in the specification.

[0028] Many specific details are set forth in the following description in order to provide a thorough understanding of the present invention. However, the present invention may be practiced in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0029] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude other embodiments.

[0030] Embodiment 1

[0031] Refer to Figures 1 to 2, which is the first embodiment of the present invention. This embodiment provides a method for managing equipment operation and maintenance data, including:

[0032] S1: Collect the operating parameters of industrial equipment to form a set of collected data.

[0033] Specifically, industrial equipment includes processing equipment, conveying equipment, and detection equipment on the production line. Among them, the operating parameters include temperature data, pressure data, and vibration data. The temperature data is collected by an infrared temperature sensor at a sampling period of 500 ms to obtain the temperature values of each monitoring point of the equipment. The pressure data is collected by a pressure sensor at a sampling period of 200 ms to obtain the pressure values of each pressure measurement point of the equipment. The vibration data is collected by an acceleration sensor at a sampling period of 100 ms to obtain the vibration acceleration values and vibration displacement values of each vibration measurement point of the equipment.

[0034] Further, align the temperature data, pressure data, and vibration data according to the collection timestamps of the operating parameters, and divide the aligned operating parameters into several sets of collected data at preset time intervals.

[0035] Furthermore, perform data preprocessing on the temperature data, pressure data, and vibration data in each set of collected data respectively to generate a standardized set of collected data. The preprocessing includes removing abnormal mutation values, supplementing missing values, and data normalization processing.

[0036] S2: Input the set of collected data into a support vector machine model and output the equipment anomaly probability value and the equipment remaining life prediction value.

[0037] Specifically, input the standardized set of collected data into the support vector machine model for analysis and prediction according to the time series structure. The support vector machine model includes a state diagnosis model and a life prediction model.

[0038] Further, the state diagnosis model constructs a feature space mapping relationship using a radial basis kernel function, and performs non-linear classification on the sample data in the feature space by minimizing the structural risk criterion. Calculate the equipment anomaly probability value based on the distance function of the classification hyperplane. The specific formula is as follows:

[0039]

[0040] Among them, P(x) is the equipment anomaly probability value, x is the input feature vector, n is the number of support vectors, α i is the Lagrange multiplier, y i is the class label of the i-th support vector, x i is the input feature vector of the i-th support vector, σ is the RBF kernel function parameter, λ is the probability conversion coefficient, and μ is the mean of the feature vectors.

[0041] It should be noted that the kernel function parameters and slack variables of the radial basis kernel function are optimized by grid search and cross-validation methods.

[0042] Furthermore, the life prediction model adopts a support vector regression structure, selects the ε-insensitive loss function to construct the optimization objective, establishes a regression prediction model by extracting the temperature trend characteristics, pressure fluctuation characteristics and vibration spectrum characteristics in the collected data group, and trains the regression prediction model in combination with the life decay law in the historical operation data to output the predicted value of the remaining life of the device. The specific formula is as follows:

[0043]

[0044] Among them, R(x) is the predicted value of the remaining life of the device, R0 is the nominal life of the device, m is the number of degradation characteristics, ω i i is the weight coefficient of the i-th characteristic, a i is the measured value of the i-th characteristic, is the ideal value of the i-th characteristic, θ is the life decay coefficient, b is the current value of the key environmental factor, η is the standard value of the environmental factor, and δ is the tolerance coefficient of the environmental factor.

[0045] It should be noted that the insensitive coefficient determines the optimal value through the grid search method.

[0046] S3: Generate the device status level according to the device anomaly probability value, and establish a maintenance priority matrix through the combination relationship between the device status level and the predicted value of the remaining life of the device.

[0047] Specifically, generate the device status level according to the device anomaly probability value, and divide the device operation status into normal operation status, sub-healthy status and fault warning status through the preset threshold division method.

[0048] Furthermore, when the device anomaly probability value is less than the first threshold, the device operation status is divided into the normal operation status; if the device is in the normal operation status and belongs to the abundant life interval, it is determined as a low-priority maintenance task, and the urgency of the maintenance task is defined as routine maintenance; when the device anomaly probability value is greater than the first threshold and less than the second threshold, the device operation status is divided into the sub-healthy status; if the device is in the sub-healthy status and belongs to the transition life interval, it is determined as a medium-priority maintenance task, and the urgency of the maintenance task is defined as planned processing; when the device anomaly probability value is greater than the second threshold, the device operation status is divided into the fault warning status; if the device is in the fault warning status and belongs to the emergency life interval, it is determined as a high-priority maintenance task, and the urgency of the maintenance task is defined as immediate processing.

[0049] It should be noted that the first threshold is determined by analyzing the abnormal probability distribution under the normal operating state of the device and combining the statistical analysis of the normal failure frequency in historical data; the second threshold is determined by the transitional analysis between the sub-healthy state and the fault warning state of the device.

[0050] Furthermore, the predicted remaining life value of the device is divided into an ample life interval, a transitional life interval, and an emergency life interval according to the degree of life consumption.

[0051] Specifically, when the predicted remaining life value of the device is greater than life threshold A, it belongs to the ample life interval; when the predicted remaining life value of the device is less than life threshold A and greater than life threshold B, it belongs to the transitional life interval; when the predicted remaining life value of the device is less than life threshold B, it belongs to the emergency life interval.

[0052] It should be noted that life threshold A is determined by analyzing the average life data, historical failure occurrence frequency, and the estimated health state of the device under normal operating conditions; life threshold B is determined by comprehensively considering the failure risk of the device and the decline trend of the remaining life.

[0053] Further, a maintenance priority matrix is established according to the combination of the device state level and the interval of the predicted remaining life value of the device, and the maintenance priority matrix adopts a three-dimensional structure.

[0054] It should be noted that the horizontal dimension represents the device state level, the vertical dimension represents the remaining life interval, and the depth dimension represents the urgency of the maintenance task.

[0055] Furthermore, the maintenance priority level is determined by the cross-mapping of the state level and the life interval, and the priority is adjusted by the weight coefficient between different dimension combinations.

[0056] Specifically, when the combination of the device state level and the remaining life interval does not match, the priority is adjusted by the weight coefficient; if the state level is high but the life is ample, the state level is given priority; if the state is normal but the life is in an emergency, the remaining life is given priority.

[0057] It should be noted that the normal operating state corresponds to the low priority with the ample life interval, the sub-healthy state corresponds to the medium priority with the transitional life interval, and the fault warning state corresponds to the high priority with the emergency life interval.

[0058] S4: Select the device to be maintained according to the maintenance priority matrix, extract the characteristic parameters of the collected data group, match the standard maintenance plan in the maintenance plan library, and generate a customized maintenance plan for the device to be maintained.

[0059] Specifically, the devices to be maintained are selected according to the priority level order of the maintenance priority matrix, and the devices with high priority are processed first; the devices with the same priority are sorted according to the abnormal probability value.

[0060] Furthermore, the characteristic parameters are extracted from the acquisition data group of the devices to be maintained, and the characteristic parameters are matched with the standard maintenance plans in the maintenance plan library, where the maintenance plan library adopts a hierarchical structure.

[0061] It should be noted that the characteristic parameters include temperature characteristic parameters, pressure characteristic parameters, and vibration characteristic parameters. The temperature characteristic parameters include temperature mean value, temperature volatility, and temperature gradient change trend; the pressure characteristic parameters include pressure peak value, pressure pulsation frequency, and pressure fluctuation range; the vibration characteristic parameters include amplitude spectrum, phase spectrum, and envelope spectrum characteristics; the hierarchical structure includes device type layer, fault mode layer, and maintenance measure layer.

[0062] Even further, based on the matching result, the standard maintenance plan with the optimal match is determined through the calculation of characteristic similarity, and combined with the operation history record, maintenance history record, and spare part replacement record of the device to be maintained, the standard maintenance plan is adjusted personalizedly to form a customized maintenance plan for the device to be maintained.

[0063] It should be noted that the personalized adjustment includes maintenance cycle adjustment, maintenance item optimization, and maintenance resource allocation. The customized maintenance plan includes maintenance time arrangement, maintenance item list, spare part requirement list, personnel skill requirements, and maintenance quality standards.

[0064] Furthermore, this embodiment also provides a highly reliable wireless network transmission system based on dual-link redundancy, including: an acquisition module for acquiring the operation parameters of industrial devices to form an acquisition data group; an output module for inputting the acquisition data group into a support vector machine model and outputting the device abnormal probability value and the device remaining life prediction value; a establishment module for generating a device status level according to the device abnormal probability value, and establishing a maintenance priority matrix through the combined relationship between the device status level and the device remaining life prediction value; a generation module for selecting the devices to be maintained according to the maintenance priority matrix, extracting the characteristic parameters of the acquisition data group, matching the standard maintenance plans in the maintenance plan library, and generating a customized maintenance plan for the devices to be maintained.

[0065] This embodiment also provides a computer device applicable to the case of the device operation and maintenance data management method, including a memory and a processor; the memory is used for storing computer executable instructions, and the processor is used for executing the computer executable instructions to implement the device operation and maintenance data management method proposed in the above embodiment.

[0066] The computer device can be a terminal, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads provided on the outer shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0067] In summary, the present invention forms a standardized acquisition data set by collecting the operating parameters of industrial equipment, and inputs it into a support vector machine model for analysis to achieve dual prediction of the abnormal state and remaining life of the equipment; a maintenance priority matrix with a three-dimensional structure is established through the combined relationship between the equipment status level and the predicted remaining life value to achieve precise classification of equipment maintenance tasks; finally, the equipment to be maintained is selected based on the maintenance priority matrix, and the standard maintenance plan is personalized adjusted in combination with the equipment history record, thereby forming a targeted customized maintenance plan. The present invention combines data-driven and intelligent algorithms, while improving the equipment operation and maintenance efficiency, effectively reducing the maintenance cost and extending the service life of the equipment.

[0068] Embodiment 2

[0069] Referring to Table 1, this is the second embodiment of the present invention. This embodiment provides a method for managing equipment operation and maintenance data. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0070] Specifically, 6 key pump devices in a chemical plant are selected as experimental objects, and an operation and maintenance management experiment is carried out on them for 3 months. These pump devices have the same model, all of which are centrifugal pumps of a certain brand, with a nominal service life of 50,000 hours, but they have different commissioning times and different operating conditions. Before the experiment starts, first, a temperature sensor (accuracy ±0.1°C), a pressure sensor (accuracy

[0071] ±0.01 MPa) and a vibration sensor (sampling frequency 10 kHz) are installed on each pump device, and the sampling interval is set to 10 minutes. An industrial-grade data collector is used to collect the equipment operation parameters, and the data is transmitted to the data processing server in real time through the OPC protocol.

[0072] Furthermore, in the data preprocessing stage, the collected temperature, pressure, and vibration data are subjected to time alignment processing, outliers and missing values are removed, and normalization processing is performed. The normalization uses the Z-score method to convert the data into a standard normal distribution with a mean of 0 and a standard deviation of 1. For the vibration data, spectral analysis is additionally performed to extract spectral features in the range of 0 - 1000 Hz.

[0073] Moreover, the training of the support vector machine model uses historical operation data, including normal operation data, equipment failure data, and maintenance records within 2 years. The state diagnosis model selects the RBF kernel function, the kernel parameter γ is set to 0.1, the slack variable C is 1.0, and the model parameters are optimized through 5-fold cross-validation. The remaining life prediction model adopts the ε-SVR structure, ε is set to 0.1, and the grid search method is used to determine the optimal parameter combination.

[0074] Specifically, two thresholds are used for equipment state level division: the first threshold is set to 0.3, and the second threshold is set to 0.7. The remaining life interval is divided according to the following criteria: the life threshold A is 50% of the equipment nominal life, and the life threshold B is 20% of the equipment nominal life. The maintenance priority matrix adopts a three-dimensional structure of 3×3×3. The priority is determined through the cross-mapping of the equipment state level and the remaining life interval, and a weight coefficient is introduced for dynamic adjustment. The maintenance plan library adopts a three-layer structure: the first layer is the equipment type, the second layer is the failure type, and the third layer is the specific maintenance plan. The feature matching uses the cosine similarity algorithm, and the similarity threshold is set to 0.8. When generating a customized maintenance plan, the standard maintenance plan is adjusted specifically by comprehensively considering the equipment operation history record, maintenance history record, and spare part replacement record.

[0075] Furthermore, as shown in Table 1, from the distribution of the abnormal probability values, this method can accurately identify equipment in different operating states. For example, the abnormal probability value of Pump-003 is 0.82, which is significantly higher than the set second threshold of 0.7 and is correctly classified as the fault warning state; while the abnormal probability values of Pump-001 and Pump-004 are 0.25 and 0.28 respectively, which are lower than the first threshold of 0.3, indicating that these two devices are in good operating states. This precise state recognition ability benefits from the radial basis kernel function adopted by the support vector machine model, which can effectively capture the non-linear characteristics of the equipment operation data.

[0076] Table 1 Comparison Table of Equipment Performance and Maintenance Indicators

[0077] Index item Pump-001 Pump-002 Pump-003 Pump-004 Pump-005 Pump-006 Running time 42000h 38000h 45000h 36000h 41000h 39000h Abnormal probability value 0.25 0.45 0.82 0.28 0.68 0.35 Remaining life prediction value 12000h 8500h 3200h 15000h 4800h 9600h Status level Normal operation Sub-healthy Fault warning Normal operation Sub-healthy Normal operation Maintenance priority Low Medium High Low High Medium Maintenance plan matching degree 92.5％ 89.3％ 94.6％ 91.8％ 93.2％ 88.9％ Fault prevention rate 95.8％ 88.7％ 92.3％ 94.5％ 90.1％ 93.4％

[0078] Furthermore, in terms of remaining life prediction, the proposed method demonstrates high accuracy. Taking Pump-005 as an example, the device has been operating for 41,000 hours, which is close to 82% of its nominal life (50,000 hours). The method predicts its remaining life to be 4,800 hours, which highly coincides with the actual operating condition. By comparing the data of Pump-002 and Pump-005, it can be found that although both are in a sub-healthy state, due to the difference in the predicted remaining life values (8,500 hours and 4,800 hours respectively), the system assigns a higher maintenance priority to Pump-005, reflecting the rationality of the proposed method in maintenance decision-making.

[0079] Specifically, the maintenance plan matching degree reflects the degree of fit between the customized maintenance plan and the actual requirements of the device. The data shows that the maintenance plan matching degree of all devices exceeds 88%. Among them, Pump-003 in the fault warning state reaches a high matching degree of 94.6%, indicating that the proposed method can generate highly personalized maintenance plans according to the specific conditions of the device. The fault prevention rate index generally maintains a high level above 90%, proving that the proposed method has significant effects in preventive maintenance.

[0080] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A method for managing device operation and maintenance data, characterized in that: Including, Collecting the operation parameters of industrial equipment to form a collection data group; Inputting the collection data group into a support vector machine model to output the equipment anomaly probability value and the equipment remaining life prediction value; Generating an equipment status level according to the equipment anomaly probability value, and establishing a maintenance priority matrix through the combination relationship between the equipment status level and the equipment remaining life prediction value; Selecting the equipment to be maintained according to the maintenance priority matrix, extracting the characteristic parameters of the collection data group, matching the standard maintenance plan in the maintenance plan library, and generating a customized maintenance plan for the equipment to be maintained.

2. The device operation and maintenance data management method according to claim 1, characterized in that: The method for generating the customized maintenance plan is as follows: Selecting the equipment to be maintained according to the priority level order of the maintenance priority matrix, and giving priority to processing high-priority equipment; Extracting the characteristic parameters from the collection data group of the equipment to be maintained, and performing feature matching between the characteristic parameters and the standard maintenance plan in the maintenance plan library, where the maintenance plan library adopts a hierarchical structure; Based on the matching result, determining the standard maintenance plan with the optimal match through feature similarity calculation, and combining the operation history record, maintenance history record and spare part replacement record of the equipment to be maintained to perform personalized adjustment on the standard maintenance plan to form a customized maintenance plan for the equipment to be maintained.

3. The device operation and maintenance data management method according to claim 2, wherein: Generating an equipment status level according to the equipment anomaly probability value, and establishing a maintenance priority matrix through the combination relationship between the equipment status level and the equipment remaining life prediction value, including: Generating an equipment status level according to the equipment anomaly probability value, and dividing the equipment operation status into a normal operation status, a sub-healthy status and a fault warning status through a preset threshold division method; At the same time, dividing the equipment remaining life prediction value into a sufficient life interval, a transition life interval and an emergency life interval according to the life consumption degree; Establishing a maintenance priority matrix according to the interval combination of the equipment status level and the equipment remaining life prediction value, where the maintenance priority matrix adopts a three-dimensional structure; Determining the maintenance priority level through the cross mapping of the status level and the life interval, and adjusting the priority through a weight coefficient between different dimension combinations.

4. The device operation and maintenance data management method according to claim 3, characterized in that: Also including, When the equipment anomaly probability value is less than the first threshold, the equipment operation status is divided into a normal operation status; if the equipment is in the normal operation status and belongs to the sufficient life interval, it is determined as a low-priority maintenance task, and the urgency of the maintenance task is defined as routine maintenance; When the equipment anomaly probability value is greater than the first threshold and less than the second threshold, the equipment operation status is divided into a sub-healthy status; if the equipment is in the sub-healthy status and belongs to the transition life interval, it is determined as a medium-priority maintenance task, and the urgency of the maintenance task is defined as planned processing; When the equipment anomaly probability value is greater than the second threshold, the equipment operation status is divided into a fault warning status; If the equipment is in the fault warning status and belongs to the emergency life interval, it is determined as a high-priority maintenance task, and the urgency of the maintenance task is defined as immediate processing; When the predicted remaining life of the device is greater than the life threshold A, it belongs to the abundant life interval; when the predicted remaining life of the device is less than the life threshold A and greater than the life threshold B, it belongs to the transitional life interval; when the predicted remaining life of the device is less than the life threshold B, it belongs to the emergency life interval; When the combination of the device status level and the remaining life interval does not match, the priority is adjusted through the weight coefficient.

5. The device operation and maintenance data management method according to claim 4, characterized in that: Input the collected data group into the support vector machine model, and output the device abnormal probability value and the predicted remaining life value of the device, including: Input the standardized collected data group into the support vector machine model for analysis and prediction according to the time series structure, where the support vector machine model includes a status diagnosis model and a life prediction model; The status diagnosis model constructs a feature space mapping relationship using the radial basis kernel function, and performs non-linear classification on the sample data in the feature space by minimizing the structural risk criterion, and calculates the device abnormal probability value according to the distance function of the classification hyperplane; The life prediction model adopts a support vector regression structure, selects the ε-insensitive loss function to construct the optimization objective, establishes a regression prediction model by extracting the temperature trend feature, pressure fluctuation feature and vibration spectrum feature in the collected data group, and trains the regression prediction model in combination with the life attenuation law in the historical operation data, and outputs the predicted remaining life value of the device.

6. The device operation and maintenance data management method according to claim 5, characterized in that: The specific formula for the device abnormal probability value is as follows: Among them, P(x) is the device anomaly probability value, x is the input feature vector, n is the number of support vectors, α i is the Lagrange multiplier, y i is the class label of the i-th support vector, x i is the input feature vector of the i-th support vector, σ is the RBF kernel function parameter, λ is the probability conversion coefficient, and μ is the mean of the feature vectors; The specific formula for the predicted remaining life value of the device is as follows: Among them, R(x) is the predicted remaining life of the device, R0 is the nominal life of the device, m is the number of degradation characteristics, ω i i is the weight coefficient of the i-th characteristic, a i is the measured value of the i-th characteristic, is the ideal value of the i-th characteristic, θ is the life attenuation coefficient, b is the current value of the key environmental factor, η is the standard value of the environmental factor, and δ is the tolerance coefficient of the environmental factor.

7. The method for managing device operation and maintenance data according to claim 5, characterized in that: The formation method of the collected data group is Align the temperature data, pressure data and vibration data according to the collection timestamp of the operation parameters, and divide the aligned operation parameters into several collected data groups according to a preset time interval; Perform data preprocessing on the temperature data, pressure data and vibration data in the collected data group respectively to generate a standardized collected data group.

8. A device operation and maintenance data management system, based on the high-reliability wireless network transmission method with dual-link redundancy according to any one of claims 1 to 7, characterized in that: Including A collection module for collecting the operation parameters of industrial equipment to form a collected data group; An output module for inputting the collected data group into the support vector machine model and outputting the device abnormal probability value and the predicted remaining life value of the device; A establishment module for generating a device status level according to the device abnormal probability value, and establishing a maintenance priority matrix through the combination relationship between the device status level and the predicted remaining life value of the device; A generation module for selecting the device to be maintained according to the maintenance priority matrix, extracting the characteristic parameters of the collected data group, matching the standard maintenance plan in the maintenance plan library, and generating a customized maintenance plan for the device to be maintained.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the device operation and maintenance data management method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the device operation and maintenance data management method according to any one of claims 1 to 7.

Images