Converter station secondary equipment fault rate evaluation method, device, equipment and storage medium

Abstract

The embodiment of the invention provides a converter station secondary equipment fault rate evaluation method and device, equipment and a storage medium, and the method comprises the steps: obtaining a current state score and a historical maintenance event of secondary equipment, and carrying out the calculation through a preset fault rate evolution model according to the current state score and the historical maintenance event, and obtaining a fault rate. Through the method, accurate evaluation and prediction of the fault rate of the secondary equipment of the converter station are realized, the pain point that dynamic aging and maintenance influence are ignored in a traditional method is solved, and reliable technical support is provided for intelligent operation and maintenance of a power system.

Description

Technical Field

[0001] The present application relates to the field of intelligent detection technology for converter stations, and in particular to a method, apparatus, device, and storage medium for evaluating the failure rate of secondary equipment in a converter station. Background Art

[0002] Converter station secondary equipment is the core control unit of HVDC transmission systems, providing critical functions such as relay protection, monitoring, and communications. Its operational reliability directly determines the safety and stability of the power system. With the large-scale construction of UHVDC projects, the complexity of converter station equipment has increased significantly. Traditional periodic maintenance models are no longer able to meet the smart grid's demand for accurate equipment status perception and preventive maintenance. In this context, dynamically assessing secondary equipment failure rates, accurately identifying potential hazards, and predicting lifespan trends have become key technical challenges in improving power system reliability and economical operation and maintenance.

[0003] The existing method for calculating the failure rate of electrical equipment mainly relies on the status score obtained from the equipment status evaluation for estimation. The accuracy of the status score greatly affects the accuracy of the failure rate calculation. In addition, this method is difficult to dynamically evaluate the equipment failure rate based on the equipment's operating stage and ignores the impact of historical equipment accidents on the current failure rate calculation. It has disadvantages such as low credibility and low precision.

[0004] In summary, how to achieve high-accuracy evaluation of the failure rate of secondary equipment in converter stations is a technical problem that urgently needs to be solved in this field. Summary of the Invention

[0005] The embodiments of the present application provide a method, apparatus, device, and storage medium for evaluating the failure rate of secondary equipment in a converter station, so as to solve the problem of how to achieve high-accuracy evaluation of the failure rate of secondary equipment in a converter station.

[0006] In a first aspect, an embodiment of the present application provides a method for evaluating the failure rate of secondary equipment in a converter station, comprising:

[0007] Obtain current status scores and historical maintenance events of secondary equipment;

[0008] According to the current status score and the historical maintenance events, the failure rate is calculated through a pre-set failure rate evolution model to obtain the failure rate. The failure rate evolution model is based on the real-time status score of the secondary equipment and the historical maintenance events, and is obtained by dynamically correcting the pre-set Weil distribution model through the service age decrease factor and the failure rate increase factor.

[0009] In one possible implementation, the method further includes:

[0010] Establishing the Weil distribution model;

[0011] Based on the status score of the secondary equipment obtained in real time, the actual service age of the secondary equipment is calculated using the Weil distribution model;

[0012] Calculating the service age reduction factor and the failure rate increase factor according to the number of historical maintenance events;

[0013] The Weil distribution model is dynamically modified based on the actual service age, the service age decrement factor, the failure rate increase factor and the maintenance interval time in the historical maintenance events to obtain the failure rate evolution model.

[0014] In a possible implementation, the actual service age of the secondary equipment is calculated based on the status score of the secondary equipment obtained in real time using the Weil distribution model, including:

[0015] Substituting the status score of the secondary device into the exponential relationship model between the failure rate and the status to obtain the current failure rate;

[0016] Based on the current failure rate and the parameters in the Weil distribution model, the actual service age is obtained through inverse calculation.

[0017] In a possible implementation, the service age reduction factor is calculated based on the number of historical maintenance events, including:

[0018] The basic service age reduction factor is calculated based on the historical maintenance times;

[0019] Based on the pre-set overhaul probability, minor repair probability and influence coefficient, the maintenance coefficient is calculated;

[0020] The service age reduction factor is obtained based on the maintenance coefficient and the basic service age reduction factor.

[0021] In a possible implementation, calculating the failure rate increasing factor according to the number of historical maintenance events includes:

[0022] The historical maintenance times are input into a preset failure rate increasing factor formula to calculate the failure rate increasing factor.

[0023] In a possible implementation, constructing the Weil distribution model includes:

[0024] Establishing an initial Weil distribution model and initializing parameters of the initial Weil distribution model to obtain initialization parameters;

[0025] updating the parameters of the initial Will distribution model by a least squares method according to the initialization parameters and the pre-acquired historical fault data of the secondary equipment;

[0026] Calculating the residual sum of squares of the parameters in real time;

[0027] Until the residual sum of squares is within a preset convergence range, the current parameter is set as the target parameter;

[0028] The target parameters are input into the initial Weil distribution model to obtain the Weil distribution model.

[0029] In one possible implementation, the method further includes:

[0030] Based on the failure rate, a repair and maintenance recommendation for the secondary equipment is generated.

[0031] In a second aspect, an embodiment of the present application provides a device for evaluating the failure rate of secondary equipment in a converter station, comprising:

[0032] The acquisition module is used to obtain the current status score and historical maintenance events of secondary equipment;

[0033] An evolutionary calculation module is used to calculate the failure rate based on the current status score and the historical maintenance events using a preset failure rate evolution model. The failure rate evolution model is obtained by dynamically correcting a preset Will distribution model based on the real-time status score of the secondary equipment and the historical maintenance events using an age reduction factor and a failure rate increase factor.

[0034] In a possible implementation, the device further includes:

[0035] Establishing a module for establishing the Will distribution model;

[0036] A first calculation module is configured to calculate the actual service life of the secondary equipment based on the status score of the secondary equipment obtained in real time and using the Weil distribution model;

[0037] A second calculation module is configured to calculate the service age reduction factor and the failure rate increase factor based on the number of historical maintenance events in the historical maintenance events;

[0038] A correction module is used to dynamically correct the Weil distribution model based on the actual service age, the service age decrement factor, the failure rate increase factor and the maintenance interval time in the historical maintenance events to obtain the failure rate evolution model.

[0039] In a possible implementation, the first calculation module specifically includes:

[0040] Substituting the status score of the secondary device into the exponential relationship model between the failure rate and the status to obtain the current failure rate;

[0041] Based on the current failure rate and the parameters in the Weil distribution model, the actual service age is obtained through inverse calculation.

[0042] In a possible implementation, the second calculation module specifically includes:

[0043] The basic service age reduction factor is calculated based on the historical maintenance times;

[0044] Based on the pre-set overhaul probability, minor repair probability and influence coefficient, the maintenance coefficient is calculated;

[0045] The service age reduction factor is obtained based on the maintenance coefficient and the basic service age reduction factor.

[0046] In a possible implementation, the second calculation module specifically includes:

[0047] The historical maintenance times are input into a preset failure rate increasing factor formula to calculate the failure rate increasing factor.

[0048] In a possible implementation, the establishing module specifically includes:

[0049] Establishing an initial Weil distribution model and initializing parameters of the initial Weil distribution model to obtain initialization parameters;

[0050] updating the parameters of the initial Will distribution model by a least squares method according to the initialization parameters and the pre-acquired historical fault data of the secondary equipment;

[0051] Calculating the residual sum of squares of the parameters in real time;

[0052] Until the residual sum of squares is within a preset convergence range, the current parameter is set as the target parameter;

[0053] The target parameters are input into the initial Weil distribution model to obtain the Weil distribution model.

[0054] In a possible implementation, the device further includes:

[0055] A generating module is used to generate an inspection and maintenance suggestion for the secondary equipment based on the failure rate.

[0056] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory, a processor;

[0057] The memory stores computer-executable instructions;

[0058] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0059] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementation methods of the first aspect.

[0060] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0061] The method, apparatus, device, and storage medium for evaluating the failure rate of secondary equipment in converter stations, provided in the embodiments of this application, obtain the current status score and historical maintenance events of the secondary equipment. Based on these current status scores and historical maintenance events, the failure rate is calculated using a pre-defined failure rate evolution model. This method enables accurate evaluation and prediction of the failure rate of secondary equipment in converter stations, addressing the pain point of traditional methods that ignore the impact of dynamic aging and maintenance, and providing reliable technical support for intelligent power system operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0063] Figure 1 Schematic diagram of the process of the converter station secondary equipment failure rate evaluation method provided in this application Figure 1 ;

[0064] Figure 2 Schematic diagram of the process of the converter station secondary equipment failure rate evaluation method provided in this application Figure 2 ;

[0065] Figure 3 This is a schematic diagram of a typical equipment failure curve;

[0066] Figure 4 Schematic diagram of the process of the converter station secondary equipment failure rate evaluation method provided in this application Figure 3 ;

[0067] Figure 5 Schematic diagram of the process of the converter station secondary equipment failure rate evaluation method provided in this application Figure 4 ;

[0068] Figure 6 Schematic diagram of the process of the converter station secondary equipment failure rate evaluation method provided in this application Figure 5 ;

[0069] Figure 7 Schematic diagram of fault fitting curve;

[0070] Figure 8 Schematic diagram of failure rate curve before and after correction;

[0071] Figure 9 This is a schematic diagram of the structure of the converter station secondary equipment failure rate assessment device provided by this application;

[0072] Figure 10 This is a schematic diagram of the structure of the electronic device provided in this application.

[0073] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0074] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0075] Converter station secondary equipment is the core control unit of the HVDC transmission system, responsible for key functions such as relay protection, monitoring, and communication. Its operational reliability directly determines the safety and stability of the power system. With the large-scale construction of ultra-high voltage DC projects, the complexity of converter station equipment has increased significantly. The traditional regular maintenance model can no longer meet the smart grid's needs for accurate perception of equipment status and preventive maintenance. In this context, how to dynamically evaluate the failure rate of secondary equipment, accurately identify potential hazards, and predict lifespan trends has become a key technical challenge for improving power system reliability and economic operation and maintenance. Existing methods for calculating electrical equipment failure rates mainly rely on the status score obtained from equipment status evaluation. The accuracy of the status score greatly affects the accuracy of the failure rate calculation. This method also makes it difficult to dynamically evaluate the equipment failure rate based on the equipment's operating stage and ignores the impact of historical equipment accidents on the current failure rate calculation. It has shortcomings such as low reliability and low precision.

[0076] To address the above-mentioned issues, the present application provides a method, apparatus, device, and storage medium for evaluating the failure rate of secondary equipment in converter stations, achieving highly accurate failure rate estimation for converter station secondary equipment. Specifically, existing methods for calculating the failure rate of electrical equipment primarily rely on a status score derived from equipment status evaluation. The accuracy of the status score significantly impacts the accuracy of the failure rate calculation. Furthermore, this method struggles to dynamically evaluate the equipment failure rate based on the equipment's current operating stage and ignores the impact of historical equipment accidents on the current failure rate calculation. Consequently, this method suffers from shortcomings such as low reliability and precision. In light of these issues, the inventors investigated whether a Weil distribution could be used to construct a failure rate distribution model for secondary equipment at different stages. Furthermore, they proposed a comprehensive fault evolution algorithm, combining a maintenance age reduction factor and a failure rate increase factor. Based on this method, accurate failure rate estimation can be performed by combining historical maintenance events and current status scores for secondary equipment. Furthermore, the Weil distribution secondary equipment failure rate model is used to verify whether the currently calculated failure rate conforms to statistical laws and to roughly determine the future failure rate of secondary equipment, providing a reliable basis for rationally arranging equipment maintenance and other operational decisions. Based on this, the present application proposes a solution.

[0077] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0078] Figure 1 Schematic diagram of the process of the converter station secondary equipment failure rate evaluation method provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0079] S101: Obtain the current status score and historical maintenance events of the secondary equipment.

[0080] In this step, in order to dynamically evaluate the equipment failure rate based on the operating stage of the secondary equipment and improve its evaluation accuracy, the failure rate can be accurately evaluated based on the equipment's status score and historical maintenance events.

[0081] Specifically, the current status score of the secondary device can be obtained through the following technical means:

[0082] Real-time collection of equipment operating parameters through sensors and online monitoring systems (such as SCADA and IED equipment), such as electrical parameters: insulation resistance, leakage current, and partial discharge.

[0083] Communication performance: signal delay, bit error rate, and number of communication interruptions.

[0084] Mechanical status: relay contact wear, cooling fan vibration value.

[0085] The current status score is calculated based on pre-set scoring rules.

[0086] For example, taking a converter station relay protection device as an example, the scoring rules are defined as follows:

[0087] Insulation performance: Insulation resistance (MΩ), weight: 30%, rule: ≥1000 → 100; 500-1000 → linear mapping; <500 → 0.

[0088] Communication reliability: signal delay (ms), weight: 20%, rule: ≤10 → 100; 10-50 → linear mapping; >50 → 0.

[0089] Mechanical action stability: average annual number of false operations, weight: 25%, rule: 0 times → 100; 1 time → 80; ≥2 times → 50; ≥3 times → 0.

[0090] Self-test alarm frequency: average number of alarms per month, weight: 15%, rule: 0 → 100; 1 → 90; 2 → 70; ≥ 3 → 30.

[0091] Environmental adaptability: The percentage of time when temperature and humidity exceed the standard. Weight: 10%. Rules: 0% → 100; >0% and ≤5% → 80; >5% and ≤10% → 50; >10% → 0.

[0092] Assume that the measured data for a device are as follows: insulation resistance 800 MΩ (score = 80), signal delay 20 ms (score = 60), average annual false operation 1 (score = 80), average monthly alarm 0 (score = 100), and temperature and humidity exceeding the standard account for 3% (score = 80).

[0093] Current status score: S=0.3×80+0.2×60+0.25×80+0.15×100+0.1×80=83.5.

[0094] Optionally, in order to obtain the status score of the secondary device more accurately in real time, dynamic calibration can be performed, that is, the weights in the scoring rules are dynamically adjusted regularly according to the aging law of the device.

[0095] Historical maintenance events can be obtained through the equipment operation and maintenance management system, which can record the following information:

[0096] Maintenance time point: For example, maintenance should be carried out in the 3rd and 7th years after commissioning.

[0097] Overhaul type: major overhaul (replacement of core components) or minor overhaul (routine maintenance).

[0098] Maintenance interval: The interval between the first and second maintenance is 4 years, and the interval between the second and third maintenance is 3 years. Optionally, the number of historical maintenance times can also be included.

[0099] It should be noted that the above acquisition method is only an example, and the status scoring rule is also only an example. In actual application scenarios, the settings can be adjusted according to the actual device conditions.

[0100] S102: Based on the current status score and historical maintenance events, a failure rate is calculated using a pre-set failure rate evolution model to obtain a failure rate.

[0101] In this step, after obtaining the current status score and historical maintenance events of the secondary equipment, a failure rate evolution model is pre-defined to accurately assess the secondary equipment failure rate. This failure rate evolution model is based on the secondary equipment's real-time status score and historical maintenance events, dynamically modifying a pre-defined Weil distribution model using an age-decreasing factor and a failure rate-increasing factor. Specifically, the current status score and historical maintenance events are input into this model for evolutionary calculation, resulting in an accurate failure rate.

[0102] Optionally, after accurately evaluating the failure rate of secondary equipment, it is also possible to generate inspection and maintenance recommendations for the secondary equipment based on the failure rate.

[0103] Specifically, a failure rate threshold may be preset, for example, an emergency threshold of 0.5 times / year (immediate shutdown for maintenance).

[0104] High priority threshold: 0.3 times / year (maintenance scheduled within 1 month).

[0105] Medium priority threshold: 0.2 times / year (planned maintenance within 3 months).

[0106] Low priority threshold: less than 0.2 times / year (routine inspection and monitoring).

[0107] Maintenance levels are determined based on the assessed failure rate and the set failure rate threshold. Trend prediction trigger rules can also be set. For example, a rapidly rising trend: If the failure rate is predicted to increase by 30% or more over the next year, the priority is increased. A slowly rising trend: If the failure rate increases by 10% to 30% over the next year, the maintenance cycle is optimized. A stable or declining trend: Maintain the current strategy.

[0108] Optionally, you can also match maintenance types based on failure rates, for example:

[0109] Overhaul:

[0110] Trigger conditions: Failure rate between 0.3 and 0.5 or life of key components (such as relays) reaches 80%.

[0111] Recommended measures: Replace core components and conduct comprehensive inspection.

[0112] Minor repairs:

[0113] Trigger conditions: Failure rate between 0.2 and 0.3 or local performance degradation.

[0114] Recommended actions: Clean, tighten wiring, and upgrade software.

[0115] Replacement suggestions:

[0116] Trigger conditions: Failure rate is greater than 0.5 or equivalent service life exceeds the characteristic life.

[0117] Recommended action: Eliminate old equipment and upgrade to new models.

[0118] It should be noted that the above rule for generating maintenance suggestions is only an example and can be set according to actual scenarios.

[0119] The method for assessing the failure rate of secondary equipment in converter stations, provided in an embodiment of the present application, obtains the current status score and historical maintenance events of the secondary equipment. Based on this current status score and historical maintenance events, a pre-defined failure rate evolution model is used to calculate the failure rate. This method enables accurate assessment and prediction of the failure rate of secondary equipment in converter stations, addressing the pain point of traditional methods that ignore the impact of dynamic aging and maintenance, and providing reliable technical support for intelligent power system operation and maintenance.

[0120] Figure 2 Schematic diagram of the process of the converter station secondary equipment failure rate evaluation method provided in this application Figure 2 ,like Figure 2 As shown, based on the above embodiment, the method further includes:

[0121] S201: Establish Weil distribution model.

[0122] In this step, in order to establish a Weibull distribution model that is consistent with the calculation of the failure rate of the secondary equipment of the converter station, it can be established based on the shape parameter and scale parameter. Among them, the shape parameter determines the trend of the failure rate over time, and the scale parameter represents the characteristic life of the secondary equipment, that is, the time scale for the failure rate to reach a specific threshold.

[0123] Figure 3 This is a typical fault curve diagram of the equipment, such as Figure 3 As shown, when the shape parameter When , the failure rate shows a downward trend, reflecting the early failure stage in the failure model; when When the failure rate remains constant, it is suitable for describing the accidental failure stage of the equipment; when When , the failure rate shows an upward trend, which is suitable for characterizing the failure rate characteristics of equipment aging failure stage.

[0124] The Weibull distribution can adapt to the failure modes of different devices by adjusting the above two parameters. In addition, the failure rate function of the Weibull distribution can be directly expressed as a time power function, which is convenient for dynamic correction.

[0125] It's important to note that the Weibull distribution, through its shape and scale parameters, accurately describes the dynamic evolution of equipment failures from accidental to aging failures. In converter station secondary equipment, this model not only provides a mathematical foundation for failure rate assessment but also integrates real-time status with maintenance history through dynamic correction factors, providing a reliable theoretical framework for preventive maintenance and lifespan prediction.

[0126] Specifically, an initial Will distribution model is established, and the parameters of the initial Will distribution model are initialized to obtain the initialization parameters. According to the initialization parameters and the historical fault data of the secondary equipment obtained in advance, the parameters of the initial Will distribution model are updated by the least squares method, and the residual sum of squares of the parameters is calculated in real time until the residual sum of squares is within the pre-set convergence range. Then, the current parameters are set as the target parameters, and the target parameters are input into the initial Will distribution model to obtain the Will distribution model.

[0127] The Weil distribution model can be expressed by the following formula:

[0128]

[0129] in, represents the failure rate of the equipment during the operating time t, represents the shape parameter, represents the scale parameter.

[0130] S202: Based on the status score of the secondary equipment obtained in real time, the actual service life of the secondary equipment is calculated using the Weil distribution model.

[0131] In this step, the traditional method directly uses the actual operating time of the equipment as the input of the failure rate model, which means that the aging degree and failure risk of equipment with the same operating time are consistent. However, in actual scenarios, environmental impacts, load differences, maintenance effects, etc. will affect the aging degree of the equipment. Therefore, in order to make the input of the failure rate model closer to the actual aging degree, the actual service life of the secondary equipment can be calculated based on the status score of the secondary equipment obtained in real time through the Weil distribution model.

[0132] Specifically, the status score of the secondary equipment is substituted into the exponential relationship model between the failure rate and the status to obtain the current failure rate. Based on the current failure rate and the parameters in the Weil distribution model, the actual service age is obtained through inverse calculation.

[0133] The calculated actual service life reflects the impact of actual working conditions on the failure rate, and it replaces the operating time t in the above Will distribution model.

[0134] S203: Calculate the service age decrease factor and the failure rate increase factor based on the number of historical maintenance events.

[0135] In this step, historical equipment maintenance events can extend the equipment's operating life to a certain extent and reduce its failure rate. However, as equipment ages, its failure rate increases year by year. To reflect the dynamic impact of maintenance events and age on the calculation of secondary equipment failure rates, we introduce an age reduction factor and a failure rate increase factor.

[0136] Specifically, the basic service age decrease factor is calculated based on the historical number of overhauls, the maintenance coefficient is calculated based on the pre-set overhaul probability and minor repair probability and the influence coefficient, the service age decrease factor is obtained based on the maintenance coefficient and the basic service age decrease factor, and the historical number of overhauls is input into the pre-set failure rate increase factor formula to calculate the failure rate increase factor.

[0137] S204: Dynamically modify the Weil distribution model based on the actual service age, service age decrement factor, failure rate increase factor, and maintenance interval time in historical maintenance events to obtain a failure rate evolution model.

[0138] In this step, after calculating the actual service age, service age reduction factor, and failure rate increase factor, in order to dynamically balance the maintenance life extension and aging effect and improve the failure rate prediction accuracy, the Weil distribution model is dynamically modified based on the actual service age, service age reduction factor, failure rate increase factor and historical maintenance events and maintenance interval time to obtain the failure rate evolution model.

[0139] Specifically, the failure rate evolution model can be expressed by the following formula:

[0140]

[0141] in, represents the failure rate evolution model obtained after correction, represents the Weil distribution model, represents the service age reduction factor, represents the failure rate increasing factor, Indicates the time interval between two maintenance stations. Among them, the time offset term is , indicating that the maintenance reduces the equivalent service life of the equipment Years, simulating the "younger" effect, the coefficient amplification term is , reflecting the increase in failure rate caused by the overall aging of the equipment after multiple maintenance. , and , make a correction to the model to form an updated failure rate model .

[0142] The method for evaluating the failure rate of secondary equipment in a converter station provided in an embodiment of the present application establishes a Weil distribution model. Based on the status score of the secondary equipment obtained in real time, the actual service age of the secondary equipment is calculated through the Weil distribution model. According to the number of historical maintenance events in the historical maintenance events, the service age reduction factor and the failure rate increase factor are calculated. The Weil distribution model is dynamically corrected based on the actual service age, the service age reduction factor, the failure rate increase factor, and the maintenance interval time in the historical maintenance events to obtain a failure rate evolution model. The above method dynamically calibrates the model input through the status score and quantifies the dynamic balance between maintenance and aging through the correction factor, so that the failure rate assessment is upgraded from a static time-driven to a dynamic deduction of the "status-maintenance-aging" multi-factor coupling, thereby improving the prediction accuracy, adapting to complex operation and maintenance scenarios, and providing a quantitative decision-making basis for preventive maintenance.

[0143] Figure 4 Schematic diagram of the process of the converter station secondary equipment failure rate evaluation method provided in this application Figure 3 ,like Figure 4 As shown, based on the above embodiment, step S202 specifically includes:

[0144] S401: Substitute the status score of the secondary device into the exponential relationship model between the failure rate and the status to obtain the current failure rate.

[0145] S402: Based on the current failure rate and the parameters in the Weil distribution model, the actual service life is obtained through inverse calculation.

[0146] Actual service age estimation based on current status score: The failure rate evaluation method based on equipment status score is as follows:

[0147]

[0148] in, represents the current failure rate, S represents the status score, and parameters K and C are constants that can be obtained by the inversion method based on historical statistical data.

[0149] The actual service life of secondary equipment is calculated by combining the Will distribution model with the current rate. The calculation method is as follows:

[0150]

[0151] in, represents the current failure rate, S represents the status score, represents the shape parameter, represents the scale parameter.

[0152] Compared with the equipment operating time t in the original data, it can better reflect the equipment operating conditions.

[0153] The method for assessing the failure rate of secondary equipment in converter stations, provided in an embodiment of the present application, substitutes the secondary equipment's status score into an exponential relationship model between failure rate and status to obtain the current failure rate. Based on the current failure rate and the parameters in the Weil distribution model, the actual service age is determined through inverse calculation. This method forms a closed-loop quantitative chain of "status → risk → time" by linking status score → failure rate → actual service age. This method addresses the shortcomings of traditional models that ignore environmental and load differences, enabling personalized aging assessment.

[0154] Figure 5 Schematic diagram of the process of the converter station secondary equipment failure rate evaluation method provided in this application Figure 4 ,like Figure 5 As shown, based on the above embodiment, step S203 specifically includes:

[0155] S501: Calculate the basic service age reduction factor based on the number of historical maintenance times.

[0156] S502: Calculate the maintenance coefficient based on the pre-set overhaul probability, minor repair probability and influence coefficient.

[0157] S503: Obtain the service age reduction factor based on the maintenance coefficient and the basic service age reduction factor.

[0158] Optionally, step S203 may further include:

[0159] S504: Input the historical maintenance times into a preset failure rate increasing factor formula to calculate the failure rate increasing factor.

[0160] Historical maintenance events of equipment will extend the equipment's operating life to a certain extent and reduce the equipment's failure rate during operation. However, as the equipment's operating age increases, the failure rate will increase year by year. In order to reflect the dynamic impact of maintenance events and operating age on the calculation of secondary equipment failure rate, the service age reduction factor is now introduced. and failure rate increasing factor .

[0161] Service age reduction factor By influence coefficient and basic service age reduction factor Calculated. Failure rate increasing factor and maintenance age reduction factor The calculation formula is as follows.

[0162]

[0163]

[0164]

[0165]

[0166] Where i represents the cumulative number of times the equipment has been overhauled. Assume that the probability of overhaul is The influence coefficient of overhaul on the service life of the device is , the probability of minor repair is , the influence coefficient of minor repair on the service life of the device is .

[0167] It should be noted that the basic service age reduction factor indicates that as the number of maintenance times i increases, the reduction effect gradually weakens (for example, the first maintenance effect is significant, and the subsequent marginal benefits decrease), which is consistent with the engineering experience of "the first repair effect is the best" in actual maintenance.

[0168] The impact coefficient incorporates the differences between major and minor repairs, reflecting the actual effects of different maintenance types (e.g., major repairs have a stronger life extension effect).

[0169] The service age reduction factor represents the comprehensive maintenance frequency and type, quantifies the reduction in equivalent service age, and accurately simulates the dynamic impact of maintenance on equipment life.

[0170] The failure increment factor increases with the number of maintenance cycles, i, and approaches 1.09, reflecting the hidden aging of equipment due to repeated maintenance (such as material fatigue and residual defects from repairs). This balances short-term maintenance benefits with long-term aging costs, avoiding over-reliance on maintenance for a "rejuvenating" effect.

[0171] The converter station secondary equipment failure rate assessment method provided in the embodiments of the present application calculates a basic age-decreasing factor based on the number of historical overhauls, a maintenance coefficient based on pre-set overhaul and minor repair probabilities and an impact coefficient, and an age-decreasing factor based on the maintenance coefficient and the basic age-decreasing factor. The failure rate-increasing factor is calculated by inputting the number of historical overhauls into a pre-set failure rate-increasing factor formula. This method accurately quantifies the life-extending effect of overhauls and the cumulative effect of aging. It can also flexibly adapt to complex operation and maintenance scenarios (non-fixed intervals, multi-type maintenance), balances short-term maintenance benefits with long-term aging risks, and optimizes lifecycle costs and reliability.

[0172] Figure 6Schematic diagram of the process of the converter station secondary equipment failure rate evaluation method provided in this application Figure 5 ,like Figure 6 As shown, based on the above embodiments, step S201 specifically includes:

[0173] S601: Establish an initial Weil distribution model and initialize the parameters of the initial Weil distribution model to obtain the initialization parameters.

[0174] S602: Based on the initialization parameters and the pre-acquired historical fault data of the secondary equipment, the parameters of the initial Will distribution model are updated by the least square method.

[0175] S603: Calculate the residual sum of squares of the parameters in real time.

[0176] S604: until the residual sum of squares is within a preset convergence range, the current parameter is set as the target parameter.

[0177] S605: Input the target parameters into the initial Weil distribution model to obtain the Weil distribution model.

[0178] For the secondary equipment in the converter station, only the initial Weil distribution model of its accidental failure stage and aging failure stage is considered. Combined with the historical failure rate parameters, the initial Weil distribution model is fitted using the L-Marquart algorithm to obtain the Weil distribution model.

[0179] Specifically, initialize the initial Will distribution model parameters, that is, initialize the shape parameters and scale parameters , get the initial parameters and .

[0180] The iterative update of parameters by the least squares method specifically includes:

[0181] First, a historical fault data set is input to construct a residual vector, and then the Jacobian matrix is calculated. The Levenberg-Marquardt (LM) algorithm is used to iteratively solve the problem. The sum of squared residuals is calculated after each iteration until the sum of squared residuals is within a preset range. The calculation is terminated and the parameters obtained after the iteration are set as target parameters. The target parameters are input into the initial Weil distribution model to obtain the Weil distribution model.

[0182] Optionally, you can also set the number of iterations, and end the iterative calculation when the number of iterations is reached.

[0183] The method for evaluating the failure rate of secondary equipment in a converter station provided in an embodiment of the present application establishes an initial Weibull distribution model and initializes the parameters of the initial Weibull distribution model to obtain the initialization parameters. Based on the initialization parameters and pre-acquired historical failure data of the secondary equipment, the parameters of the initial Weibull distribution model are updated by the least squares method, and the residual sum of squares of the parameters is calculated in real time until the residual sum of squares is within a pre-set convergence range. The current parameters are then set as target parameters, and the target parameters are input into the initial Weibull distribution model to obtain the Weibull distribution model. The above method achieves high-precision fitting of the Weibull distribution model, and the least squares method is combined with the LM algorithm to improve the model's ability to fit historical data.

[0184] For example, taking a device status score of 75, K=0.00137, and C=0.0541 as an example, the converter station secondary equipment failure rate evaluation method provided in this application is illustrated. Based on the current failure rate calculation formula of S402 in the aforementioned embodiment, the current failure rate of the device is calculated to be 0.0792. The corrected failure rate of the device is shown in Table 1.

[0185] Figure 7 The fault fitting curve is shown in the figure. The parameters of the Weil distribution failure rate model are obtained by fitting the historical data in Table 1: =1.38, =25.53; during the aging failure period =7.50, =13.94. Since the equipment score is in the abnormal state range, the equipment is considered to be in the aging failure stage. Combining the equipment failure rate of 0.0792 and the aging failure period 、 Parameters, using the above calculation formula for actual service age, are calculated =9.9.

[0186] It is known that the equipment is overhauled once every three months. In the 10 years of operation, it has been overhauled 40 times, with an overhaul interval of 0.25 years. Combined with the above-mentioned failure rate increasing factor and maintenance age reduction factor The service age reduction factor and failure rate increase factor were calculated to be 0.223 and 1.09 respectively.

[0187] The failure rate evolution model was obtained by modifying the fitted Weil distribution model using the age degradation factor and the failure rate increase factor. Based on the above failure rate evolution model formula, the corrected failure rate of this equipment was calculated to be 0.08634, which is higher than the failure rate of 0.0792 recorded in the table, but lower than the average failure rate of 0.1217.

[0188] The revised failure rate is lower than the average failure rate. This is because the average failure rate uses the worst-case score in the condition score range to calculate the failure rate, which is not accurate and does not fully reflect the actual operation of the equipment, and does not conform to statistical laws. However, the revised failure rate calculation method takes into account the historical failure rate distribution of the equipment and uses the comprehensive fault evolution algorithm to modify the distribution model. This can more accurately identify potential equipment failures, resulting in a higher failure rate than the original formula. Figure 8 Schematic diagram of the failure rate curve before and after correction, as shown in Figure 8 As shown in the figure, it can be seen that the revised failure rate calculation method can reasonably describe the actual operation of the equipment, and the revised failure rate is generally greater than the failure rate before the correction, indicating that the calculation method can better discover hidden faults of the equipment and is more in line with statistical laws, making it easier for operation and maintenance personnel to generate decision-making suggestions and thus calculate the optimal maintenance time.

[0189] Table 1

[0190] Commissioning time (t / a) Failure rate (times / unit / a) Commissioning time (t / a) Failure rate (times / unit / a) 1.5 0.0221 7.0 0.0266 2.0 0.0202 7.5 0.0332 2.5 0.0224 8.0 0.0326 3.0 0.0240 8.5 0.0453 3.5 0.0167 9.0 0.0411 4.0 0.0250 9.5 0.0726 4.5 0.0267 10.0 0.0694 5.0 0.0220 10.5 0.115 5.5 0.0285 11.0 0.135 6.0 0.0256 11.5 0.188 6.5 0.0299 12.0 0.211

[0191] Figure 9 This is a schematic diagram of the structure of the converter station secondary equipment failure rate assessment device provided by this application, as shown in Figure 9 As shown, the converter station secondary equipment failure rate assessment device 900 provided in this embodiment includes:

[0192] Acquisition module 901, used to obtain the current status score and historical maintenance events of the secondary equipment;

[0193] The evolution calculation module 902 is used to calculate the failure rate based on the current status score and historical maintenance events using a pre-set failure rate evolution model. The failure rate evolution model is based on the real-time status score and historical maintenance events of the secondary equipment, and is obtained by dynamically correcting the pre-set Weil distribution model using the service age reduction factor and the failure rate increase factor.

[0194] Optionally, the converter station secondary equipment failure rate assessment device 900 further includes:

[0195] Establishing module 903, for establishing the Will distribution model.

[0196] The first calculation module 904 is configured to calculate the actual service life of the secondary equipment based on the status score of the secondary equipment obtained in real time by using the Weil distribution model.

[0197] The second calculation module 905 is used to calculate the service age reduction factor and the failure rate increase factor according to the historical maintenance times in the historical maintenance events.

[0198] The correction module 906 is used to dynamically correct the Weil distribution model based on the actual service age, service age reduction factor, failure rate increase factor and maintenance interval time in historical maintenance events to obtain a failure rate evolution model.

[0199] In one possible implementation, the first calculation module 904 is specifically configured to:

[0200] Substitute the status score of the secondary equipment into the exponential relationship model between failure rate and status to obtain the current failure rate;

[0201] Based on the current failure rate and the parameters in the Weil distribution model, the actual service age is obtained through inverse calculation.

[0202] In one possible implementation, the second calculation module 905 specifically includes:

[0203] The basic service age reduction factor is calculated based on the number of historical maintenance times;

[0204] Based on the pre-set overhaul probability, minor repair probability and influence coefficient, the maintenance coefficient is calculated;

[0205] Based on the maintenance coefficient and the basic service age reduction factor, the service age reduction factor is obtained.

[0206] Optionally, the second calculation module 905 further includes:

[0207] The historical maintenance times are input into the pre-set failure rate increasing factor formula to calculate the failure rate increasing factor.

[0208] In a possible implementation, establishing module 903 specifically includes:

[0209] Establish an initial Weil distribution model, initialize the parameters of the initial Weil distribution model, and obtain the initialization parameters;

[0210] Based on the initialization parameters and the historical fault data of the secondary equipment obtained in advance, the parameters of the initial Will distribution model are updated by the least square method;

[0211] Calculate the residual sum of squares of parameters in real time;

[0212] Until the residual sum of squares is within the pre-set convergence range, the current parameters are set as the target parameters;

[0213] The target parameters are input into the initial Weil distribution model to obtain the Weil distribution model.

[0214] In a possible implementation, the converter station secondary equipment failure rate assessment device 900 further includes:

[0215] The generating module 907 is used to generate a repair and maintenance suggestion for the secondary equipment based on the failure rate.

[0216] The converter station secondary equipment failure rate assessment device provided in this embodiment can execute the converter station secondary equipment failure rate assessment method provided in the above method embodiment. Its implementation principle and technical effects are similar, and are not described in detail in this embodiment.

[0217] Figure 10 This is a schematic diagram of the structure of the electronic device provided in this application. Figure 10 As shown, the electronic device 1000 provided in this embodiment includes: at least one processor 1001 and a memory 1002. Optionally, the electronic device 1000 further includes a communication component 1003. The processor 1001, the memory 1002 and the communication component 1003 are connected via a bus 1004.

[0218] During the specific implementation process, at least one processor 1001 executes the computer-executable instructions stored in the memory 1002, so that the at least one processor 1001 executes the methods of the above-mentioned embodiments.

[0219] The specific implementation process of the processor 1001 can be found in the above-mentioned various method embodiments. The implementation principles and technical effects are similar and will not be repeated here in this embodiment.

[0220] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0221] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage.

[0222] A bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0223] The present application also provides a computer program product, including a computer program, which implements the methods of the above embodiments when executed by a processor.

[0224] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the methods of the above-mentioned embodiments are implemented.

[0225] The readable storage medium may be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0226] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0227] The division of units is merely a logical functional division; actual implementations may employ alternative divisions, for example, combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, any coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units, whether electrical, mechanical, or otherwise, through some interface.

[0228] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0229] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0230] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0231] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0232] Finally, it should be noted that those skilled in the art will readily identify other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The present invention is not limited to the precise structure described above and illustrated in the accompanying drawings, and various modifications and variations may be made without departing from the scope thereof. The scope of the present invention is limited solely by the appended claims.

Claims

1. A method for evaluating the failure rate of secondary equipment in a converter station, characterized in that: include: Obtain current status scores and historical maintenance events of secondary equipment; According to the current status score and the historical maintenance events, the failure rate is calculated through a pre-set failure rate evolution model to obtain the failure rate. The failure rate evolution model is based on the real-time status score of the secondary equipment and the historical maintenance events, and is obtained by dynamically correcting the pre-set Weil distribution model through the service age decrease factor and the failure rate increase factor.

2. The method according to claim 1, characterized in that The method further comprises: Establishing the Weil distribution model; Based on the status score of the secondary equipment obtained in real time, the actual service age of the secondary equipment is calculated using the Weil distribution model; Calculating the service age reduction factor and the failure rate increase factor according to the number of historical maintenance events; The Weil distribution model is dynamically modified based on the actual service age, the service age decrement factor, the failure rate increase factor and the maintenance interval time in the historical maintenance events to obtain the failure rate evolution model.

3. The method according to claim 2, characterized in that The actual service age of the secondary equipment is calculated based on the status score of the secondary equipment obtained in real time through the Weil distribution model, including: Substituting the status score of the secondary device into the exponential relationship model between the failure rate and the status to obtain the current failure rate; Based on the current failure rate and the parameters in the Weil distribution model, the actual service age is obtained through inverse calculation.

4. The method according to claim 2, characterized in that The service age reduction factor is calculated based on the number of historical maintenance events, including: The basic service age reduction factor is calculated based on the historical maintenance times; Based on the pre-set overhaul probability, minor repair probability and influence coefficient, the maintenance coefficient is calculated; The service age reduction factor is obtained based on the maintenance coefficient and the basic service age reduction factor.

5. The method according to claim 2, characterized in that The failure rate increasing factor is calculated based on the number of historical maintenance events, including: The historical maintenance times are input into a preset failure rate increasing factor formula to calculate the failure rate increasing factor.

6. The method according to claim 2, characterized in that The construction of the Will distribution model includes: Establishing an initial Weil distribution model and initializing parameters of the initial Weil distribution model to obtain initialization parameters; updating the parameters of the initial Will distribution model by a least squares method according to the initialization parameters and the pre-acquired historical fault data of the secondary equipment; Calculating the residual sum of squares of the parameters in real time; Until the residual sum of squares is within a preset convergence range, the current parameter is set as the target parameter; The target parameters are input into the initial Weil distribution model to obtain the Weil distribution model.

7. The method according to claim 1, characterized in that The method further comprises: Based on the failure rate, a repair and maintenance recommendation for the secondary equipment is generated.

8. A converter station secondary equipment failure rate assessment device, characterized in that: include: The acquisition module is used to obtain the current status score and historical maintenance events of secondary equipment; An evolutionary calculation module is used to calculate the failure rate based on the current status score and the historical maintenance events using a preset failure rate evolution model. The failure rate evolution model is obtained by dynamically correcting a preset Will distribution model based on the real-time status score of the secondary equipment and the historical maintenance events using an age reduction factor and a failure rate increase factor.

9. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the method for evaluating the failure rate of secondary equipment in a converter station according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method for evaluating the failure rate of secondary equipment in a converter station according to any one of claims 1 to 7.

Images