Tube busbar status prediction method and system based on mutation strategy optimization algorithm

Abstract

The present invention provides a method and system for predicting the state of a tubular busbar based on a mutation strategy optimization algorithm, which relates to the technical field of predicting the state of a tubular busbar, including: collecting operating parameter data of an insulated tubular busbar; constructing an operating prediction model based on a decision function; optimizing the operating prediction model based on a mutation strategy; inputting the operating parameter data of the current insulated tubular busbar into the optimized operating prediction model to obtain the current operating state of the insulated tubular busbar. The method solves the technical problem in the prior art that it is impossible to carry out daily inspection and temperature measurement of the tubular busbar operation, and achieves the technical effect of real-time monitoring of the operating state of the insulated tubular busbar and providing more accurate decisions.

Description

Technical Field

[0001] The present invention relates to the technical field of tube type busbar state prediction, and in particular to a tube type busbar state prediction method and system based on a mutation strategy optimization algorithm. Background Art

[0002] Insulated tubular busbar is a new type of busbar. In recent years, insulated tubular busbar has been widely used in power plants, substations, photovoltaic power generation projects and other fields. However, due to the construction process, multi-layer shielding and insulation structure of fully insulated tubular busbar, the operation effect of fully insulated tubular busbar is not ideal.

[0003] At present, the reasons for the unsatisfactory operation of the fully insulated tubular busbar are as follows:

[0004] 1. Since the fully insulated tubular busbar has high requirements for the installation process of the intermediate joints and terminal heads, poor on-site installation process is likely to leave hidden faults;

[0005] 2. Due to long-term operation and mechanical vibration, there is a phenomenon of screw loosening and retreat, resulting in a decrease in contact surface and current carrying capacity, leading to overheating failure;

[0006] 3. In order to ensure the reliable operation of the intermediate joints, some fully insulated tubular busbars are equipped with insulating shielding tubes, which are usually composed of two layers of epoxy resin tubes and one layer of aluminum tube. Due to the installation of the shielding tube, the intermediate joints have poor heat dissipation, which is prone to overheating failures and are not easy to be discovered in advance.

[0007] Since the fully-insulated tubular busbar is wrapped with more than 30 layers of protective, moisture-proof and insulating materials on the outside, it is impossible to carry out inspections and temperature measurements during daily operations. It is impossible to discover the operating defects and hidden dangers of the fully-insulated tubular busbar, especially the intermediate connectors, and they can only be resolved after a failure occurs. Summary of the invention

[0008] The purpose of the present invention is to provide a method and system for predicting the state of a tubular busbar based on a mutation strategy optimization algorithm, so as to solve the technical problem in the prior art that it is impossible to carry out daily inspection and temperature measurement of the tubular busbar operation.

[0009] In a first aspect, the present invention provides a method for predicting a state of a tubular busbar based on a mutation strategy optimization algorithm, which is applied to determine the operating state of an insulated tubular busbar, the method comprising:

[0010] Collect operating parameter data of insulated tubular busbars;

[0011] Based on the decision function, build and run the prediction model;

[0012] Based on the mutation strategy, optimizing the operation prediction model;

[0013] The operating parameter data of the current insulated tubular busbar is input into the optimized operation prediction model to obtain the current operating status of the insulated tubular busbar.

[0014] In a possible embodiment, after collecting the operating parameter data of the insulated tubular busbar, the method further includes:

[0015] Preprocess the collected operating parameter data of the insulated tubular busbar.

[0016] In a possible embodiment, based on the decision function, a running prediction model is constructed, including:

[0017] Based on the decision function, construct the objective function;

[0018] The objective function is optimized to obtain a regression function, wherein the regression function is the operation prediction model, and the operation prediction model expression is:

[0019]

[0020] In the formula, α i , is the Lagrange coefficient, exp(-||x i -x j || 2 / 2σ 2 ) is the kernel function and b is a constant.

[0021] In a possible embodiment, the objective function is optimized to obtain a regression function, including:

[0022] Introduce slack variables and Lagrangian functions to obtain the objective function;

[0023] Based on the Gaussian radial basis kernel function, the objective function is optimized to obtain the regression function.

[0024] In a possible embodiment, the operation prediction model is optimized based on a mutation strategy, including:

[0025] S310, determining the initialization population and parameters based on the historical operating parameter data of the insulated tubular busbar;

[0026] S320, based on k-fold cross validation, calculate the fitness value of the particle, and find the individual optimum and the group optimum;

[0027] S330, based on the traversal replacement algorithm, updating the speed and position of the particle;

[0028] S350, recalculate the fitness value of the particle, and update the individual optimum and the group optimum;

[0029] S360, update the optimal position of the group based on the dimension-by-dimension centroid reverse mutation strategy algorithm;

[0030] S370: Whether the termination condition is met, if so, output the combined value of the penalty parameter and the kernel function parameter, if not, execute step S330.

[0031] In a possible embodiment, the operation prediction model is optimized based on the mutation strategy, further comprising:

[0032] According to the center of gravity direction learning, let x i =(x i1 ,x i2 …x iD ) is a feasible solution in D-dimensional space, x ij ∈[a j ,b](j=1,2,…D), and can be obtained by To determine the reverse solution element corresponding to the feasible solution Where k is a random number uniformly distributed in the interval [0,1]. The position of the center point in the reverse process is dynamic and related to the center of gravity M.

[0033] based on Calculate the population center M i ;

[0034] based on Calculate the inverse solution of the center of gravity of the i-th dimension (i=1,2,…,D);

[0035] If the i-th dimension centroid reverse solution <The best particle Gbest in the i-th dimension, then use Update the Gbest position; until the loop ends.

[0036] In a possible embodiment, the operating parameter data is input into the optimized operation prediction model to obtain the current operating state of the insulated tubular busbar, including:

[0037] Inputting the operating parameter data into the optimized operating prediction model to obtain a current prediction result;

[0038] Compare current forecast results with historical forecast results;

[0039] If the current prediction result is the same as the historical prediction result, it is determined that the insulated tubular busbar is operating normally;

[0040] If the current prediction result is different from the historical prediction result, it is determined that the operating status of the insulated tubular busbar is abnormal.

[0041] In a second aspect, the present invention further provides a tubular busbar state prediction system based on a mutation strategy optimization algorithm, which is applied to determine the operating state of an insulated tubular busbar, and the system comprises:

[0042] The acquisition module collects the operating parameter data of the insulated tubular busbar;

[0043] Building modules, based on decision functions, build and run prediction models;

[0044] An optimization module, which optimizes the operation prediction model based on a mutation strategy;

[0045] The prediction module inputs the operating parameter data of the current insulated tubular busbar into the optimized operation prediction model to obtain the current operating status of the insulated tubular busbar.

[0046] In a third aspect, the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0047] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores machine-executable instructions. When the machine-executable instructions are called and executed by a processor, the machine-executable instructions cause the processor to execute the steps of any one of the methods described in the first aspect above.

[0048] The present invention provides a method and system for predicting the state of a tubular busbar based on a mutation strategy optimization algorithm, which collects operating parameter data of an insulated tubular busbar; constructs an operation prediction model based on a decision function; optimizes the operation prediction model based on a mutation strategy; inputs the operating parameter data of the current insulated tubular busbar into the optimized operation prediction model to obtain the current operating state of the insulated tubular busbar, thereby being able to monitor the operating state of the insulated tubular busbar in real time and provide more accurate decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 One of the flow diagrams of a method for predicting a tube busbar state based on a mutation strategy optimization algorithm provided by an embodiment of the present invention;

[0051] Figure 2 A second flow chart of a method for predicting a tube busbar state based on a mutation strategy optimization algorithm provided by an embodiment of the present invention;

[0052] Figure 3 A schematic diagram of a process for optimizing a running prediction model provided by an embodiment of the present invention;

[0053] Figure 4 A schematic diagram of a flow chart of a tube busbar state prediction system based on a mutation strategy optimization algorithm provided by an embodiment of the present invention;

[0054] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0056] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0058] Due to the construction process of the fully insulated tubular busbar, multi-layer shielding and insulation structure, the current operation effect of the fully insulated tubular busbar is not ideal. In addition, because the fully insulated tubular busbar is wrapped with more than 30 layers of protective, moisture-proof, and insulating materials, it is impossible to conduct patrols and temperature measurements during daily operation, and it is impossible to discover the operating defects and hidden dangers of the fully insulated tubular busbar, especially the intermediate connector, and they can only be solved after a failure occurs. Based on this, the present application provides a method and system for predicting the state of a tubular busbar based on a mutation strategy optimization algorithm, which constructs an operation prediction model based on a decision function; optimizes the operation prediction model based on a mutation strategy; collects the operating parameters of the current insulated tubular busbar, the operating parameters including current value, ambient temperature value, and humidity value; inputs the operating parameters into the optimized operation prediction model to obtain the current operating state of the insulated tubular busbar, thereby preventing the occurrence of failures in advance.

[0059] Figure 1 The present invention provides a flow chart of a method for predicting the state of a tube busbar based on a mutation strategy optimization algorithm. Figure 1 As shown, the execution subject of the method may be a server. The method is mainly used to determine the operating state of the insulated tubular busbar. The method includes:

[0060] S100, collecting operating parameter data of the insulated tubular busbar.

[0061] The operating parameters of the insulated tubular busbar include the internal temperature of the tubular busbar, the external temperature of the tubular busbar, the ambient temperature and humidity, vibration, noise and other data.

[0062] In the present application, the operating parameter data of the insulated tubular busbar can be collected by triggering a manually set timed task, for example, collecting the data once every 10 seconds. It should be noted that the collection of operating parameter data is not limited to the timed triggering method, and in other embodiments, a manual triggering method can also be used.

[0063] In order to make the collected operating parameter data complete and continuous, the collected operating parameter data are preprocessed through missing value processing method and data normalization processing method.

[0064] In a possible embodiment, step S100 further includes preprocessing the collected operating parameter data, wherein the preprocessing method includes the following contents:

[0065] S110, determining whether there are continuous missing operation parameter data;

[0066] S120, if there are continuous missing data, remove the continuously missing operating parameter data;

[0067] S130. If non-continuous missing data exist, process the non-continuous missing data.

[0068] Specifically, when the insulated tube busbar measurement device fails and the collected data is abnormal, part of the data will be missing. For continuous missing data, the entire data is directly eliminated; for non-continuous missing data, the Lagrange interpolation method can be used to process the missing values ​​of the operating parameter data.

[0069] The Lagrange interpolation method is used to process the missing values ​​of the operating parameter data. The specific processing process is as follows:

[0070] Given the 2n+2 numbers x1, x2, ..., x in the operating parameter data of the insulated tube busbar, n+1 , y1, y2, ..., y n+1 , where x1, x2, …x n+1 are different from each other, then there exists a unique polynomial y of degree not exceeding n, satisfying y(x k )=y k (k=1,2…n+1), that is:

[0071]

[0072] In the formula, x and y are the data of insulated tube busbar, x k and k To determine the value.

[0073] Furthermore, the units of the collected operating parameter data of the insulated tubular busbars of different dimensions are different, which will have an adverse effect on the final prediction result. Therefore, it is necessary to normalize the operating parameter data of the insulated tubular busbars.

[0074] In this application, the min-max standardization method is used for data preprocessing. The operating parameter data is mapped to the range [0,1] by the min-max standardization method. The specific formula is as follows:

[0075]

[0076] In the formula, x, x * Respectively represent the insulated tube mother data samples before and after the transformation, x min 、x max Represent the maximum and minimum values ​​in the insulating tube mother data sample respectively.

[0077] It should be noted that the prediction of single-point current fluctuations, which in turn affects the power prediction value of nearby points, is compared with the normal historical data of the insulated tube busbar operation. If a large error occurs, the fault is located and the grounding here is abnormal, and the operating status of the insulated tube busbar is abnormal.

[0078] S200: constructing and operating a prediction model based on the decision function.

[0079] Among them, the operating prediction model can be used to inspect and measure the operating status of the insulated tubular busbar to determine whether there is a fault. Determining whether there is a fault mainly involves determining whether the insulated tubular busbar is uninsulated.

[0080] like Figure 2 As shown, in the present application, a support vector machine model can be selected to construct an operation prediction model. When predicting the insulated tube bus data, a support vector machine is introduced. The support vector machine is essentially a classification machine that can divide the space where the characteristic factors are located into the largest spacing. Therefore, in the present invention, the support vector machine model is applied to the regression problem to construct an operation prediction model, wherein the goal of the regression problem is to find a decision function that can be used to predict the output value y corresponding to the data x input into any insulated tube bus, that is, the mathematical formula of the decision function is:

[0081] y=(x)+b

[0082] Wherein: b represents a constant.

[0083] In some possible embodiments, step S100, constructing an operation prediction model based on a decision function, includes the following sub-steps:

[0084] S11. Constructing the objective function based on the decision function;

[0085] S12. Optimize the objective function to obtain a regression function, wherein the regression function is an operation prediction model.

[0086] Specifically, firstly, a data sample set of an insulated tubular busbar is given:

[0087] D=(x i ,y i ), i=1,2...,n,

[0088] Among them, x i represents the input vector, y i Represents the target output, and n represents the number of samples contained in the data sample set.

[0089] Then, all the insulated tube bus data sample points are mapped to a high-dimensional space using the mapping ψ, i.e. x→ψ(x), so the mathematical formula of the objective function of the support vector machine model is:

[0090] f(x)=w T ψ(x)+b

[0091] In the formula, w represents the normal vector, w T represents the transpose of w, and b represents a constant.

[0092] Finally, according to the structural risk minimization principle of support vector machine, it is necessary to minimize the objective function to obtain the coefficients w and b in the above formula.

[0093] The mathematical formula of the objective function R(w) of the support vector machine is:

[0094]

[0095] In the formula, C is the penalty parameter, y i is, f(x i ) is, ψ(x i ) is, and ε is the insensitive loss function.

[0096] And introduce slack variables ζ1 and The objective function R(w) is transformed into the optimization problem of slack variables, which is the following formula:

[0097]

[0098] Among them, i ≥0, and

[0099] Then introduce the Lagrangian function, according to the optimal condition

[0100]

[0101] Solve to get the value of α and get the regression function expression:

[0102]

[0103] Where: α i , is the Lagrange coefficient; k(x i ,x j ) is the kernel function.

[0104] In order to build a model for determining the operation prediction of insulated tubular busbars, it is necessary to introduce a kernel function into the support vector machine, so that the support vector machine can be transformed from a linear classifier into a nonlinear classifier in a practical sense. By introducing the kernel function, the nonlinear problem in low-dimensional space can be converted into a linear problem in high-dimensional space.

[0105] In this application, the prediction model is optimized by selecting the Gaussian radial basis kernel function. The Gaussian radial basis kernel function is a local kernel function, which has strong locality and can map a data sample from a low-dimensional space to a high-dimensional space. The advantage of the radial basis kernel function is that it has fewer parameters, has good anti-interference ability to noise, and has the widest range of applicability.

[0106] The expression of the radial basis Gaussian kernel function is:

[0107] k(x,y)=exp(-‖xy‖ 2 / 2σ 2 )

[0108] Therefore, the above regression function expression is expressed as:

[0109]

[0110] Through the above algorithm, according to the known operating parameter data of the insulated tubular busbar, the predicted data of the operating state of the insulated tubular busbar can be obtained.

[0111] S300: Optimizing the operation prediction model based on a mutation strategy.

[0112] Since the operation prediction model is relatively rough in algorithm and the accuracy is not high, the operation prediction model is optimized based on the mutation strategy.

[0113] In the present application, a mutation strategy is adopted to optimize the SVM algorithm by performing dimension-by-dimensional centroid reverse learning on the best particles to optimize the operation prediction model, thereby improving the accuracy of the operation prediction model and improving the accuracy of detecting the operating status of the insulated tubular busbar.

[0114] It should be noted that in the mutation strategy of the best particle for dimension-by-dimension centroid reverse learning, the dimension-by-dimension mutation method of the best particle can reduce inter-dimensional interference; the centroid reverse learning method can expand the search space, increase the diversity of the population, and improve the convergence accuracy; the dimension-by-dimension learning method of the best particle can reduce the amount of calculation and achieve better results.

[0115] In a possible embodiment, S300, optimizing the operation prediction model based on a mutation strategy, specifically further includes the following steps:

[0116] S310, determining the initialization population and parameters based on the historical operating parameter data of the insulated tubular busbar;

[0117] S320, based on k-fold cross validation, calculate the fitness value of the particle, and find the individual optimum and the group optimum;

[0118] S330, based on the traversal replacement algorithm, updating the speed and position of the particle;

[0119] S350, recalculate the fitness value of the particle, and update the individual optimum and the group optimum;

[0120] S360, update the optimal position of the group based on the dimension-by-dimension centroid reverse mutation strategy algorithm;

[0121] S370: Whether the termination condition is met, if so, output the combined value of the penalty parameter and the kernel function parameter, if not, execute step S330.

[0122] Specifically, first, define the particle members in the optimization algorithm as space subjects, and the space where the subjects are located is the search space, that is, the search space where the subject of the problem is located is a D-dimensional space, in which there is a population composed of n subjects. That is, select any combination data X=(x1,x2,…,x D ) is used to represent the D-dimensional vector x D =(x i,1 ,x i,2 ,…,x i,D ) T It represents the specific position of the insulated tubular busbar in the search space, and the data in the D-dimensional vector constitutes the initial population Pop.

[0123] Each row in the population Pop represents a particle. The value of each particle can be substituted into K-fold cross validation to calculate its fitness. The individual optimal Pbest and the optimal Gbest of the entire group are determined based on the calculated fitness.

[0124] like Figure 3 As shown, in this application, based on the mutation strategy, the operation prediction model is optimized, which specifically includes the following steps:

[0125] Step 1. Divide the historical operating parameter data of the insulated tubular bus into K (K=5) subsets of equal size;

[0126] Step 2. For each subset i (1≤i≤K).

[0127] The i-th subset is used as the validation set, and the other K-1 subsets are used as the training set. The model is fitted using the data on the training set, and predictions are made on the validation set. The performance indicators of the model on the validation set, such as accuracy, precision, recall, etc., are calculated.

[0128] Step 3. Average the performance indicators in K experiments to obtain the average performance indicator of the model. By comparison, the individual optimal Pbest and the entire group optimal Gbest are obtained.

[0129] Step 4. In each loop traversal iteration, the operating parameter data of the insulated tubular busbar updates its own speed and position through the extreme values ​​of the particles and the extreme values ​​of all data, where the traversal replacement formula is as follows:

[0130]

[0131] Where: is the speed of the insulated tube bus data at this time; i=1,2,....n; d=1,2,...D; W is the inertia weight; is the last speed of the insulated tube bus data; c1, c2 are acceleration factors, which are non-negative constants; r1, r2 are random numbers distributed between [0,1]; is the dth dimension of the individual extreme value; The last location information; is the dth dimension of the global optimal solution; This is the location information at this time.

[0132] It should be noted that a larger W inertia weight value indicates that the optimization effect based on all data is good, while the local optimization effect is weak. On the contrary, if the W inertia weight is smaller, the local optimization effect is better, while the global optimization effect is weak.

[0133] The first term in the above formula Sometimes also called the memory term, to record the impact of the previous speed and direction; the second term Also known as the self-cognition term, it is a vector that is the particle's best point of cognition based on its own experience; the third part It is also called the group cognition term, which mainly reflects the ability of each particle to collaborate and share with each other. It is a parameter variable used to identify and judge the best in the group.

[0134] Step 5. Substitute the value of each particle in the entire population Pop into the fitness function to determine the fitness of each particle, and update the individual optimum and group optimum according to the fitness of each particle.

[0135] The fitness value of the current global optimal solution can be used to determine whether the optimization requirement is met. If not, return to step 4 above to cyclically update the speed and position of the solution until the optimization requirement is met or the number of iterations has reached the maximum number of iterations.

[0136] In the present invention, the number of iterations is set to 100, and the process stops after the iteration is completed; a minimum error value, that is, a minimum threshold value, is set to 0.5, and the process stops when the final result meets the value.

[0137] Specifically, let x i =(x i1 ,x i2 ,…,x iD ) is a feasible solution in D-dimensional space, and x ij ∈[a j ,b j ](j=1,2,...,D), and its corresponding reverse solution Determined by the following formula:

[0138]

[0139] In the formula, a i 、b i For domain [a j ,b j ]data(i=1,2…D);x i is a feasible solution in D-dimensional space.

[0140] Let (x1, x2, …, x n ) are n points with unit mass in the D-dimensional search space, then the overall center of gravity is defined as:

[0141]

[0142] Let x i =(x i1 ,x i2 ,…,x iD ) is a feasible solution in D-dimensional space, and x ij ∈[a j ,b j ](j=1,2,...,D), its corresponding reverse solution Determined by the following formula:

[0143]

[0144] Where k is a random number uniformly distributed in the interval [0,1], and the position of the center point in the reverse process is dynamic and related to the center of gravity M.

[0145] Assume that the optimal particle of the current iteration number Gbest = (Gbest1, Gbest2, ..., Gbest D ) inverse solution in the i-th dimension in Determined by the following formula:

[0146]

[0147] Among them, k is a random number uniformly distributed in the interval [0,1], M i is the component of the center of gravity M in the i-th dimension.

[0148] Step 6. Calculate the optimal position of the individual based on the dimension-by-dimension centroid reverse mutation strategy algorithm. First, according to the formula: Calculate the population center M i ; Then use Calculate the inverse solution of the center of gravity of the i-th dimension (i=1,2,…,D); if the i-th dimension centroid reverse solution <The best particle Gbest in the i-th dimension, then use Update the Gbest position; until the loop ends.

[0149] Step 7. Determine whether the optimization requirement is met based on the fitness value of the current global optimal solution Gbest. If not, return to step 3 until the optimization requirement is met or the number of iterations has reached the maximum number of iterations, and finally obtain the optimal combination value of the penalty parameter C and the kernel function parameter y.

[0150] The optimal combination value of the penalty parameter C and the kernel function parameter y obtained in the above mutation strategy algorithm of performing dimension-by-dimensional center of gravity reverse learning through the best particle is substituted into the operation prediction model to obtain the optimized operation prediction model.

[0151] S400, inputting the operating parameter data of the current insulated tubular busbar into the optimized operation prediction model to obtain the current operating status of the insulated tubular busbar.

[0152] By inputting the operating parameter data of the insulated tubular busbar that currently needs to be predicted into the optimized operation prediction model, it can be determined whether there is a fault in the current operating state of the insulated tubular busbar.

[0153] Specifically, taking the current data of the insulated tube busbar as an example, the operation prediction model obtained by the above process has found a decision function that can be used to predict the output value y corresponding to the input of any insulated tube busbar data x; based on the historical insulated tube busbar current data, it can be obtained whether the current at a certain point is abnormal. If the current data abnormality at this point is not sufficient to indicate the operating status of the insulated tube busbar, the present invention will find an appropriate algorithm to find the data around the abnormal data point to determine whether the data is abnormal. If the surrounding data are all abnormal, it indicates that this section of the insulated tube busbar may have a grounding point fault, resulting in the insulated tube busbar being uninsulated.

[0154] Figure 4 The present invention provides a flow chart of a busbar status prediction system based on a mutation strategy optimization algorithm. Figure 4 As shown, the execution subject of the system can be a server. The system is mainly used to determine the operating state of the insulated tubular busbar. The system includes:

[0155] The acquisition module collects the operating parameter data of the insulated tubular busbar;

[0156] Building modules, based on decision functions, build and run prediction models;

[0157] An optimization module, which optimizes the operation prediction model based on a mutation strategy;

[0158] The prediction module inputs the operating parameter data of the current insulated tubular busbar into the optimized operation prediction model to obtain the current operating status of the insulated tubular busbar.

[0159] In a possible embodiment, after collecting the operating parameter data of the insulated tubular busbar, the method further includes:

[0160] Preprocess the collected operating parameter data of the insulated tubular busbar.

[0161] In a possible embodiment, based on the decision function, a running prediction model is constructed, including:

[0162] Based on the decision function, construct the objective function;

[0163] The objective function is optimized to obtain a regression function, wherein the regression function is the operation prediction model, and the operation prediction model expression is:

[0164]

[0165] In the formula, α i , is the Lagrange coefficient, exp(-||x i -x j || 2 / 2σ 2 ) is the kernel function and b is a constant.

[0166] In a possible embodiment, the objective function is optimized to obtain a regression function, including:

[0167] Introduce slack variables and Lagrangian functions to obtain the objective function;

[0168] Based on the Gaussian radial basis kernel function, the objective function is optimized to obtain the regression function.

[0169] In a possible embodiment, the operation prediction model is optimized based on a mutation strategy, including:

[0170] S310, determining the initialization population and parameters based on the historical operating parameter data of the insulated tubular busbar;

[0171] S320, based on k-fold cross validation, calculate the fitness value of the particle, and find the individual optimum and the group optimum;

[0172] S330, based on the traversal replacement algorithm, updating the speed and position of the particle;

[0173] S350, recalculate the fitness value of the particle, and update the individual optimum and the group optimum;

[0174] S360, update the optimal position of the group based on the dimension-by-dimension centroid reverse mutation strategy algorithm;

[0175] S370: Whether the termination condition is met, if so, output the combined value of the penalty parameter and the kernel function parameter, if not, execute step S330.

[0176] In a possible embodiment, the operation prediction model is optimized based on the mutation strategy, further comprising:

[0177] According to the center of gravity direction learning, let x i =(x i1 ,x i1 …x iD ) is a feasible solution in D-dimensional space, x ih ∈[a j ,b](j=1,2,…D), and can be obtained by To determine the reverse solution element corresponding to the feasible solution Where k is a random number uniformly distributed in the interval [0,1]. The position of the center point in the reverse process is dynamic and related to the center of gravity M.

[0178] based on Calculate the population center M i ;

[0179] based on Calculate the inverse solution of the center of gravity of the i-th dimension (i=1,2,…,D);

[0180] If the i-th dimension centroid reverse solution <The best particle Gbest in the i-th dimension, then use Update the Gbest position; until the loop ends.

[0181] In a possible embodiment, the operating parameter data is input into the optimized operation prediction model to obtain the current operating state of the insulated tubular busbar, including:

[0182] Inputting the operating parameter data into the optimized operating prediction model to obtain a current prediction result;

[0183] Compare current forecast results with historical forecast results;

[0184] If the current prediction result is the same as the historical prediction result, it is determined that the insulated tubular busbar is operating normally;

[0185] If the current prediction result is different from the historical prediction result, it is determined that the operating status of the insulated tubular busbar is abnormal.

[0186] The implementation principle and technical effects of the system provided in the embodiment of the present application are the same as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the system embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0187] like Figure 5 As shown, an electronic device 600 provided in an embodiment of the present application includes: a processor 601, a memory 602 and a bus, the memory 602 stores machine-readable instructions executable by the processor 601, when the electronic device is running, the processor 601 and the memory 602 communicate through the bus, and the processor 601 executes the machine-readable instructions to perform the steps of the above-mentioned method for predicting the state of a tube bus based on the mutation strategy optimization algorithm.

[0188] Specifically, the above-mentioned memory 602 and processor 601 can be general-purpose memories and processors, which are not specifically limited here. When the processor 601 runs the computer program stored in the memory 602, it can execute the above-mentioned tube bus state prediction method based on the mutation strategy optimization algorithm.

[0189] The processor 601 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 601. The above processor 601 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 602, and the processor 601 reads the information in the memory 602 and completes the steps of the above method in combination with its hardware.

[0190] Corresponding to the above-mentioned method for predicting the state of a tube busbar based on a mutation strategy optimization algorithm, an embodiment of the present application also provides a computer-readable storage medium, which stores machine-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the steps of the above-mentioned method for predicting the state of a tube busbar based on a mutation strategy optimization algorithm.

[0191] The tubular busbar state prediction system based on the mutation strategy optimization algorithm provided in the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device. The device provided in the embodiment of the present application has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brief description, the parts not mentioned in the device embodiment can refer to the corresponding contents in the aforementioned method embodiment. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0192] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0193] For another example, the flowchart and block diagram in the accompanying drawings show the possible architecture, functions and operations of the device, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and a part of the module, program segment or code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0194] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0195] In addition, each functional unit in the embodiments provided in the present application 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.

[0196] If the function is implemented in the form of 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 application can essentially or in other words, the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions for an electronic device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store program codes.

[0197] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0198] In the description of the present invention, it should be noted that the terms "first", "second", "third", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0199] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the state of a tube busbar based on a mutation strategy optimization algorithm, characterized in that: Applied to determining the operating state of an insulated tubular busbar, the method comprises: Collecting operating parameter data of the insulated tubular busbar, wherein the operating parameter data includes internal temperature of the tubular busbar, external temperature of the tubular busbar, ambient temperature and humidity, vibration and noise; Based on the decision function, an operation prediction model is constructed, and the expression of the operation prediction model is: In the formula, α i , is the Lagrange coefficient, exp(-||x i -x j || 2 / 2σ 2 ) is the kernel function, where exp is the natural exponential function, x i and x j is a sample in the data sample set of a given insulated tube busbar, σ is the width parameter of the function, b is a constant, f(x) is the predicted operating state data, and n is the number of operating parameter data; Based on the mutation strategy, the operation prediction model is optimized, wherein the mutation strategy includes: S310, based on the historical operation parameter data of the insulated tube bus, determining the initialization population and parameters; S320, based on the k-fold cross validation, calculating the fitness value of the particle, and finding the individual optimum and the group optimum; S330, based on the traversal replacement algorithm, updating the speed and position of the particle; S350, recalculating the fitness value of the particle, updating the individual optimum and the group optimum; S360, updating the group optimal position based on the dimension-by-dimension centroid reverse mutation strategy algorithm; S370, whether the termination condition is met, if so, output the combined value of the penalty parameter and the kernel function parameter, if not, execute step S330; and S360, based on the dimension-by-dimension centroid reverse mutation strategy algorithm, updating the group optimal position, including: according to the centroid direction learning, set x i =(x i1 ,x i2 …x iD )(i=1,2,…n) is a feasible solution in D-dimensional space, x ij ∈[a j ,b j ](j=1,2,…D),x ij is a normal feasible solution x i The value in the j dimension, a j =min j＝1,2,…D {x i1 ,x i2 …x iD },b j =max j＝1,2,…D {x i1 ,x i2 …x iD } and can be To determine the reverse solution element corresponding to the feasible solution Where k is a random number uniformly distributed in the interval [0,1], M is the center of gravity, Reverse solution, x i The feasible solution is that the position of the center point in the reverse process is dynamic and related to the center of gravity M; based on where x1, x2, ....x n represents all feasible solutions in the D-dimensional space, n represents the number of feasible solutions, and calculates the population center M i ; Based on Gbest i =(Gbest1, Gbest2, …, Gbest D ) inverse solution in the i-th dimension In the formula is the inverse solution of the center of gravity of the i-th dimension, K is a random number uniformly distributed in the interval [0,1], Gbest i is the feasible solution of the i-th dimension, Mi is the component of the center of gravity M in the i-th dimension, and the reverse solution of the center of gravity of the i-th dimension is calculated If the i-th dimension centroid reverse solution <The best particle Gbest in the i-th dimension, then use the center of gravity direction to solve Update the position of the optimal particle Gbest until the loop ends; The operating parameter data of the current insulated tubular busbar is input into the optimized operation prediction model to obtain the current operating status of the insulated tubular busbar, and the current prediction result is compared with the historical prediction result. If the current prediction result is the same as the historical prediction result, it is determined that the operating status of the insulated tubular busbar is normal. If the current prediction result is different from the historical prediction result, it is determined that the operating status of the insulated tubular busbar is abnormal.

2. The method according to claim 1, characterized in that Collect the operating parameter data of the insulated tubular busbar, and then include: Preprocess the collected operating parameter data of the insulated tubular busbar.

3. The method according to claim 1, characterized in that Based on the decision function, a prediction model is constructed and run, including: Based on the decision function, construct the objective function; The objective function is optimized to obtain a regression function, wherein the regression function is the operation prediction model.

4. The method according to claim 3, characterized in that The objective function is optimized to obtain a regression function, including: Introduce slack variables and Lagrangian functions to obtain the objective function; Based on the Gaussian radial basis kernel function, the objective function is optimized to obtain the regression function.

5. A tube busbar state prediction system based on a mutation strategy optimization algorithm, characterized in that: Applicable to determining the operating status of an insulated tubular busbar, the system comprises: A collection module collects operating parameter data of the insulated tubular busbar, wherein the operating parameter data includes the internal temperature of the tubular busbar, the external temperature of the tubular busbar, the ambient temperature and humidity, vibration and noise; The construction module constructs an operation prediction model based on the decision function. The expression of the operation prediction model is: In the formula, α i , is the Lagrange coefficient, exp(-||x i -x j || 2 / 2σ 2 ) is the kernel function, where exp is the natural exponential function, x i , x j , σ, b are constants, f(x) is the predicted operating state data, and n is the number of operating parameter data; The optimization module optimizes the operation prediction model based on the mutation strategy, wherein the mutation strategy includes: S310, based on the historical operation parameter data of the insulated tubular busbar, determining the initialization population and parameters; S320, based on the k-fold cross validation, calculating the fitness value of the particle, and finding the individual optimum and the group optimum; S330, based on the traversal replacement algorithm, updating the speed and position of the particle; S350, recalculating the fitness value of the particle, updating the individual optimum and the group optimum; S360, updating the group optimal position based on the dimension-by-dimension centroid reverse mutation strategy algorithm; S370, whether the termination condition is met, if so, output the combined value of the penalty parameter and the kernel function parameter, if not, execute step S330; and S360, based on the dimension-by-dimension centroid reverse mutation strategy algorithm, updating the group optimal position, including: according to the centroid direction learning, set x i =(x i1 ,x i2 …x iD )(i=1,2,…n) is a feasible solution in D-dimensional space, x ij ∈[a j ,b j ](j=1,2,…D),x ij is a normal feasible solution x i The value in the j dimension, a j =min j＝1,2,…D {x i1 ,x i2 …x iD },b j =max j＝1,2,…D {x i1 ,x i2 …x iD } and can be To determine the reverse solution element corresponding to the feasible solution Where k is a random number uniformly distributed in the interval [0,1], M is the center of gravity, Reverse solution, x i The feasible solution is that the position of the center point in the reverse process is dynamic and related to the center of gravity M; based on where x1, x2, ....x n represents all feasible solutions in the D-dimensional space, n represents the number of feasible solutions, and calculates the population center M i ; Based on Gbest i =(Gbest1, Gbest2, …, Gbest D ) inverse solution in the i-th dimension In the formula is the inverse solution of the center of gravity of the i-th dimension, K is a random number uniformly distributed in the interval [0,1], Gbest i is the feasible solution of the i-th dimension, Mi is the component of the center of gravity M in the i-th dimension, and the reverse solution of the center of gravity of the i-th dimension is calculated If the i-th dimension centroid reverse solution <The best particle Gbest in the i-th dimension, then use the center of gravity direction to solve Update the position of the optimal particle Gbest until the loop ends; The prediction module inputs the operating parameter data of the current insulated tubular busbar into the optimized operation prediction model to obtain the current operating status of the insulated tubular busbar, and compares the current prediction result with the historical prediction result. If the current prediction result is the same as the historical prediction result, it is determined that the operating status of the insulated tubular busbar is normal; if the current prediction result is different from the historical prediction result, it is determined that the operating status of the insulated tubular busbar is abnormal.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores machine-executable instructions. When the machine-executable instructions are called and executed by a processor, the machine-executable instructions cause the processor to execute the method according to any one of claims 1 to 4.

Images