Plug-in terminal intelligent monitoring system

Abstract

The present invention provides a plug-in terminal intelligent monitoring system, which relates to the plug-in terminal monitoring technology field. The present invention constructs a comprehensive and real-time intelligent monitoring system by integrating multiple monitoring means such as resistance sensing, stress sensing, environmental monitoring and infrared image analysis. The system can automatically collect and process the resistance data, stress data, environmental data and infrared images of the plug-in terminal, and through advanced data processing and analysis technology, quickly and accurately evaluate the operating status of the terminal and generate an early warning signal. Compared with traditional monitoring methods, this solution significantly improves the comprehensiveness and real-time nature of monitoring, can timely discover and warn of potential faults and risks, effectively prevent the occurrence of equipment failures and safety accidents, improve the reliability and safety of the system, and meet the needs of modern industry for intelligent and automated monitoring.

Description

Technical Field

[0001] The invention relates to the technical field of pluggable terminal monitoring, in particular to a pluggable terminal intelligent monitoring system. Background Art

[0002] In modern industrial and power systems, plug-in terminals are widely used for electrical connections, and their reliability and safety are crucial to the stable operation of the entire system. However, due to environmental factors, mechanical stress, and changes in electrical loads, plug-in terminals may have problems such as poor contact and abnormal temperature rise. If these problems are not discovered and handled in time, they may cause equipment failure or even safety accidents. Traditional monitoring methods usually rely on manual inspections or monitoring of a single parameter, which cannot fully and real-time reflect the operating status of the terminal. They are still in the stage of analyzing real-time measurement data. When an alarm is issued, the fault has already occurred. It is a passive detection method that is difficult to meet the needs of modern industry for efficient and intelligent monitoring.

[0003] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0004] The purpose of the present invention is to provide a plug-in terminal intelligent monitoring system to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] Plug-in terminal intelligent monitoring system, including:

[0007] A data acquisition module, which is communicatively connected with the data processing module, comprises a resistance sensing unit, a stress sensing unit and an environment sensing unit, and is used to respectively collect resistance data, stress data and environment data of each group of plug-in terminals, and send the resistance data, stress data and environment data to the data processing module;

[0008] An image acquisition module, which is communicatively connected with the image processing module and is used to acquire infrared images of each group of plug-in terminals and send the infrared images to the image processing module;

[0009] A data processing module, the data processing module is communicatively connected with the comprehensive processing module, and is used to generate a first warning coefficient according to the resistance data, stress data, and environmental data of each group of plug-in terminals, and send the first warning coefficient to the comprehensive processing module;

[0010] An image processing module, which is in communication with the comprehensive processing module and is used to divide the infrared image into regions, perform temperature detection on different regions, generate a second warning coefficient according to the detection result and send it to the comprehensive processing module;

[0011] A comprehensive processing module, the comprehensive processing module is connected to the monitoring platform for performing weighted processing on the first warning coefficient and the second warning coefficient to generate a comprehensive warning coefficient, and sending the comprehensive warning coefficient to the monitoring platform;

[0012] A monitoring platform, which is in communication with the alarm module and is used to display the comprehensive warning coefficient of each group of plug-in terminals, generate an alarm signal according to the size of the comprehensive warning coefficient and send it to the alarm module;

[0013] An alarm module is used to issue an audible and visual alarm according to a received alarm signal.

[0014] Preferably, the resistance sensing unit is a contact resistance sensor, and the resistance data is contact resistance data; the stress sensing unit is a strain gauge sensor; the environment sensing unit includes a temperature sensor and a humidity sensor, and the environment data includes environment temperature data and environment humidity data.

[0015] Preferably, the generation logic of the first warning coefficient and the second warning coefficient is:

[0016] All data collected after the plug-in terminal works normally continuously for T time are read to obtain resistance data, stress data, and environmental data of each group of plug-in terminals within T time, and N frames of infrared images of the plug-in terminal are collected at intervals of time t within T time;

[0017] According to the environmental data corresponding to each group of plug-in terminals, the resistance data and stress data are respectively corrected to reduce the impact of ambient temperature and humidity on the resistance data and stress data. The infrared image is converted into grayscale and divided into regions, and the temperature change is reflected according to the grayscale difference in each region.

[0018] A time series prediction model is constructed to analyze the corrected resistance data and stress data, and then a linear regression model is constructed to analyze the grayscale difference in each area of ​​the infrared image to generate a prediction model at time point T. mb The first warning coefficient is generated according to the predicted resistance data and stress data, and the second warning coefficient is generated according to the grayscale difference in each area of ​​the infrared image.

[0019] Preferably, the resistance data is corrected according to the ambient humidity data in the environmental data, and the calculation method is:

[0020]

[0021] Where Rjc i Represents the corrected contact resistance data, V i Indicates the contact voltage, I i Indicates the contact current, K h represents the environmental humidity data, a represents the first correction coefficient, and the subscript i represents the data number, i=1, 2, 3, ..., M;

[0022] The stress data is corrected according to the ambient temperature data in the environmental data. The calculation method is:

[0023]

[0024] Where Ryb i Indicates the resistance of the strain gauge in the strain gauge sensor, K T represents the temperature coefficient of the strain gauge, T h represents the ambient temperature data, T0 represents the reference temperature of the strain gauge, R0 represents the reference resistance of the strain gauge, and k represents the sensitivity coefficient of the strain gauge;

[0025] All the resistance data Rjc within T time i and stress data F i Divide into set A and set B respectively, calculate the mean and standard deviation of set A and set S respectively, the calculation method is:

[0026]

[0027]

[0028] In the formula Represent the means of set A and set B respectively, σ1 and σ2 represent the standard deviations of set A and set B respectively;

[0029] when , the data set is considered abnormal, and the data set is removed from set A, and the mean is used Replace the group of data to optimize the set A;

[0030] when , the data set is considered abnormal and is removed from set B. Replace this group of data to optimize set B;

[0031] Where μ represents the preset fluctuation coefficient;

[0032] Based on the optimized set A and set B, a time series prediction model is constructed to predict the time at the time point Tmb The predicted resistance data and stress data are calibrated as Rjc' and F', and the first warning coefficient is generated according to Rjc' and F' The calculation method is:

[0033]

[0034] Where Rjc max 、Rjc min Respectively represent the maximum and minimum values ​​in set A, F max 、F min They represent the maximum and minimum values ​​in set B respectively, β1 and β2 represent the resistance weight and stress weight respectively, β1, β2∈[0,1] and β1+β2=1.

[0035] Preferably, after grayscale conversion of the infrared image, the image is divided into X*Y regions in the horizontal and vertical directions, and the grayscale mean of each region in the image is calculated and calibrated as The subscripts (x, y) represent the horizontal and vertical coordinates of the region, respectively, and the superscript j represents the image number, j = 1, 2, 3, ..., N;

[0036] Calculate the grayscale difference of each area between two adjacent infrared images The calculation method is:

[0037]

[0038] If starting from the nth frame, the grayscale difference of each area in the continuous p-frame infrared image All less than or equal to ΔHD yz , the plug-in terminal is considered to be in a stable working state, where ΔHD yz represents a preset grayscale difference threshold, and divides the infrared images of the nth to Nth frames into a set C;

[0039] According to the infrared images in set C, calculate the long-term grayscale mean of each area Grayscale difference mean The calculation method is:

[0040]

[0041] At time point T mb The grayscale mean value of each area of ​​the predicted infrared image is calibrated as The grayscale difference of each area is calibrated as The calculation method is:

[0042]

[0043] Then according to the grayscale difference in each area Generate the second warning coefficient The calculation method is:

[0044]

[0045] In the formula Respectively represent the grayscale difference corresponding to the same area in set C The maximum and minimum values ​​of .

[0046] Preferably, according to the first warning coefficient and the second warning coefficient Perform weighted processing to generate a comprehensive early warning coefficient The calculation method is:

[0047]

[0048] In the formula, γ1 and γ2 represent external weight and internal weight respectively, c represents the adjustment coefficient, γ1,γ2∈[0,1] and γ1+γ2=1.

[0049] Preferably, when the comprehensive warning coefficient When the corresponding plug-in terminal is considered to be at risk, an alarm signal is generated and an alarm is issued. Indicates the preset warning threshold.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] The present invention constructs a comprehensive, real-time intelligent monitoring system by integrating multiple monitoring methods such as resistance sensing, stress sensing, environmental monitoring and infrared image analysis. The system can automatically collect and process the resistance data, stress data, environmental data and infrared images of the plug-in terminal, and through advanced data processing and analysis technology, quickly and accurately evaluate the operating status of the terminal and generate early warning signals. Compared with traditional monitoring methods, this solution significantly improves the comprehensiveness and real-time nature of monitoring, can timely discover and warn of potential faults and risks, effectively prevent equipment failures and safety accidents, improve the reliability and safety of the system, and meet the needs of modern industry for intelligent and automated monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a schematic diagram of the overall module structure of the present invention;

[0053] Figure 2 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0054] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0055] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0056] Example:

[0057] See also Figure 1-Figure 2 , the present invention provides a technical solution:

[0058] The plug-in terminal intelligent monitoring system includes: a data acquisition module, an image acquisition module, a data processing module, an image processing module, a comprehensive processing module, a monitoring platform, and an alarm module.

[0059] The data acquisition module is communicatively connected to the data processing module, and includes a resistance sensing unit, a stress sensing unit, and an environment sensing unit, which are respectively used to collect resistance data, stress data, and environment data of each group of plug-in terminals, and send the resistance data, stress data, and environment data to the data processing module.

[0060] The resistance sensing unit is a contact resistance sensor of the DT-500 series from TE Connectivity, and the collected resistance data is contact resistance data, which is used to accurately measure the contact resistance and ensure the stability of the electrical connection; the stress sensing unit adopts a strain gauge sensor of the KMR series from HBM, which is used to monitor the mechanical stress changes of the plug-in terminal to avoid loosening; the environmental sensing unit includes a temperature sensor and a humidity sensor, and adopts an integrated temperature and humidity sensor of the SHT3x series from Sensirion. The collected environmental data includes environmental temperature data and environmental humidity data, which are used to correct the resistance data and stress data and reduce the impact of environmental influences on the test results.

[0061] The image acquisition module is communicatively connected with the image processing module and uses FLIR's A310 infrared thermal imager, which can capture high-resolution infrared images, for acquiring infrared images of each group of plug-in terminals and sending the infrared images to the image processing module.

[0062] The data processing module is communicatively connected with the comprehensive processing module and adopts the CompactRIO series programmable automation controller of National Instruments. The controller has powerful data processing capability and is used to generate the first warning coefficient according to the resistance data, stress data and environmental data of each group of plug-in terminals, and send the first warning coefficient to the comprehensive processing module.

[0063] The image processing module is communicatively connected with the comprehensive processing module, and uses MatroxSolios X series image acquisition card of Matrox Imaging, which can process infrared images at high speed, divide infrared images into regions, perform temperature detection on different regions, generate a second warning coefficient according to the detection result and send it to the comprehensive processing module.

[0064] The comprehensive processing module is communicatively connected with the monitoring platform and adopts ABB's AC500 series PLC (programmable logic controller), which has advanced data analysis and decision-making functions, and is used to perform weighted processing on the first warning coefficient and the second warning coefficient, generate a comprehensive warning coefficient, and send the comprehensive warning coefficient to the monitoring platform.

[0065] The monitoring platform is communicatively connected with the alarm module and uses the WinCC SCADA system deployed with Siemens to display the comprehensive warning coefficient of each group of plug-in terminals, generate an alarm signal according to the size of the comprehensive warning coefficient and send it to the alarm module. The alarm module uses the LS5 series sound and light alarm installed with Patlite to issue an sound and light alarm according to the received alarm signal.

[0066] The generation logic of the first warning coefficient and the second warning coefficient is:

[0067] All data collected after the plug-in terminal works normally continuously for T time are read to obtain the resistance data, stress data, and environmental data of each group of plug-in terminals within T time, and N frames of infrared images of the plug-in terminal are collected at intervals of time t within T time.

[0068] In this step, by continuously collecting data within time T, the continuity and integrity of the data are ensured, which can reflect the actual working status of the plug-in terminal over a long period of time, provide a sufficient data basis for subsequent data analysis and prediction, and enhance the accuracy of the analysis and the reliability of the prediction.

[0069] The resistance data and stress data are corrected according to the environmental data corresponding to each group of plug-in terminals to reduce the impact of ambient temperature and humidity on the resistance data and stress data. The infrared image is converted into grayscale and divided into regions to reflect the temperature change according to the grayscale difference in each region.

[0070] When the moisture content in the air is high, a water film may form at the metal connection of the pluggable terminal, causing the measured contact resistance data to be too large. Therefore, the resistance data needs to be corrected according to the ambient humidity data in the environmental data. The calculation method is:

[0071]

[0072] Where Rjc i Represents the corrected contact resistance data, V i Indicates the contact voltage, I i Indicates the contact current, K h represents the ambient humidity data, a represents the first correction coefficient, and the subscript i represents the data number, i=1,2,3,...,M.

[0073] Similarly, the strain gauge is mainly affected by the ambient temperature. When the ambient temperature rises, the strain gauge will not only deform due to stress, but also deform due to temperature. Therefore, the stress data needs to be corrected according to the ambient temperature data in the environmental data. The calculation method is:

[0074]

[0075] Where Ryb i Indicates the resistance of the strain gauge in the strain gauge sensor, K T represents the temperature coefficient of the strain gauge, T h represents the ambient temperature data, T0 represents the reference temperature of the strain gauge, R0 represents the reference resistance of the strain gauge, and k represents the sensitivity coefficient of the strain gauge.

[0076] By introducing environmental humidity data to correct the resistance data, and environmental temperature data to correct the stress data, the impact of environmental factors on the measured data can be effectively reduced. The corrected data is closer to the actual state of the plug-in terminal in the actual working environment, which improves the credibility and accuracy of the data and provides a more reliable basis for subsequent analysis and early warning. The correction formula also contains adjustable parameters (such as the first correction coefficient a, the temperature coefficient K of the strain gauge, etc.). T These parameters can be adjusted according to actual conditions to adapt to different application scenarios and environmental conditions, thus improving the adaptability and practicality of the system.

[0077] A time series prediction model is constructed to analyze the corrected resistance data and stress data, and then a linear regression model is constructed to analyze the grayscale difference in each area of ​​the infrared image to generate a prediction model at time point T. mbThe first warning coefficient is generated according to the predicted resistance data and stress data, and the second warning coefficient is generated according to the grayscale difference in each area of ​​the infrared image.

[0078] Unlike resistance data and stress data, resistance data and stress data, when not affected by external interference, mainly depend on the material of the plug-in terminal itself and are affected by ambient temperature and humidity. Ambient temperature and humidity have strong regularity and periodicity, so the ARIMA autoregressive moving model can be used for prediction. However, since the plug-in terminal will accumulate heat during operation, it will slowly heat up until it reaches a thermal equilibrium temperature, so a linear regression model is used for prediction. By using two different models to predict data at a certain time point in the future, potential failure risks can be identified in advance, allowing the system to take measures before a failure occurs, improving the system's preventive and response speed.

[0079] All the resistance data Rjc within T time i and stress data F i Divide into set A and set B respectively, calculate the mean and standard deviation of set A and set B respectively, the calculation method is:

[0080]

[0081] In the formula Represent the means of set A and set B respectively, σ1 and σ2 represent the standard deviations of set A and set B respectively;

[0082] when , the data set is considered abnormal, and the data set is removed from set A, and the mean is used Replace this group of data to optimize set A; when , the data set is considered abnormal and is removed from set B. This group of data is replaced to achieve the optimization of set B; where μ represents the preset volatility coefficient.

[0083] In this step, when the power grid fluctuates or is hit by external force, the resistance data Rjc i and stress data F i Large fluctuations occur, which are obviously not caused by the nature of the plug-in terminal itself. Therefore, they need to be eliminated to maintain the accuracy and reliability of the data set. By eliminating abnormal data, the risk of false alarms caused by abnormal values ​​is reduced. At the same time, it ensures that normal data is not mistakenly eliminated, reducing the possibility of false alarms and missed alarms, making the early warning more accurate and reducing unnecessary maintenance work and costs.

[0084] Based on the optimized set A and set B, a time series prediction model is constructed to predict the time at the time point T mb The predicted resistance data and stress data are calibrated as Rjc' and F', and the first warning coefficient is generated according to Rjc' and F' The calculation method is:

[0085]

[0086] Where Rjc max 、Rjc min Respectively represent the maximum and minimum values ​​in set A, F max 、F min They represent the maximum and minimum values ​​in set B respectively, β1 and β2 represent the resistance weight and stress weight respectively, β1, β2∈[0,1] and β1+β2=1.

[0087] After the infrared image is grayscale converted, the image is divided into X*Y regions in the horizontal and vertical directions, and the grayscale mean of each region in the image is calculated and calibrated as Since the higher the temperature, the higher the brightness of the area in the infrared image, the larger the gray value, so the gray mean can be used to reflect the average temperature in the area. The subscript (x, y) represents the horizontal and vertical coordinates of the area, respectively, and the superscript j represents the image number, j = 1, 2, 3, ..., N;

[0088] Calculate the grayscale difference of each area between two adjacent infrared images The calculation method is:

[0089]

[0090] Since the temperature of the plug-in terminal rises rapidly during the process from connecting to the circuit to stable operation, it is necessary to filter out the data during this period to avoid affecting the subsequent judgment. Therefore, if the grayscale difference of each area in the continuous p-frame infrared image is All less than or equal to ΔHD yz , it is considered that the plug-in terminal is in a stable working state, the temperature in each area rises only at a very slow rate, and the corresponding change curve becomes flat, where ΔHD yz represents a preset grayscale difference threshold, and divides the infrared images of the nth to Nth frames into a set C;

[0091] According to the infrared images in set C, calculate the long-term grayscale mean of each area Grayscale difference mean The calculation method is:

[0092]

[0093] At time point T mb The grayscale mean value of each area of ​​the predicted infrared image is calibrated as The grayscale difference of each area is calibrated as The calculation method is:

[0094]

[0095] Then according to the grayscale difference in each area Generate the second warning coefficient The calculation method is:

[0096]

[0097] In the formula Respectively represent the grayscale difference corresponding to the same area in set C The maximum and minimum values ​​of .

[0098] According to the first warning factor and the second warning coefficient Perform weighted processing to generate a comprehensive early warning coefficient The calculation method is:

[0099]

[0100] In the formula, γ1 and γ2 represent external weight and internal weight respectively, c represents the adjustment coefficient, γ1,γ2∈[0,1] and γ1+γ2=1.

[0101] When the comprehensive warning factor When the corresponding plug-in terminal is considered to be at risk, an alarm signal is generated and an alarm is issued. Indicates the preset warning threshold.

[0102] The workflow of the intelligent monitoring system is as follows:

[0103] S1: Collect resistance data, stress data, environmental data and infrared images of the plug-in terminal during continuous normal operation for T time, use environmental data to correct resistance data and stress data, and perform grayscale conversion and area division on infrared images;

[0104] S2: Based on the corrected resistance data and stress data, a time series prediction model is constructed, and based on the infrared image, a linear regression model is constructed. mb The resistance data, stress data and grayscale difference in each area of ​​the infrared image are predicted;

[0105] S3: According to the time point T mbThe resistance data and stress data at time T generate the first warning coefficient. mb The grayscale difference in each area of ​​the infrared image generates a second warning coefficient;

[0106] S4: Perform weighted processing on the first warning coefficient and the second warning coefficient to generate a comprehensive warning coefficient, compare the comprehensive warning coefficient with a preset warning threshold, generate an alarm signal according to the comparison result, and issue an alarm.

[0107] In summary, the present invention constructs a comprehensive, real-time intelligent monitoring system by integrating multiple monitoring methods such as resistance sensing, stress sensing, environmental monitoring and infrared image analysis. The system can automatically collect and process the resistance data, stress data, environmental data and infrared images of the plug-in terminal, and through advanced data processing and analysis technology, quickly and accurately evaluate the operating status of the terminal and generate early warning signals. Compared with traditional monitoring methods, this solution significantly improves the comprehensiveness and real-time nature of monitoring, can timely discover and warn of potential faults and risks, effectively prevent equipment failures and safety accidents, improve the reliability and safety of the system, and meet the needs of modern industry for intelligent and automated monitoring.

[0108] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0109] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0110] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0111] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. Plug-in terminal intelligent monitoring system, characterized in that: include: A data acquisition module, which is communicatively connected with the data processing module and includes a resistance sensing unit, a stress sensing unit, and an environment sensing unit, which are respectively used to collect resistance data, stress data, and environment data of each group of plug-in terminals, and send the resistance data, stress data, and environment data to the data processing module, wherein the resistance sensing unit is a contact resistance sensor, and the resistance data is contact resistance data; the stress sensing unit is a strain gauge sensor; the environment sensing unit includes a temperature sensor and a humidity sensor, and the environment data includes environment temperature data and environment humidity data; An image acquisition module, which is communicatively connected with the image processing module and is used to acquire infrared images of each group of plug-in terminals and send the infrared images to the image processing module; A data processing module, the data processing module is communicatively connected with the comprehensive processing module, and is used to generate a first warning coefficient according to the resistance data, stress data, and environmental data of each group of plug-in terminals, and send the first warning coefficient to the comprehensive processing module; An image processing module, which is in communication with the comprehensive processing module and is used to divide the infrared image into regions, perform temperature detection on different regions, generate a second warning coefficient according to the detection result and send it to the comprehensive processing module; A comprehensive processing module, the comprehensive processing module is connected to the monitoring platform for performing weighted processing on the first warning coefficient and the second warning coefficient to generate a comprehensive warning coefficient, and sending the comprehensive warning coefficient to the monitoring platform; A monitoring platform, which is in communication with the alarm module and is used to display the comprehensive warning coefficient of each group of plug-in terminals, generate an alarm signal according to the size of the comprehensive warning coefficient and send it to the alarm module; An alarm module, the alarm module is used to issue an audible and visual alarm according to a received alarm signal; The generation logic of the first warning coefficient and the second warning coefficient is: All data collected after the plug-in terminal works normally continuously for T time are read to obtain resistance data, stress data, and environmental data of each group of plug-in terminals within T time, and N frames of infrared images of the plug-in terminal are collected at intervals of time t within T time; According to the environmental data corresponding to each group of plug-in terminals, the resistance data and stress data are respectively corrected to reduce the impact of ambient temperature and humidity on the resistance data and stress data. The infrared image is converted into grayscale and divided into regions, and the temperature change is reflected according to the grayscale difference in each region. A time series prediction model is constructed to analyze the corrected resistance data and stress data, and then a linear regression model is constructed to analyze the grayscale difference in each area of ​​the infrared image to generate a prediction model at time point T. mb The predicted resistance data, stress data and grayscale difference in each area of ​​the infrared image are used to generate a first warning coefficient according to the predicted resistance data and stress data, and a second warning coefficient is generated according to the grayscale difference in each area of ​​the infrared image; The resistance data is corrected according to the ambient humidity data in the environmental data. The calculation method is: Where Rjc i Represents the corrected contact resistance data, V i Indicates the contact voltage, I i Indicates the contact current, K h represents the environmental humidity data, a represents the first correction coefficient, and the subscript i represents the data number, i=1,2,3,…,M; The stress data is corrected according to the ambient temperature data in the environmental data. The calculation method is: Where Ryb i Indicates the resistance of the strain gauge in the strain gauge sensor, K T represents the temperature coefficient of the strain gauge, T h represents the ambient temperature data, T0 represents the reference temperature of the strain gauge, R0 represents the reference resistance of the strain gauge, and k represents the sensitivity coefficient of the strain gauge; All the resistance data Rjc within T time i and stress data F i Divide into set A and set B respectively, calculate the mean and standard deviation of set A and set B respectively, the calculation method is: In the formula Represent the means of set A and set B respectively, σ1 and σ2 represent the standard deviations of set A and set B respectively; when , the data set is considered abnormal and is removed from set A. Replace the group of data to optimize the set A; when , the data set is considered abnormal and is removed from set B. Replace this group of data to optimize set B; Where μ represents the preset fluctuation coefficient; Based on the optimized set A and set B, a time series prediction model is constructed to predict the time at the time point T mb The predicted resistance data and stress data are calibrated as Rjc′ and F′, and the first warning coefficient is generated according to Rjc′ and F′ The calculation method is: Where Rjc max 、Rjc min Respectively represent the maximum and minimum values ​​in set A, F max 、F min They represent the maximum and minimum values ​​in set B, β1 and β2 represent the resistance weight and stress weight, β1, β2∈[0,1] and β1+β2=1; After the infrared image is grayscale converted, the image is divided into X*Y regions in the horizontal and vertical directions, and the grayscale mean of each region in the image is calculated and calibrated as The subscripts (x, y) represent the horizontal and vertical coordinates of the region, respectively, and the superscript j represents the image number, j = 1, 2, 3, ..., N; Calculate the grayscale difference of each area between two adjacent infrared images The calculation method is: If starting from the nth frame, the grayscale difference of each area in the continuous p-frame infrared image All less than or equal to ΔHD yz , the plug-in terminal is considered to be in a stable working state, where ΔHD yz represents a preset grayscale difference threshold, and divides the infrared images of the nth to Nth frames into a set C; According to the infrared images in set C, calculate the long-term grayscale mean of each area Grayscale difference mean The calculation method is: At time point T mb The grayscale mean value of each area of ​​the predicted infrared image is calibrated as The grayscale difference of each area is calibrated as The calculation method is: Then according to the grayscale difference in each area Generate the second warning coefficient The calculation method is: In the formula Respectively represent the grayscale difference corresponding to the same area in set C The maximum and minimum values ​​of .

2. The plug-in terminal intelligent monitoring system according to claim 1, characterized in that: According to the first warning factor and the second warning coefficient Perform weighted processing to generate a comprehensive early warning coefficient The calculation method is: In the formula, γ1 and γ2 represent external weight and internal weight respectively, c represents the adjustment coefficient, γ1,γ2∈[0,1] and γ1+γ2=1.

3. The plug-in terminal intelligent monitoring system according to claim 2, characterized in that: When the comprehensive warning factor When the corresponding plug-in terminal is considered to be at risk, an alarm signal is generated and an alarm is issued. Indicates the preset warning threshold.

Images