Power equipment mobile monitoring system based on industrial cloud

Abstract

The invention relates to the technical field of power equipment monitoring, and discloses a power equipment mobile monitoring system based on industrial cloud, which comprises a data acquisition unit, a local server, an industrial cloud server and a mobile intelligent terminal, and is characterized in that the data acquisition unit is in communication connection with the local server, the local server is in communication connection with the industrial cloud server, and the industrial cloud server is in communication connection with the mobile intelligent terminal; and the local server and the industrial cloud server are respectively in communication connection with the mobile intelligent terminal. Based on the scheme, the real-time data and the real-time video of the equipment can be displayed, and the historical data can be statistically analyzed; fault diagnosis is carried out on the operation state data, the key parameters and the operation condition videos of the equipment in real time, and a fault diagnosis and maintenance scheme model is continuously optimized, so that the fault diagnosis and maintenance efficiency is improved, and abnormal early warning of the equipment and professional maintenance experience support are realized.

Description

Technical Field

[0001] The present application relates to the technical field of power equipment monitoring, for example, to a mobile monitoring system for power equipment based on industrial cloud. Background Art

[0002] Power equipment is the foundation of the power system and is responsible for the production, transmission, distribution and use of electric energy. There are many types of power equipment, including power generation equipment, primary equipment, secondary equipment, etc. Common power generation equipment includes generators, power plant boilers, steam turbines, gas turbines, etc.; primary equipment includes transformers, circuit breakers, disconnectors, lightning arresters, current limiting reactors, etc.; secondary equipment includes relay protection devices, automatic control systems, measuring instruments, etc. In the total cost of the power industry, the purchase and maintenance costs of power equipment account for a large proportion. Once the power equipment has an abnormal shutdown or serious failure, it will have a serious negative impact on the power system, users and social and economic activities.

[0003] At present, the operating methods in the field of monitoring of power equipment can warn of power equipment failures and locate the fault locations. However, the existing solutions only monitor the real-time data and daily data of power equipment, and lack monitoring of the equipment's operating condition video; and only provide a method of fault diagnosis through comparison of manually preset error values, but do not provide an intelligent fault diagnosis model algorithm, and the fault diagnosis method is not integrated with video information, nor does it have the ability for continuous optimization; only analyze the fault location and the severity of the fault, do not analyze the historical maintenance data of the power equipment and establish a professional maintenance knowledge experience base; and fail to provide a convenient and fast inspection plan and generate detailed inspection reports to improve inspection efficiency and facilitate the tracing and troubleshooting of abnormal problems.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of this application. Summary of the invention

[0005] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0006] The present disclosure provides an industrial cloud-based mobile monitoring system for electric power equipment, the system comprising:

[0007] A data acquisition unit, a local server, an industrial cloud server and a mobile intelligent terminal. The data acquisition unit is connected to the local server in communication. The local server is connected to the industrial cloud server in communication. The local server and the industrial cloud server are connected to the mobile intelligent terminal in communication.

[0008] The data acquisition unit is used to store the sent operation status data and device key parameter data in the local database of the local server; the data acquisition unit is used to send the operation condition video and store it in the local file system of the local server; the mobile intelligent terminal is used to transmit the uploaded maintenance information to the local database of the local server;

[0009] The local server is used to transmit the stored operation status data, device key parameter data, operation condition video, and maintenance status information to the industrial cloud server;

[0010] The industrial cloud server is used to receive the device data information sent by the local server, analyze all the historical data received previously, establish a fault diagnosis and maintenance plan model and encapsulate it into an API service, and detect whether the diagnostic accuracy k improved by the model is greater than the preset threshold m. If k>m, the model is streamlined and sent to the local server; if k<m, the model is continuously optimized;

[0011] The local server is used to receive the streamlined fault diagnosis and maintenance plan model sent by the industrial cloud server and encapsulate it into an API service;

[0012] The mobile intelligent terminal is used to call the API service interface of the streamlined fault diagnosis and maintenance plan model of the local server to obtain the diagnostic result and maintenance plan n, and at the same time call the API service interface of the fault diagnosis and maintenance plan model of the industrial cloud server to obtain the diagnostic result and maintenance plan q.

[0013] In some embodiments, if the diagnostic results of n and q are different, the mobile intelligent terminal displays the fault diagnosis result and maintenance plan q of the industrial cloud server;

[0014] If the fault diagnosis result and maintenance plan q are not obtained within the preset duration, the mobile intelligent terminal displays the fault diagnosis and maintenance plan n of the local server and pushes the abnormal information of the API service of the fault diagnosis and maintenance plan model of the cloud intelligent algorithm module to relevant personnel to facilitate the operation and maintenance personnel to repair the abnormality in time;

[0015] After waiting for the API service of the fault diagnosis and maintenance plan model of the cloud intelligent algorithm module to return to normal, the mobile intelligent terminal displays the fault diagnosis result and maintenance plan q of the industrial cloud server.

[0016] In some embodiments, the fault diagnosis and maintenance plan model established by the industrial cloud server includes the fault diagnosis and maintenance plan model M of data information data and the fault diagnosis and maintenance plan model Mv of video information ideo ;

[0017] Among them, the fault diagnosis and maintenance plan model M of the data information is established data,include:

[0018] Clean and normalize the operating status data, key parameter data and maintenance status data of power equipment to eliminate noise and outliers in the data and improve data quality;

[0019] Use dimensionality reduction methods to remove redundant features and evaluate the core parameters that affect the operating status of power equipment;

[0020] The data projected from the original data X to the new feature subspace is divided into the training set data X train And the test set data X test ; Use TensorFlow deep learning algorithm to train the training set X train Conduct training to establish a fault diagnosis and maintenance solution model based on data information;

[0021] Use the test set data X test The accuracy of the trained fault diagnosis and maintenance solution model is evaluated; if the accuracy does not exceed the preset accuracy c, the model is continuously optimized until the accuracy exceeds c; if the accuracy exceeds the preset accuracy c, the model is used as the fault diagnosis and maintenance solution model of the data information.

[0022] In some embodiments, the data cleaning and normalization of the operation status data, key parameter data and maintenance status data information of the power equipment includes:

[0023] The Z-Score method is used to process outliers. If |Z|>a, the corresponding data point is considered an outlier and is discarded from the original data, where a is the preset threshold.

[0024] The calculation formula of the Z-Score method satisfies:

[0025]

[0026] Where x is the data point, u is the mean, and σ is the standard deviation;

[0027] The normalization process satisfies the formula:

[0028]

[0029] Among them, χ' is the normalized data, min(x) is the minimum value corresponding to the data point, and max(x) is the maximum value corresponding to the data point.

[0030] In some embodiments, the use of a dimensionality reduction method to remove redundant features and evaluate core parameters that affect the operating state of the power equipment includes:

[0031] Calculate the intra-class scatter matrix SW Measures the difference between samples in the same category, S W The calculation formula is:

[0032]

[0033] in, is the intra-class scatter matrix of the i-th class, C i is the sample set of the i-th class, u i is the mean vector of the i-th class, and x is a sample of the i-th class;

[0034] Calculate the inter-class scatter matrix S B It measures the difference between different categories, S B The calculation formula is:

[0035]

[0036] Among them, N i is the number of samples in the i-th class, u is the mean vector of all samples, u i is the mean vector of the i-th class;

[0037] Calculate the optimal projection matrix W so that the projected data maximizes the difference between classes and minimizes the difference within classes, which is achieved by maximizing the following ratio:

[0038]

[0039] S B W=λS W W,

[0040] Among them, Tr represents the trace of the matrix. Solve this eigenvalue problem to obtain the eigenvalue λ and the eigenvector W. Select the eigenvector corresponding to the largest d' eigenvalues ​​to form the projection matrix W, where d' is the target dimension.

[0041] Project the original data X into the new feature subspace, satisfying the formula X main =XW, where X main It is the data projected from the original data X to the new feature subspace.

[0042] In some embodiments, a fault diagnosis and maintenance solution model Mv of the video information is established. ideo ,include:

[0043] Extract the video clips of the key time period from the historical operation condition video of the power equipment according to the equipment operation status, and decompose the video clips of the key time period into video frame images;

[0044] Improve the quality of video frame images using enhancement techniques including contrast adjustment, denoising, and image sharpening;

[0045] Adjust the contrast formula to satisfy:

[0046] I adjusted =αI+β,

[0047] Among them, I is the pixel value of the original image, I adjusted is the pixel value of the adjusted image, α is the contrast factor, and β is the brightness offset;

[0048] The denoising formula satisfies:

[0049]

[0050] Where I(q) is the grayscale value of pixel q, I denoised (p) is the grayscale value of pixel p after denoising, w(p,q) is the similarity weight between pixels p and q, and Ω is the set of pixels involved in the calculation;

[0051] The sharpening formula satisfies:

[0052] I sharpened =I+k(II blurred ),

[0053] Among them, I sharpened is the sharpened image, I blurred is the blurred image, k is the sharpening factor;

[0054] Use feature point detection algorithm to extract key feature points in video frame images;

[0055] Annotate video frames based on historical operating status information and historical maintenance records of power equipment, marking normal / abnormal and maintenance status;

[0056] The historical operating condition videos are randomly divided into training set operating condition videos and test set operating condition videos;

[0057] Use the training set operating condition videos to train the deep learning model and establish a fault diagnosis and maintenance solution model based on video information;

[0058] The performance of the model is evaluated using the test set operating condition video. If the accuracy does not exceed the preset accuracy c, the model is optimized until the accuracy exceeds c. If the accuracy exceeds the preset accuracy c, the model is used as the fault diagnosis and maintenance solution model of the video information.

[0059] In some embodiments, a fault diagnosis and maintenance solution model is used to perform fault diagnosis, including:

[0060] Fault diagnosis and maintenance plan model using data information dataThe real-time operation status data and key parameter data of the equipment are tested, and the diagnostic results and maintenance plans are R1;

[0061] Fault diagnosis and maintenance plan model Mv using video information ideo The real-time operating condition video of the equipment is tested, and the diagnostic result and maintenance plan are R2;

[0062] If R1 and R2 are the same, the diagnostic result and maintenance plan of the test are R1; if R1 and R2 are different, the abnormality levels of R1 and R2 are determined, and the diagnostic result and maintenance plan with a higher abnormality level are used as the final diagnostic result and maintenance plan.

[0063] In some embodiments, the mobile smart terminal is also used to display the fault diagnosis results and maintenance solutions of the industrial cloud server.

[0064] In some embodiments, the data acquisition unit includes a data acquisition module and a video acquisition module; the data acquisition module includes a wired sensor and a wireless sensor, both of which are used to collect the operating status data and key parameters of the monitored power equipment in real time, and transmit them to the local server; the video acquisition module includes a wired video acquisition device and a wireless video acquisition device, which are used to collect the operating condition video of each power equipment in real time, and transmit them to the local server;

[0065] The local server includes a user management module, a local file system, a local database, a local intelligent algorithm module, a local diagnosis module and a local service encapsulation module;

[0066] The user management module is used to implement functions such as adding users, deleting users, changing passwords and user rights management; the local file system is used to store real-time operating condition video files and real-time inspection reports of local power equipment; the local database is used to store user names, passwords, creators, creation time, permissions and password modification time information of users, and is used to store operating status data, key equipment parameters, maintenance data and inspection data of local power equipment, and is used to store metadata information of video files such as the name of local video files, acquisition device information, upload time and storage path; the local intelligent algorithm module is used to receive the simplified fault diagnosis and maintenance solution model sent by the industrial cloud server; the local diagnosis module is used to call the simplified fault diagnosis and maintenance solution model of the local intelligent algorithm module to perform fault diagnosis on the power equipment and calculate the diagnosis results and maintenance solutions; the local service encapsulation module is used to encapsulate the user management module, the real-time operating status data of local power equipment, real-time key equipment parameters, real-time maintenance data, real-time inspection data, real-time operating condition video, simplified fault diagnosis and maintenance solution model and the diagnosis results and maintenance solutions of the local intelligent algorithm module into a RESTful API service;

[0067] The industrial cloud server includes a cloud file system, a cloud database, a cloud intelligent algorithm module, a cloud diagnosis module and a cloud service packaging module;

[0068] The cloud file system is used to store the historical operating condition video files and historical inspection reports of each local power equipment; the cloud database is used to store the historical operating status data, historical equipment key parameters, historical maintenance data, historical inspection data of each local power equipment, as well as the metadata information of historical video files such as the name of the video file, video acquisition device information, video upload time and storage path; the cloud intelligent algorithm module is used to establish a fault diagnosis and maintenance solution model for the power equipment based on the historical data of each power equipment, and send the model to the local server after simplifying it according to the model optimization situation; the cloud diagnosis module is used to call the fault diagnosis and maintenance solution model of the cloud intelligent module to perform fault diagnosis on the power equipment and calculate the diagnosis results and maintenance solutions; the cloud service packaging module is used to package the historical operating status data, historical equipment key parameters, historical maintenance data, historical inspection data, historical inspection reports, historical operating condition videos, fault diagnosis and maintenance solution models and the fault diagnosis results and maintenance solutions of the cloud diagnosis module into a RESTful API service;

[0069] The mobile intelligent terminal includes a user login module, a user information module, a device selection module, a real-time data monitoring module, a historical data monitoring module, an abnormal warning module and a patrol module; the user login module, the user information module and the real-time data monitoring module all call the API interface of the local service encapsulation module, the historical data monitoring module calls the API interface of the cloud service encapsulation module, and the abnormal warning module and the patrol module call the API interfaces of the local service encapsulation module and the cloud service encapsulation module;

[0070] The user login module is used to implement the login and password modification operations of the mobile smart terminal. After successful login, the interface that the user can view is automatically displayed according to the user's permissions; the user information module is used to display the user's creation time, permissions, and password modification time; the equipment selection module is used to select the power equipment to be monitored; the real-time data monitoring module is used to display the real-time operating status data, key equipment operating parameters, and real-time operating condition videos of the selected power equipment; the historical data monitoring module is used to display the historical operating status data, historical key equipment operating parameters, historical operating condition videos, historical maintenance records, historical inspection data, and historical inspection reports of the selected equipment; the abnormal warning module is used to display the real-time fault diagnosis results and recommended maintenance plans of the selected equipment If the diagnosis result is abnormal, the abnormal information will be pushed to the relevant personnel. After receiving the abnormal prompt and the recommended maintenance plan, the relevant personnel will make a comprehensive assessment and submit the abnormal handling opinions. After the abnormal information is processed, the maintenance record will be uploaded to the local server; in the inspection module, the inspection personnel scan the machine code of each device, which can display the real-time operation status data, real-time operation key parameters, real-time operation condition video and other real-time data of the equipment. It can display the historical operation status data of the equipment, historical equipment operation key parameters, historical operation condition video, historical maintenance record, historical inspection data, historical inspection report and the real-time fault diagnosis results and recommended maintenance plan of the equipment. After the inspection personnel completes the inspection, they select the inspection personnel name and inspection status information. After submission, the inspection report is automatically generated and sent to the local server.

[0071] The industrial cloud-based mobile monitoring system for electric power equipment provided by the embodiments of the present disclosure can achieve the following technical effects:

[0072] Based on this solution, it is possible to display the real-time data and real-time video of the equipment and perform statistical analysis on the historical data; perform real-time fault diagnosis on the equipment's operating status data, equipment key parameters and operating condition videos, and continuously optimize the fault diagnosis and maintenance solution model, thereby improving the efficiency of fault diagnosis and maintenance, and realizing equipment abnormality warning and professional maintenance experience support; by scanning the machine code attached to the equipment, the key operating information of the equipment can be obtained and an inspection report can be generated, thereby improving the inspection efficiency and facilitating the traceability of the inspection process; in addition, the push of abnormal warning information makes it convenient for staff to deal with equipment abnormalities in a timely manner, and the design of mobile smart terminals eliminates the need to monitor power equipment in fixed places, which reflects the convenience and speed of this solution, while the authority management mechanism reflects the security of this solution.

[0073] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0075] Figure 1 It is a data interaction diagram of an industrial cloud-based mobile monitoring system for power equipment provided by an embodiment of the present disclosure;

[0076] Figure 2 It is a structural diagram of an industrial cloud-based mobile monitoring system for power equipment provided by an embodiment of the present disclosure;

[0077] Figure 3 It is a flowchart of a method for mobile monitoring of power equipment based on industrial cloud provided by an embodiment of the present disclosure;

[0078] Figure 4 It is a structural schematic diagram of another industrial cloud-based mobile monitoring system for power equipment provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0079] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0080] The terms "first", "second", etc. in the embodiments of the present disclosure are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so as to describe the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0081] Unless otherwise stated, the term "plurality" means two or more.

[0082] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0083] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0084] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0085] The industrial cloud-based mobile monitoring system for power equipment provided by the embodiments of the present disclosure is described below in conjunction with the accompanying drawings.

[0086] Figure 1 It is a data interaction diagram of an industrial cloud-based mobile monitoring system for power equipment provided in an embodiment of the present disclosure.

[0087] like Figure 1 As shown, the industrial cloud-based mobile monitoring system for electric power equipment may include a data acquisition unit 101, a local server 102, an industrial cloud server 103 and a mobile intelligent terminal 104, wherein the data acquisition unit 101 is communicatively connected to the local server 102, the local server 102 is communicatively connected to the industrial cloud server 103, and the local server 102 and the industrial cloud server 103 are communicatively connected to the mobile intelligent terminal 104 respectively;

[0088] The data acquisition unit 101 is used to store the sent operating status data and equipment key parameter data in the local database of the local server 102; the data acquisition unit 101 is used to send the operating condition video to be stored in the local file system of the local server 102; the mobile smart terminal 104 is used to transmit the uploaded maintenance information to the local database of the local server 102;

[0089] The local server 102 is used to transmit the stored operation status data, equipment key parameter data, operation condition video, and maintenance status information to the industrial cloud server 103;

[0090] The industrial cloud server 103 is used to receive the device data information sent by the local server 102, analyze all the historical data received previously, establish a fault diagnosis and repair plan model and encapsulate it into an API service, and detect whether the diagnostic accuracy k improved by the model is greater than the preset threshold m. If k > m, the model is streamlined and then sent to the local server 102; if k < m, the model is continuously optimized.

[0091] The local server 102 is used to receive the streamlined fault diagnosis and repair plan model sent by the industrial cloud server 103 and encapsulate it into an API service.

[0092] The mobile intelligent terminal 104 is used to call the API service interface of the streamlined fault diagnosis and repair plan model of the local server 102 to obtain the diagnostic result and repair plan n, and at the same time call the API service interface of the fault diagnosis and repair plan model of the industrial cloud server 103 to obtain the diagnostic result and repair plan q.

[0093] In some embodiments, if the diagnostic results of n and q are different, the mobile intelligent terminal 104 displays the fault diagnosis result and repair plan q of the industrial cloud server 103.

[0094] If the fault diagnosis result and repair plan q are not obtained within the preset time period, the mobile intelligent terminal 104 displays the fault diagnosis and repair plan n of the local server 102 and pushes the fault diagnosis and repair plan model API service exception information of the cloud intelligent algorithm module to relevant personnel to facilitate the operation and maintenance personnel to repair the exception in a timely manner.

[0095] After waiting for the fault diagnosis and repair plan model API service of the cloud intelligent algorithm module to return to normal, the mobile intelligent terminal 104 displays the fault diagnosis result and repair plan q of the industrial cloud server 103.

[0096] In some embodiments, the fault diagnosis and repair plan model established by the industrial cloud server 103 includes the fault diagnosis and repair plan model M of data information data and the fault diagnosis and repair plan model Mv of video information ideo ;

[0097] Among them, establishing the fault diagnosis and repair plan model M of the data information data , includes:

[0098] Perform data cleaning and normalization processing on the operation status data, equipment key parameter data, and maintenance status data information of the power equipment to eliminate noise and outliers in the data and improve data quality.

[0099] Use a dimensionality reduction method to remove redundant features and evaluate the core parameters affecting the operation status of the power equipment.

[0100] The data projected from the original data X to the new feature subspace is divided into the training set data X train And the test set data X test ; Use TensorFlow deep learning algorithm to train the training set X train Conduct training to establish a fault diagnosis and maintenance solution model based on data information;

[0101] Use the test set data X test The accuracy of the trained fault diagnosis and maintenance solution model is evaluated; if the accuracy does not exceed the preset accuracy c, the model is continuously optimized until the accuracy exceeds c; if the accuracy exceeds the preset accuracy c, the model is used as the fault diagnosis and maintenance solution model of the data information.

[0102] In some embodiments, the data cleaning and normalization of the operation status data, key parameter data and maintenance status data information of the power equipment includes:

[0103] The Z-Score method is used to process outliers. If |Z|>a, the corresponding data point is considered an outlier and is discarded from the original data, where a is the preset threshold.

[0104] The calculation formula of the Z-Score method satisfies:

[0105]

[0106] Where x is the data point, u is the mean, and σ is the standard deviation;

[0107] The normalization process satisfies the formula:

[0108]

[0109] Among them, χ' is the normalized data, min(x) is the minimum value corresponding to the data point, and max(x) is the maximum value corresponding to the data point.

[0110] In some embodiments, the use of a dimensionality reduction method to remove redundant features and evaluate core parameters that affect the operating state of the power equipment includes:

[0111] Calculate the intra-class scatter matrix S W Measures the difference between samples in the same category, S W The calculation formula is:

[0112]

[0113] in, is the intra-class scatter matrix of the i-th class, C i is the sample set of the i-th class, ui is the mean vector of the i-th class, and x is a sample of the i-th class;

[0114] Calculate the inter-class scatter matrix S B It measures the difference between different categories, S B The calculation formula is:

[0115]

[0116] Among them, N i is the number of samples in the i-th class, u is the mean vector of all samples, u i is the mean vector of the i-th class;

[0117] Calculate the optimal projection matrix W so that the projected data maximizes the difference between classes and minimizes the difference within classes, which is achieved by maximizing the following ratio:

[0118]

[0119] S B W=λS W W,

[0120] Among them, Tr represents the trace of the matrix. Solve this eigenvalue problem to obtain the eigenvalue λ and the eigenvector W. Select the eigenvector corresponding to the largest d' eigenvalues ​​to form the projection matrix W, where d' is the target dimension.

[0121] Project the original data X into the new feature subspace, satisfying the formula X main =XW, where X main It is the data projected from the original data X to the new feature subspace.

[0122] In some embodiments, a fault diagnosis and maintenance solution model Mv of the video information is established. ideo ,include:

[0123] Extract the video clips of the key time period from the historical operation condition video of the power equipment according to the equipment operation status, and decompose the video clips of the key time period into video frame images;

[0124] Improve the quality of video frame images using enhancement techniques including contrast adjustment, denoising, and image sharpening;

[0125] Adjust the contrast formula to satisfy:

[0126] I adjusted =αI+β,

[0127] Among them, I is the pixel value of the original image, I adjusted is the pixel value of the adjusted image, α is the contrast factor, and β is the brightness offset;

[0128] The denoising formula satisfies:

[0129]

[0130] Where I(q) is the grayscale value of pixel q, I denoised (p) is the grayscale value of pixel p after denoising, w(p,q) is the similarity weight between pixels p and q, and Ω is the set of pixels involved in the calculation;

[0131] The sharpening formula satisfies:

[0132] I sharpened =I+k(II blurred ),

[0133] Among them, I sharpened is the sharpened image, I blurred is the blurred image, k is the sharpening factor;

[0134] Use feature point detection algorithm to extract key feature points in video frame images;

[0135] Annotate video frames based on historical operating status information and historical maintenance records of power equipment, marking normal / abnormal and maintenance status;

[0136] The historical operating condition videos are randomly divided into training set operating condition videos and test set operating condition videos;

[0137] Use the training set operating condition videos to train the deep learning model and establish a fault diagnosis and maintenance solution model based on video information;

[0138] The performance of the model is evaluated using the test set operating condition video. If the accuracy does not exceed the preset accuracy c, the model is optimized until the accuracy exceeds c. If the accuracy exceeds the preset accuracy c, the model is used as the fault diagnosis and maintenance solution model of the video information.

[0139] In some embodiments, a fault diagnosis and maintenance solution model is used to perform fault diagnosis, including:

[0140] Fault diagnosis and maintenance plan model using data information data The real-time operation status data and key parameter data of the equipment are tested, and the diagnostic results and maintenance plans are R1;

[0141] Fault diagnosis and maintenance plan model Mv using video information ideo The real-time operating condition video of the equipment is tested, and the diagnostic result and maintenance plan are R2;

[0142] If R1 and R2 are the same, the diagnostic result and maintenance plan of the test are R1; if R1 and R2 are different, the abnormality levels of R1 and R2 are determined, and the diagnostic result and maintenance plan with a higher abnormality level are used as the final diagnostic result and maintenance plan.

[0143] In some embodiments, the mobile smart terminal 104 is also used to display the fault diagnosis results and maintenance solutions of the industrial cloud server 103.

[0144] Figure 2 is a structural diagram of a mobile monitoring system for power equipment based on industrial cloud provided by an embodiment of the present disclosure, such as Figure 2 As shown, in some embodiments, the data acquisition unit 101 includes a data acquisition module and a video acquisition module; the data acquisition module includes a wired sensor and a wireless sensor, both of which are used to collect the operating status data and key parameters of the monitored power equipment in real time, and transmit them to the local server 102; the video acquisition module includes a wired video acquisition device and a wireless video acquisition device, which are used to collect the operating condition video of each power equipment in real time, and transmit them to the local server 102;

[0145] The local server 102 includes a user management module, a local file system, a local database, a local intelligent algorithm module, a local diagnosis module and a local service encapsulation module;

[0146] The user management module is used to implement functions such as adding users, deleting users, changing passwords and user authority management; the local file system is used to store real-time operating condition video files and real-time inspection reports of local power equipment; the local database is used to store user names, passwords, creators, creation time, permissions and password modification time information of users, and is used to store operating status data, key equipment parameters, maintenance data and inspection data of local power equipment, and is used to store metadata information of video files such as the name of local video files, acquisition device information, upload time and storage path; the local intelligent algorithm module is used to receive the simplified fault diagnosis and maintenance solution model sent by the industrial cloud server 103; the local diagnosis module is used to call the simplified fault diagnosis and maintenance solution model of the local intelligent algorithm module to perform fault diagnosis on the power equipment and calculate the diagnosis results and maintenance solutions; the local service encapsulation module is used to encapsulate the user management module, the real-time operating status data of local power equipment, real-time key equipment parameters, real-time maintenance data, real-time inspection data, real-time operating condition video, simplified fault diagnosis and maintenance solution model and the diagnosis results and maintenance solutions of the local intelligent algorithm module into a RESTful API service;

[0147] The industrial cloud server 103 includes a cloud file system, a cloud database, a cloud intelligent algorithm module, a cloud diagnosis module and a cloud service packaging module;

[0148] The cloud file system is used to store the historical operating condition video files and historical inspection reports of each local power equipment; the cloud database is used to store the historical operating status data, historical equipment key parameters, historical maintenance data, historical inspection data of each local power equipment, and metadata information of historical video files such as the name of the video file, video acquisition device information, video upload time and storage path; the cloud intelligent algorithm module is used to establish a fault diagnosis and maintenance solution model of the power equipment according to the historical data of each power equipment, and send the model to the local server 102 after simplifying the model according to the model optimization situation; the cloud diagnosis module is used to call the fault diagnosis and maintenance solution model of the cloud intelligent module to perform fault diagnosis on the power equipment and calculate the diagnosis results and maintenance solutions; the cloud service packaging module is used to package the historical operating status data of the power equipment, historical equipment key parameters, historical maintenance data, historical inspection data, historical inspection reports, historical operating condition videos, fault diagnosis and maintenance solution models and the fault diagnosis results and maintenance solutions of the cloud diagnosis module into a RESTful API service;

[0149] The mobile intelligent terminal 104 includes a user login module, a user information module, a device selection module, a real-time data monitoring module, a historical data monitoring module, an abnormal warning module and a patrol module; the user login module, the user information module and the real-time data monitoring module all call the API interface of the local service encapsulation module, the historical data monitoring module calls the API interface of the cloud service encapsulation module, and the abnormal warning module and the patrol module call the API interfaces of the local service encapsulation module and the cloud service encapsulation module;

[0150] The user login module is used to implement the login and password modification operations of the mobile intelligent terminal 104. After successful login, the interface that the user can view is automatically displayed according to the user's authority; the user information module is used to display the user's creation time, authority, and password modification time; the equipment selection module is used to select the power equipment to be monitored; the real-time data monitoring module is used to display the real-time operating status data, key equipment operating parameters, and real-time operating condition videos of the selected power equipment; the historical data monitoring module is used to display the historical operating status data, historical key equipment operating parameters, historical operating condition videos, historical maintenance records, historical inspection data, and historical inspection reports of the selected equipment; the abnormal warning module is used to display the real-time fault diagnosis results and recommended maintenance plans of the selected equipment, If the diagnosis result is abnormal, the abnormal information will be pushed to the relevant personnel. After receiving the abnormal prompt and the recommended maintenance plan, the relevant personnel will make a comprehensive assessment and submit the abnormal handling opinion. After the abnormal information is processed, the maintenance record will be uploaded to the local server 102; in the inspection module, the inspection personnel scan the machine code of each device, which can display the real-time operation status data, real-time operation key parameters, real-time operation condition video and other real-time data of the equipment. It can display the historical operation status data of the equipment, historical equipment operation key parameters, historical operation condition video, historical maintenance record, historical inspection data, historical inspection report and the real-time fault diagnosis results and recommended maintenance plan of the equipment. After the inspection personnel completes the inspection, they select the inspection personnel name and inspection status information. After submission, the inspection report is automatically generated and sent to the local server 102.

[0151] and Figure 1 Corresponding to the mobile monitoring system of power equipment based on industrial cloud, the present disclosure also provides a mobile monitoring method of power equipment based on industrial cloud, such as Figure 3 As shown, the mobile monitoring method for power equipment based on industrial cloud may include S1-S7:

[0152] S1. The operating status data and key equipment parameter data sent by the data acquisition unit are stored in the local database of the local server; the operating condition video sent by the data acquisition unit is stored in the local file system of the local server; the maintenance information uploaded by the mobile smart terminal is transmitted to the local database of the local server.

[0153] S2. The local server transmits the stored operating status data, equipment key parameter data, operating condition video, and maintenance status information to the industrial cloud server.

[0154] S3. The industrial cloud server receives the device data information sent by the local server, analyzes all the historical data received previously, establishes a fault diagnosis and repair plan model, encapsulates it into an API service, and checks whether the improved diagnostic accuracy k of the model is greater than the preset threshold m. If k > m, the model is streamlined and then sent to the local server; if k < m, the model continues to be optimized.

[0155] S4. The local server receives the streamlined fault diagnosis and repair plan model sent by the industrial cloud server and encapsulates it into an API service.

[0156] S5. The mobile intelligent terminal calls the API service interface of the streamlined fault diagnosis and repair plan model of the local server to obtain the diagnostic result and repair plan n, and at the same time calls the API service interface of the fault diagnosis and repair plan model of the industrial cloud server to obtain the diagnostic result and repair plan q.

[0157] S6. The mobile intelligent terminal preferentially displays the fault diagnosis result and repair plan of the industrial cloud server. If the diagnostic results of n and q are different, the mobile intelligent terminal displays the fault diagnosis result and repair plan q of the industrial cloud server; if the fault diagnosis result and repair plan q cannot be obtained after 30 seconds of timeout, the mobile intelligent terminal displays the fault diagnosis and repair plan n of the local server and pushes the abnormal information of the API service of the fault diagnosis and repair plan model of the cloud intelligent algorithm module to relevant personnel to facilitate the operation and maintenance personnel to repair the abnormality in a timely manner.

[0158] S7. After the API service of the fault diagnosis and repair plan model of the cloud intelligent algorithm module returns to normal, the mobile intelligent terminal displays the fault diagnosis result and repair plan q of the industrial cloud server.

[0159] Furthermore, the fault diagnosis and repair plan model established by the industrial cloud server includes a fault diagnosis and repair plan model M for data information data and a fault diagnosis and repair plan model Mv for video information ideo These two models.

[0160] The establishment of the fault diagnosis and repair plan model M for the data information data includes the following steps:

[0161] M1. Clean and normalize the data information such as the operation status data, key parameter data, and repair status of the power equipment to eliminate noise and outliers in the data and improve the data quality.

[0162] M1.1. Use the Z-Score method for outlier processing. If |Z| > a (preset threshold), the corresponding data point is considered an outlier and discarded from the original data.

[0163] The calculation formula of the Z-Score method is as follows:

[0164]

[0165] Here, x is the data point, u is the mean, and σ is the standard deviation.

[0166] M1.2, the normalization calculation formula is as follows:

[0167]

[0168] M2. Use dimensionality reduction methods to remove redundant features and evaluate the core parameters that affect the operating status of power equipment.

[0169] In this embodiment, the linear discriminant analysis (LDA) model is used for dimensionality reduction.

[0170] M2.1. Calculate the intra-class scatter matrix S W It measures the difference between samples in the same category, S W The calculation formula is as follows:

[0171]

[0172] in, is the intra-class scatter matrix of the i-th class, C i is the sample set of the i-th class, u i is the mean vector of the i-th class, and x is a sample of the i-th class.

[0173] M2.2. Calculate the inter-class scatter matrix S B It measures the difference between different categories, S B The calculation formula is as follows:

[0174]

[0175] Among them, N i is the number of samples in the i-th class, u is the mean vector of all samples, u i is the mean vector of the ith class.

[0176] M2.3. Calculate the optimal projection matrix W so that the projected data has the largest difference between classes and the smallest difference within classes. This can be achieved by maximizing the following ratio:

[0177]

[0178] S B W=λS W W,

[0179] Where Tr represents the trace of the matrix. Solving this eigenvalue problem, we get the eigenvalue λ and the eigenvector W. We select the eigenvectors corresponding to the largest d' eigenvalues ​​to form the projection matrix W, where d' is the target dimension.

[0180] M2.4. Project the original data X into the new feature subspace

[0181] X main =XW,

[0182] M3, X main The data is divided into training set data X train And the test set data X test The ratio of training set to test set is 7:3. The TensorFlow deep learning algorithm is used to train the training set X train Conduct training and establish a fault diagnosis and maintenance solution model based on data information.

[0183] M4. Use test set data X test The accuracy of the trained fault diagnosis and maintenance solution model is evaluated. If the accuracy does not exceed the preset accuracy c, the model is optimized until the accuracy exceeds c; if the accuracy exceeds the preset accuracy c, the model is used as the fault diagnosis and maintenance solution model of the data information.

[0184] The fault diagnosis and maintenance solution model Mv of the video information ideo The establishment includes the following steps:

[0185] N1. Extract video clips of key time periods from the historical operating condition video of the power equipment according to the equipment operating status, and decompose the video clips of the key time periods into video frame images;

[0186] N2. Use image enhancement techniques such as contrast adjustment, denoising, and sharpening to improve the quality of video frame images;

[0187] The formula for adjusting contrast is as follows:

[0188] I adjusted =αI+β,

[0189] Among them, I is the pixel value of the original image, I adjusted is the pixel value of the adjusted image, α is the contrast factor, and β is the brightness shift.

[0190] The denoising formula is as follows:

[0191]

[0192] Where I(q) is the grayscale value of pixel q, I denoised(p) is the grayscale value of pixel p after denoising, w(p,q) is the similarity weight between pixels p and q, and Ω is the set of pixels involved in the calculation.

[0193] The sharpening formula is as follows:

[0194] I sharpened =I+k(II blurred ),

[0195] Among them, I is the original image, I sharpened is the sharpened image, I blurred is the blurred image, and k is the sharpening factor.

[0196] N3. Use feature point detection algorithm to extract key feature points in video frame images;

[0197] N4. Label the video frames according to the historical operation status information and historical maintenance records of the power equipment, marking normal / abnormal and maintenance status;

[0198] N5: Randomly divide the historical operating condition videos into training set operating condition videos and test set operating condition videos, with a ratio of 7:3;

[0199] N6. Use the training set operating condition videos to train the deep learning model and establish a fault diagnosis and maintenance solution model based on video information;

[0200] N7. Use the test set operating condition video to evaluate the performance of the model. If the accuracy does not exceed the preset accuracy c, continue to optimize the model until the accuracy exceeds c; if the accuracy exceeds the preset accuracy c, use the model as the fault diagnosis and maintenance solution model of the video information.

[0201] The method of using the fault diagnosis and maintenance solution model to perform fault diagnosis includes the following steps:

[0202] O1. Fault diagnosis and maintenance solution model using data information M data The real-time operation status data and key parameter data of the equipment are tested, and the diagnostic results and maintenance plans are R1;

[0203] O2. Fault diagnosis and maintenance solution model Mv using video information ideo The real-time operating condition video of the equipment is tested, and the diagnostic result and maintenance plan are R2;

[0204] O3. If R1 and R2 are the same, the diagnostic result and maintenance plan of the test are R1; if R1 and R2 are different, the abnormality levels of R1 and R2 are determined, and the diagnostic result and maintenance plan with a higher abnormality level are used as the final diagnostic result and maintenance plan.

[0205] In the present disclosure, based on this solution, it is possible to display the real-time data and real-time video of the equipment and perform statistical analysis on the historical data; perform fault diagnosis on the equipment's operating status data, equipment key parameters and operating condition video in real time and continuously optimize the fault diagnosis and maintenance solution model, thereby improving the efficiency of fault diagnosis and maintenance, and realizing equipment abnormality warning and professional maintenance experience support; by scanning the machine code affixed to the equipment, the key operating information of the equipment can be obtained and an inspection report can be generated, thereby improving the inspection efficiency and facilitating the traceability of the inspection process; in addition, the push of abnormal warning information makes it convenient for staff to deal with equipment abnormalities in a timely manner, and the design of the mobile smart terminal makes it unnecessary to monitor the power equipment in a fixed place, which reflects the convenience and speed of this solution, while the authority management mechanism reflects the security of this solution.

[0206] Combination Figure 4 As shown, the embodiment of the present disclosure also provides another industrial cloud-based mobile monitoring system 400 for electric power equipment, including a processor 404 and a memory 401. Optionally, the system may also include a communication interface 402 and a bus 403. Among them, the processor 404, the communication interface 402, and the memory 401 can communicate with each other through the bus 403. The communication interface 402 can be used for information transmission. The processor 404 can call the logic instructions in the memory 401 to execute the industrial cloud-based mobile monitoring method for electric power equipment of the above embodiment.

[0207] In addition, the logic instructions in the memory 401 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.

[0208] The memory 401 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 404 executes the functional application and data processing by running the program instructions / modules stored in the memory 401, that is, the mobile monitoring method of power equipment based on industrial cloud in the above embodiment is realized.

[0209] The memory 401 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 401 may include a high-speed random access memory and may also include a non-volatile memory.

[0210] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute an industrial cloud-based mobile monitoring method for power equipment.

[0211] The computer-readable storage medium mentioned above may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0212] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method of the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, and other media that can store program codes, or a transient storage medium.

[0213] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent possible changes only. Unless explicitly required, separate components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. As used in the description of the embodiments, unless the context clearly indicates otherwise, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of one or more associated listings. In addition, when used in this application, the term "comprise" and its variants "comprises" and / or including (comprising) refer to the existence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the existence or addition of one or more other features, wholes, steps, operations, elements, components and / or these groups. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same or similar parts between the embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0214] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. Technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present disclosure. Technicians can clearly understand that for the convenience and simplicity of description, the specific working process of the systems, devices and units described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0215] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0216] The flowchart and block diagram in the accompanying drawings show the possible architecture, functions and operations of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and a part of the module, program segment or code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A mobile monitoring system for power equipment based on industrial cloud, characterized in that: The system includes a data acquisition unit, a local server, an industrial cloud server, and a mobile intelligent terminal. The data acquisition unit is communicatively connected to the local server, the local server is communicatively connected to the industrial cloud server, and the local server and the industrial cloud server are respectively communicatively connected to the mobile intelligent terminal; The data acquisition unit is used to store the sent operation status data and equipment key parameter data in the local database of the local server; the data acquisition unit is used to send the operation condition video for storage in the local file system of the local server; The mobile intelligent terminal is used to transmit the uploaded maintenance information to the local database of the local server; The local server is used to transmit the stored operation status data, equipment key parameter data, operation condition video, and maintenance status information to the industrial cloud server; The industrial cloud server is used to receive the equipment data information sent by the local server, analyze all the historical data received previously, establish a fault diagnosis and maintenance plan model and encapsulate it into an API service, and detect whether the diagnostic accuracy k improved by the model is greater than the preset threshold m. If k>m, the model is streamlined and sent to the local server; if k<m, the model is continuously optimized; The local server is used to receive the streamlined fault diagnosis and maintenance plan model sent by the industrial cloud server and encapsulate it into an API service; The mobile intelligent terminal is used to call the API service interface of the streamlined fault diagnosis and maintenance plan model of the local server to obtain the diagnostic result and maintenance plan n, and at the same time call the API service interface of the fault diagnosis and maintenance plan model of the industrial cloud server to obtain the diagnostic result and maintenance plan q.

2. The system according to claim 1, characterized in that If the diagnostic results of n and q are different, the mobile intelligent terminal displays the fault diagnosis result and maintenance plan q of the industrial cloud server; If the fault diagnosis result and maintenance plan q are not obtained within the preset duration, the mobile intelligent terminal displays the fault diagnosis and maintenance plan n of the local server and pushes the abnormal information of the API service of the fault diagnosis and maintenance plan model of the cloud intelligent algorithm module to relevant personnel to facilitate the operation and maintenance personnel to repair the abnormality in time; After waiting for the API service of the fault diagnosis and maintenance plan model of the cloud intelligent algorithm module to return to normal, the mobile intelligent terminal displays the fault diagnosis result and maintenance plan q of the industrial cloud server.

3. The system according to claim 1, characterized in that The fault diagnosis and maintenance solution model established by the industrial cloud server includes a fault diagnosis and maintenance solution model M of data information data , video information fault diagnosis and maintenance solution model Mv ideo ; Among them, the fault diagnosis and maintenance solution model M of the data information is established data ,include: Data cleaning and normalization processing are performed on the operation status data, equipment key parameter data, and maintenance status data information of the power equipment to eliminate noise and outliers in the data and improve data quality; The dimensionality reduction method is used to remove redundant features and evaluate the core parameters affecting the operation status of the power equipment; The data projected from the original data X to the new feature subspace is divided into the training set data X train And the test set data X test ; Use TensorFlow deep learning algorithm to train the training set X train Conduct training to establish a fault diagnosis and maintenance solution model based on data information; Use the test set data X test The accuracy of the trained fault diagnosis and maintenance solution model is evaluated; if the accuracy does not exceed the preset accuracy c, the model is continuously optimized until the accuracy exceeds c; if the accuracy exceeds the preset accuracy c, the model is used as the fault diagnosis and maintenance solution model of the data information.

4. The system according to claim 3, characterized in that The data cleaning and normalization processing of the operation status data, equipment key parameter data, and maintenance status data information of the power equipment includes: The Z-Score method is used for outlier processing. If |Z|>a, the corresponding data point is considered an outlier and discarded from the original data, where a is the preset threshold; The calculation formula of the Z-Score method satisfies: where x is the data point, u is the mean, and σ is the standard deviation; The normalization processing satisfies the formula: Among them, χ' is the normalized data, min(x) is the minimum value corresponding to the data point, and max(x) is the maximum value corresponding to the data point.

5. The system according to claim 3, characterized in that The dimensionality reduction method is used to remove redundant features and evaluate the core parameters that affect the operating status of the power equipment, including: Calculate the intra-class scatter matrix S W Measures the difference between samples in the same category, S W The calculation formula is: Among them, S Wi is the intra-class scatter matrix of the i-th class, C i is the sample set of the i-th class, u i is the mean vector of the i-th class, and x is a sample of the i-th class; Calculate the inter-class scatter matrix S B It measures the difference between different categories, S B The calculation formula is: Among them, N i is the number of samples in the i-th class, u is the mean vector of all samples, u i is the mean vector of the i-th class; Calculate the optimal projection matrix W so that the projected data maximizes the difference between classes and minimizes the difference within classes, which is achieved by maximizing the following ratio: S B W=λS W W, Where Tr represents the trace of the matrix. Solve this eigenvalue problem to obtain the eigenvalue λ and the eigenvector W. Select the eigenvector corresponding to the largest d' eigenvalues ​​to form the projection matrix W, where d' is the target dimension. Project the original data X to the new feature subspace, satisfying the formula X main =XW, where X main It is the data projected from the original data X to the new feature subspace.

6. The system according to claim 3, characterized in that Establish the fault diagnosis and maintenance solution model Mv of the video information ideo ,include: Extract the video clips of the key time period from the historical operation condition video of the power equipment according to the equipment operation status, and decompose the video clips of the key time period into video frame images; Improve the quality of video frame images using enhancement techniques including contrast adjustment, denoising, and image sharpening; Adjust the contrast formula to satisfy: I adjusted =αI+β, Among them, I is the pixel value of the original image, I adjusted is the pixel value of the adjusted image, α is the contrast factor, and β is the brightness offset; The denoising formula satisfies: Where I(q) is the grayscale value of pixel q, I denoised (p) is the grayscale value of pixel p after denoising, w(p,q) is the similarity weight between pixels p and q, and Ω is the set of pixels involved in the calculation; The sharpening formula satisfies: I sharpened =I+k(I-I blurred ), Among them, I sharpened is the sharpened image, I blurred is the blurred image, k is the sharpening factor; Use feature point detection algorithm to extract key feature points in video frame images; Annotate video frames based on historical operating status information and historical maintenance records of power equipment, marking normal / abnormal and maintenance status; The historical operating condition videos are randomly divided into training set operating condition videos and test set operating condition videos; Use the training set operating condition videos to train the deep learning model and establish a fault diagnosis and maintenance solution model based on video information; The performance of the model is evaluated using the test set operating condition video. If the accuracy does not exceed the preset accuracy c, the model is optimized until the accuracy exceeds c. If the accuracy exceeds the preset accuracy c, the model is used as the fault diagnosis and maintenance solution model of the video information.

7. The system according to claim 3, characterized in that Fault diagnosis and repair solution model is used for fault diagnosis, including: Fault diagnosis and maintenance plan model using data information data The real-time operation status data and key parameter data of the equipment are tested, and the diagnostic results and maintenance plans are R1; Fault diagnosis and maintenance plan model Mv using video information ideo The real-time operating condition video of the equipment is tested, and the diagnostic result and maintenance plan are R2; If R1 and R2 are the same, the diagnostic result and maintenance plan of the test are R1; if R1 and R2 are different, the abnormality levels of R1 and R2 are determined, and the diagnostic result and maintenance plan with a higher abnormality level are used as the final diagnostic result and maintenance plan.

8. The system according to claim 1, characterized in that The mobile intelligent terminal is also used to display the fault diagnosis results and maintenance solutions of the industrial cloud server.

9. The system according to claim 1, characterized in that The data acquisition unit includes a data acquisition module and a video acquisition module; the data acquisition module includes a wired sensor and a wireless sensor, both of which are used to collect the operating status data and key parameters of the monitored power equipment in real time and transmit them to the local server; The video acquisition module includes a wired video acquisition device and a wireless video acquisition device, which are used to collect the operating condition video of each power equipment in real time and transmit it to the local server; The local server includes a user management module, a local file system, a local database, a local intelligent algorithm module, a local diagnosis module and a local service encapsulation module; The user management module is used to implement functions such as adding users, deleting users, modifying passwords and user rights management; the local file system is used to store real-time operating condition video files and real-time inspection reports of local power equipment; The local database is used to store the user's username, password, creator, creation time, permissions and password modification time information, and is used to store the operating status data, equipment key parameters, maintenance data, and inspection data of local power equipment, and is used to store the metadata information of local video files such as the name of the local video file, the acquisition device information, the upload time and the storage path; the local intelligent algorithm module is used to receive the simplified fault diagnosis and maintenance solution model sent by the industrial cloud server; the local diagnosis module is used to call the simplified fault diagnosis and maintenance solution model of the local intelligent algorithm module to perform fault diagnosis on the power equipment and calculate the diagnosis results and maintenance solutions; the local service encapsulation module is used to encapsulate the user management module, the real-time operating status data of the local power equipment, the real-time equipment key parameters, the real-time maintenance data, the real-time inspection data, the real-time operating condition video, the simplified fault diagnosis and maintenance solution model and the diagnosis results and maintenance solutions of the local intelligent algorithm module into a RESTful API service; The industrial cloud server includes a cloud file system, a cloud database, a cloud intelligent algorithm module, a cloud diagnosis module and a cloud service packaging module; The cloud file system is used to store the historical operating condition video files and historical inspection reports of each local power device; the cloud database is used to store the historical operating status data, historical equipment key parameters, historical maintenance data, historical inspection data of each local power device, and metadata information of historical video files such as the name of the video file, video acquisition device information, video upload time and storage path; The cloud intelligent algorithm module is used to establish a fault diagnosis and maintenance solution model for power equipment based on the historical data of each power equipment, and send the model to the local server after simplifying it according to the model optimization situation; the cloud diagnosis module is used to call the fault diagnosis and maintenance solution model of the cloud intelligent module to perform fault diagnosis on the power equipment and calculate the diagnosis results and maintenance solutions; the cloud service packaging module is used to package the historical operating status data of the power equipment, historical equipment key parameters, historical maintenance data, historical inspection data, historical inspection reports, historical operating condition videos, fault diagnosis and maintenance solution models and the fault diagnosis results and maintenance solutions of the cloud diagnosis module into a RESTful API service; The mobile intelligent terminal includes a user login module, a user information module, a device selection module, a real-time data monitoring module, a historical data monitoring module, an abnormal warning module and a patrol module; The user login module, user information module and real-time data monitoring module all call the API interface of the local service encapsulation module, the historical data monitoring module calls the API interface of the cloud service encapsulation module, and the abnormal warning module and inspection module call the API interfaces of the local service encapsulation module and the cloud service encapsulation module; The user login module is used to implement the login and password modification operations of the mobile intelligent terminal. After successful login, the interface that the user can view is automatically displayed according to the user's authority; The user information module is used to display the user's creation time, permissions, and password modification time; The device selection module is used to select the power equipment to be monitored; The real-time data monitoring module is used to display the real-time operating status data, key operating parameters of the equipment and real-time operating condition video of the selected power equipment; the historical data monitoring module is used to display the historical operating status data, key operating parameters of the equipment, historical operating condition video, historical maintenance records, historical inspection data and historical inspection reports of the selected equipment; the abnormal warning module is used to display the real-time fault diagnosis results and recommended maintenance plans of the selected equipment. If the diagnosis result is abnormal, the abnormal information will be pushed to the relevant personnel. After receiving the abnormal prompt and the recommended maintenance plan, the relevant personnel will comprehensively evaluate and submit abnormal handling opinions. After the abnormal information is processed, the maintenance record will be uploaded to the local server; In the inspection module, the inspectors scan the machine code of each device to display the real-time data of the device, such as the real-time operating status data, real-time key operating parameters, and real-time operating condition videos. They can also display the historical operating status data, historical equipment operating key parameters, historical operating condition videos, historical maintenance records, historical inspection data, historical inspection reports, and the real-time fault diagnosis results and recommended maintenance plans of the device. After completing the inspection, the inspectors select their name and inspection status information, and after submission, the inspection report is automatically generated and sent to the local server.

Images