Fault detection method and device for disconnecting switch, medium and equipment

Abstract

The invention discloses a fault detection method and device for an isolating switch, a medium and equipment, and the method comprises the steps: obtaining the historical data of a plurality of electrical parameters, carrying out the nonlinear conversion and accumulation processing, and constructing a nonlinear multivariate gray system model containing a plurality of sub-models, so as to describe the complex nonlinear relation between the electrical parameters. Each sub-model corresponds to one electrical parameter and has different model coefficients and bias terms, so that parameter characteristic differences of different electrical parameters can be described, and the method can be used for more accurately constructing a parameter prediction model and predicting a predicted value of a target electrical parameter subsequently; and finally, comparing a predicted value with actually measured data to judge whether a fault exists or not. The method has the advantages that due to the fact that nonlinear modeling and multi-parameter comprehensive analysis are adopted, complex dynamic changes among electrical parameters can be captured more accurately, and the fault diagnosis precision is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault detection, and in particular to a fault detection method, device, medium and equipment for an isolating switch. Background Art

[0002] During the operation of high-voltage disconnectors, the mechanical characteristics of the drive motor are often reflected through electrical parameters. However, due to the differences in motor design and circuit parameters of the motor circuits of different disconnectors, the mechanical changes caused by the same fault are reflected differently in different electrical parameters. For example, a certain fault is more likely to be reflected through power on some disconnectors, but more likely to be reflected through current on other disconnectors, which will affect the accuracy of fault detection. Summary of the invention

[0003] Based on this, it is necessary to provide a fault detection method, device, medium and equipment for the isolating switch to solve the problem that the mechanical changes caused by the same fault are reflected to different degrees on different electrical parameters, resulting in insufficient accuracy of fault detection.

[0004] A fault detection method for an isolating switch, the method comprising:

[0005] Acquire historical data of multiple electrical parameters preset for the isolating switch, and perform nonlinear conversion and accumulation processing on the historical data of the target electrical parameter to obtain corresponding nonlinear accumulated data; wherein the target electrical parameter is any one of the multiple electrical parameters;

[0006] Constructing a nonlinear multivariate grey system model; wherein the nonlinear multivariate grey system model includes a plurality of sub-models, the model structures of the plurality of sub-models are the same, each sub-model corresponds to an electrical parameter, the nonlinear multivariate grey system model is used to describe the nonlinear relationship between the plurality of electrical parameters, and the model coefficients and bias terms of the electrical parameters in different sub-models are different;

[0007] estimating model coefficients and bias terms of the target electrical parameters in the nonlinear multivariate grey system model according to historical data and nonlinear accumulated data of the target electrical parameters;

[0008] Building a parameter prediction model based on the model coefficient and the bias term of the target electrical parameter, and acquiring prediction data of the target electrical parameter based on the parameter prediction model to obtain prediction data of each electrical parameter;

[0009] The measured data of the multiple electrical parameters of the isolating switch are obtained, and the error between the predicted data and the measured data of each electrical parameter is calculated. If the error of any electrical parameter is greater than a preset error threshold of the corresponding electrical parameter, it is determined that the isolating switch is faulty.

[0010] In one embodiment, the nonlinear conversion and accumulation processing of the historical data of the target electrical parameter is performed as follows:

[0011]

[0012] In the above formula, represents the historical data of the i-th target electrical parameter at time k; For duration t The nonlinear accumulation data; p is a parameter used to control the nonlinear complexity; α is a parameter for adjusting the amplitude of periodic oscillation; β is a parameter for adjusting the frequency of periodic oscillation.

[0013] In one embodiment, the sub-model of the ith electrical parameter in the nonlinear multivariate grey system model is expressed as:

[0014]

[0015] In the above formula, Represents the nonlinear cumulative data of the i-th target electrical parameter within the time t; a i represents the model coefficient of the i-th target electrical parameter; b i represents the bias phase of the i-th target electrical parameter; p is a parameter used to control the nonlinear complexity.

[0016] In one embodiment, the model coefficients and bias terms of the target electrical parameters in the nonlinear multivariate grey system model are estimated based on the historical data and nonlinear accumulated data of the target electrical parameters, which are expressed as:

[0017]

[0018] In the above formula, a i represents the model coefficient of the i-th target electrical parameter; N1 represents the total number of nonlinear accumulated data of the i-th target electrical parameter; represents the nth nonlinear accumulated data of the ith target electrical parameter; b i represents the bias phase of the i-th target electrical parameter; N2 represents the total number of historical data of the i-th target electrical parameter; Represents the nth historical data of the ith target electrical parameter.

[0019] In one embodiment, the acquisition of the prediction data of the target electrical parameter based on the parameter prediction model to obtain the prediction data of each electrical parameter is expressed as:

[0020]

[0021] In the above formula, Represents the nonlinear cumulative data of the i-th target electrical parameter within the time length t+1; represents the first nonlinear cumulative data of the i-th target electrical parameter; a i represents the model coefficient of the i-th target electrical parameter; b i represents the bias phase of the i-th target electrical parameter; Represents the nonlinear cumulative data of the i-th target electrical parameter within the time length t; Represents the predicted data at time t+1.

[0022] In one embodiment, the error between the predicted data and the measured data of each electrical parameter is calculated as:

[0023]

[0024] In the above formula, E i (t) represents the error of the i-th target electrical parameter, X i,pred (t) represents the predicted data of the i-th target electrical parameter; X i,real (t) represents the measured data of the i-th target electrical parameter; γ represents the error adjustment coefficient.

[0025] In one embodiment, after determining that the isolating switch is faulty, the method further comprises:

[0026] If the error of the target electrical parameter is greater than the corresponding preset error threshold, the model coefficient of the target electrical parameter is adjusted according to the error of the target electrical parameter, which is expressed as:

[0027]

[0028] In the above formula, a i,new represents the updated model coefficient of the i-th target electrical parameter; a i,old represents the model coefficient before the i-th target electrical parameter is updated; E i (t) represents the error of the i-th target electrical parameter; η represents the learning rate, which is used to control the step size of parameter update; α represents the sensitivity coefficient of the nonlinear error of the i-th target electrical parameter.

[0029] A method for detecting a fault of an isolating switch, the device comprising:

[0030] A data acquisition module, used to acquire historical data of multiple electrical parameters preset by the disconnector, and perform nonlinear conversion and accumulation processing on the historical data of the target electrical parameter to obtain corresponding nonlinear accumulated data; wherein the target electrical parameter is any one of the multiple electrical parameters;

[0031] A nonlinear multivariate grey system model building module is used to build a nonlinear multivariate grey system model; wherein the nonlinear multivariate grey system model includes a plurality of sub-models, the model structures of the plurality of sub-models are the same, each sub-model corresponds to an electrical parameter, the nonlinear multivariate grey system model is used to describe the nonlinear relationship between the plurality of electrical parameters, and the model coefficients and bias terms of the electrical parameters in different sub-models are different; the model coefficients and bias terms of the target electrical parameters in the nonlinear multivariate grey system model are estimated according to the historical data and nonlinear accumulated data of the target electrical parameters;

[0032] A prediction module, configured to construct a parameter prediction model based on the model coefficient and the bias term of the target electrical parameter, and obtain prediction data of the target electrical parameter based on the parameter prediction model to obtain prediction data of each electrical parameter;

[0033] The fault judgment module is used to obtain the measured data of the multiple electrical parameters of the isolating switch and calculate the error between the predicted data and the measured data of each electrical parameter. If the error of any electrical parameter is greater than the preset error threshold of the corresponding electrical parameter, it is determined that the isolating switch is faulty.

[0034] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the steps of the above-mentioned disconnector fault detection method.

[0035] A fault detection device for an isolating switch comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above-mentioned fault detection method for the isolating switch.

[0036] The present invention provides a fault detection method, device, medium and equipment for disconnecting switches, which obtains historical data of multiple electrical parameters, performs nonlinear conversion and cumulative processing, and constructs a nonlinear multivariate grey system model containing multiple sub-models to describe the complex nonlinear relationship between the electrical parameters. Each sub-model corresponds to an electrical parameter and has different model coefficients and bias terms, which can describe the parameter characteristic differences of different electrical parameters and can be used to more accurately construct a parameter prediction model and predict the predicted value of the target electrical parameter in the future. Finally, the predicted value is compared with the measured data to determine whether a fault exists. The beneficial effect of this method is that due to the use of nonlinear modeling and multi-parameter comprehensive analysis, it can more accurately capture the complex dynamic changes between electrical parameters, thereby significantly improving the accuracy of fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] in:

[0039] Figure 1 A schematic diagram of a flow chart of a fault detection method for an isolating switch;

[0040] Figure 2 It is a structural schematic diagram of a fault detection device for an isolating switch;

[0041] Figure 3 The structural block diagram of the fault detection device of the isolating switch. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. 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.

[0043] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0044] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0045] like Figure 1 As shown, Figure 1 1 is a flow chart of a fault detection method for an isolating switch in an embodiment. The steps provided by the fault detection method for an isolating switch in this embodiment include:

[0046] S101, acquiring historical data of a plurality of electrical parameters preset for the isolating switch, and performing nonlinear conversion and accumulation processing on the historical data of the target electrical parameters to obtain corresponding nonlinear accumulated data.

[0047] Among them, electrical parameters refer to various electrical characteristics that can be measured during the operation of the isolating switch. The preset multiple electrical parameters here include but are not limited to power, current, voltage and other parameters. For the convenience of explanation, the following mainly combines power and current for example. The historical data refers to the electrical parameter values ​​collected by the isolating switch at different time points, such as the electrical parameter values ​​sampled every 10 seconds or every 1 minute. The target electrical parameter is any one of the multiple electrical parameters, that is, the same operation needs to be performed on each electrical parameter in this step.

[0048] It is understandable that electrical parameters under fault conditions often have nonlinear characteristics. For example, in power data, we observe that load fluctuations of disconnectors may cause periodic nonlinear fluctuations in the data, while current data may exhibit smoother nonlinear fluctuations when a fault occurs. In order to effectively capture these nonlinear characteristics, we perform nonlinear transformation and accumulation processing on each electrical parameter to obtain the corresponding nonlinear accumulated data. The nonlinear accumulated data not only includes the characteristics of periodic nonlinear power fluctuations under load fluctuations, but also includes the characteristics of subtle current fluctuations.

[0049] Optionally, nonlinear conversion and accumulation processing is performed on each electrical parameter, which may be logarithmic transformation or exponential transformation of each electrical parameter, and then the logarithmic values ​​or exponential values ​​at different time points are accumulated to obtain nonlinear accumulated data.

[0050] S102, construct nonlinear multivariate grey system model.

[0051] Among them, the nonlinear multivariate grey system model includes multiple sub-models, and the model structures of the multiple sub-models are the same. Each sub-model corresponds to an electrical parameter. The nonlinear multivariate grey system model reflects the complex nonlinear relationship between various electrical parameters through the same sub-model structure, while the model coefficients and bias terms of the electrical parameters in different sub-models are different, thereby reflecting the electrical characteristics of each electrical parameter.

[0052] For example, when problems such as mechanical jamming occur, the power output of the motor may fluctuate rapidly, while the current changes slowly. Through such nonlinear multivariate modeling, the complex nonlinear relationship between various electrical parameters can be reflected, and such differences can be better captured.

[0053] S103, estimating the model coefficients and bias terms of the target electrical parameters in the nonlinear multivariate grey system model according to the historical data and nonlinear accumulated data of the target electrical parameters.

[0054] Optionally, this step can use a regression algorithm (such as the least squares method) to fit the model coefficients and bias terms through historical data and nonlinear cumulative data. An optimization algorithm (such as a genetic algorithm or a gradient descent method) is also used to minimize the error between the model prediction value and the actual value, and the model coefficients and bias terms are gradually adjusted.

[0055] In this way, by estimating each electrical parameter separately, the nonlinear multivariate grey system model can accurately describe the nonlinear relationship between the electrical parameters.

[0056] S104, constructing a parameter prediction model based on the model coefficient and the bias term of the target electrical parameter, and acquiring prediction data of the target electrical parameter based on the parameter prediction model to obtain prediction data of each electrical parameter.

[0057] That is, the model coefficients and bias terms estimated in S103 determine how the parameter prediction model predicts the behavior of the electrical parameters. The parameter prediction model can adopt a regression model, a time series model, or a neural network model, and the specific selection depends on the complexity and nonlinear characteristics of the data.

[0058] Enter a new time point or condition and use the parameter prediction model to generate the predicted value of the target electrical parameter. Repeat this process for each electrical parameter to obtain the predicted data of all electrical parameters.

[0059] S105, obtaining measured data of multiple electrical parameters of the isolating switch, and calculating the error between the predicted data and the measured data of each electrical parameter. If the error of any electrical parameter is greater than a preset error threshold of the corresponding electrical parameter, it is determined that the isolating switch is faulty.

[0060] The measured data here refers to the electrical parameter values ​​obtained in real time during the current operation of the disconnector, which corresponds to the predicted data in time. The size of the error reflects the difference between the actual operating state and the expected prediction model, which can be in the form of absolute value of the difference or mean square error.

[0061] Specifically, the error of each electrical parameter is compared with the corresponding preset error threshold. If the error of an electrical parameter exceeds the corresponding preset error threshold, it means that the actual value of the electrical parameter does not match the prediction model, and it is determined that the disconnector is faulty. At this time, the system can automatically trigger a fault alarm and conduct further fault location analysis.

[0062] The above-mentioned fault detection method for the disconnector obtains historical data of multiple electrical parameters, performs nonlinear conversion and accumulation processing, and constructs a nonlinear multivariate grey system model containing multiple sub-models to describe the complex nonlinear relationship between the electrical parameters. Each sub-model corresponds to an electrical parameter and has different model coefficients and bias terms, which can describe the parameter characteristic differences of different electrical parameters and can be used to more accurately construct parameter prediction models and predict the predicted values ​​of target electrical parameters in the future. Finally, the predicted values ​​are compared with the measured data to determine whether there is a fault. The beneficial effect of this method is that due to the use of nonlinear modeling and multi-parameter comprehensive analysis, it can more accurately capture the complex dynamic changes between electrical parameters, thereby significantly improving the accuracy of fault diagnosis.

[0063] In a specific embodiment, in S101, the historical data of the target electrical parameter is subjected to nonlinear conversion and accumulation processing, which is expressed as:

[0064]

[0065] In the above formula, represents the historical data of the i-th target electrical parameter at time k; For duration t The nonlinear accumulated data; p is a parameter used to control the nonlinear complexity, which affects the power of the data; α is a parameter for adjusting the amplitude of periodic oscillations, which affects the intensity of fluctuations; β is a parameter for adjusting the frequency of periodic oscillations, which affects the oscillation period. p, α, and β can be determined experimentally or empirically to ensure that the nonlinear characteristics of the data are properly captured. In this way, the accumulated data can better reflect the complex nonlinear characteristics of electrical parameters, which is conducive to more accurate modeling and fault prediction.

[0066] In a specific embodiment, the sub-model of the i-th electrical parameter in the nonlinear multivariate grey system model is expressed as:

[0067]

[0068] In the above formula, Represents the nonlinear cumulative data of the i-th target electrical parameter within the time t; a i represents the model coefficient of the i-th target electrical parameter. Different electrical parameters may have different model coefficients to reflect their response differences under fault conditions; b i represents the bias phase of the i-th target electrical parameter, which reflects the reference value of the electrical parameter in a fault-free state; p is a parameter used to control nonlinear complexity, which is used to simulate the response curve of electrical parameters (such as power and current) under different fault conditions. For example, some faults may cause rapid fluctuations in power while slow changes in current. By adjusting p, this difference can be accurately captured.

[0069] This sub-model can flexibly reflect the nonlinear behavior of electrical parameters. i , bias term b i and the nonlinear complexity parameter p, customized modeling can be performed for different fault types and electrical parameters, thereby improving the accuracy and responsiveness of fault detection.

[0070] In a specific embodiment, in S103, the model coefficients and bias terms of the target electrical parameters in the nonlinear multivariate grey system model are estimated according to the historical data of the target electrical parameters and the nonlinear accumulated data, which can be expressed as:

[0071]

[0072] In the above formula, a i represents the model coefficient of the i-th target electrical parameter; N1 represents the total number of nonlinear accumulated data of the i-th target electrical parameter; represents the nth nonlinear accumulated data of the ith target electrical parameter; b i represents the bias phase of the i-th target electrical parameter; N2 represents the total number of historical data of the i-th target electrical parameter; Represents the nth historical data of the ith target electrical parameter.

[0073] Among them, the model coefficient a i It reflects the dynamic change relationship of electrical parameters. Through the correlation calculation of adjacent nonlinear cumulative data, the trend and characteristics of electrical parameters changing over time can be captured. i It is determined by the average value of historical data, which represents the stable baseline of the parameter. Different electrical parameters may have different baseline levels, so the bias term can help the model establish differences between different parameters. This estimation method combines the nonlinear accumulation processing of historical data to enhance the model's adaptability to the complex relationship between different electrical parameters, thereby improving the accuracy and robustness of fault diagnosis.

[0074] In a specific embodiment, the prediction data of the target electrical parameter is obtained based on the parameter prediction model to obtain the prediction data of each electrical parameter, which is expressed as:

[0075]

[0076] In the above formula, Represents the nonlinear cumulative data of the i-th target electrical parameter within the time length t+1; represents the first nonlinear cumulative data of the i-th target electrical parameter; a i represents the model coefficient of the i-th target electrical parameter; b i represents the bias phase of the i-th target electrical parameter; Represents the nonlinear cumulative data of the i-th target electrical parameter within the time length t; Represents the predicted data at time t+1.

[0077] The first formula describes how to use historical data and model parameters (including model coefficients a i and the bias term b i ) to predict the nonlinear cumulative data at future time points. The core of the formula is the exponential decay model It reflects the nonlinear change characteristics of the target electrical parameters over time. The second formula calculates the difference between the nonlinear accumulated data, allowing us to regress from the accumulated data to the actual electrical parameter value so that we can directly compare it with the measured data when predicting.

[0078] Furthermore, in order to enhance the real-time and adaptability of the model, especially when the working environment of the disconnector changes greatly, we introduced a nonlinear adaptive feedback and correction mechanism (Adaptive Non near Feedback Adjustment System, ANFAS), which can monitor the errors of power and current data in real time and dynamically adjust the model coefficients to improve the accuracy of fault prediction.

[0079] In a specific embodiment, the error between the predicted data and the measured data of each electrical parameter is calculated in S105 and is expressed as:

[0080]

[0081] In the above formula, E i (t) represents the error of the i-th target electrical parameter, X i,pred (t) represents the predicted data of the i-th target electrical parameter; X i,real (t) represents the measured data of the i-th target electrical parameter; γ represents the error adjustment coefficient.

[0082] Among them, the error calculation method reduces the instability of the error under different amplitudes of electrical parameter prediction data by introducing the adjustment coefficient γ and the normalization term, and can more accurately reflect the difference between the predicted value and the measured value. Especially when the parameter changes greatly, this method can effectively suppress the problem of too large or too small error, and improve the stability and accuracy of fault diagnosis.

[0083] Furthermore, after the system detects that the error exceeds the threshold, the model adjusts the model coefficients of the electrical parameters through an adaptive feedback mechanism so that it can better adapt to the new data environment.

[0084] In a specific embodiment, after determining that the disconnector has a fault in S105, the method further includes: if the error of the target electrical parameter is greater than the corresponding preset error threshold, adjusting the model coefficient of the target electrical parameter according to the error of the target electrical parameter, which is expressed as:

[0085]

[0086] In the above formula, a i,new represents the updated model coefficient of the i-th target electrical parameter; a i,old represents the model coefficient before the i-th target electrical parameter is updated; E i (t) represents the error of the i-th target electrical parameter; η represents the learning rate, which is used to control the step size of parameter update. A smaller η value ensures stable but slower adjustment, while a larger η value makes the model coefficient update faster but may cause oscillation or instability; α iRepresents the sensitivity coefficient of the nonlinear error of the i-th target electrical parameter.

[0087] Through the adaptive feedback mechanism, the model can dynamically adjust the model coefficients according to real-time data during operation, so that the model can better adapt to the new data environment, especially when the electrical parameters change abnormally. This mechanism enhances the robustness and adaptability of the system and avoids model failure due to environmental changes or faults.

[0088] In one embodiment, Figure 2 As shown, a fault detection device for an isolating switch is proposed, the device comprising:

[0089] The data acquisition module 201 is used to acquire historical data of multiple electrical parameters preset by the disconnector, and perform nonlinear conversion and accumulation processing on the historical data of the target electrical parameter to obtain corresponding nonlinear accumulated data; wherein the target electrical parameter is any one of the multiple electrical parameters;

[0090] A nonlinear multivariate grey system model building module 202 is used to build a nonlinear multivariate grey system model; wherein the nonlinear multivariate grey system model includes a plurality of sub-models, the model structures of the plurality of sub-models are the same, each sub-model corresponds to an electrical parameter, the nonlinear multivariate grey system model is used to describe the nonlinear relationship between the plurality of electrical parameters, and the model coefficients and bias terms of the electrical parameters in different sub-models are different; the model coefficients and bias terms of the target electrical parameters in the nonlinear multivariate grey system model are estimated according to the historical data of the target electrical parameters and the nonlinear accumulated data;

[0091] A prediction module 203, for constructing a parameter prediction model based on the model coefficient and the bias term of the target electrical parameter, and acquiring prediction data of the target electrical parameter based on the parameter prediction model to obtain prediction data of each electrical parameter;

[0092] The fault judgment module 204 is used to obtain the measured data of multiple electrical parameters of the disconnector and calculate the error between the predicted data and the measured data of each electrical parameter. If the error of any electrical parameter is greater than the preset error threshold of the corresponding electrical parameter, it is determined that the disconnector is faulty.

[0093] Figure 3 FIG. 2 shows an internal structure diagram of a fault detection device for an isolating switch in one embodiment. Figure 3As shown, the fault detection device of the isolating switch includes a processor, a memory and a network interface connected via a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the fault detection device of the isolating switch stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor may implement the fault detection method of the isolating switch. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor may execute the fault detection method of the isolating switch. Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the fault detection device of the isolating switch to which the scheme of the present application is applied. The specific fault detection device of the isolating switch may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0094] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented: obtaining historical data of multiple electrical parameters preset by an isolating switch, and performing nonlinear conversion and accumulation processing on the historical data of a target electrical parameter to obtain corresponding nonlinear accumulated data; wherein the target electrical parameter is any one of the multiple electrical parameters; constructing a nonlinear multivariate grey system model; wherein the nonlinear multivariate grey system model includes multiple sub-models, the model structures of the multiple sub-models are the same, each sub-model corresponds to an electrical parameter, and the nonlinear multivariate grey system model is used to describe the nonlinear relationship between the multiple electrical parameters. Linear relationship, the model coefficients and bias items of electrical parameters in different sub-models are different; the model coefficients and bias items of the target electrical parameters in the nonlinear multivariate grey system model are estimated according to the historical data and nonlinear cumulative data of the target electrical parameters; a parameter prediction model is constructed based on the model coefficients and bias items of the target electrical parameters, and the prediction data of the target electrical parameters are obtained based on the parameter prediction model to obtain the prediction data of each electrical parameter; the measured data of multiple electrical parameters of the disconnector are obtained, and the error between the predicted data and the measured data of each electrical parameter is calculated. If the error of any electrical parameter is greater than the preset error threshold of the corresponding electrical parameter, it is determined that the disconnector is faulty.

[0095] A fault detection device for an isolating switch comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: obtaining historical data of multiple electrical parameters preset for the isolating switch, and performing nonlinear conversion and accumulation processing on the historical data of the target electrical parameter to obtain corresponding nonlinear accumulated data; wherein the target electrical parameter is any one of the multiple electrical parameters; constructing a nonlinear multivariate grey system model; wherein the nonlinear multivariate grey system model comprises multiple sub-models, the model structures of the multiple sub-models are the same, each sub-model corresponds to an electrical parameter, and the nonlinear multivariate grey system model is used to describe The nonlinear relationship between multiple electrical parameters, the model coefficients and bias items of electrical parameters in different sub-models are different; the model coefficients and bias items of the target electrical parameters in the nonlinear multivariate grey system model are estimated based on the historical data and nonlinear cumulative data of the target electrical parameters; a parameter prediction model is constructed based on the model coefficients and bias items of the target electrical parameters, and the prediction data of the target electrical parameters are obtained based on the parameter prediction model to obtain the prediction data of each electrical parameter; the measured data of multiple electrical parameters of the disconnector are obtained, and the error between the predicted data and the measured data of each electrical parameter is calculated. If the error of any electrical parameter is greater than the preset error threshold of the corresponding electrical parameter, it is determined that the disconnector is faulty.

[0096] It should be noted that the above-mentioned isolating switch fault detection method, device, equipment and computer-readable storage medium belong to a general inventive concept, and the contents of the isolating switch fault detection method, device, equipment and computer-readable storage medium embodiments are applicable to each other.

[0097] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0098] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0099] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A fault detection method for an isolating switch, characterized in that: The method comprises: Acquire historical data of multiple electrical parameters preset for the isolating switch, and perform nonlinear conversion and accumulation processing on the historical data of the target electrical parameter to obtain corresponding nonlinear accumulated data; wherein the target electrical parameter is any one of the multiple electrical parameters; Constructing a nonlinear multivariate grey system model; wherein the nonlinear multivariate grey system model includes a plurality of sub-models, the model structures of the plurality of sub-models are the same, each sub-model corresponds to an electrical parameter, the nonlinear multivariate grey system model is used to describe the nonlinear relationship between the plurality of electrical parameters, and the model coefficients and bias terms of the electrical parameters in different sub-models are different; estimating model coefficients and bias terms of the target electrical parameters in the nonlinear multivariate grey system model according to historical data and nonlinear accumulated data of the target electrical parameters; Building a parameter prediction model based on the model coefficient and the bias term of the target electrical parameter, and acquiring prediction data of the target electrical parameter based on the parameter prediction model to obtain prediction data of each electrical parameter; The measured data of the multiple electrical parameters of the isolating switch are obtained, and the error between the predicted data and the measured data of each electrical parameter is calculated. If the error of any electrical parameter is greater than a preset error threshold of the corresponding electrical parameter, it is determined that the isolating switch is faulty.

2. The method according to claim 1, characterized in that The nonlinear conversion and accumulation processing of the historical data of the target electrical parameters is expressed as: In the above formula, represents the historical data of the i-th target electrical parameter at time k; For duration t The nonlinear accumulation data; p is a parameter used to control the nonlinear complexity; α is a parameter for adjusting the amplitude of periodic oscillation; β is a parameter for adjusting the frequency of periodic oscillation.

3. The method according to claim 1, characterized in that: The sub-model of the i-th electrical parameter in the nonlinear multivariate grey system model is expressed as: In the above formula, Represents the nonlinear cumulative data of the i-th target electrical parameter within the time t; a i represents the model coefficient of the i-th target electrical parameter; b i represents the bias phase of the i-th target electrical parameter; p is a parameter used to control the nonlinear complexity.

4. The method according to claim 1, characterized in that: The model coefficients and bias terms of the target electrical parameters in the nonlinear multivariate grey system model are estimated based on the historical data and nonlinear accumulated data of the target electrical parameters, which are expressed as: In the above formula, a i represents the model coefficient of the i-th target electrical parameter; N1 represents the total number of nonlinear accumulated data of the i-th target electrical parameter; represents the nth nonlinear accumulated data of the i-th target electrical parameter; b i represents the bias phase of the i-th target electrical parameter; N2 represents the total number of historical data of the i-th target electrical parameter; Represents the nth historical data of the ith target electrical parameter.

5. The method according to claim 1, characterized in that The prediction data of the target electrical parameter is obtained based on the parameter prediction model to obtain the prediction data of each electrical parameter, which is expressed as: In the above formula, Represents the nonlinear cumulative data of the i-th target electrical parameter within the time length t+1; represents the first nonlinear cumulative data of the i-th target electrical parameter; a i represents the model coefficient of the i-th target electrical parameter; b i represents the bias phase of the i-th target electrical parameter; Represents the nonlinear cumulative data of the i-th target electrical parameter within the time length t; Represents the predicted data at time t+1.

6. The method according to claim 1, characterized in that The error between the predicted data and the measured data of each electrical parameter is calculated as: In the above formula, E i (t) represents the error of the i-th target electrical parameter, X i,pred (t) represents the predicted data of the i-th target electrical parameter; X i,real (t) represents the measured data of the i-th target electrical parameter; γ represents the error adjustment coefficient.

7. The method according to claim 1, characterized in that After determining that the isolating switch has a fault, the method further includes: If the error of the target electrical parameter is greater than the corresponding preset error threshold, the model coefficient of the target electrical parameter is adjusted according to the error of the target electrical parameter, which is expressed as: In the above formula, a i,new represents the updated model coefficient of the i-th target electrical parameter; a i,old represents the model coefficient before the i-th target electrical parameter is updated; E i (t) represents the error of the i-th target electrical parameter; η represents the learning rate, which is used to control the step size of parameter update; α represents the sensitivity coefficient of the nonlinear error of the i-th target electrical parameter.

8. A fault detection method for an isolating switch, characterized in that: The device comprises: A data acquisition module, used to acquire historical data of multiple electrical parameters preset by the disconnector, and perform nonlinear conversion and accumulation processing on the historical data of the target electrical parameter to obtain corresponding nonlinear accumulated data; wherein the target electrical parameter is any one of the multiple electrical parameters; A nonlinear multivariate grey system model building module is used to build a nonlinear multivariate grey system model; wherein the nonlinear multivariate grey system model includes a plurality of sub-models, the model structures of the plurality of sub-models are the same, each sub-model corresponds to an electrical parameter, the nonlinear multivariate grey system model is used to describe the nonlinear relationship between the plurality of electrical parameters, and the model coefficients and bias terms of the electrical parameters in different sub-models are different; the model coefficients and bias terms of the target electrical parameters in the nonlinear multivariate grey system model are estimated according to the historical data and nonlinear accumulated data of the target electrical parameters; A prediction module, configured to construct a parameter prediction model based on the model coefficient and the bias term of the target electrical parameter, and obtain prediction data of the target electrical parameter based on the parameter prediction model to obtain prediction data of each electrical parameter; The fault judgment module is used to obtain the measured data of the multiple electrical parameters of the isolating switch and calculate the error between the predicted data and the measured data of each electrical parameter. If the error of any electrical parameter is greater than the preset error threshold of the corresponding electrical parameter, it is determined that the isolating switch is faulty.

9. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

10. A fault detection device for an isolating switch, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method according to any one of claims 1 to 7.

Images