A power grid power transmission and transformation equipment multi-scale feature extraction method and system

Abstract

The application discloses a kind of power grid transmission and transformation equipment multiscale feature extraction method and system, method includes: obtaining transmission and transformation system key parameters;Transmission and transformation system key parameters are preprocessed and multi-source data fusion, to obtain fused multi-source data;Fused multi-source data is extracted using deep learning model with multiscale feature, obtains fault information;Based on transmission and transformation system key parameters, establish secondary grey model, using secondary grey model to each equipment of transmission and transformation system is evaluated.The application is applied by the comprehensive application of key technologies such as multi-source data fusion, multiscale feature extraction and fault classification and transmission and transformation equipment state evaluation, improve the efficiency and accuracy of power grid transmission and transformation equipment state monitoring, overcome the limitation of traditional method relying on single data source, realize the comprehensive, in-depth analysis of equipment state, potential fault can be found in time, enhance the reliability of safe and stable operation of power grid system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power systems, and in particular to a power grid transmission and transformation equipment multi-scale feature extraction method and system. BACKGROUND

[0002] With the continuous acceleration of social modernization, residential electricity, industrial electricity and the like are showing a sustained upward trend, and the dependence of modern society on power supply is deepening. As an important component of power grid system for transmitting and transforming electric energy, the stable operation of transmission and transformation equipment is of great significance to the safety and reliability of the power grid system. Transmission and transformation equipment failure can cause industrial production interruption, limited resident life and even electric explosion, and therefore, efficient, accurate and real-time state monitoring of power grid system transmission and transformation equipment is an urgent problem to be solved in the field of electric power.

[0003] At present, the commonly used transmission and transformation equipment monitoring is often based on a single data to judge whether the state is faulty, such as current, voltage and the like. However, in the work of transmission and transformation equipment, its working state is not only affected by a single factor, but also affected by multiple factors. For example, current and voltage data reflect the electrical performance of the transmission and transformation equipment; temperature reflects the special situation of equipment abnormality; vibration signal reflects the abnormal problem that there may be mechanical component damage inside the equipment. Therefore, the analysis and fusion of multi-source data are particularly important for the power grid system. In addition, the current feature extraction method for transmission equipment monitoring is mostly focused on a single time scale. A single time scale is sufficient for reflecting instantaneous state, but it cannot reflect the long-term slowly changing state of the transmission equipment, and it is these slowly changing problems that may cause the equipment to gradually deteriorate and eventually be scrapped. A single time scale cannot timely discover the problem and lacks prediction ability. SUMMARY

[0004] This section is intended to summarize some aspects of the embodiments of the present application and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of the specification to avoid obscuring the purpose of this section, the abstract and the title, and such simplifications or omissions cannot be used to limit the scope of the present application.

[0005] In view of the above existing problems, the present application is proposed. Therefore, the present application provides a power grid transmission and transformation equipment multi-scale feature extraction method to solve the problem that the traditional transmission and transformation equipment monitoring method is single and cannot comprehensively and accurately reflect the equipment state and predict potential faults.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a power grid transmission and transformation equipment multi-scale feature extraction method, comprising:

[0008] obtaining key parameters of a power transmission and transformation system;

[0009] preprocessing and multi-source data fusion are performed on the key parameters of the power transmission and transformation system to obtain fused multi-source data;

[0010] multi-scale feature extraction is performed on the fused multi-source data by using a deep learning model to obtain fault information;

[0011] Based on the key parameters of the power transmission and transformation system, a two-level gray model is established, and the state of each device in the power transmission and transformation system is evaluated by using the two-level gray model.

[0012] As a preferred scheme of the power grid power transmission and transformation equipment multi-scale feature extraction method, wherein: the multi-source data fusion comprises,

[0013] After obtaining the key parameters of the power transmission and transformation system by using sensors, data fusion is performed on various data sources in different sensors, which is represented as:

[0014]

[0015] Wherein, n is the number of data sources, P a,i is the voltage and current data of the power transmission and transformation system equipment, P e,i is the temperature data of the power transmission and transformation system equipment, P u,i is the vibration data of the power transmission and transformation system equipment, D i ′ is the evaluation score of the data source without fusion.

[0016] As a preferred scheme of the power grid power transmission and transformation equipment multi-scale feature extraction method, wherein: the multi-scale feature extraction of the fused multi-source data by using a deep learning model to obtain fault information comprises,

[0017] A deep learning model based on a fusion attention mechanism is used to extract features and classify the fused multi-source data.

[0018] The deep learning model is composed of a multi-scale data input layer, a feature extraction layer, an attention mechanism layer, and a diagnostic result output layer.

[0019] As a preferred scheme of the power grid power transmission and transformation equipment multi-scale feature extraction method, wherein: further comprising,

[0020] The input layer receives the fused multi-source data;

[0021] Multi-scale features are extracted by using the feature extraction layer;

[0022] Features are obtained by using the attention mechanism;

[0023] The diagnostic result output layer outputs a fault and a fault classification using the diagnostic result.

[0024] As a preferred scheme of the power grid transmission and transformation equipment multi-scale feature extraction method, the two-level grey model is established based on the key parameters of the transmission and transformation system, and the two-level grey model includes,

[0025] In the two-level grey model, U is a total evaluation criterion composed of two-level evaluation criterion subsets U i , denoted as U={U1, U2, …, U m}, weights A={A1, A2, …, A m}, two-level evaluation criteria U i ={U i1 ,U i2 ,…,U in}, weights A i ={A i1 ,A i2 ,…,A in};

[0026] The weights are determined by expert weighting method, and the weights of each index are evaluated by experts, and then normalized and averaged.

[0027] As a preferred scheme of the power grid transmission and transformation equipment multi-scale feature extraction method, the two-level grey model is established based on the key parameters of the transmission and transformation system, and the two-level grey model includes,

[0028] A sample matrix is constructed by giving evaluation scores by several experts;

[0029] Four grey classes are set, and the four classes include excellent, good, general, and poor;

[0030] Each grey evaluation coefficient and a total coefficient are calculated.

[0031] As a preferred scheme of the power grid transmission and transformation equipment multi-scale feature extraction method, the two-level grey model is established based on the key parameters of the transmission and transformation system, and the two-level grey model includes,

[0032] The grey evaluation weight is calculated to obtain a grey evaluation matrix, so as to obtain a comprehensive evaluation result, and the result is normalized and compared with a threshold value to obtain a state evaluation of each device of the transmission and transformation system.

[0033] In a second aspect, the application provides a system for extracting multi-scale features of power grid transmission and transformation equipment, which includes,

[0034] An acquisition module is configured to acquire key parameters of a transmission and transformation system;

[0035] A preprocessing module is configured to preprocess the key parameters of the transmission and transformation system and fuse multi-source data to obtain fused multi-source data.

[0036] a feature extraction module configured to perform multi-scale feature extraction on the fused multi-source data using a deep learning model to obtain fault information;

[0037] an evaluation module configured to establish a two-stage grey model based on the key parameters of the power transmission and transformation system, and perform state evaluation on each device of the power transmission and transformation system using the two-stage grey model.

[0038] In a third aspect, the present application provides a computing device, comprising:

[0039] a memory and a processor;

[0040] The memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions, which implement the steps of the power grid transmission and transformation device multi-scale feature extraction method when executed by the processor.

[0041] In a fourth aspect, the present application provides a computer readable storage medium storing computer executable instructions, which implement the steps of the power grid transmission and transformation device multi-scale feature extraction method when executed by the processor.

[0042] Compared with the prior art, the present application has the following beneficial effects: through the comprehensive application of multi-source data fusion, multi-scale feature extraction, fault classification, and power transmission and transformation device state evaluation, the efficiency and accuracy of power grid transmission and transformation device state monitoring are improved, the limitations of traditional methods relying on a single data source are overcome, comprehensive and in-depth analysis of the device state is achieved, potential faults can be discovered in a timely manner, and the reliability of the safe and stable operation of the power grid system is enhanced. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor. Among them:

[0044] Figure 1 The overall flowchart of the power grid transmission and transformation device multi-scale feature extraction method according to an embodiment of the present application is shown in the figure.

[0045] Figure 2 The feature extraction method diagram of the power grid transmission and transformation device multi-scale feature extraction method according to an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0046] In order to make the above objectives, characteristics and advantages of the present application more obvious and comprehensible, the specific embodiments of the present application will be described in detail below with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all the other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present application.

[0047] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. The present application, however, can be practiced in a variety of ways beyond the specific details set forth herein without departing from the scope of the present application, and it is understood that the application is not limited in this respect.

[0048] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. The "in one embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an embodiment that is independent of or selected from other embodiments.

[0049] The present application is described in detail in conjunction with the schematic drawings. In the detailed description of the embodiments of the present application, the sectional view of the device structure is partially enlarged without the general proportion for the convenience of description, and the schematic drawings are only examples, which should not limit the scope of protection of the present application. In addition, the three-dimensional spatial dimensions of length, width and depth should be included in actual manufacturing.

[0050] Meanwhile, in the description of the present application, it should be noted that the terms "upper, lower, inner and outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the indicated system or element must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first, second or third" are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0051] In the present application, unless otherwise explicitly specified and limited, the terms "mounting, connecting, connection" should be understood broadly, for example: it can be fixed connection, detachable connection or integral connection; it can also be mechanical connection, electrical connection or direct connection, it can also be indirectly connected through an intermediate medium, or it can be the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0052] Example 1

[0053] Reference Figure 1As an embodiment of the present invention, a multi-scale feature extraction method for power grid transmission and transformation equipment is provided, comprising:

[0054] S100: Obtain key parameters of the power transmission and transformation system;

[0055] In this application embodiment, the key parameters of the power transmission and transformation system include data such as voltage, current, temperature, and vibration signals of the power grid system's power transmission and transformation system.

[0056] S102: Preprocess and fuse key parameters of the power transmission and transformation system from multiple sources to obtain fused multi-source data;

[0057] In this embodiment of the application, to achieve multi-source data fusion, the variables are defined as follows:

[0058] (1) S: follows the identification framework Ω={P a ,P e ,P u The N data sources (the sources are voltage, current, temperature, and vibration of the power transmission and transformation equipment, respectively);

[0059] (2)n Ω The number of categories from which the target features are to be extracted;

[0060] (3)m Xi (p j ): Data source combination Xi against target pattern p j The basic probability distribution.

[0061] Based on the above variable definitions, first calculate all subsets X of set S. i where i = 1, 2, ..., 2 N -1, all subsets together form set X, representing the various combinations of N data sources. Simultaneously, calculate subset p. j ,in, This subset forms set P.

[0062] For each data source combination X obtained above i The confidence level is calculated using the following formula, where m s (p k ) is a known probability assignment of a target pattern to one of the data sources s.

[0063]

[0064] Suppose there exists And it satisfies the following formula:

[0065]

[0066] If it exists

[0067]

[0068] Then X1 is the final decision combination, where ε1 and ε2 are pre-set thresholds.

[0069] Preferably, after the above process is completed, key parameters of the power transmission and transformation system are acquired using sensors, and data from multiple data sources in different sensors are fused, as shown below:

[0070]

[0071] Where n is the number of data sources, P a,i For voltage and current data of power transmission and transformation system equipment, P e,i For temperature data of power transmission and transformation system equipment, P u,i For vibration data of power transmission and transformation system equipment, D i ′ represents the evaluation score for unintegrated data sources.

[0072] It should be noted that this invention, through clearly defined variables and calculation processes, achieves effective preprocessing and multi-source data fusion of key parameters (voltage, current, temperature, vibration signals, etc.) of power transmission and transformation systems. By calculating the confidence levels of different data source combinations and determining the final decision combination based on set thresholds, the accurate fusion of multi-source data is ensured, providing a reliable data foundation for subsequent feature extraction and fault prediction.

[0073] S104: Use a deep learning model to extract multi-scale features from the fused multi-source data to obtain fault information;

[0074] Preferably, a deep learning model based on a fusion attention mechanism is used to extract features and classify fused multi-source data;

[0075] Preferably, the deep learning model consists of a multi-scale data input layer, a feature extraction layer, an attention mechanism layer, and a diagnostic result output layer.

[0076] Preferably, the input layer receives fused multi-source data; a feature extraction layer extracts multi-scale features; an attention mechanism is used to acquire features; and a diagnostic result output layer diagnoses and classifies faults. The specific process is as follows: Figure 2 As shown.

[0077] It should be noted that this invention, by introducing a deep learning model based on a fusion attention mechanism, achieves in-depth mining and efficient utilization of fused multi-source data. The model receives fused multi-source data through a multi-scale data input layer, extracts multi-scale features from the data using a feature extraction layer, further focuses on key features through an attention mechanism layer, and finally achieves fault diagnosis and accurate classification through a diagnostic result output layer. This invention not only improves the accuracy and efficiency of fault information extraction but also enhances the model's ability to identify complex fault modes.

[0078] S106: Based on the key parameters of the power transmission and transformation system, establish a two-level grey model and use the two-level grey model to evaluate the status of each device in the power transmission and transformation system;

[0079] Preferably, in the two-level grey model, U is the overall evaluation criterion, which is composed of a subset of the two-level evaluation criteria. i Composition, denoted as U = {U1, U2, ..., U...} m}, weights A = {A1, A2, ..., A m Secondary evaluation criteria U i ={U i1 U i2 ,…,U in}, weight A i ={A i1 A i2 ,…,A in};

[0080] Preferably, the weighting method is adopted by experts, who evaluate the weight of each indicator and then normalize and average it.

[0081] Preferably, a sample matrix is ​​constructed by providing evaluation scores from several experts;

[0082] In this embodiment of the application, the sample matrix is ​​constructed as follows:

[0083]

[0084] Preferably, four gray categories are set, including excellent, good, average and poor;

[0085] Preferably, calculate each grayscale evaluation coefficient and the total coefficient;

[0086] In this embodiment, excellent, good, average, and poor are represented by 1, 2, 3, and 4, respectively, and the letter is e; the calculation of each grayscale evaluation coefficient and the total coefficient is expressed by the following formula:

[0087]

[0088] Preferably, the grey evaluation weights are calculated to obtain the grey evaluation matrix, thereby obtaining the comprehensive evaluation result. After normalizing the result, it is compared with the threshold to obtain the status evaluation of each device in the power transmission and transformation system.

[0089] In the embodiments of this application, the gray class intervals, i.e. the thresholds, are [0.85,1), [0.7,0.85), [0.5,0.7) and [0,0.5].

[0090] It should be noted that this invention achieves accurate assessment of the status of various devices in the power transmission and transformation system by constructing a two-level grey model based on key parameters of the system. The model uses an expert weighting method to determine the weights of each level of assessment criteria, organizes expert evaluations, and constructs a sample matrix. By setting four grey categories—excellent, good, average, and poor—it calculates the evaluation coefficient for each grey level and the total coefficient, thereby obtaining the grey evaluation matrix and the comprehensive evaluation result. After normalizing the evaluation results, they are compared with preset thresholds to obtain the status assessment of each device. This process not only improves the objectivity and accuracy of the status assessment but also helps to promptly identify potential equipment problems.

[0091] The above is an illustrative scheme of a multi-scale feature extraction method for power grid transmission and transformation equipment according to this embodiment. It should be noted that the technical solution of this multi-scale feature extraction system for power grid transmission and transformation equipment belongs to the same concept as the technical solution of the aforementioned multi-scale feature extraction method for power grid transmission and transformation equipment. Details not described in detail in the technical solution of the multi-scale feature extraction system for power grid transmission and transformation equipment in this embodiment can be found in the description of the technical solution of the aforementioned multi-scale feature extraction method for power grid transmission and transformation equipment.

[0092] The multi-scale feature extraction system for power grid transmission and transformation equipment in this embodiment includes:

[0093] The acquisition module is used to acquire key parameters of the power transmission and transformation system;

[0094] The preprocessing module is used to preprocess key parameters of the power transmission and transformation system and fuse multi-source data to obtain fused multi-source data.

[0095] The feature extraction module is used to extract multi-scale features from the fused multi-source data using a deep learning model to obtain fault information;

[0096] The evaluation module is used to establish a two-level grey model based on the key parameters of the power transmission and transformation system, and to use the two-level grey model to evaluate the status of each device in the power transmission and transformation system.

[0097] This embodiment also provides a computing device suitable for multi-scale feature extraction of power grid transmission and transformation equipment, including:

[0098] The system includes a memory and a processor. The memory stores computer-executable instructions, and the processor executes these instructions to implement the multi-scale feature extraction method for power grid transmission and transformation equipment as proposed in the above embodiments.

[0099] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, it implements the method for multi-scale feature extraction of power grid transmission and transformation equipment as proposed in the above embodiments.

[0100] The storage medium proposed in this embodiment and the method for multi-scale feature extraction of power grid transmission and transformation equipment proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0101] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

Claims

1. A method for multi-scale feature extraction of power grid transmission and transformation equipment, characterized in that, include: Obtain key parameters of the power transmission and transformation system; The key parameters of the power transmission and transformation system are preprocessed and multi-source data are fused to obtain fused multi-source data; The fused multi-source data is used to perform multi-scale feature extraction using a deep learning model to obtain fault information; Based on the key parameters of the power transmission and transformation system, a two-level grey model is established, and the status of each device in the power transmission and transformation system is evaluated using the two-level grey model. Multi-source data fusion includes, After acquiring key parameters of the power transmission and transformation system using sensors, data from multiple data sources in different sensors is fused, as shown below: ； in, For the number of data sources, For voltage and current data of power transmission and transformation system equipment, Temperature data for power transmission and transformation system equipment. For vibration data of power transmission and transformation system equipment, Evaluate scores for unintegrated data sources; Based on the key parameters of the power transmission and transformation system, a two-level grey model is established, including: In the aforementioned secondary gray model, The overall evaluation criteria consist of a subset of secondary evaluation criteria. Composition, denoted as Weight Secondary evaluation criteria Weight ; The weighting method adopts the expert weighting method, which organizes experts to evaluate the weight of each indicator and then normalizes and averages it. It also includes, A sample matrix is ​​constructed by assigning evaluation scores to several experts; Four categories are defined, namely, excellent, good, average, and poor. Calculate the evaluation coefficient for each grayscale level and the total coefficient; The condition assessment of each device in the power transmission and transformation system using the aforementioned two-level grey model includes: The grey evaluation weights are calculated to obtain the grey evaluation matrix, thereby obtaining the comprehensive evaluation result. After normalizing the result, it is compared with the threshold to obtain the status evaluation of each device in the power transmission and transformation system.

2. The multi-scale feature extraction method for power grid transmission and transformation equipment as described in claim 1, characterized in that, The fused multi-source data is used to perform multi-scale feature extraction using a deep learning model to obtain fault information, including... A deep learning model based on a fusion attention mechanism is used to extract features and classify fused multi-source data. A deep learning model consists of a multi-scale data input layer, a feature extraction layer, an attention mechanism layer, and a diagnostic result output layer.

3. The multi-scale feature extraction method for power grid transmission and transformation equipment as described in claim 2, characterized in that, It also includes, The input layer receives the fused multi-source data; Multi-scale features are extracted using the feature extraction layer. Features are acquired using the attention mechanism described above; The diagnostic results are used to diagnose and classify faults in the output layer.

4. A system for performing the multi-scale feature extraction method for power grid transmission and transformation equipment as described in any one of claims 1 to 3, characterized in that, include, The acquisition module is used to acquire key parameters of the power transmission and transformation system; The preprocessing module is used to preprocess the key parameters of the power transmission and transformation system and fuse multi-source data to obtain fused multi-source data. The feature extraction module is used to extract multi-scale features from the fused multi-source data using a deep learning model to obtain fault information; The evaluation module is used to establish a two-level grey model based on the key parameters of the power transmission and transformation system, and to use the two-level grey model to evaluate the status of each device in the power transmission and transformation system.

5. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the multi-scale feature extraction method for power grid transmission and transformation equipment according to any one of claims 1 to 3.

6. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the multi-scale feature extraction method for power grid transmission and transformation equipment as described in any one of claims 1 to 3.

Images