A method and system for determining a fault repair time of power transmission and transformation equipment

Abstract

The application discloses a method and system for determining the fault maintenance time of power transmission and transformation equipment. The method firstly fits the Weibull distribution of the equipment failure rate according to the historical statistical data of the equipment failure rate, forms a basic failure rate model, then respectively corrects the basic failure rate model obtained by fitting from long-term evolution factors and short-term sudden change factors to form an actual failure rate model, the long-term evolution factors consider familial defects, individual defects and maintenance behaviors, and finally calculates the equipment failure cumulative probability prediction value based on the equipment actual failure rate model, and determines the optimal maintenance period by solving the constraint equation of the equipment failure cumulative probability prediction calculation value being equal to the failure cumulative probability threshold value. The application can more reasonably determine the maintenance period, avoid over-maintenance or under-maintenance, and thus provide more accurate and effective decision support for the medium and long-term maintenance plan of the equipment.

Description

Technical Field

[0001] This invention belongs to the field of power system maintenance technology, specifically relating to a method and system for determining the fault maintenance time of power transmission and transformation equipment. Background Technology

[0002] Condition-based maintenance of power transmission and transformation equipment aims to comprehensively consider the current operating status of the equipment, the development trend of potential faults, and the possible consequences of equipment failures. This allows for the development of targeted and optimized maintenance strategies to effectively reduce equipment failure rates, lower maintenance costs, and improve the safe operation of the power grid. Condition-based maintenance of power transmission and transformation equipment is divided into short-term maintenance decisions and medium- to long-term maintenance decisions. Medium- to long-term maintenance mainly adopts a periodic maintenance approach, which determines the maintenance cycle based on statistical analysis of equipment failure rates, ensuring that the failure rate does not exceed empirical values. The main drawback of current methods for determining maintenance cycles is that they do not consider the impact of long-term sudden changes such as familial defects, individual defects, and maintenance practices, as well as short-term sudden changes, on the equipment failure rate curve, leading to over- or under-maintenance. Summary of the Invention

[0003] The purpose of this invention is to address the aforementioned problems in the prior art by providing a method and system for determining the maintenance time of power transmission and transformation equipment faults, which can reasonably determine the maintenance cycle and avoid over-maintenance or under-maintenance.

[0004] To achieve the above objectives, the technical solution of the present invention is as follows:

[0005] In a first aspect, the present invention provides a method for determining the fault repair time of power transmission and transformation equipment, the method comprising:

[0006] S1. Using historical fault data of power transmission and transformation equipment, the Weibull distribution function of the equipment during the random fault period and the loss fault period is piecewise fitted, the boundary years between the random fault period and the loss fault period are calculated, and the basic failure rate model of power transmission and transformation equipment is constructed.

[0007] S2. Correct the fitted basic failure rate model according to the following formula to obtain the actual failure rate model:

[0008] λ(t)=η×λ0(t-ΔT1-ΔT2);

[0009]

[0010]

[0011] ΔT3=t k×s -t k×(s-1) ;

[0012] In the above formula, λ(t) represents the final actual failure rate model; λ0(t) represents the equipment failure rate obtained from the basic failure rate model at time t-ΔT1-ΔT2; η represents the correction coefficients of family defects and individual defects on the Weibull distribution function; ΔT1 is the first time interval, used to represent the regression effect of maintenance behavior on equipment operating time; ΔT2 is the second time interval, used to represent the regression effect of short-term sudden changes on equipment operating time; ΔT3 represents the time interval between the two most recent health status assessments of the equipment; t k×s t represents the actual operating time of the equipment after the s-th health status evaluation following the k-th maintenance; k×(s-1) JK represents the actual operating time of the equipment after the (s-1)th health status evaluation following the kth maintenance; JK represents the current health status evaluation value of the equipment; JK0 represents the critical value of the health status evaluation between normal equipment operation and equipment failure; 100 indicates that the equipment is operating in optimal condition; MTBF1 represents the mean time between failures (MTBF1) of similar equipment manufactured by other companies; t 1_i t1 represents the actual operating years of the i-th piece of equipment among similar equipment manufactured by other manufacturers; n1 represents the total number of failures that occurred during the operation of similar equipment manufactured by other manufacturers; MTBF2 represents the mean time between failures (MTBF2) of this individual piece of equipment; t2 represents the actual operating years of this individual piece of equipment; n2 represents the number of failures that occurred during the operation of this individual piece of equipment; t k This represents the operating time of the individual device before the k-th maintenance. This represents the equivalent operating time of the individual device after the kth maintenance.

[0013] S3. Calculate the cumulative probability value of equipment failure from the completion of the last maintenance to the next moment based on the actual failure rate model, and determine the moment when the cumulative probability value of equipment failure reaches the threshold value of cumulative probability of equipment failure. This moment is the best time for the next maintenance.

[0014] The expression for the well-fitted basic failure rate model is:

[0015]

[0016] In the above formula, λ0(t) represents the equipment failure rate at time t; α1 and β1 are the shape parameter and scale parameter of the random failure period, respectively; α2 and β2 are the shape parameter and scale parameter of the wear failure period, respectively; and l represents the dividing year between the random failure period and the wear failure period.

[0017] In step S1, a BP neural network improved with the LM algorithm is used to fit the parameters α and β of the Weibull distribution function; the specific fitting steps are as follows:

[0018] A1. Initialize parameters α and β;

[0019] A2. Calculate the partial derivatives with respect to parameters α and β, and obtain the parameter estimate α after the first iteration using the LM algorithm. 1 β 1 And the sum of squared residuals;

[0020] A3. Based on the parameter estimate α after the first iteration 1 β 1 The second iteration is performed, and the parameter estimate α is obtained after the second iteration using the LM algorithm. 2 β 2 And the sum of squared residuals from the second iteration;

[0021] A4. Compare the sum of squared residuals of the first and second iterations. If the sum of squared residuals of the second iteration is less than the sum of squared residuals of the first iteration, then the second iteration ends and proceeds to A5; otherwise, increase the damping coefficient in the LM algorithm during the second iteration and return to A3.

[0022] A5. Return to step A2 and continue iterative calculation until the absolute value of the difference between the parameter estimate obtained after a certain iteration and the parameter estimate obtained before a certain iteration is less than the preset system allowable error. The entire iterative process ends, and the parameter estimate obtained in the last iteration is output.

[0023] In step S1, the dividing line between the period of accidental failure and the period of wear-out failure is obtained by solving the objective function; the formula for calculating the objective function is:

[0024]

[0025] In the above formula, S l Let represent the objective function; I represent the dividing line between the period of random failure and the period of attrition failure; n represent the last year of the period of attrition failure; λ0(t) 偶 λ0(t) represents the portion of the fitted Weibull distribution function corresponding to the loss and failure period. 损 λ represents the portion of the fitted Weibull distribution function corresponding to the loss and failure period. 实_t This represents the actual equipment failure rate at time t.

[0026] The formula for calculating the cumulative probability value of equipment failure is:

[0027]

[0028] In the above formula, Px represents the cumulative probability value of equipment failure from the completion of the k-th maintenance to the next maintenance; t′ represents the equivalent service life of the equipment at the current moment, t x Indicates the next scheduled maintenance time for the equipment;

[0029] In step S3, the formula for calculating the cumulative probability threshold of equipment failure is:

[0030]

[0031] In the above formula, P max T represents the cumulative probability threshold value for equipment failure; O Indicates the design life of the equipment; T max This indicates the maximum interval between scheduled equipment maintenance.

[0032] Secondly, the present invention provides a system for determining the fault repair time of power transmission and transformation equipment, the system comprising a basic fault rate model fitting module, an actual fault rate model construction module, and an optimal repair time calculation module:

[0033] The basic failure rate model fitting module is used to perform piecewise fitting of the Weibull distribution function of the equipment during the random failure period and the loss failure period using the historical failure data of the power transmission and transformation equipment, calculate the boundary years between the random failure period and the loss failure period, and construct the basic failure rate model of the power transmission and transformation equipment.

[0034] The actual failure rate model construction module is used to correct the fitted basic failure rate model according to the following formula to obtain the actual failure rate model:

[0035] λ(t)=η×λ0(t-ΔT1-ΔT2);

[0036]

[0037] ΔT3=t k×s -t k×(s-1) ;

[0038] In the above formula, λ(t) represents the final actual failure rate model; λ0(t) represents the equipment failure rate obtained from the basic failure rate model at time t-ΔT1-ΔT2; η represents the correction coefficients of family defects and individual defects on the Weibull distribution function; ΔT1 is the first time interval, used to represent the regression effect of maintenance behavior on equipment operating time; ΔT2 is the second time interval, used to represent the regression effect of short-term sudden changes on equipment operating time; ΔT3 represents the time interval between the two most recent health status assessments of the equipment; t k×s t represents the actual operating time of the equipment after the s-th health status evaluation following the k-th maintenance; k×(s-1) JK represents the actual operating time of the equipment after the (s-1)th health status evaluation following the kth maintenance; JK represents the current health status evaluation value of the equipment; JK0 represents the critical value of the health status evaluation between normal equipment operation and equipment failure; 100 indicates that the equipment is operating in optimal condition; MTBF1 represents the mean time between failures (MTBF1) of similar equipment manufactured by other companies; t1_ix t1 represents the actual operating years of the i-th piece of equipment among similar equipment manufactured by other manufacturers; n1 represents the total number of failures that occurred during the operation of similar equipment manufactured by other manufacturers; MTBF2 represents the mean time between failures (MTBF2) of this individual piece of equipment; t2 represents the actual operating years of this individual piece of equipment; n2 represents the number of failures that occurred during the operation of this individual piece of equipment; t k This represents the operating time of the individual device before the k-th maintenance. This represents the equivalent operating time of the individual device after the kth maintenance.

[0039] The optimal maintenance time calculation module is used to calculate the cumulative probability value of equipment failure from the completion of the last maintenance to the next time based on the actual failure rate model, and to determine the time when the cumulative probability value of equipment failure reaches the threshold value of cumulative probability of equipment failure. This time is the optimal time for the next maintenance.

[0040] The expression for the well-fitted basic failure rate model is:

[0041]

[0042] In the above formula, λ0(t) represents the equipment failure rate at time t; α1 and β1 are the shape parameter and scale parameter of the random failure period, respectively; α2 and β2 are the shape parameter and scale parameter of the wear failure period, respectively; and l represents the dividing year between the random failure period and the wear failure period.

[0043] The basic failure rate model fitting module uses the Marquardt method or a BP neural network improved with the LM algorithm to fit the parameters α and β of the Weibull distribution function; the specific fitting steps are as follows:

[0044] A1. Initialize parameters α and β;

[0045] A2. Calculate the partial derivatives with respect to parameters α and β, and obtain the parameter estimate α after the first iteration using the LM algorithm. 1 β 1 And the sum of squared residuals;

[0046] A3. Based on the parameter estimate α after the first iteration 1 β 2 The second iteration is performed, and the parameter estimate α is obtained after the second iteration using the LM algorithm. 2 β 2 And the sum of squared residuals from the second iteration;

[0047] A4. Compare the sum of squared residuals of the first and second iterations. If the sum of squared residuals of the second iteration is less than the sum of squared residuals of the first iteration, then the second iteration ends and proceeds to A5; otherwise, increase the damping coefficient in the LM algorithm during the second iteration and return to A3.

[0048] A5. Return to step A2 and continue iterative calculation until the absolute value of the difference between the parameter estimate obtained after a certain iteration and the parameter estimate obtained before a certain iteration is less than the preset system allowable error. The entire iterative process ends, and the parameter estimate obtained in the last iteration is output.

[0049] The basic failure rate model fitting module obtains the dividing line between the period of random failure and the period of wear and tear failure by solving the objective function; the formula for calculating the objective function is:

[0050]

[0051] In the above formula, S l Let represent the objective function; l represent the dividing line between the period of random failure and the period of attrition failure; n represent the last year of the period of attrition failure; λ0(t) 偶 λ0(t) represents the portion of the fitted Weibull distribution function corresponding to the loss and failure period. 损 λ represents the portion of the fitted Weibull distribution function corresponding to the loss and failure period. 实_t This represents the actual equipment failure rate at time t.

[0052] The optimal maintenance time calculation module calculates the cumulative probability value of equipment failure according to the following formula:

[0053]

[0054] In the above formula, P1 represents the cumulative probability value of equipment failure from the completion of the k-th maintenance to the next maintenance; t′ represents the equivalent service life of the equipment at the current moment, t x Indicates the next scheduled maintenance time for the equipment;

[0055] Calculate the cumulative probability threshold value for equipment failure using the following formula:

[0056]

[0057] In the above formula, P max T represents the cumulative probability threshold value of equipment failure; T0 represents the design life of the equipment; T max This indicates the maximum interval between scheduled equipment maintenance.

[0058] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0059] The present invention discloses a method for determining the maintenance time of power transmission and transformation equipment. First, based on historical statistical data of equipment failure rates, a basic failure rate model is formed by fitting a Weibull distribution of the equipment failure rate. Then, the fitted basic failure rate model is modified from two aspects: long-term evolution factors and short-term sudden change factors, forming an actual failure rate model. The long-term evolution factors consider family defects, individual defects, and maintenance behavior. Finally, based on the actual equipment failure rate model, the cumulative probability prediction value of equipment failure is calculated. By solving the constraint equation that the calculated cumulative probability prediction value of equipment failure equals the cumulative probability threshold value, the optimal maintenance cycle is determined. This provides more accurate and effective decision support for the formulation of medium- and long-term maintenance plans for equipment, avoiding over-maintenance or under-maintenance. Therefore, the present invention can more rationally determine the maintenance cycle and avoid over-maintenance or under-maintenance. Attached Figure Description

[0060] Figure 1 This is a flowchart of the maintenance method of the present invention.

[0061] Figure 2 This is a schematic diagram of the maintenance system of the present invention. Detailed Implementation

[0062] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings.

[0063] Example 1:

[0064] See Figure 1 A method for determining the fault repair time of power transmission and transformation equipment, which is carried out in the following steps:

[0065] S1. Assuming the power transmission and transformation equipment to be analyzed operates during the random failure period and the loss failure period, since the variation patterns of the random failure period and the loss failure period conform to the bathtub curve, the Weibull distribution function is used to characterize the features of different periods of the bathtub curve. The Weibull distribution function is widely used in reliability analysis, especially suitable for the distribution pattern of aging cumulative failures in electromechanical products. The expression of the basic failure rate model designed from the Weibull distribution function is as follows:

[0066]

[0067] In the above formula, λ0(t) represents the equipment failure rate at time t; α1 and β1 are the shape parameter and scale parameter of the random failure period, respectively; α2 and β2 are the shape parameter and scale parameter of the wear failure period, respectively; l represents the dividing period between the random failure period and the wear failure period.

[0068] (1) The Weibull distribution function of the power transmission and transformation equipment during the random fault period and the loss fault period is piecewise fitted using the historical fault statistics of the power transmission and transformation equipment; specifically, the parameters α and β of the Weibull distribution function are fitted using a BP neural network improved by the LM algorithm; the specific fitting process is as follows:

[0069] A1. Initialize parameters α and β;

[0070] A2. Calculate the partial derivatives with respect to parameters α and β, and obtain the parameter estimate α after the first iteration using the LM algorithm. 1 β 1 And the sum of squared residuals;

[0071] A3. Based on the parameter estimate α after the first iteration 1 β 1 The second iteration is performed, and the parameter estimate α is obtained after the second iteration using the LM algorithm. 2 β 2 And the sum of squared residuals from the second iteration;

[0072] A4. Compare the sum of squared residuals of the first and second iterations. If the sum of squared residuals of the second iteration is less than the sum of squared residuals of the first iteration, then the second iteration ends and proceeds to A5; otherwise, increase the damping coefficient μ in the LM algorithm during the second iteration and return to A3.

[0073] A5. Return to step A2 and continue iterative calculation until the absolute value of the difference between the parameter estimate obtained after a certain iteration and the parameter estimate obtained before a certain iteration is less than the preset error allowable value ε. The entire iterative process ends, and the parameter estimate obtained in the last iteration is output.

[0074] A backpropagation (BP) neural network consists of an input layer for input data; hidden layers, typically containing one or more hidden units; and an output layer for outputting the shape parameter α and scale parameter β of the Weibull distribution. Mean squared error (MSE) is usually chosen as the loss function. The input data is propagated forward and backward to obtain the output value (i.e., the estimated shape and scale parameters). Forward propagation refers to the sample data being input from the input layer, processed layer by layer through the hidden layers, and then passed to the output. If the output layer's output does not meet the expected value, backpropagation begins. Backpropagation involves propagating the output error back through the hidden layers, finding the minimum value of the error function to continuously adjust the network's weights and biases. This continuous adjustment of weights and biases constitutes the network's learning and training process, until the error reaches the expected range.

[0075] Assuming the output layer target vector of a BP network is Y and the activation function is f(), then C can be used to represent the corresponding bias function W and input weights P, i.e., C = f(p, w). Introducing r...t (W)=y t -f(p t The vectors r(W) and r(W) are formed by the vectors r(W), therefore E(W) can be expressed as:

[0076]

[0077] In the above formula, J is the Jacobian matrix of r;

[0078] Based on the Jacobian matrix, without considering the second derivative term of r(W), the Hessian matrix is ​​constructed as follows:

[0079]

[0080] The Hessian matrix form can be approximated as H = J T J, and thus complete the transformation of the Gauss-Newton formula. Through the above calculation and transformation, the second derivative of the objective function E(W) can be transformed into the solution of the first derivative, and the computational workload can be greatly reduced; the expression of the Gauss-Newton formula is as follows:

[0081]

[0082] By improving the Gauss-Newton formula, we obtain the LM method iterative formula:

[0083]

[0084] In the above formula, i is the identity matrix; μ is the damping coefficient;

[0085] The learning and training methods for BP neural networks can be selected from Gauss-Newton's method (μ→0) and the standard gradient method (μ→∞). The weight variables and biases are continuously adjusted until the training requirements are met. The training formula is as follows:

[0086]

[0087] Traditional backpropagation (BP) neural network algorithms use gradient descent to update network weights and biases. This invention employs the Levenberg-Marquardt (LM) algorithm, which adds a more complex second-order optimization process, resulting in faster convergence. The LM algorithm, also known as the Levenberg-Marquardt algorithm, is an optimization algorithm for solving nonlinear least squares problems, combining the advantages of gradient descent and Newton's method. During the training process using the LM algorithm, the following parameters are introduced: allowable training error ε, damping coefficient μ, and constant β; the threshold and connection weights are initialized, and the damping coefficient μ = μ0 and the iteration count k = 0 are set; the objective function E(W), network output, and J are calculated, and ΔW is calculated based on these parameters; if E(W) = 0, the network output is calculated. kIf ) < ε, then the network stops computation; otherwise, continue computation on E(W). k+1 According to the threshold vector and weight W k+1 =W k +ΔW is used for calculation, if E(W) k+1 ) < E(W k If k = k + 1 and μ = μ / β, then the network output and objective function can be returned and recalculated; otherwise, if μ = μβ, then ΔW can be calculated directly.

[0088] (2) By solving the objective function, the boundary years between the random failure period and the loss failure period are obtained, forming the basic failure rate model of the power transmission and transformation equipment; the calculation formula of the objective function is:

[0089]

[0090] In the above formula, S l Let represent the objective function; l represent the dividing line between the period of random failure and the period of attrition failure; n represent the last year of the period of attrition failure; λ0(t) 偶 λ0(t) represents the portion of the fitted Weibull distribution function corresponding to the loss and failure period. 损 λ represents the portion of the fitted Weibull distribution function corresponding to the loss and failure period; 实_t This represents the actual equipment failure rate at time t;

[0091] S2. Because factors such as familial defects, individual defects, and maintenance practices can affect the basic failure rate curve of equipment over a long timescale, the basic failure rate model needs to be modified accordingly to reflect the impact of these long-term evolutionary factors: For familial defects, the actual mean time between failures (MTBF) of equipment manufactured by the same manufacturer is compared with the overall MTBF of similar equipment, and the ratio of the two is used to linearize the basic failure rate of similar products; for individual defects, similar to familial defects, to reflect the individual differences between different equipment manufactured by the same manufacturer, the failure rate curve of equipment manufactured by the same manufacturer needs to be linearized based on the actual operating conditions of the equipment; maintenance practices can improve... Equipment performance, reduced equipment failure rate, and extended equipment lifespan are reflected in the equipment failure rate curve. Maintenance actions have a regressive effect on the equipment's service life. However, maintenance actions cannot restore the equipment to its original condition because the equipment itself is affected by material aging, and maintenance only repairs the deteriorated state of the equipment to a certain extent. Therefore, the equivalent service life of the equipment after the current maintenance should not be less than the equivalent service life after the last maintenance. For short-term sudden changes, the actual equivalent operating time of the equipment at the current moment is calculated by combining the equipment health status evaluation score, thereby obtaining the equipment failure rate after considering short-term sudden changes, so as to correct the basic failure rate model of the equipment due to short-term sudden changes.

[0092] Specifically, the fitted basic failure rate model is corrected according to the following formula to obtain the actual failure rate model:

[0093] λ(t)=η×λ0(t-ΔT1-ΔT2);

[0094]

[0095] ΔT3=t k×s -t k×(s-1) ;

[0096] In the above formula, λ(t) represents the final actual failure rate model; λ0(t) represents the equipment failure rate obtained from the basic failure rate model at time t-ΔT1-ΔT2; η represents the correction coefficients of family defects and individual defects on the Weibull distribution function; ΔT1 is the first time interval, used to represent the regression effect of maintenance behavior on equipment operating time; ΔT2 is the second time interval, used to represent the regression effect of short-term sudden changes on equipment operating time; ΔT3 represents the time interval between the two most recent health status assessments of the equipment, which is generally a constant value; t k×s t represents the actual operating time of the equipment after the S-th health status evaluation following the k-th overhaul; k×(s-1) JK represents the actual operating time of the equipment after the (s-1)th health status evaluation following the kth overhaul; JK represents the current health status evaluation value of the equipment; JK0 represents the critical value of the health status evaluation between normal equipment operation and equipment failure, generally taken as 80 points, with 100 points indicating that the equipment is operating in the best condition; MTBF1 represents the mean time between failures (MTBF1) of similar equipment manufactured by other companies; t 1_i t1 represents the actual operating years of the i-th piece of equipment among similar equipment manufactured by other manufacturers; n1 represents the total number of failures that occurred during the operation of similar equipment manufactured by other manufacturers; MTBF2 represents the mean time between failures (MTBF2) of this individual piece of equipment; t2 represents the actual operating years of this individual piece of equipment; n2 represents the number of failures that occurred during the operation of this individual piece of equipment; t k This represents the operating time of the individual device before the k-th maintenance. This represents the equivalent operating time of the individual device after the kth maintenance.

[0097] S3. Calculate the cumulative probability value P1 of equipment failure from the completion of the last maintenance to the next moment based on the actual failure rate model, and calculate the threshold value Px for the cumulative probability of equipment failure. ax Finally, the moment when the cumulative probability value of equipment failure reaches the cumulative probability threshold value is determined, and this moment is the optimal moment t for the next maintenance. best The formula for calculating the cumulative probability value of equipment failure is:

[0098]

[0099] In the above formula, P1 represents the cumulative probability value of equipment failure from the completion of the k-th maintenance to the next maintenance; t′ represents the equivalent service life of the equipment at the current moment, t x Indicates the next scheduled maintenance time for the equipment;

[0100] Considering that the early failure period and wear-out failure period are relatively short compared to the entire operating life of the equipment, the midpoint of the equipment's design life is used instead of the midpoint of the random failure period. The formula for calculating the cumulative failure probability threshold is as follows:

[0101]

[0102] In the above formula, P max T represents the cumulative probability threshold value for equipment failure; O Indicates the design life of the equipment; T max This indicates the maximum interval between scheduled equipment maintenance.

[0103] To verify the effectiveness of the maintenance method proposed in this invention, a simulation analysis was conducted on a 220kV transformer of a certain type within a local power grid. The historical failure rate statistics for this transformer at different service periods are shown in Table 1. The MTBF1 is 6.32 years, and the MTBF2 is 7.6 years. This transformer has been in operation for 8 years, with a design life of 20 years and a maximum maintenance interval of 8 years. The basic failure rate fitting curve is shown in Table 1. Figure 2 As shown, the optimal dividing line period l is 15 years, and the optimal time t for the next overhaul is finally determined. best The lifespan is 10.5 years; the basic failure rate model is as follows:

[0104]

[0105] Table 1 Historical statistics on failure rates

[0106]

[0107] Compared with traditional equipment condition-based maintenance schemes, this invention effectively avoids the reduction in equipment utilization caused by "over-maintenance," as well as the resulting waste of human and material resources, and reduces the impact on power grid reliability. When the equipment condition evaluation score JK approaches the critical score, the timing of its next maintenance should be slightly extended based on the maximum maintenance interval.

[0108] Example 2:

[0109] See Figure 2A system for determining the fault repair time of power transmission and transformation equipment includes a basic fault rate model fitting module, an actual fault rate model construction module, and an optimal repair time calculation module. The basic fault rate model fitting module uses historical fault data of the power transmission and transformation equipment to piecewise fit the Weibull distribution function of the equipment during the random fault period and the loss fault period, calculates the boundary years between the random fault period and the loss fault period, and constructs a basic fault rate model of the power transmission and transformation equipment. Specifically, a BP neural network improved from the LM algorithm is used to fit the parameters α and β of the Weibull distribution. The specific fitting steps are as follows:

[0110] A1. Initialize parameters α and β;

[0111] A2. Calculate the partial derivatives with respect to parameters α and β, and obtain the parameter estimate α after the first iteration using the LM algorithm. 1 β 1 And the sum of squared residuals;

[0112] A3. Based on the parameter estimate α after the first iteration 1 β 1 The second iteration is performed, and the parameter estimate α is obtained after the second iteration using the LM algorithm. 2 β 1 And the sum of squared residuals from the second iteration;

[0113] A4. Compare the sum of squared residuals of the first and second iterations. If the sum of squared residuals of the second iteration is less than the sum of squared residuals of the first iteration, then the second iteration ends and proceeds to A5; otherwise, increase the damping coefficient in the LM algorithm during the second iteration and return to A3.

[0114] A5. Return to step A2 and continue iterative calculation until the absolute value of the difference between the parameter estimate obtained after a certain iteration and the parameter estimate obtained before a certain iteration is less than the preset system allowable error. The entire iterative process ends, and the parameter estimate obtained in the last iteration is output.

[0115] Specifically, the dividing line between the period of random failure and the period of wear and tear failure is obtained by solving the objective function. The formula for calculating the objective function is as follows:

[0116]

[0117] In the above formula, S l Let represent the objective function; l represent the dividing line between the period of random failure and the period of attrition failure; n represent the last year of the period of attrition failure; λ0(t) 偶 λ0(t) represents the portion of the fitted Weibull distribution function corresponding to the loss and failure period. 损 This represents the portion of the fitted Weibull distribution function that corresponds to the period of loss and failure.

[0118] The expression for the basic failure rate model is:

[0119]

[0120] In the above formula, λ0(t) represents the equipment failure rate at time t; α1 and β1 are the shape parameter and scale parameter of the random failure period, respectively; α2 and β2 are the shape parameter and scale parameter of the wear failure period, respectively; l represents the dividing period between the random failure period and the wear failure period.

[0121] The actual failure rate model construction module is used to correct the fitted basic failure rate model according to the following formula to obtain the actual failure rate model:

[0122] λ(t)=η×λ0(t-ΔT1-ΔT2);

[0123]

[0124] ΔT3=t k×s -t k×(s-1) ;

[0125] In the above formula, λ(t) represents the final actual failure rate model; λ0(t) represents the fitted Weibull distribution function; η represents the correction coefficients for family defects and individual defects on the Weibull distribution function; ΔT1 represents the rollback effect of maintenance behavior on equipment uptime; ΔT2 represents the rollback effect of short-term sudden changes on equipment uptime; ΔT3 represents the time interval between the two most recent health status assessments of the equipment; t k×s tk represents the equivalent operating time of the equipment after the s-th health status evaluation following the k-th overhaul; ×(s-1) JK represents the equivalent operating time of the equipment after the (S-1)th health status evaluation following the kth overhaul; JK represents the current health status evaluation value of the equipment; JK0 represents the critical health status evaluation value between normal equipment operation and equipment failure; 100 indicates that the equipment is operating in optimal condition; MTBF1 represents the mean time between failures (MTBF1) of similar equipment manufactured by other companies; T 1_i t1 represents the actual operating years of the i-th piece of equipment among similar equipment manufactured by other manufacturers; n1 represents the total number of failures that occurred during the operation of similar equipment manufactured by other manufacturers; MTBF2 represents the mean time between failures (MTBF2) of this individual piece of equipment; t2 represents the actual operating years of this individual piece of equipment; n2 represents the number of failures that occurred during the operation of this individual piece of equipment; t k This represents the operating time of the individual device before the k-th maintenance. This represents the equivalent operating time of the individual device after the kth maintenance.

[0126] The optimal maintenance time calculation module is used to calculate the cumulative probability value of equipment failure from the completion of the last maintenance to the next time based on the actual failure rate model, and to determine the time when the cumulative probability value of equipment failure reaches the equipment failure cumulative probability threshold. This time is the optimal time for the next maintenance. The formula for calculating the cumulative probability value of equipment failure is as follows:

[0127]

[0128] In the above formula, P1 represents the cumulative probability value of equipment failure from the completion of the k-th maintenance to the next maintenance; t′ represents the equivalent service life of the equipment at the current moment, t x Indicates the next scheduled maintenance time for the equipment;

[0129] The formula for calculating the cumulative probability threshold of equipment failure is as follows:

[0130]

[0131] In the above formula, P max T represents the cumulative probability threshold value for equipment failure; O Indicates the design life of the equipment; T max This indicates the maximum interval between scheduled equipment maintenance.

Claims

1. A method for determining the fault repair time of power transmission and transformation equipment, characterized in that: The method includes: S1. Using historical fault data of power transmission and transformation equipment, the Weibull distribution function of the equipment during the random fault period and the loss fault period is piecewise fitted, the boundary years between the random fault period and the loss fault period are calculated, and the basic failure rate model of power transmission and transformation equipment is constructed. S2. Correct the fitted basic failure rate model according to the following formula to obtain the actual failure rate model: λ(t)=η×λ0(t-ΔT1-ΔT2); λT3=t k×s -t k×(s-1) ; In the above formula, λ(t) represents the final actual failure rate model; λ0(t) represents the equipment failure rate obtained from the basic failure rate model at time t-ΔT1-ΔT2; η represents the correction coefficients of family defects and individual defects on the Weibull distribution function; ΔT1 is the first time interval, used to represent the regression effect of maintenance behavior on equipment operating time; ΔT2 is the second time interval, used to represent the regression effect of short-term sudden changes on equipment operating time; ΔT3 represents the time interval between the two most recent health status assessments of the equipment; t k×s t represents the actual operating time of the equipment after the s-th health status evaluation following the k-th maintenance; k ×(s-1) JK represents the actual operating time of the equipment after the (S-1)th health status evaluation following the kth overhaul; JK represents the current health status evaluation value of the equipment; JK0 represents the critical health status evaluation value between normal equipment operation and equipment failure; 100 indicates that the equipment is operating in optimal condition; MTBF1 represents the mean time between failures (MTBF1) of similar equipment manufactured by other companies; f 1_i t1 represents the actual operating years of the i-th piece of equipment among similar equipment manufactured by other manufacturers; n1 represents the total number of failures that occurred during the operation of similar equipment manufactured by other manufacturers; MTBF2 represents the mean time between failures (MTBF2) of this individual piece of equipment; t2 represents the actual operating years of this individual piece of equipment; n2 represents the number of failures that occurred during the operation of this individual piece of equipment; t k This represents the operating time of the individual device before the k-th maintenance. This represents the equivalent operating time of the individual device after the kth maintenance. S3. Calculate the cumulative probability value of equipment failure from the completion of the last maintenance to the next moment based on the actual failure rate model, and determine the moment when the cumulative probability value of equipment failure reaches the threshold value of cumulative probability of equipment failure. This moment is the best time for the next maintenance.

2. The method for determining the fault repair time of power transmission and transformation equipment according to claim 1, characterized in that: The expression for the well-fitted basic failure rate model is: In the above formula, λ0(t) represents the equipment failure rate at time t; α1 and β1 are the shape parameter and scale parameter of the random failure period, respectively; α2 and β2 are the shape parameter and scale parameter of the wear failure period, respectively; l represents the dividing year between the random failure period and the wear failure period.

3. The method for determining the fault repair time of power transmission and transformation equipment according to claim 2, characterized in that: In step S1, a BP neural network improved by the LM algorithm is used to fit the parameters α and β of the Weibull distribution function. The specific fitting process is as follows: A1. Initialize parameters α and β; A2. Calculate the partial derivatives with respect to parameters α and β, and obtain the parameter estimate α after the first iteration using the LM algorithm. 1 β 1 And the sum of squared residuals of a BP neural network; A3. Based on the parameter estimate α after the first iteration 1 β 1 The second iteration is performed, and the parameter estimate α is obtained after the second iteration using the LM algorithm. 2 β 2 And the sum of squared residuals from the second iteration; A4. Compare the sum of squared residuals of the first and second iterations. If the sum of squared residuals of the second iteration is less than the sum of squared residuals of the first iteration, then the second iteration ends and proceeds to A5; otherwise, increase the damping coefficient in the LM algorithm during the second iteration and return to A3. A5. Return to step A2 and continue iterative calculation until the absolute value of the difference between the parameter estimate obtained after a certain iteration and the parameter estimate obtained before a certain iteration is less than the preset system allowable error. The entire iterative process ends, and the parameter estimate obtained in the last iteration is output.

4. The method for determining the fault repair time of power transmission and transformation equipment according to claim 2, characterized in that: In step S1, the dividing line between the period of accidental failure and the period of wear-out failure is obtained by solving the objective function; the formula for calculating the objective function is: In the above formula, S l Let represent the objective function; l represent the dividing line between the period of random failure and the period of attrition failure; n represent the last year of the period of attrition failure; λ0(t) 偶 λ0(t) represents the portion of the fitted Weibull distribution function corresponding to the loss and failure period. 损 λ represents the portion of the fitted Weibull distribution function corresponding to the loss and failure period; 实_t This represents the actual equipment failure rate at time t.

5. A method for determining the fault repair time of power transmission and transformation equipment according to claim 1 or 2, characterized in that: The formula for calculating the cumulative probability value of equipment failure is: In the above formula, P1 represents the cumulative probability value of equipment failure from the completion of the k-th maintenance to the next maintenance. t′ represents the equivalent service life of the equipment at the current moment, t x Indicates the next scheduled maintenance time for the equipment; In step S3, the formula for calculating the cumulative probability threshold of equipment failure is: In the above formula, P max T represents the cumulative probability threshold value of equipment failure; T0 represents the design life of the equipment; T max This indicates the maximum interval between scheduled equipment maintenance.

6. A system for determining the fault repair time of power transmission and transformation equipment, characterized in that: The system includes a basic failure rate model fitting module, an actual failure rate model construction module, and an optimal maintenance time calculation module. The basic failure rate model fitting module is used to perform piecewise fitting of the Weibull distribution function of the equipment during the random failure period and the loss failure period using the historical failure data of the power transmission and transformation equipment, calculate the boundary years between the random failure period and the loss failure period, and construct the basic failure rate model of the power transmission and transformation equipment. The actual failure rate model construction module is used to correct the fitted basic failure rate model according to the following formula to obtain the actual failure rate model: λ(t)=η×λ0(t-ΔT1-ΔT2); ΔT3=t k×s -t k×(s-1) ; In the above formula, λ(t) represents the final actual failure rate model; λ0(t) represents the equipment failure rate obtained from the basic failure rate model at time t-ΔT1-ΔT2. η represents the correction coefficients for familial and individual defects on the Weibull distribution function; ΔT1 is the first time interval, used to represent the regression effect of maintenance on equipment uptime; ΔT2 is the second time interval, used to represent the regression effect of short-term sudden changes on equipment uptime; ΔT3 represents the time interval between the two most recent health status assessments of the equipment; t k×s This represents the actual operating time of the equipment after the s-th health status evaluation following the k-th maintenance. t k ×(s-1) JK represents the actual operating time of the equipment after the (S-1)th health status evaluation following the kth maintenance; JK represents the current health status evaluation value of the equipment; JK0 represents the critical health status evaluation value between normal equipment operation and equipment malfunction. 100 indicates that the equipment is operating at its optimal condition; MTBF1 represents the mean time between failures (MTBF1) of similar equipment manufactured by other companies; t 1_i n1 represents the actual operating years of the i-th piece of equipment among similar equipment produced by other manufacturers; n1 represents the total number of failures that occurred during the operation of similar equipment produced by other manufacturers; MTBF2 represents the mean time between failures (MTBF2) of this individual piece of equipment. t2 represents the actual operating years of the individual device; n2 represents the number of times the individual device experienced a failure during its operation; t k This represents the operating time of the individual device before the k-th maintenance. This represents the equivalent operating time of the individual device after the kth maintenance. The optimal maintenance time calculation module is used to calculate the cumulative probability value of equipment failure from the completion of the last maintenance to the next time based on the actual failure rate model, and to determine the time when the cumulative probability value of equipment failure reaches the threshold value of cumulative probability of equipment failure. This time is the optimal time for the next maintenance.

7. The system for determining the fault repair time of power transmission and transformation equipment according to claim 6, characterized in that: The expression for the well-fitted basic failure rate model is: In the above formula, λ0(t) represents the equipment failure rate at time t; α1 and β1 are the shape parameter and scale parameter of the random failure period, respectively; α2 and β2 are the shape parameter and scale parameter of the wear failure period, respectively; l represents the dividing year between the random failure period and the wear failure period.

8. The system for determining the fault repair time of power transmission and transformation equipment according to claim 7, characterized in that: The basic failure rate model fitting module uses a BP neural network improved from the LM algorithm to fit the parameters α and β of the Weibull distribution function. The specific fitting steps are as follows: A1. Initialize parameters α and β; A2. Calculate the partial derivatives with respect to parameters α and β, and obtain the parameter estimate α after the first iteration using the LM algorithm. 1 β 1 And the sum of squared residuals; A3. Based on the parameter estimate α after the first iteration 1 β 1 The second iteration is performed, and the parameter estimate α is obtained after the second iteration using the LM algorithm. 2 β 2 And the sum of squared residuals from the second iteration; A4. Compare the sum of squared residuals of the first and second iterations. If the sum of squared residuals of the second iteration is less than the sum of squared residuals of the first iteration, then the second iteration ends and proceeds to A5; otherwise, increase the damping coefficient in the LM algorithm during the second iteration and return to A3. A5. Return to step A2 and continue iterative calculation until the absolute value of the difference between the parameter estimate obtained after a certain iteration and the parameter estimate obtained before a certain iteration is less than the preset system allowable error. The entire iterative process ends, and the parameter estimate obtained in the last iteration is output.

9. A system for determining the fault repair time of power transmission and transformation equipment according to claim 7, characterized in that: The basic failure rate model fitting module obtains the dividing line between the period of random failure and the period of wear and tear failure by solving the objective function; the formula for calculating the objective function is: In the above formula, S l Let represent the objective function; l represent the dividing line between the period of random failure and the period of attrition failure; n represent the last year of the period of attrition failure; λ0(t) 偶 λ0(t) represents the portion of the fitted Weibull distribution function corresponding to the loss and failure period. 损 λ represents the portion of the fitted Weibull distribution function corresponding to the loss and failure period. 实_t This represents the actual equipment failure rate at time t.

10. A system for determining the fault repair time of power transmission and transformation equipment according to claim 6 or 7, characterized in that: The optimal maintenance time calculation module calculates the cumulative probability value of equipment failure according to the following formula: In the above formula, P1 represents the cumulative probability value of equipment failure from the completion of the k-th maintenance to the next maintenance. t′ represents the equivalent service life of the equipment at the current moment, t x Indicates the next scheduled maintenance time for the equipment; Calculate the cumulative probability threshold value for equipment failure using the following formula: In the above formula, P max T represents the cumulative probability threshold value of equipment failure; T0 represents the design life of the equipment; T max This indicates the maximum interval between scheduled equipment maintenance.

Images