Intelligent management system and method for power transformation operation and maintenance

Abstract

The invention discloses a power transformation operation and maintenance intelligent management system and method, and relates to the technical field of intelligent management. A thermal imaging image of first equipment is collected and preprocessed, and a first image is obtained and converted into a first image matrix; performing feature extraction on the first image through a perceptual hash algorithm to obtain corresponding temperature features; acquiring a second image by acquiring a second device, and performing feature extraction to obtain a temperature feature of the second image; calculating the Hamming distance between the second image and all the first images in the standard image library, obtaining the minimum Hamming distance, comparing the minimum Hamming distance with a preset similarity threshold value, obtaining the operation state of the second equipment, and outputting a recognition result; formulating an equipment maintenance task for the identified abnormal equipment, calculating the matching degree between each maintainer and each equipment maintenance task, and selecting the maintainer corresponding to the maximum matching degree to execute the equipment maintenance task; and constructing a user management interface, and displaying the equipment operation state and the equipment maintenance task progress.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, and in particular to an intelligent management system and method for substation operation and maintenance. Background Art

[0002] In recent years, my country's power industry has developed rapidly, and substations are an important part of the power system, responsible for the transformation of voltage and current, as well as the reception and distribution of electrical energy. They ensure the safe, stable and efficient operation of the power system.

[0003] However, the traditional substation operation and maintenance management system still has the following shortcomings:

[0004] Lack of real-time monitoring means leads to untimely detection of equipment anomalies, which may lead to the expansion of faults and affect the stable operation of the power system;

[0005] The ability to process and analyze data is limited, making it difficult to effectively process and mine large amounts of monitoring data, and unable to accurately detect the operating status of equipment;

[0006] The unreasonable allocation of maintenance tasks and the lack of a scientific automatic allocation mechanism lead to problems such as uneven distribution of maintenance tasks and mismatch between maintenance personnel's skills and tasks, which affect maintenance efficiency and quality. Summary of the invention

[0007] The purpose of the present invention is to provide an intelligent management system for substation operation and maintenance to solve the deficiencies in the background technology.

[0008] The technical solution of the present invention is: an intelligent management system for substation operation and maintenance, comprising: an image acquisition and preprocessing module, which acquires a thermal imaging image of a first device through a thermal imaging camera and performs preprocessing to obtain a first image, and converts the first image into a first image matrix; wherein the first device refers to a normally operating device, including but not limited to a transformer, a circuit breaker, and a capacitor;

[0009] A feature extraction module extracts features from the first image by using a perceptual hash algorithm, obtains temperature features of the first image, and stores the first image and the corresponding temperature features in a standard image library;

[0010] The image recognition and matching module acquires the second image by collecting data from the second device, performs feature extraction, and obtains the temperature feature of the second image; calculates the Hamming distance between the second image and all first images in the standard image library, obtains the minimum Hamming distance and compares it with a preset similarity threshold, obtains the operating status of the second device, and outputs the recognition result;

[0011] The abnormal equipment maintenance module obtains the corresponding abnormal equipment according to the identification results and formulates equipment maintenance tasks, calculates the matching degree between each maintenance personnel and each equipment maintenance task, and selects the maintenance personnel with the maximum matching degree to perform the equipment maintenance task.

[0012] Preferably, preprocessing the thermal imaging image specifically includes: reducing the thermal imaging image to a fixed size of N×N, where N=32; graying the color thermal imaging image using image processing software, and performing temperature calibration, converting the gray value in the image into an actual temperature value to obtain a first image, and converting it into a first image matrix;

[0013] For a standard image of size N×N, the corresponding matrix size is N×N, where each temperature value is represented as the element value of the corresponding position in the matrix.

[0014] Preferably, the method for extracting features from the first image is as follows: performing discrete cosine transform on the first image to obtain a DCT coefficient matrix;

[0015] The calculation formula is as follows:

[0016]

[0017] Where, F(u,v) is an element in the DCT coefficient matrix; f(x,y) is an element in the first image matrix; cos() is the cosine function, and π is the pi; N is the size of the first image matrix, and the total number of rows and columns of the matrix is ​​N; u and v represent the uth row and vth column in the DCT coefficient matrix; x and y represent the xth row and yth column in the first image matrix; the value range of u, v, x, and y is [0, N-1]; α(u) and α(v) are normalization coefficients;

[0018] in,

[0019] Preferably, extracting an 8×8 coefficient submatrix at the upper left corner from the DCT coefficient matrix, and calculating a mean value of the 8×8 coefficient submatrix at the upper left corner;

[0020] The calculation formula is as follows:

[0021]

[0022] In the formula, Mean represents the mean;

[0023] Each DCT coefficient is numerically compared with the DCT mean, and the DCT coefficients greater than or equal to the mean are recorded as 1; the DCT coefficients less than the mean are recorded as 0, and a binary array with a length of 64 bits is generated as the hash value of the first image, that is, the temperature feature of the first image.

[0024] Preferably, the implementation content of the image recognition and matching module specifically includes:

[0025] The second image is acquired by collecting data from the second device, and feature extraction is performed to obtain temperature features of the second image; the first image and the corresponding temperature features are acquired by traversing the standard image library, and the Hamming distance between the second image and all the first images is calculated to obtain the minimum Hamming distance;

[0026] The calculation formula is as follows:

[0027]

[0028] Where H is the Hamming distance, Fm is the temperature feature of the second image, and Fb is the temperature feature of the first image. Represents the exclusive OR operation;

[0029] The obtained minimum Hamming distance is compared with the preset similarity threshold. If the minimum Hamming distance is less than or equal to the similarity threshold, it means that the temperatures of the two images are similar and the second device is in a normal operating state, and a normal label is output; otherwise, it means that the second device is in an abnormal operating state, an abnormal label is output, and an early warning prompt is issued;

[0030] According to the matching result of the second image, the corresponding operating status of the second device is obtained, and a recognition result is output; wherein the recognition result is a normal label or an abnormal label.

[0031] Preferably, the calculation method of the matching degree between each maintenance personnel and each maintenance task is:

[0032] The total number of maintenance personnel is n, and the equipment maintenance tasks are m. Based on the experience and skills of each maintenance personnel, the matching degree between each maintenance personnel and each maintenance task is calculated;

[0033] The calculation formula is as follows:

[0034] M ij =ω1·S(i,j)+ω2·E(i,j)+ω3·U(i)+ω4·T(j);

[0035] Where i = 1, 2, ..., n, n is the total number of maintenance personnel; j = 1, 2, ..., m, m is the total number of maintenance tasks; M ij represents the matching degree of maintenance personnel i to perform equipment maintenance task j; S(i,j) represents the degree of mastery of the skills required for equipment maintenance task j by maintenance personnel i; E(i,j) represents the matching degree between the experience of maintenance personnel i and the requirements of equipment maintenance task j; U(i) represents the availability of maintenance personnel i; T(j) is the urgency of equipment maintenance task j; ω1, ω2, ω3, ω4 represent the weights of each factor respectively.

[0036] Preferably, E(i,j) is calculated by the success rate of maintenance personnel i completing similar equipment maintenance tasks j; U(i) is quantified by the current load of the maintenance personnel, that is, the inverse of the current load; T(j) is quantified based on the deadline of the equipment maintenance task, and the deadlines of m equipment maintenance tasks are sorted and represented by a number from 1 to m, with m representing the most urgent.

[0037] The present invention also provides a method for intelligent management of substation operation and maintenance, comprising the following steps:

[0038] Capturing a thermal imaging image of the first device through a thermal imaging camera and preprocessing the image to obtain a first image, and converting the first image into a first image matrix;

[0039] Extract features from the first image using a perceptual hash algorithm to obtain temperature features of the first image, and store the first image and the corresponding temperature features in a standard image library;

[0040] The second image is acquired by collecting the second device, and the temperature feature of the second image is acquired by feature extraction; the Hamming distance between the second image and all the first images in the standard image library is calculated, the minimum Hamming distance is obtained and compared with the preset similarity threshold, the operating state of the second device is acquired, and the recognition result is output;

[0041] According to the recognition results, the corresponding abnormal equipment is obtained and equipment maintenance tasks are formulated. The matching degree between each maintenance personnel and each equipment maintenance task is calculated, and the maintenance personnel with the maximum matching degree is selected to perform the equipment maintenance task.

[0042] By building a user management interface, the equipment operation status and equipment maintenance task progress are displayed.

[0043] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0044] The present invention collects the thermal imaging image of the first device through a thermal imaging camera and performs preprocessing, which is conducive to removing noise in the image and improving the image quality, thereby providing a more accurate data basis for subsequent feature extraction and matching;

[0045] The present invention can effectively extract representative temperature features from images by using a perceptual hash algorithm. These features can reflect the operating status of the device and can effectively solve the problems of complex feature extraction and large amount of calculation in traditional methods.

[0046] The present invention monitors the second device in real time and compares it with the first image in the standard image library, which is conducive to quickly and accurately identifying the operating status of the target device and improving the system operation and maintenance efficiency;

[0047] By calculating the matching degree between maintenance personnel and maintenance tasks, the present invention can select the most suitable maintenance personnel to perform the task, realizes the automatic allocation of equipment maintenance tasks, and improves the maintenance efficiency and quality; provides a user management interface, which allows operators to easily view the real-time operating status of the equipment and the progress of the maintenance tasks, which helps to improve the work efficiency of the operators and also facilitates the supervision and management of the management level. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The present invention will be further described below in conjunction with the accompanying drawings.

[0049] Figure 1 This is a module block diagram of a substation operation and maintenance intelligent management system of the present invention.

[0050] Figure 2 The present invention is a flowchart of an intelligent management method for substation operation and maintenance. DETAILED DESCRIPTION

[0051] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0052] Embodiment 1, as Figure 1 As shown, a substation operation and maintenance intelligent management system includes: an image acquisition and preprocessing module, a feature extraction module, an image recognition and matching module, an abnormal equipment maintenance module and a management interface module;

[0053] An image acquisition and preprocessing module, which acquires a thermal imaging image of a first device through a thermal imaging camera installed in the substation; wherein the first device refers to a normally operating device, including but not limited to a transformer, a circuit breaker, and a capacitor;

[0054] Preprocessing the thermal imaging image specifically includes: reducing the thermal imaging image to a fixed size of N×N, where N=32; graying the color thermal imaging image using image processing software, and performing temperature calibration, converting the gray value in the image into an actual temperature value, obtaining a first image, and converting it into a first image matrix;

[0055] Furthermore, for a first image of size N×N, the corresponding matrix size is N×N; wherein each temperature value can be directly used as the element value of the corresponding position in the matrix;

[0056] In the embodiment of the present invention, preprocessing the collected thermal imaging images is beneficial to removing the differences in image size and proportion, retaining only the basic structure and light and dark information, ensuring image consistency and reducing computational complexity; in thermal imaging images, color is usually used to indicate the high and low temperature, while grayscale values ​​can more directly reflect temperature information and facilitate subsequent processing and analysis;

[0057] A feature extraction module, which uses a perceptual hash algorithm to extract features from the first image, obtains temperature features, and stores the first image and the corresponding temperature features in a standard image library;

[0058] Further, performing discrete cosine transform (DCT) on the first image to obtain a DCT coefficient matrix;

[0059] The calculation formula is as follows:

[0060]

[0061] Where, F(u,v) is an element in the DCT coefficient matrix; f(x,y) is an element in the first image matrix; cos() is the cosine function, and π is the pi; N is the size of the first image matrix, that is, the total number of rows and columns of the matrix is ​​N; u and v represent the uth row and vth column in the DCT coefficient matrix; x and y represent the xth row and yth column in the first image matrix; the value range of u, v, x, and y is [0, N-1]; α(u) and α(v) are normalization coefficients;

[0062] in,

[0063] It should be noted that by defining α(u) and α(v), the coefficient matrix after DCT transformation has unit norm on different frequency components, which meets the requirements of orthogonal normalization. This orthogonal normalization property makes DCT have good performance in applications such as image compression and feature extraction, because it reduces information redundancy and improves the efficiency and effect of transformation.

[0064] Extract the upper left 8×8 coefficient submatrix from the DCT coefficient matrix, and calculate the mean of the upper left 8×8 coefficient submatrix; wherein the coefficient submatrix contains the low-frequency information of the image and reflects the overall temperature characteristics of the image;

[0065] The calculation formula is as follows:

[0066]

[0067] In the formula, Mean represents the mean;

[0068] Compare each DCT coefficient with the DCT mean, record the DCT coefficient greater than or equal to the mean as 1, and record the DCT coefficient less than the mean as 0, and generate a 64-bit binary array as the hash value of the first image, that is, the temperature feature of the first image;

[0069] In an embodiment of the present invention, the perceptual hash algorithm can quickly generate a fingerprint of an image, thereby quickly retrieving similar image temperatures in massive data; by simplifying image representation and reducing computational complexity, the perceptual hash algorithm can effectively process large-scale image data sets.

[0070] The image recognition and matching module acquires a second image by collecting data from the second device, and performs feature extraction to acquire temperature features of the second image; wherein the second device is a device to be detected, and the second image is a thermal imaging image preprocessed by the second device;

[0071] Traverse the standard image library to obtain the first image and the corresponding temperature features, calculate the Hamming distance between the second image and all the first images, and obtain the minimum Hamming distance;

[0072] The calculation formula is as follows:

[0073]

[0074] Where H is the Hamming distance, Fm is the temperature feature of the second image, and Fb is the temperature feature of the first image. Represents the exclusive OR operation;

[0075] The obtained minimum Hamming distance is compared with a preset similarity threshold. If the minimum Hamming distance is less than or equal to the similarity threshold, it means that the temperatures of the two images are similar and the second device is in a normal operating state, and a normal label is output; otherwise, it means that the second device is in an abnormal operating state, an abnormal label is output, and an early warning prompt is issued; wherein the similarity threshold is determined based on the experience of domain experts or previous practical experience;

[0076] According to the matching result of the second image, the corresponding operating state of the second device is obtained, and a recognition result is output; wherein the recognition result is a normal label or an abnormal label;

[0077] It should be noted that the advantage of the Hamming distance is that it is simple to calculate, efficient, and suitable for comparison of binary data. However, its disadvantage is that it can only be applied to strings of equal length and is not applicable to non-binary data, which limits its scope of application.

[0078] The abnormal equipment maintenance module obtains the corresponding abnormal equipment according to the identification results and formulates equipment maintenance tasks; the equipment maintenance tasks include but are not limited to maintenance personnel, the type of abnormal equipment, and the deadline for completing the task;

[0079] By calculating the matching degree between each maintenance personnel and each equipment maintenance task, the maintenance personnel with the maximum matching degree is selected to perform the equipment maintenance task;

[0080] Furthermore, the total number of maintenance personnel is n, and the equipment maintenance tasks are m. Based on the experience and skills of each maintenance personnel, the matching degree between each maintenance personnel and each maintenance task is calculated;

[0081] The calculation formula is as follows:

[0082] M ij =ω1·S(i,j)+ω2·E(i,j)+ω3·U(i)+ω4·T(j);

[0083] Where i = 1, 2, ..., n, n is the total number of maintenance personnel; j = 1, 2, ..., m, m is the total number of maintenance tasks; M ij represents the matching degree of maintenance personnel i to perform equipment maintenance task j; S(i,j) represents the mastery degree of maintenance personnel i on the skills required for equipment maintenance task j; E(i,j) represents the matching degree between the experience of maintenance personnel i and the requirements of equipment maintenance task j; U(i) represents the availability of maintenance personnel i; T(j) is the urgency of equipment maintenance task j; ω1, ω2, ω3, ω4 represent the weights of each factor respectively, and the specific values ​​are set according to the importance of the business;

[0084] Among them, E(i,j) is calculated by the success rate of maintenance personnel i completing similar equipment maintenance tasks j; U(i) is quantified by the current load of the maintenance personnel, that is, the inverse of the current load; T(j) is quantified based on the deadline of the equipment maintenance task. The deadlines of m equipment maintenance tasks are sorted and represented by a number from 1 to m, where m represents the most urgent.

[0085] In the embodiment of the present invention, by accurately matching the skills, experience and availability of maintenance personnel with the task requirements, it can be ensured that each maintenance task is performed by the most suitable personnel. This not only improves the efficiency of task completion, but also improves the quality of maintenance work and avoids waste of resources and excessive load.

[0086] The management interface module builds a user management interface to display the equipment operation status and equipment maintenance task progress.

[0087] Embodiment 2, as Figure 2 As shown, a method for intelligent management of substation operation and maintenance includes the following steps:

[0088] Capturing a thermal imaging image of the first device through a thermal imaging camera and preprocessing the image to obtain a first image, and converting the first image into a first image matrix;

[0089] Extract features from the first image using a perceptual hash algorithm to obtain temperature features of the first image, and store the first image and the corresponding temperature features in a standard image library;

[0090] The second image is acquired by collecting the second device, and the temperature feature of the second image is acquired by feature extraction; the Hamming distance between the second image and all the first images in the standard image library is calculated, the minimum Hamming distance is obtained and compared with the preset similarity threshold, the operating state of the second device is acquired, and the recognition result is output;

[0091] According to the recognition results, the corresponding abnormal equipment is obtained and equipment maintenance tasks are formulated. The matching degree between each maintenance personnel and each equipment maintenance task is calculated, and the maintenance personnel with the maximum matching degree is selected to perform the equipment maintenance task.

[0092] By building a user management interface, the equipment operation status and equipment maintenance task progress are displayed.

[0093] In the embodiments provided by the present invention, it should be understood that the disclosed system can be implemented in other ways. For example, the above-described embodiments of the invention are only illustrative, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0094] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0095] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0096] It is obvious to a person skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the essential characteristics of the present invention.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A substation operation and maintenance intelligent management system, characterized in that: include: An image acquisition and preprocessing module, which acquires a thermal imaging image of the first device through a thermal imaging camera and performs preprocessing to obtain a first image, and converts the first image into a first image matrix; A feature extraction module extracts features from the first image by using a perceptual hash algorithm, obtains temperature features of the first image, and stores the first image and the corresponding temperature features in a standard image library; The image recognition and matching module acquires the second image by collecting data from the second device, and performs feature extraction to acquire the temperature feature of the second image; Calculate the Hamming distance between the second image and all first images in the standard image library, obtain the minimum Hamming distance and compare it with a preset similarity threshold, obtain the operating status of the second device, and output the recognition result; The abnormal equipment maintenance module obtains the corresponding abnormal equipment according to the identification results and formulates equipment maintenance tasks, calculates the matching degree between each maintenance personnel and each equipment maintenance task, and selects the maintenance personnel with the maximum matching degree to perform the equipment maintenance task.

2. The intelligent management system for substation operation and maintenance according to claim 1 is characterized in that: Preprocessing the thermal imaging image specifically includes: reducing the thermal imaging image to a fixed size of N×N, where N=32; graying the color thermal imaging image using image processing software, and performing temperature calibration, converting the gray value in the image into an actual temperature value, obtaining a first image, and converting it into a first image matrix; For a standard image of size N×N, the corresponding matrix size is N×N, where each temperature value is represented as the element value of the corresponding position in the matrix.

3. The intelligent management system for substation operation and maintenance according to claim 2 is characterized in that: The method for extracting features from the first image is as follows: performing discrete cosine transform on the first image to obtain a DCT coefficient matrix; The calculation formula is as follows: Where, F(u,v) is an element in the DCT coefficient matrix; f(x,y) is an element in the first image matrix; cos() is the cosine function, π is the pi; N is the size of the first image matrix; u and v represent the uth row and vth column in the DCT coefficient matrix; x and y represent the xth row and yth column in the first image matrix; the value range of u, v, x, and y is [0, N-1]; α(u) and α(v) are normalization coefficients; in, 4. The intelligent management system for substation operation and maintenance according to claim 3 is characterized in that: Extract the upper left 8×8 coefficient submatrix from the DCT coefficient matrix, and calculate the mean of the upper left 8×8 coefficient submatrix; The calculation formula is as follows: In the formula, Mean represents the mean; Each DCT coefficient is numerically compared with the DCT mean, and the DCT coefficients greater than or equal to the mean are recorded as 1; the DCT coefficients less than the mean are recorded as 0, and a binary array with a length of 64 bits is generated as the hash value of the first image, that is, the temperature feature of the first image.

5. The intelligent management system for substation operation and maintenance according to claim 4 is characterized in that: The implementation content of the image recognition and matching module specifically includes: The second image is acquired by collecting data from the second device, and feature extraction is performed to obtain temperature features of the second image; the first image and the corresponding temperature features are acquired by traversing the standard image library, and the Hamming distance between the second image and all the first images is calculated to obtain the minimum Hamming distance; The calculation formula is as follows: Where H is the Hamming distance, Fm is the temperature feature of the second image, and Fb is the temperature feature of the first image. Represents the exclusive OR operation; The obtained minimum Hamming distance is compared with the preset similarity threshold. If the minimum Hamming distance is less than or equal to the similarity threshold, it means that the temperatures of the two images are similar and the second device is in a normal operating state, and a normal label is output; otherwise, it means that the second device is in an abnormal operating state, an abnormal label is output, and an early warning prompt is issued; According to the matching result of the second image, the corresponding operating status of the second device is obtained, and a recognition result is output; wherein the recognition result is a normal label or an abnormal label.

6. The intelligent management system for substation operation and maintenance according to claim 5, characterized in that: The calculation method for the matching degree between each maintenance personnel and each maintenance task is: The total number of maintenance personnel is n, and the equipment maintenance tasks are m. Based on the experience and skills of each maintenance personnel, the matching degree between each maintenance personnel and each maintenance task is calculated; The calculation formula is as follows: M ij =ω1·S(i,j)+ω2·E(i,j)+ω3·U(i)+ω4·T(j); Where i = 1, 2, ..., n, n is the total number of maintenance personnel; j = 1, 2, ..., m, m is the total number of maintenance tasks; M ij represents the matching degree of maintenance personnel i to perform equipment maintenance task j; S(i,j) represents the degree of mastery of the skills required for equipment maintenance task j by maintenance personnel i; E(i,j) represents the matching degree between the experience of maintenance personnel i and the requirements of equipment maintenance task j; U(i) represents the availability of maintenance personnel i; T(j) is the urgency of equipment maintenance task j; ω1, ω2, ω3, ω4 represent the weights of each factor respectively.

7. A method for intelligent management of substation operation and maintenance, characterized in that: The following steps are involved: Capturing a thermal imaging image of the first device through a thermal imaging camera and preprocessing the image to obtain a first image, and converting the first image into a first image matrix; Extract features from the first image using a perceptual hash algorithm to obtain temperature features of the first image, and store the first image and the corresponding temperature features in a standard image library; Acquire a second image by collecting data from the second device, and perform feature extraction to obtain temperature features of the second image; Calculate the Hamming distance between the second image and all first images in the standard image library, obtain the minimum Hamming distance and compare it with a preset similarity threshold, obtain the operating status of the second device, and output the recognition result; According to the recognition results, the corresponding abnormal equipment is obtained and equipment maintenance tasks are formulated. The matching degree between each maintenance personnel and each equipment maintenance task is calculated, and the maintenance personnel with the maximum matching degree is selected to perform the equipment maintenance task. By building a user management interface, the equipment operation status and equipment maintenance task progress are displayed.

Images