Dynamic correction method and system for equipment failure mode occurrence degree

Abstract

The invention discloses a dynamic correction method and system for equipment fault mode occurrence degree, and belongs to the technical field of power plant electrical overhaul and maintenance, and the method comprises the steps: collecting operation parameters, maintenance records and historical fault data of target electrical equipment, and recognizing a potential fault mode set of the target electrical equipment; failure mode and influence analysis is carried out on each failure mode, and the initial occurrence degree, severity and detectability of each failure mode are determined; calculating an initial risk priority number of each fault mode, and determining an initial risk according to a preset risk grade division rule; dynamically adjusting the initial occurrence degree, recalculating the updated risk priority number, and generating a corrected risk level; and constructing a dynamic maintenance decision model, and outputting a maintenance priority and a maintenance time window for each fault mode. According to the method, the defects of real-time performance, comprehensiveness and flexibility of electrical operation and maintenance of the power plant are overcome, and efficient and accurate data support is provided for operation and maintenance of electrical equipment.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of power plant electrical maintenance, and particularly relates to a dynamic correction method and system for equipment failure mode occurrence degree. BACKGROUND

[0002] With the continuous improvement of the requirements of the power industry on equipment reliability, reliability-centered maintenance (RCM) gradually becomes the core strategy of power plant equipment management. The goal of RCM is to identify potential failure modes of equipment, assess their risk levels, and develop targeted maintenance strategies through systematic analysis methods, so as to ensure the safe operation of equipment while reducing maintenance costs. However, the traditional equipment failure mode analysis method and maintenance decision model still have significant limitations in dynamic, real-time and refinement, and are difficult to adapt to the needs of complex and changing industrial scenes. At present, failure mode and effects analysis (FMEA) is a classic tool in equipment reliability management. It systematically analyzes the failure, cause and effect of equipment through a structured table, so as to arrange overhaul plans in advance and avoid unplanned shutdowns. However, the limitation of traditional FMEA is that it relies on static data and manual experience, and lacks adaptability to real-time state of equipment and dynamic changes of environment.

[0003] As an improvement, mathematical models are introduced to process and analyze data to make up for the shortcomings of FMEA. These mathematical models predict the remaining life or failure probability of equipment components through numerical simulation, such as predicting the wear trend of high-voltage motor bearings and issuing a two-week warning in advance. The method improves the accuracy of failure prediction to some extent, but the prediction model relies on a single dimension of operating parameters and fails to effectively integrate equipment maintenance records, environmental factors and component quality data, resulting in one-sided prediction results. The output of the model is mostly a fixed probability value, which cannot be associated with real-time risk levels and is difficult to support dynamic maintenance decisions. In terms of maintenance decision-making, existing technologies usually divide risk levels based on fixed RPN thresholds to generate maintenance plans. However, in the current operation and maintenance of electrical equipment, the dynamic changes of state parameters and environmental parameters during the operation of electrical equipment are not effectively combined, resulting in inaccurate risk level assessment, and maintenance plans cannot be adjusted according to real-time risk changes, which may cause electrical equipment failure due to insufficient resources and delayed processing or excessive maintenance. SUMMARY

[0004] The present application provides a dynamic correction method and system for equipment failure mode occurrence degree, aiming to solve the problem that in the current operation and maintenance of electrical equipment, the dynamic changes of state parameters and environmental parameters during the operation of electrical equipment are not effectively combined, resulting in inaccurate risk level assessment, and maintenance plans cannot be adjusted according to real-time risk changes, which may cause electrical equipment failure due to insufficient resources and delayed processing or excessive maintenance.

[0005] To achieve the above object, the application adopts the following technical scheme: The application provides a dynamic correction method for a device failure mode occurrence degree, comprising the following steps: S1, by collecting the operation parameters, maintenance records and historical failure data of the target electrical device, identifying the potential failure mode set of the target electrical device in the current preset operation cycle; S2, based on the potential failure mode set, failure mode and effect analysis is performed on each failure mode to determine the initial occurrence degree, severity and detectability of each failure mode; the initial risk priority number of each failure mode is calculated, and the initial risk is determined according to the preset risk level division rule; S3, based on the multi-dimensional optimization criterion, the initial occurrence degree is dynamically adjusted, the updated risk priority number is recalculated according to the adjusted occurrence degree, and the corrected risk level is generated based on the updated risk priority number value; Wherein, the multi-dimensional optimization criterion includes device real-time operation state parameters, environmental factor data, component wear trend prediction value and maintenance strategy priority; S4, according to the corrected risk level, a dynamic maintenance decision model is constructed, and the maintenance priority and maintenance time window for each failure mode are output, and the dynamic correction of the device failure mode occurrence degree is completed.

[0006] In some embodiments, in S1, the operation parameters include at least one of vibration spectrum data, temperature change curve, pressure fluctuation value and current voltage waveform; the historical failure data includes failure occurrence time, failure repair record and similar device failure statistical information.

[0007] In some embodiments, in S2, the determination of the initial occurrence degree specifically includes: According to the device usage time, maintenance cycle deviation, component quality evaluation index and environmental monitoring data, the occurrence probability of each failure mode is graded by combining a preset scoring table to obtain a quantitative value of the initial occurrence.

[0008] Further, in S2, the preset scoring table divides the occurrence into four levels: failure occurrence cycle greater than three years, failure occurrence cycle one to three years, failure occurrence every quarter and failure occurrence every month.

[0009] In some embodiments, in S3, the multi-dimensional optimization criterion dynamically adjusts the occurrence degree by the following way: An association model of device real-time operation state parameters and historical operation data is established to predict the component wear trend; the component wear trend prediction value is corrected in combination with environmental temperature and humidity, air pressure data; based on the maintenance strategy priority, the prediction value is weighted and optimized to generate a dynamic adjustment coefficient; the initial occurrence degree is linearly or nonlinearly corrected according to the dynamic adjustment coefficient.

[0010] Further, in S3, the correlation model includes an ARIMA model or an LSTM neural network model based on time series analysis.

[0011] In some embodiments, in S3, the revised risk level is divided into low risk, low-medium risk, medium risk, high-medium risk, and high risk.

[0012] In some embodiments, in S4, the dynamic maintenance decision model is constructed by: Based on the revised risk level, a mapping relationship between failure modes and maintenance types is established; according to the maintenance time window constraint condition, the optimal maintenance priority sequence is solved by using genetic algorithm or particle swarm optimization algorithm, with the optimization objectives of minimizing downtime loss and maximizing equipment reliability; The maintenance type includes at least one of preventive maintenance, predictive maintenance, and emergency repair.

[0013] In some embodiments, the method further comprises pushing the revised risk level, maintenance priority, and maintenance time window to the equipment management terminal in real time, and displaying them in the form of a visual chart on the terminal interface.

[0014] The application also provides a dynamic revision system for the occurrence degree of equipment failure modes, which comprises a failure mode set module, an initial risk determination module, a risk level revision module, and a dynamic revision module, wherein: The failure mode set module is used to identify the potential failure mode set of the target electrical equipment in the current preset operation cycle by collecting the operation parameters, maintenance records, and historical failure data of the target electrical equipment; The initial risk determination module is used to perform failure mode and impact analysis on each failure mode based on the potential failure mode set, determine the initial occurrence degree, severity, and detectability of each failure mode, calculate the initial risk priority number of each failure mode, and determine the initial risk according to the preset risk level division rule; The risk level revision module is used to dynamically adjust the initial occurrence degree based on multi-dimensional optimization criteria, recalculate the updated risk priority number according to the adjusted occurrence degree, and generate a revised risk level based on the updated risk priority number; The multi-dimensional optimization criteria include real-time equipment operating state parameters, environmental factor data, component wear trend prediction values, and maintenance strategy priority; The dynamic revision module is used to construct a dynamic maintenance decision model according to the revised risk level, output the maintenance priority and maintenance time window for each failure mode, and complete the dynamic revision of the occurrence degree of equipment failure modes.

[0015] The application discloses a dynamic correction method and system for a device failure mode occurrence degree, and through integration of operation parameters, maintenance records and historical failure data of a target device, three-dimensional monitoring of the device state can be realized, multi-source data fusion avoids the limitation of a single dimension in a traditional method, and the coverage of potential failure mode recognition is significantly improved; similar device statistical information in the historical failure data supports analog inference of potential failure modes of a new device, the system can add the mode into a potential failure set of the current device in advance, and reduces the risk of missed judgment; and the setting of a preset operation cycle enables the system to flexibly adjust the monitoring frequency according to the actual working condition of the device, and avoids data lag or redundancy caused by a fixed cycle.

[0016] The application quantitatively scores the initial occurrence degree, severity and detectability of each failure mode through failure mode and effects analysis, calculates an initial risk priority number, realizes standardization of the score, and reduces human bias. The preset risk level rule makes the risk classification more operable, the system can automatically trigger a regular maintenance plan, and avoids response delay caused by ambiguous risk. The application introduces a multi-dimensional optimization criterion, integrates real-time operation parameters of the device, environmental factors, component wear trend prediction and maintenance strategy priority, dynamically adjusts the initial occurrence degree, and the system can predict the remaining life through an association model; the component wear trend prediction value is generated through a time series model, and is compensated and corrected in combination with environmental data, so that the prediction accuracy is improved, and the risk assessment is closer to the actual working condition. The application constructs a dynamic maintenance decision model based on the corrected risk level, generates an optimal maintenance sequence under a constraint condition by using an optimization algorithm, the system can automatically delay the maintenance of non-key devices, and preferentially processes high-risk failures, so that the production continuity is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings are included to provide a further understanding of the application, and are incorporated in and constitute a part of this application, illustrate embodiments of the application and serve to explain the principles of the application, and do not constitute an improper limitation on the application.

[0018] Figure 1 A flowchart of the dynamic correction method for a device failure mode occurrence degree of the application; Figure 2 An architecture schematic diagram of the dynamic correction system for a device failure mode occurrence degree of the application. DETAILED DESCRIPTION

[0019] In order to make the objects, technical solutions and advantages of the embodiments of the application clearer, the technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are some embodiments of the application, rather than all the embodiments of the application. The components of the embodiments of the application described and shown in the drawings can be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the application provided in the accompanying drawings is not intended to limit the scope of the application claimed, but merely represent selected embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those of ordinary skill in the art without creative labor are within the scope of protection of the application.

[0021] It should be noted that similar reference numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0022] It should be noted that the terms "first", "second", and the like in the specification and claims of the application and the above drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0023] As shown in Figure 1 The dynamic correction method for the occurrence degree of the failure mode of the device of the application comprises the following steps: S1, by collecting the running parameters, maintenance records and historical failure data of the target electrical device, identifying the potential failure mode set of the target electrical device in the current preset running period; S2, based on the potential failure mode set, performing failure mode and effect analysis on each failure mode to determine the initial occurrence degree, severity and detectability of each failure mode; calculating the initial risk priority number of each failure mode, and determining the initial risk according to the preset risk level division rule; S3, based on the multi-dimensional optimization criterion, dynamically adjusting the initial occurrence degree, recalculating the updated risk priority number according to the adjusted occurrence degree, and generating the corrected risk level based on the updated risk priority number value; Wherein, the multi-dimensional optimization criterion includes device real-time running state parameters, environmental factor data, component wear trend prediction value and maintenance strategy priority; S4, according to the corrected risk level, constructing a dynamic maintenance decision model, outputting the maintenance priority and maintenance time window for each failure mode, and completing the dynamic correction of the occurrence degree of the device failure mode.

[0024] The dynamic correction method of the equipment failure mode occurrence degree of the application constructs a multi-dimensional data base by collecting the operation parameters, maintenance records and historical failure data of the target electrical equipment. The operation parameters include vibration spectrum data, temperature change curve, pressure fluctuation value and current voltage waveform, etc., which can comprehensively reflect the mechanical, electrical and thermodynamic state of the equipment.

[0025] The application improves the comprehensive identification of the failure mode set by integrating the maintenance records and historical failure data. In complex industrial scenarios, the cross verification of multi-source data can reduce the false alarm and missed alarm probability. Based on the potential failure mode set, the application determines the initial occurrence degree, severity and detectability of each failure mode by failure mode and effects analysis (FMEA), calculates the initial risk priority number, dynamically adjusts and corrects the initial value, integrates real-time operation state parameters, environmental factors, component wear trend prediction values and maintenance strategy priority, dynamically adjusts the initial occurrence degree value, considers not only the current state of the equipment but also the future trend prediction, and makes the risk score closer to the actual working condition.

[0026] The dynamic correction method of the equipment failure mode occurrence degree of the application constructs a dynamic maintenance decision model based on the corrected risk level, outputs the maintenance priority and maintenance time window for each failure mode, solves the optimal maintenance sequence under the constraint condition by an optimization algorithm such as genetic algorithm or particle swarm algorithm, allocates resources to high-risk failures in priority when the spare parts are limited, balances the shutdown loss and equipment reliability, dynamically adjusts the maintenance time window to adapt to the production plan changes and ensure the stable power generation load. The closed-loop linkage of risk assessment and maintenance decision is realized, so that the system can respond to the risk changes in real time and avoid the unplanned shutdown caused by information lag in the traditional method.

[0027] As shown in Figure 2 The application also provides a dynamic correction system of equipment failure mode occurrence degree, which comprises a failure mode set module, an initial risk determination module, a risk level correction module and a dynamic correction module, wherein: The failure mode set module is used to identify the potential failure mode set of the target electrical equipment in the current preset operation cycle by collecting the operation parameters, maintenance records and historical failure data of the target electrical equipment. The initial risk determination module is used to perform failure mode and effects analysis on each failure mode based on the potential failure mode set, determine the initial occurrence degree, severity and detectability of each failure mode, calculate the initial risk priority number of each failure mode, and determine the initial risk according to the preset risk level division rule. The risk grade correction module is configured to dynamically adjust the initial occurrence degree based on a multi-dimensional optimization criterion, recalculate the updated risk priority number according to the adjusted occurrence degree, and generate a corrected risk grade based on the updated risk priority number. The multi-dimensional optimization criterion includes real-time running state parameters of the equipment, environmental factor data, predicted values of component wear trends, and maintenance strategy priorities. The dynamic correction module is configured to construct a dynamic maintenance decision-making model according to the corrected risk grade, output a maintenance priority and a maintenance time window for each failure mode, and complete dynamic correction of the occurrence degree of the equipment failure mode.

[0028] In some embodiments, the dynamic correction method for the occurrence degree of the equipment failure mode discloses specific disclosed parameters such as vibration spectrum and current waveform, and historical failure data such as failure occurrence time and statistical information of similar equipment, limits the data dimension, ensures the comprehensiveness and operability of failure mode identification, and early detects motor winding insulation defects through current waveform analysis, and supports cross-equipment risk analogy through similar equipment data.

[0029] Further, the present application provides that the determination of the initial occurrence degree needs to be combined with equipment usage time, maintenance cycle deviation degree and other quantitative indicators, reduces the subjectivity of manual scoring, enhances the objectivity of scoring, divides the value of the failure occurrence degree into four grades through a preset scoring table, avoids ambiguity caused by inconsistent expert experience, and supports dynamic adjustment in the case of environmental mutation.

[0030] In addition, the present application proposes to predict the component wear trend through an LSTM correlation model, correct the predicted value in combination with environmental data, and generate a dynamic adjustment coefficient based on a maintenance strategy. The LSTM model captures the time sequence characteristics of the vibration signal, predicts the remaining life of the bearing, further corrects the predicted value through high humidity data, and improves the accuracy of the value correction of the initial occurrence degree.

[0031] The dynamic correction method for the occurrence degree of the equipment failure mode divides the risk grade into five levels from low risk to high risk, improves the accuracy of maintenance priority division through clear threshold values. In actual working conditions, the risk grade can be divided as follows: initial risk priority number < 10 is low risk; 10 ≤ initial risk priority number < 20 is low-medium risk; 20 ≤ initial risk priority number < 40 is medium risk; 40 ≤ initial risk priority number < 60 is high-medium risk; and initial risk priority number ≥ 60 is high risk.

[0032] The genetic algorithm or particle swarm algorithm is adopted to optimize the maintenance sequence, the shutdown loss and equipment reliability are balanced under multiple constraint conditions, the discrete optimization problem of spare parts scheduling is solved through the genetic algorithm, the continuous time window is optimized through the particle swarm algorithm, and the decision efficiency is improved. The application also pushes the risk level and maintenance plan in real time through a visual chart, and enhances the decision transparency. In actual working conditions, the application can display a risk heat map in the instrument panel to help operation and maintenance personnel quickly locate high-risk equipment, and the push function ensures immediate response and reduces processing delay.

[0033] To sum up, the dynamic correction method and system for the occurrence degree of the equipment failure mode can capture the change of the equipment state such as temperature rise and vibration anomaly in time through the dynamic correction mechanism, adjust the risk level, and avoid the hysteresis of the traditional static score; the risk grading and priority sorting can reduce the cost of emergency repair caused by excessive maintenance and sudden failure; the early warning and dynamic maintenance strategy can prolong the service life of key components, reduce the unplanned downtime, and ensure the production continuity; the multi-dimensional data fusion and the data calculation and integration through the optimization algorithm can change the maintenance decision from experience-driven to data-driven, solve the deficiencies of the traditional method in real-time, comprehensiveness and flexibility, and provide efficient and accurate data support for equipment operation and maintenance.

[0034] Finally, it should be noted that: the above description is only a preferred embodiment of the application, and does not limit the application in any form; any person skilled in the art can easily implement the application according to the description and the above description, make some changes, modifications and equivalent changes of the disclosed technical content, which are equivalent embodiments of the application; at the same time, any equivalent changes, modifications and evolution of the above embodiments according to the essential technology of the application are still within the protection scope of the technical solutions of the application.

Claims

1. A method for dynamically correcting the occurrence degree of equipment failure mode, characterized in that: The steps include: S1. Identify a set of potential failure modes of the target electrical equipment within a current preset operating cycle by collecting operating parameters, maintenance records, and historical failure data of the target electrical equipment; S2. Based on the potential failure mode set, perform failure mode and effect analysis on each failure mode to determine the initial occurrence, severity, and detectability of each failure mode; Calculate the initial risk priority number for each failure mode and determine the initial risk based on the preset risk level classification rules; S3. Based on the multi-dimensional optimization criterion, dynamically adjust the initial occurrence degree, recalculate the updated risk priority number based on the adjusted occurrence degree, and generate a revised risk level based on the updated risk priority value; The multi-dimensional optimization criteria include real-time equipment operating status parameters, environmental factor data, component wear trend prediction values, and maintenance strategy priorities; S4. Based on the corrected risk level, a dynamic maintenance decision model is constructed to output the maintenance priority and maintenance time window for each failure mode, completing the dynamic correction of the occurrence degree of equipment failure mode.

2. The method for dynamically correcting the occurrence degree of equipment failure mode according to claim 1, characterized in that: In said S1, the operating parameters include at least one of vibration spectrum data, temperature change curve, pressure fluctuation value and current and voltage waveform; the historical fault data includes fault occurrence time, fault repair record and similar equipment fault statistics.

3. The method for dynamically correcting the occurrence degree of equipment failure mode according to claim 1, characterized in that: In S2, the determination of the initial occurrence degree specifically includes: Based on the equipment usage time, maintenance cycle deviation, component quality evaluation indicators and environmental monitoring data, the occurrence probability of each failure mode is graded in combination with the preset scoring table to obtain the quantitative value of the initial occurrence.

4. The method for dynamically correcting the occurrence degree of equipment failure mode according to claim 3, characterized in that: In S2, the preset scoring table divides the fault into four levels: a fault occurrence cycle greater than three years, a fault occurrence cycle of one to three years, a fault occurring every quarter, and a fault occurring every month.

5. The method for dynamically correcting the occurrence degree of equipment failure mode according to claim 1, characterized in that: In S3, the multidimensional optimization criterion dynamically adjusts the occurrence degree in the following manner: Establish a correlation model between the equipment's real-time operating status parameters and historical operating data to predict component wear trends; combine ambient temperature, humidity, and air pressure data to revise component wear trend predictions; Based on the maintenance strategy priority, the predicted value is weighted and optimized to generate a dynamic adjustment coefficient; The initial occurrence degree is corrected linearly or nonlinearly according to the dynamic adjustment coefficient.

6. The method for dynamically correcting the occurrence degree of equipment failure mode according to claim 5, characterized in that: In S3, the correlation model includes an ARIMA model or an LSTM neural network model based on time series analysis.

7. The method for dynamically correcting the occurrence degree of equipment failure mode according to claim 1, characterized in that: In S3, the revised risk levels are divided into low risk, medium-low risk, medium risk, medium-high risk and high risk.

8. The method for dynamically correcting the occurrence degree of equipment failure mode according to claim 1, characterized in that: In S4, the dynamic maintenance decision model is constructed in the following way: Based on the revised risk level, a mapping relationship between failure modes and maintenance types is established. Based on the maintenance time window constraints, with minimizing downtime losses and maximizing equipment reliability as the optimization goals, a genetic algorithm or particle swarm algorithm is used to solve the optimal maintenance priority sequence. The maintenance type includes at least one of preventive maintenance, predictive maintenance, and emergency repair.

9. The method for dynamically correcting the occurrence degree of equipment failure mode according to claim 1, characterized in that: The method also includes pushing the revised risk level, maintenance priority and maintenance time window to the equipment management terminal in real time, and displaying them in the form of visual charts on the terminal interface.

10. The system on which the method for dynamically correcting the occurrence degree of equipment failure modes according to any one of claims 1 to 9 is based, characterized in that: The system includes a failure mode set module, an initial risk determination module, a risk level correction module, and a dynamic correction module, wherein: Fault mode collection module: used to identify the potential failure mode collection of the target electrical equipment within the current preset operating cycle by collecting the operating parameters, maintenance records and historical fault data of the target electrical equipment; Initial risk determination module: used to perform failure mode and effect analysis on each failure mode based on the potential failure mode set, determine the initial occurrence, severity and detectability of each failure mode; calculate the initial risk priority number of each failure mode, and determine the initial risk according to the preset risk level classification rules; Risk level correction module: used to dynamically adjust the initial occurrence degree based on multi-dimensional optimization criteria, recalculate the updated risk priority number based on the adjusted occurrence degree, and generate a revised risk level based on the updated risk priority value; The multi-dimensional optimization criteria include real-time equipment operating status parameters, environmental factor data, component wear trend prediction values, and maintenance strategy priorities; Dynamic correction module: It is used to build a dynamic maintenance decision model based on the corrected risk level, output the maintenance priority and maintenance time window for each failure mode, and complete the dynamic correction of the occurrence degree of equipment failure mode.

Images