Off-site inspection early warning method and system of Internet of Things

Abstract

The invention relates to the technical field of power system monitoring, and particularly discloses an off-site inspection early warning method and system of the Internet of Things, and the method comprises the steps: obtaining the monitoring information of power equipment, the monitoring information comprising video monitoring information and infrared monitoring information; extracting environment monitoring type data of the power equipment in the video monitoring information, and preprocessing the environment monitoring type data to obtain an environment inspection type data set; according to the off-site inspection early warning method and system based on the Internet of Things provided by the invention, the real-time monitoring and fault early warning capabilities of the operation state of power equipment are remarkably improved. Firstly, by obtaining video monitoring information and infrared monitoring information, remote and real-time monitoring of power equipment is achieved, and the problems that traditional manual inspection is time-consuming and labor-consuming, low in efficiency and difficult to deal with a large-scale power grid, especially a complex-terrain or remote area are solved.

Description

Technical Field

[0001] The present application relates to the technical field of power system monitoring, and in particular to an off-site inspection and early warning method and system for the Internet of Things. Background Art

[0002] In the power industry, traditional inspection methods mainly rely on manual on-site inspections, which are becoming less and less suitable for modern power system maintenance. With the expansion and complexity of power systems, the limitations of manual inspections are gradually becoming apparent, especially in areas with wide coverage and harsh environments. The efficiency and safety of this method are difficult to meet current needs. In addition, with the advancement of technology, especially the development of 5G communications and artificial intelligence technology, new solutions have been brought to the field of power inspections.

[0003] The existing manual inspection methods are time-consuming and labor-intensive, and it is difficult to quickly respond to the inspection needs of large-scale power grids, especially in areas with complex terrain or in remote areas. Manual inspections require a large amount of human resources, plus transportation, equipment and other costs. The inspection costs increase significantly in bad weather or remote areas. Moreover, they rely on the experience and judgment of inspectors, which can easily lead to missed inspections or false alarms, and lack objectivity and accuracy. Summary of the invention

[0004] The purpose of this application is to provide an off-site inspection and early warning method and system for the Internet of Things to solve the technical problems raised in the above-mentioned background technology.

[0005] To achieve the above objectives, this application provides the following technical solutions: In a first aspect, the present application provides an off-site inspection and early warning method for the Internet of Things, comprising: Acquiring monitoring information of the power equipment, wherein the monitoring information includes video monitoring information and infrared monitoring information; Extracting environmental monitoring type data of the power equipment in the video monitoring information, and preprocessing the environmental monitoring type data to obtain an environmental inspection type data set; Acquire multiple environmental inspection type characteristic data according to the environmental inspection type data set, integrate the multiple environmental inspection type characteristic data to obtain a first integrated line graph, and acquire a first safety reference value according to the first integrated line graph; Acquire the device temperature data corresponding to each environmental inspection type characteristic data according to the infrared monitoring information, integrate each device temperature data to obtain a second integrated line graph, and acquire a second safety reference value according to the second integrated line graph; Acquire a warning assessment value according to the first safety reference value and the second safety reference value; Compare the warning assessment value with the preset value: If the early warning evaluation value is less than or equal to the preset value, it is judged that the power equipment is operating normally; If the warning assessment value is greater than the preset value, the power equipment is judged to be operating abnormally, and a warning signal is generated and sent to the cloud server.

[0006] Preferably, the step of extracting the environmental monitoring type data of the power equipment in the video monitoring information and preprocessing the environmental monitoring type data to obtain an environmental inspection type data set includes: Extracting multiple environmental monitoring type data from the video monitoring information, wherein the environmental monitoring type data includes air temperature value, air humidity value, air smoke concentration value, and equipment noise value; Using a filtering algorithm to remove noise from the plurality of environmental monitoring type data to obtain filtered environmental monitoring type data; Obtaining the timestamp of each filtering environment monitoring type data; Dividing the air temperature value, air humidity value, air smoke concentration value, and equipment noise value according to the timestamp to obtain an air temperature set, an air humidity set, an air smoke set, and an equipment noise set; The air temperature set, air humidity set, air smoke set, and equipment noise set are combined to obtain an environmental inspection type data set.

[0007] Preferably, the step of acquiring a plurality of environmental inspection type characteristic data according to the environmental inspection type data set comprises: Obtaining a first eigenvector of each air temperature set, and constructing a first eigenmatrix according to the plurality of first eigenvectors; Obtaining a first importance scale value of each of the first feature matrices compared with a first preset feature matrix; Obtaining a second eigenvector of each of the air humidity sets, and constructing a second eigenmatrix according to the plurality of second eigenvectors; Obtaining a second importance scale value of each of the second feature matrices compared with a second preset feature matrix; Obtaining a third eigenvector of each of the air smoke sets, and constructing a third eigenmatrix according to a plurality of third eigenvectors; Obtaining a third importance scale value of each of the third feature matrices compared with a third preset feature matrix; Obtaining a fourth eigenvector of each of the device noise sets, and constructing a fourth eigenmatrix according to a plurality of fourth eigenvectors; Obtaining a fourth importance scale value of each of the fourth characteristic matrices compared with a fourth preset characteristic matrix; The first importance scale value, the second importance scale value, the third importance scale value and the fourth importance scale value corresponding to the multiple timestamps are horizontally merged to obtain multiple environmental inspection type feature data.

[0008] Preferably, the step of integrating a plurality of environmental inspection type characteristic data to obtain a first integrated line graph, and obtaining a first safety reference value according to the first integrated line graph comprises: Acquire multiple interception time points according to the timestamp; Acquiring a corresponding first importance scale value, a second importance scale value, a third importance scale value, and a fourth importance scale value based on the intercepted time point; Establishing a line graph corresponding to the first importance scale value, the second importance scale value, the third importance scale value and the fourth importance scale value respectively for the interception time point; Merging the line graphs corresponding to the first importance scale value, the second importance scale value, the third importance scale value, and the fourth importance scale value together to obtain a first integrated line graph; Obtaining slope values ​​corresponding to the first importance scale value, the second importance scale value, the third importance scale value, and the fourth importance scale value at each intercepted time point according to the first integrated line graph; An average value is calculated for the slope value of the first importance scale value, the slope value of the second importance scale value, the slope value of the third importance scale value, and the slope value of the fourth importance scale value, and the average value is used as a first safety reference value.

[0009] Preferably, the step of acquiring the device temperature data corresponding to each environmental inspection type characteristic data according to the infrared monitoring information includes: Acquire multiple temperature values ​​according to the infrared monitoring information; Align each temperature value corresponding to all the timestamps according to the timestamps to obtain a first time table; Aligning each environmental inspection type feature data corresponding to all the timestamps according to the timestamps to obtain a second timetable; Merging the first schedule and the second schedule according to the timestamps to obtain a merged schedule; The device temperature data is obtained from the fused time table based on the timestamp.

[0010] Preferably, the step of obtaining a warning assessment value according to the first safety reference value and the second safety reference value includes: Acquire environmental characteristics of environmental characteristic data corresponding to the first safety reference value, wherein the environmental characteristics include air temperature characteristics, air humidity characteristics, air smoke concentration characteristics, and equipment noise characteristics; Constructing an environment judgment matrix according to the environment characteristics, and obtaining multiple eigenvalues ​​of the environment judgment matrix and corresponding environment feature vectors; Obtaining the maximum environmental feature vector and using it as the recognition vector, and performing normalization processing on the recognition vector to obtain a first weight coefficient; Obtaining a second weight coefficient of the second safety reference value; The early warning evaluation value is calculated according to the first safety reference value, the second safety reference value, the first weight coefficient and the second weight coefficient, wherein the calculation formula is: ; in, represents the warning assessment value, represents the first weight coefficient, Indicates the first safety reference value, represents the second weight coefficient, Indicates the second safety reference value.

[0011] In a second aspect, the present application provides an off-site inspection and early warning system for the Internet of Things, comprising: A first acquisition module is used to acquire monitoring information of the power equipment, wherein the monitoring information includes video monitoring information and infrared monitoring information; A second acquisition module is used to extract the environmental monitoring type data of the power equipment in the video monitoring information, and pre-process the environmental monitoring type data to obtain an environmental inspection type data set; A third acquisition module is used to acquire multiple environmental inspection type characteristic data according to the environmental inspection type data set, integrate the multiple environmental inspection type characteristic data to obtain a first integrated line graph, and acquire a first safety reference value according to the first integrated line graph; a fourth acquisition module, configured to acquire the device temperature data corresponding to each environmental inspection type characteristic data according to the infrared monitoring information, integrate each device temperature data to obtain a second integrated line graph, and acquire a second safety reference value according to the second integrated line graph; A fifth acquisition module, configured to acquire a warning assessment value according to the first safety reference value and the second safety reference value; The judgment module is used to compare the warning evaluation value with the preset value: If the early warning evaluation value is less than or equal to the preset value, it is judged that the power equipment is operating normally; If the warning assessment value is greater than the preset value, the power equipment is judged to be operating abnormally, and a warning signal is generated and sent to the cloud server.

[0012] Preferably, the second acquisition module includes: A first acquisition unit is used to extract multiple environmental monitoring type data from the video monitoring information, wherein the environmental monitoring type data includes air temperature value, air humidity value, air smoke concentration value, and equipment noise value; A second acquisition unit is used to remove noise from the plurality of environmental monitoring type data through a filtering algorithm to obtain filtered environmental monitoring type data; A third acquisition unit, used to acquire the timestamp of each filtering environment monitoring type data; a fourth acquisition unit, configured to divide the air temperature value, the air humidity value, the air smoke concentration value, and the equipment noise value according to the timestamp to obtain an air temperature set, an air humidity set, an air smoke set, and an equipment noise set; The fifth acquisition unit is used to collect the air temperature set, the air humidity set, the air smoke set, and the equipment noise set to obtain an environmental inspection type data set.

[0013] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described in the first aspect when executing the computer program.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described in the first aspect above.

[0015] Compared with related technologies, the off-site inspection and early warning method and system based on the Internet of Things provided by this application aims to improve the real-time monitoring and fault early warning capabilities of power equipment, and has at least the following technical effects: By collecting video and infrared monitoring information, remote and real-time monitoring is achieved, overcoming the limitations of traditional manual inspections. A filtering algorithm is used to preprocess video monitoring data to reduce noise and improve accuracy. A feature matrix is ​​constructed and the importance scale value is calculated to form the first integrated line graph, which intuitively displays the changes in environmental impact. Combined with the temperature data obtained by infrared monitoring, a second integrated line graph is established to comprehensively evaluate the working conditions of the equipment. A reasonable evaluation model is set up to calculate the early warning evaluation value, comprehensively consider environmental and temperature factors, and detect potential faults in advance. The early warning threshold is set. When the evaluation value exceeds the standard, an early warning signal is automatically sent to the cloud server to achieve early warning of faults and ensure the safe and stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of an off-site inspection and early warning method for the Internet of Things shown in one embodiment of the present application.

[0017] Figure 2A block diagram of an off-site inspection and early warning system for the Internet of Things shown in one embodiment of the present application.

[0018] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0020] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0021] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0022] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantity limitation, and may indicate the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0023] In the related art, the inspection of power equipment mainly relies on manual labor, which is not only time-consuming and labor-intensive, but also difficult to implement when facing large-scale power grids, especially in areas with complex terrain or remote areas. In addition, during the use of existing inspection methods, complex terrain will form complex weather, and power equipment is easily affected by the weather. Therefore, the existing inspection methods are prone to false alarms, and it is difficult to respond quickly when subsequent power equipment fails, which cannot meet the requirements of modern power systems for efficiency and reliability.

[0024] Based on the above situation, the embodiment of the present application provides an off-site inspection and early warning method and system for the Internet of Things, which is described in detail below in conjunction with specific embodiments and drawings.

[0025] Example 1 Embodiment 1 of the present application provides an off-site inspection and early warning method for the Internet of Things. Figure 1 This is a flow chart of an off-site inspection and early warning method of the Internet of Things shown in an embodiment of the present application. Figure 1 As shown, the off-site inspection and early warning method of the Internet of Things includes: S1. Acquire monitoring information of power equipment, wherein the monitoring information includes video monitoring information and infrared monitoring information; S2, extracting the environmental monitoring type data of the power equipment in the video monitoring information, and preprocessing the environmental monitoring type data to obtain an environmental inspection type data set; S3. Acquire multiple environmental inspection type characteristic data according to the environmental inspection type data set, integrate the multiple environmental inspection type characteristic data to obtain a first integrated line graph, and acquire a first safety reference value according to the first integrated line graph; S4. Obtaining device temperature data corresponding to each environmental inspection type characteristic data according to the infrared monitoring information, integrating each device temperature data to obtain a second integrated line graph, and obtaining a second safety reference value according to the second integrated line graph; S5. Obtaining a warning assessment value according to the first safety reference value and the second safety reference value; S6. Compare the warning assessment value with the preset value: If the early warning evaluation value is less than or equal to the preset value, it is judged that the power equipment is operating normally; If the warning assessment value is greater than the preset value, the power equipment is judged to be operating abnormally, and a warning signal is generated and sent to the cloud server.

[0026] Refer to the attached Figure 1 As described in the above steps S1-S6, the present application can realize remote and real-time monitoring of power equipment by acquiring video monitoring information and infrared monitoring information. Then, by extracting and preprocessing the environmental monitoring type data (such as air temperature, humidity, smoke concentration, equipment noise) in the video monitoring information, the noise can be effectively removed, and the accuracy and reliability of the data can be improved. It is used to solve the problem of misjudgment caused by a large amount of noise and interference information that may be contained in the video monitoring information. By constructing a feature matrix and calculating the importance scale value, the impact of different environmental factors on power equipment can be quantified.

[0027] The first integrated line graph can intuitively show the changing trend of these influences, helping operation and maintenance personnel to more accurately judge the operating status of the equipment. By comprehensively analyzing multiple environmental factors, the status of the equipment can be more accurately evaluated, equipment failures caused by environmental changes can be reduced, and the safety and reliability of the system can be improved. Equipment temperature is one of the important indicators reflecting the operating status of power equipment. The equipment temperature data is obtained through infrared monitoring information, and combined with the characteristic data of environmental inspection types, the working conditions of power equipment can be more comprehensively evaluated. The second integrated line graph and the second safety reference value can more accurately reflect the actual operating status of the equipment, providing a reliable basis for fault diagnosis and prevention. The early warning evaluation value combines environmental factors and equipment temperature data, and can more comprehensively evaluate the health status of power equipment. By setting a reasonable evaluation model, potential faults can be discovered in advance, and timely measures can be taken to avoid accidents, thereby improving the safety and reliability of the system. By setting the early warning threshold, when the early warning evaluation value exceeds the preset value, the system will automatically determine that the power equipment is operating abnormally, and generate an early warning signal to send to the cloud server. This achieves early warning of faults, and operation and maintenance personnel can quickly take measures for maintenance to reduce the impact of faults on the power system.

[0028] In one embodiment, the step of extracting the environmental monitoring type data of the power equipment in the video monitoring information and preprocessing the environmental monitoring type data to obtain an environmental inspection type data set includes: S201, extracting a plurality of environmental monitoring type data from the video monitoring information, wherein the environmental monitoring type data includes air temperature value, air humidity value, air smoke concentration value, and equipment noise value; S202, removing noise from the plurality of environmental monitoring type data through a filtering algorithm to obtain filtered environmental monitoring type data; S203, obtaining the timestamp of each filtering environment monitoring type data; S204, dividing the air temperature value, air humidity value, air smoke concentration value, and device noise value according to the timestamp to obtain an air temperature set, an air humidity set, an air smoke set, and a device noise set; S205 , the air temperature set, the air humidity set, the air smoke set, and the equipment noise set are aggregated to obtain an environmental inspection type data set.

[0029] As described in the above steps S201-S205, the present application can fully understand the various aspects of the environment around the power equipment, including air temperature, humidity, smoke concentration and equipment noise, by extracting multiple environmental monitoring type data from the video monitoring information, which solves the problem that the traditional inspection method only relies on a single data source (such as equipment temperature) and cannot fully reflect the complexity of the equipment operating environment. Through multi-dimensional data collection, the operating conditions of the equipment can be more comprehensively understood, and the misjudgment or missed detection caused by environmental factors can be reduced. After that, the filtering algorithm is used to remove noise, which can improve the quality and reliability of the data. The filtered data is smoother, reducing the fluctuations caused by external interference or sensor errors, making subsequent data analysis more accurate and reliable, and solving the noise interference problem that may exist in the original data. These noises will seriously affect the accuracy of data analysis. Through filtering processing, irrelevant interference signals can be eliminated and useful information can be retained, thereby improving the credibility of the data and the accuracy of the analysis results; then adding a timestamp to each filtered environmental monitoring type data can ensure the time consistency of the data. The introduction of timestamps gives the data a time dimension, which is convenient for subsequent time series analysis and data alignment, helps to more accurately track and analyze the changes in the operating status of the equipment, solves the problems of data disorder and time inconsistency, and ensures the time alignment of different types of environmental monitoring data. Then, different types of data are divided by timestamps to form multiple independent data sets, each of which contains a certain type of environmental monitoring data in the same time period. This division method is helpful for subsequent data processing and analysis, making the changing trend of each environmental factor clearer, and solving the problem of data being mixed together and difficult to analyze in the prior art. By dividing by timestamp, different types of environmental monitoring data can be processed separately, avoiding mutual interference between data. Finally, different types of environmental monitoring data are collected to form a comprehensive environmental inspection type data set. This comprehensive data set contains complete information on multiple environmental factors, providing a basis for subsequent multi-dimensional analysis and comprehensive evaluation.

[0030] In one embodiment, the step of acquiring a plurality of environmental inspection type characteristic data according to the environmental inspection type data set includes: S301, obtaining a first eigenvector of each air temperature set, and constructing a first eigenmatrix according to a plurality of first eigenvectors; S302, obtaining a first importance scale value of each of the first feature matrices compared with a first preset feature matrix; S303, obtaining a second eigenvector of each of the air humidity sets, and constructing a second eigenmatrix according to the plurality of second eigenvectors; S304, obtaining a second importance scale value of each of the second feature matrices compared with a second preset feature matrix; S305, obtaining a third eigenvector of each of the air smoke sets, and constructing a third eigenmatrix according to a plurality of third eigenvectors; S306, obtaining a third importance scale value of each of the third feature matrices compared with a third preset feature matrix; S307, obtaining a fourth eigenvector of each of the device noise sets, and constructing a fourth eigenmatrix according to the plurality of fourth eigenvectors; S308, obtaining a fourth importance scale value of each of the fourth characteristic matrices compared with a fourth preset characteristic matrix; S309: horizontally merge the first importance scale value, the second importance scale value, the third importance scale value and the fourth importance scale value corresponding to the multiple timestamps to obtain multiple environmental inspection type feature data.

[0031] As described in the above steps S301-S309, the present application can convert complex temperature data into a structured form by obtaining the first eigenvector of each air temperature set and constructing a first eigenmatrix, thereby solving the problem that the original temperature data is difficult to analyze directly. Then, by comparing the first eigenmatrix with the preset eigenmatrix, the difference between the current temperature data and the standard state can be quantified. The first importance scale value reflects the degree of influence of temperature change on the operating state of the equipment, solving the problem that the influence of temperature data change on the equipment is difficult to quantify. Then, by obtaining the second eigenvector of each air humidity set and constructing the second eigenmatrix, the humidity data can be converted into a structured form, solving the problem that the original humidity data is difficult to analyze directly. Through the construction of eigenvectors and eigenmatrix, the complex changes of humidity data can be simplified into an operational form, improving the efficiency and accuracy of data processing. By comparing the second eigenmatrix with the preset eigenmatrix, the difference between the current humidity data and the standard state can be quantified. Then, by obtaining the third eigenvector of each air smoke set and constructing the third eigenmatrix, the smoke data can be converted into a structured form. By comparing the third eigenmatrix with the preset eigenmatrix, the difference between the current smoke data and the standard state can be quantified. The third importance scale value reflects the degree of influence of smoke changes on the operating status of the equipment. Then, the fourth eigenvector of each of the equipment noise sets is obtained and the fourth eigenmatrix is ​​constructed, so that the noise data can be converted into a structured form. This structured data is convenient for subsequent analysis and processing, and helps to extract the key features of noise changes. By comparing the fourth eigenmatrix with the preset eigenmatrix, the difference between the current noise data and the standard state can be quantified. The fourth importance scale value reflects the degree of influence of noise changes on the operating status of the equipment. By horizontally merging the importance scale values ​​of different environmental factors, a comprehensive environmental inspection type feature data set can be formed, which solves the problem of incomplete information in a single data set. By integrating multiple data sets, the various aspects of the equipment operating environment can be fully reflected.

[0032] In one embodiment, the step of integrating multiple environmental inspection type feature data to obtain a first integrated line graph, and obtaining a first safety reference value according to the first integrated line graph includes: S310, acquiring multiple interception time points according to the timestamp; S311, acquiring a corresponding first importance scale value, a second importance scale value, a third importance scale value, and a fourth importance scale value based on the interception time point; S312, establishing a line graph corresponding to the first importance scale value, the second importance scale value, the third importance scale value and the fourth importance scale value respectively at the interception time point; S313, merging the line graphs corresponding to the first importance scale value, the second importance scale value, the third importance scale value, and the fourth importance scale value together to obtain a first integrated line graph; S314, obtaining slope values ​​corresponding to the first importance scale value, the second importance scale value, the third importance scale value, and the fourth importance scale value of each interception time point according to the first integrated line graph; S315: Calculate an average value of the slope value of the first importance scale value, the slope value of the second importance scale value, the slope value of the third importance scale value, and the slope value of the fourth importance scale value, and use the average value as a first safety reference value.

[0033] As described in the above steps S310-S315, the present application can ensure the time consistency of the data by obtaining multiple interception time points according to the timestamp, which is convenient for subsequent time series analysis. The selection of these time points can cover different stages of equipment operation, which is helpful to comprehensively evaluate the state changes of the equipment in different time periods, and ensure the time alignment of different types of environmental monitoring data. After that, by obtaining the importance scale value of each environmental factor based on the interception time point, the environmental data at different time points can be compared and analyzed. These scale values ​​reflect the degree of influence of each environmental factor on the equipment operation state at different time points, and solve the problem that the data of a single time point is difficult to fully reflect the equipment operation state. Through the acquisition of data at multiple time points, the environmental changes of the equipment in different time periods can be more comprehensively understood. By establishing a line graph, the change trend of the importance scale value of each environmental factor over time can be intuitively displayed. Then, by fusing multiple line graphs together to form a first integrated line graph, the change trend of each environmental factor can be fully displayed. By calculating the slope value of the importance scale value at each time point, the change rate of each environmental factor can be quantified. The slope value reflects the changing trend of environmental factors over time. By calculating the average of the slope values ​​of various environmental factors, a comprehensive safety reference value can be obtained, which solves the limitation of single environmental factor assessment. By combining the slope values ​​of multiple environmental factors, the operating status of the equipment can be more comprehensively assessed, the misjudgment caused by a single factor can be reduced, and the accuracy and reliability of the assessment can be improved.

[0034] In one embodiment, the step of obtaining the device temperature data corresponding to each environmental inspection type characteristic data according to the infrared monitoring information includes: S401, acquiring multiple temperature values ​​according to the infrared monitoring information; S402, aligning each temperature value corresponding to all the timestamps according to the timestamps to obtain a first time table; S403, aligning each environmental inspection type characteristic data corresponding to all the timestamps according to the timestamps to obtain a second time table; S404, merging the first schedule and the second schedule according to the timestamps to obtain a fused schedule; S405 . Obtain device temperature data from the fusion schedule based on the timestamp.

[0035] As described in the above steps S401-S405, the present application obtains multiple temperature values ​​through infrared monitoring information, which can reflect the temperature distribution on the surface of the power equipment in real time and accurately. Infrared thermal imaging technology has the advantages of non-contact measurement, high resolution and real-time monitoring, and can timely detect the temperature anomaly of the equipment. Then, by aligning the temperature values ​​corresponding to all timestamps to form a first timetable, the continuity and consistency of the temperature data in time can be ensured, the problem of inconsistent temperature data time can be solved, and the orderliness and comparability of the data can be ensured. By aligning the timestamps, the time characteristics of temperature changes can be more accurately analyzed, potential anomalies and trends can be found, and the efficiency and accuracy of data processing can be improved. By aligning the environmental inspection type feature data corresponding to all timestamps to form a second timetable, the continuity and consistency of environmental data in time can be ensured. This helps the subsequent time series analysis and facilitates the tracking of trends and laws of environmental changes. By fusing the first timetable and the second timetable according to the timestamps to form a fusion timetable, the temperature data and environmental data can be combined to form a comprehensive data set. This comprehensive data set helps to comprehensively evaluate the operating status of the equipment and solves the problem of incomplete information from a single data source. By fusing temperature data and environmental data, we can fully reflect the various aspects of the equipment operating environment. Finally, by extracting equipment temperature data from the fusion schedule based on timestamps, we can ensure the time consistency of temperature data and environmental data, solve the problem of time inconsistency between temperature data and environmental data, and ensure the orderliness and comparability of data. By aligning timestamps, we can accurately extract temperature data from the fusion schedule, discover the relationship between temperature changes and environmental factors, and improve the efficiency and accuracy of data processing.

[0036] In one embodiment, the step of obtaining a warning assessment value according to the first safety reference value and the second safety reference value includes: S501, obtaining environmental characteristics of environmental characteristic data corresponding to the first safety reference value, wherein the environmental characteristics include air temperature characteristics, air humidity characteristics, air smoke concentration characteristics, and equipment noise characteristics; S502, constructing an environment judgment matrix according to the environment characteristics, and obtaining multiple eigenvalues ​​of the environment judgment matrix and corresponding environment feature vectors; S503, obtaining the maximum environmental feature vector, using it as the recognition vector, and normalizing the recognition vector to obtain a first weight coefficient; S504, obtaining a second weight coefficient of the second safety reference value; S505: Calculate a warning assessment value according to the first safety reference value, the second safety reference value, the first weight coefficient, and the second weight coefficient, wherein the calculation formula is: ; in, represents the warning assessment value, represents the first weight coefficient, Indicates the first safety reference value, represents the second weight coefficient, Indicates the second safety reference value.

[0037] As described in the above steps S501-S505, the present application can obtain detailed information about the operating status of the equipment under different environmental conditions by acquiring environmental characteristic data corresponding to the first safety reference value. These environmental characteristics include air temperature, air humidity, air smoke concentration, equipment noise, etc., which solves the problem that a single environmental characteristic data is difficult to fully reflect the operating status of the equipment. By acquiring a variety of environmental characteristic data, it is possible to have a more comprehensive understanding of the performance of the equipment under different environmental conditions, reduce misjudgments caused by a single factor, and improve the comprehensiveness and accuracy of the evaluation. After that, by constructing an environmental judgment matrix, different environmental characteristic data can be structured to form a comprehensive data model. The eigenvalues ​​and eigenvectors of the environmental judgment matrix reflect the degree of influence of different environmental characteristics on the operating status of the equipment, solving the problem that environmental characteristic data are difficult to comprehensively analyze. By constructing an environmental judgment matrix, multiple environmental feature data can be integrated together to form a unified model, which is convenient for subsequent mathematical analysis and processing, and improves the accuracy and reliability of the evaluation. By selecting the maximum environmental feature vector and normalizing it, the importance of each environmental feature on the operating status of the equipment can be determined. Among them, the key vector is the characteristic value extracted from the environmental monitoring data, which is used to represent the impact of different environmental factors (such as temperature, humidity, smoke concentration and noise) on the operating status of power equipment. These characteristic values ​​are calculated and compared to select the most important one, and then standardized, and finally used to evaluate the health status of the equipment and predict potential failures. In short, the key vector helps us understand the impact of environmental changes on the equipment more accurately, so as to discover and solve problems in advance. The first weight coefficient reflects the relative importance of different environmental characteristics in the comprehensive evaluation, which solves the problem of uneven weight distribution between different environmental characteristics. By selecting the maximum environmental feature vector and performing normalization processing, it is possible to ensure that each environmental feature is reasonably weighted in the comprehensive evaluation, thereby improving the scientificity and accuracy of the evaluation. By obtaining the second weight coefficient of the second safety reference value, the importance of the device temperature data in the comprehensive evaluation can be quantified (by obtaining the device temperature data and using it as the device temperature identification vector, and performing normalization processing on the device temperature identification vector to obtain the second weight coefficient). The second weight coefficient reflects the degree of influence of the device temperature on the device operating state, and solves the problem of unclear weight of the device temperature data in the comprehensive evaluation. By comprehensively considering the first safety reference value, the second safety reference value, the first weight coefficient and the second weight coefficient, the early warning evaluation value can be calculated. The early warning evaluation value combines the influence of environmental characteristics and device temperature, and can more comprehensively evaluate the operating state of the device. Through the above calculation formula, the influence of environmental characteristics and device temperature can be combined to obtain a comprehensive early warning evaluation value. This evaluation value can comprehensively reflect the operating state of the device.

[0038] Example 2

[0039] Embodiment 2 of the present application provides an off-site inspection and early warning system for the Internet of Things, Figure 2 This is a block diagram of an off-site inspection and early warning system for the Internet of Things according to an embodiment of the present application. Figure 2 As shown, the off-site inspection and early warning system of the Internet of Things includes: The first acquisition module 1 is used to acquire monitoring information of the power equipment, wherein the monitoring information includes video monitoring information and infrared monitoring information; The second acquisition module 2 is used to extract the environmental monitoring type data of the power equipment in the video monitoring information, and pre-process the environmental monitoring type data to obtain an environmental inspection type data set; A third acquisition module 3 is used to acquire multiple environmental inspection type characteristic data according to the environmental inspection type data set, and integrate the multiple environmental inspection type characteristic data to obtain a first integrated line graph, and acquire a first safety reference value according to the first integrated line graph; The fourth acquisition module 4 is used to obtain the device temperature data corresponding to each environmental inspection type characteristic data according to the infrared monitoring information, and to integrate each device temperature data to obtain a second integrated line graph, and to obtain a second safety reference value according to the second integrated line graph; A fifth acquisition module 5, configured to acquire a warning assessment value according to the first safety reference value and the second safety reference value; The judgment module 6 is used to compare the early warning evaluation value with the preset value: If the early warning evaluation value is less than or equal to the preset value, it is judged that the power equipment is operating normally; If the warning assessment value is greater than the preset value, the power equipment is judged to be operating abnormally, and a warning signal is generated and sent to the cloud server.

[0040] The second acquisition module 2 includes: A first acquisition unit 2-1 is used to extract multiple environmental monitoring type data from the video monitoring information, wherein the environmental monitoring type data includes air temperature value, air humidity value, air smoke concentration value, and equipment noise value; A second acquisition unit 2-2 is used to remove noise from the plurality of environmental monitoring type data through a filtering algorithm to obtain filtered environmental monitoring type data; The third acquisition unit 2-3 is used to obtain the timestamp of each filtering environment monitoring type data; A fourth acquisition unit 2-4 is used to divide the air temperature value, the air humidity value, the air smoke concentration value, and the equipment noise value according to the timestamp to obtain an air temperature set, an air humidity set, an air smoke set, and an equipment noise set; The fifth acquisition unit 2-5 is used to collect the air temperature set, the air humidity set, the air smoke set, and the equipment noise set to obtain an environmental inspection type data set.

[0041] Example 3

[0042] Embodiment 3 of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the off-site inspection and early warning method of the Internet of Things provided in Embodiment 1 are implemented.

[0043] In a possible implementation manner, the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the off-site inspection and early warning method of the Internet of Things provided in Example 1 are implemented.

[0044] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0045] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0046] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. An off-site inspection and early warning method for the Internet of Things, characterized in that: include: Acquiring monitoring information of the power equipment, wherein the monitoring information includes video monitoring information and infrared monitoring information; Extracting environmental monitoring type data of the power equipment in the video monitoring information, and preprocessing the environmental monitoring type data to obtain an environmental inspection type data set; Acquire multiple environmental inspection type characteristic data according to the environmental inspection type data set, integrate the multiple environmental inspection type characteristic data to obtain a first integrated line graph, and acquire a first safety reference value according to the first integrated line graph; Acquire the device temperature data corresponding to each environmental inspection type characteristic data according to the infrared monitoring information, integrate each device temperature data to obtain a second integrated line graph, and acquire a second safety reference value according to the second integrated line graph; Acquire a warning assessment value according to the first safety reference value and the second safety reference value; Compare the warning assessment value with the preset value: If the early warning evaluation value is less than or equal to the preset value, it is judged that the power equipment is operating normally; If the warning assessment value is greater than the preset value, the power equipment is judged to be operating abnormally, and a warning signal is generated and sent to the cloud server.

2. According to claim 1, the off-site inspection and early warning method of the Internet of Things is characterized in that: The step of extracting the environmental monitoring type data of the power equipment in the video monitoring information and preprocessing the environmental monitoring type data to obtain an environmental inspection type data set includes: Extracting a plurality of environmental monitoring type data from the video monitoring information, wherein the environmental monitoring type data includes an air temperature value, an air humidity value, an air smoke concentration value, and an equipment noise value; Using a filtering algorithm to remove noise from the plurality of environmental monitoring type data to obtain filtered environmental monitoring type data; Obtaining the timestamp of each filtering environment monitoring type data; Dividing the air temperature value, air humidity value, air smoke concentration value and equipment noise value according to the timestamp to obtain an air temperature set, an air humidity set, an air smoke set and an equipment noise set; The air temperature set, the air humidity set, the air smoke set and the equipment noise set are combined to obtain an environmental inspection type data set.

3. The off-site inspection and early warning method of the Internet of Things according to claim 2 is characterized in that: The step of acquiring a plurality of environmental inspection type characteristic data according to the environmental inspection type data set comprises: Obtaining a first eigenvector of each air temperature set, and constructing a first eigenmatrix according to the plurality of first eigenvectors; Obtaining a first importance scale value of each of the first feature matrices compared with a first preset feature matrix; Obtaining a second eigenvector of each of the air humidity sets, and constructing a second eigenmatrix according to the plurality of second eigenvectors; Obtaining a second importance scale value of each of the second feature matrices compared with a second preset feature matrix; Obtaining a third eigenvector of each of the air smoke sets, and constructing a third eigenmatrix according to a plurality of third eigenvectors; Obtaining a third importance scale value of each of the third feature matrices compared with a third preset feature matrix; Obtaining a fourth eigenvector of each of the device noise sets, and constructing a fourth eigenmatrix according to a plurality of fourth eigenvectors; Obtaining a fourth importance scale value of each of the fourth characteristic matrices compared with a fourth preset characteristic matrix; The first importance scale value, the second importance scale value, the third importance scale value and the fourth importance scale value corresponding to the multiple timestamps are horizontally merged to obtain multiple environmental inspection type feature data.

4. The off-site inspection and early warning method of the Internet of Things according to claim 3 is characterized in that: The step of integrating the plurality of environmental inspection type characteristic data to obtain a first integrated line graph, and obtaining a first safety reference value according to the first integrated line graph comprises: Acquire multiple interception time points according to the timestamp; Acquiring a corresponding first importance scale value, a second importance scale value, a third importance scale value, and a fourth importance scale value based on the intercepted time point; Establishing a line graph corresponding to the first importance scale value, the second importance scale value, the third importance scale value and the fourth importance scale value respectively for the interception time point; Merging the line graphs corresponding to the first importance scale value, the second importance scale value, the third importance scale value, and the fourth importance scale value together to obtain a first integrated line graph; Obtaining slope values ​​corresponding to the first importance scale value, the second importance scale value, the third importance scale value, and the fourth importance scale value at each intercepted time point according to the first integrated line graph; An average value is calculated for the slope value of the first importance scale value, the slope value of the second importance scale value, the slope value of the third importance scale value, and the slope value of the fourth importance scale value, and the average value is used as a first safety reference value.

5. The off-site inspection and early warning method of the Internet of Things according to claim 2 is characterized in that: The step of obtaining the device temperature data corresponding to each environmental inspection type characteristic data according to the infrared monitoring information includes: Acquire multiple temperature values ​​according to the infrared monitoring information; Align each temperature value corresponding to all the timestamps according to the timestamps to obtain a first time table; Aligning each environmental inspection type feature data corresponding to all the timestamps according to the timestamps to obtain a second timetable; Merging the first schedule and the second schedule according to the timestamps to obtain a merged schedule; The device temperature data is obtained from the fused time table based on the timestamp.

6. The off-site inspection and early warning method of the Internet of Things according to claim 1 is characterized in that: The step of obtaining a warning assessment value according to the first safety reference value and the second safety reference value comprises: Acquire environmental characteristics of environmental characteristic data corresponding to the first safety reference value, wherein the environmental characteristics include air temperature characteristics, air humidity characteristics, air smoke concentration characteristics, and equipment noise characteristics; Constructing an environment judgment matrix according to the environment characteristics, and obtaining multiple eigenvalues ​​of the environment judgment matrix and corresponding environment feature vectors; Obtaining the maximum environmental feature vector and using it as the recognition vector, and performing normalization processing on the recognition vector to obtain a first weight coefficient; Obtaining a second weight coefficient of the second safety reference value; The early warning evaluation value is calculated according to the first safety reference value, the second safety reference value, the first weight coefficient and the second weight coefficient, wherein the calculation formula is: ； In the formula, represents the warning assessment value, represents the first weight coefficient, Indicates the first safety reference value, represents the second weight coefficient, Indicates the second safety reference value.

7. An off-site inspection and early warning system for the Internet of Things, characterized in that: include: A first acquisition module is used to acquire monitoring information of the power equipment, wherein the monitoring information includes video monitoring information and infrared monitoring information; A second acquisition module is used to extract the environmental monitoring type data of the power equipment in the video monitoring information, and pre-process the environmental monitoring type data to obtain an environmental inspection type data set; A third acquisition module is used to acquire multiple environmental inspection type characteristic data according to the environmental inspection type data set, integrate the multiple environmental inspection type characteristic data to obtain a first integrated line graph, and acquire a first safety reference value according to the first integrated line graph; a fourth acquisition module, configured to acquire the device temperature data corresponding to each environmental inspection type characteristic data according to the infrared monitoring information, integrate each device temperature data to obtain a second integrated line graph, and acquire a second safety reference value according to the second integrated line graph; A fifth acquisition module, configured to acquire a warning assessment value according to the first safety reference value and the second safety reference value; The judgment module is used to compare the warning evaluation value with the preset value: If the early warning evaluation value is less than or equal to the preset value, it is judged that the power equipment is operating normally; If the warning assessment value is greater than the preset value, the power equipment is judged to be operating abnormally, and a warning signal is generated and sent to the cloud server.

8. The off-site inspection and early warning system of the Internet of Things according to claim 7 is characterized in that: The second acquisition module includes: A first acquisition unit is used to extract multiple environmental monitoring type data from the video monitoring information, wherein the environmental monitoring type data includes air temperature value, air humidity value, air smoke concentration value, and equipment noise value; A second acquisition unit is used to remove noise from the plurality of environmental monitoring type data through a filtering algorithm to obtain filtered environmental monitoring type data; A third acquisition unit, used to acquire the timestamp of each filtering environment monitoring type data; a fourth acquisition unit, configured to divide the air temperature value, the air humidity value, the air smoke concentration value, and the equipment noise value according to the timestamp to obtain an air temperature set, an air humidity set, an air smoke set, and an equipment noise set; The fifth acquisition unit is used to collect the air temperature set, the air humidity set, the air smoke set, and the equipment noise set to obtain an environmental inspection type data set.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images