GIS internal humidity detection method and system based on microsensor

Abstract

The invention discloses a GIS internal humidity detection method and system based on a microsensor, and relates to GIS internal humidity detection.The GIS internal humidity detection method comprises the steps that the microsensor is adopted to record GIS internal environment data and initial calibration parameters, data preprocessing is conducted on the GIS internal environment data, and the GIS internal environment data comprises GIS real-time environment data and GIS historical environment data; constructing a dynamic environment compensation model according to the GIS internal environment data, and inputting the GIS real-time environment data into the dynamic environment compensation model to obtain dynamic environment compensation parameters; and training the initial calibration parameter to obtain an adjusted calibration parameter, feeding back the adjusted calibration parameter to the microsensor, updating the working state of the sensor, and performing detection again to obtain the internal humidity of the GIS. According to the invention, the accuracy and reliability of the humidity detection result are ensured, and the operation efficiency and safety of the GIS equipment are improved.

Description

Technical Field

[0001] The invention relates to the technical field of GIS internal humidity detection, in particular to a GIS internal humidity detection method and system based on a microsensor. Background Art

[0002] Gas Insulated Substation (GIS) is a common high-voltage power facility used for power conversion, transmission and distribution in power transmission and distribution systems. The environmental humidity has an important impact on its internal operation. Due to the strong enclosure and complex internal structure of GIS equipment, it is difficult to accurately measure the humidity inside the equipment.

[0003] GIS equipment contains SF 6 Gas, which is used as an insulating and arc-extinguishing medium in GIS, can cause internal flashover of GIS and reduce the insulation performance of the equipment when its humidity is too high. 6 The allowable humidity of the gas must be strictly controlled, generally not exceeding 90%.

[0004] The existing GIS humidity detection method based on LC sensors requires placing the LC sensor in the internal environment of the GIS. Due to factors such as temperature changes and high air pressure inside the GIS, the LC sensor coil will deform, thus affecting the detection accuracy. Therefore, a high-precision and high-reliability method is needed to detect the internal humidity of the GIS. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the above existing problems, the present invention is proposed.

[0007] Therefore, the present invention provides a method and system for detecting humidity inside a GIS based on a microsensor, which can solve the problems mentioned in the background technology.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0009] In a first aspect, the present invention provides a method for detecting humidity inside a GIS based on a microsensor, which comprises using a microsensor to record GIS internal environmental data and initial calibration parameters, and performing data preprocessing on the GIS internal environmental data, wherein the GIS internal environmental data comprises GIS real-time environmental data and GIS historical environmental data;

[0010] Constructing a dynamic environmental compensation model according to the internal environmental data of the GIS, and inputting the real-time environmental data of the GIS into the dynamic environmental compensation model to obtain dynamic environmental compensation parameters;

[0011] The initial calibration parameters are trained to obtain adjusted calibration parameters, the adjusted calibration parameters are fed back to the microsensor, the working state of the sensor is updated, and the internal humidity of the GIS is re-detected.

[0012] As a preferred solution of the microsensor-based GIS internal humidity detection method of the present invention, wherein: the microsensor is an LC wireless passive sensor;

[0013] The GIS real-time environmental data includes real-time GIS internal humidity, real-time GIS internal temperature and real-time GIS internal air pressure;

[0014] The GIS historical environmental data includes historical GIS internal humidity, historical GIS internal temperature and historical GIS internal air pressure;

[0015] The initial calibration parameters include resonant frequency, Q value and sensitivity coefficient;

[0016] The data preprocessing includes data cleaning and data filling.

[0017] As a preferred solution of the micro-sensor-based GIS internal humidity detection method of the present invention, the dynamic environment compensation model is constructed including:

[0018] Use the initial calibration parameters to preliminarily calibrate the collected data, and construct vector matrix functions of real-time environmental data and historical environmental data respectively;

[0019] Calculate the integral from the initial moment to the current moment t, accumulate the compensation amount at each time point, and obtain the environmental compensation parameter. The calculation formula is as follows:

[0020] E c (t) = ∫ 0 (M(H r (τ),T r (τ),P r (τ))-M(H h (τ),T h (τ),P h (τ)))dτ

[0021] Among them, E c (t) represents the compensation amount of environmental data, τ is the integral variable, H r (τ) is the real-time humidity data at the current time τ, T r(τ) is the real-time temperature data at the current time τ, P r (τ) is the real-time air pressure data at the current time τ, H h (τ) is the historical humidity data at the historical time τ, Th ( τ) is the historical temperature data of the historical time τ, P h (τ) is the historical air pressure data at historical time τ, M(H, T, P) is the vector matrix function based on humidity, temperature and air pressure, and the calculation formula is as follows:

[0022]

[0023] Among them, α i is the humidity coefficient, β i is the temperature coefficient, γ i is the air pressure coefficient, i=1, 2, 3, H is humidity, T is temperature, and P is air pressure.

[0024] As a preferred solution of the microsensor-based GIS internal humidity detection method of the present invention, the training of the initial calibration parameters includes:

[0025] Correct the real-time environmental data by calculating environmental compensation parameters and generate a compensation data set;

[0026] Define the error function and build a calibration parameter adjustment model to adjust the initial calibration parameters;

[0027] The error function is iterated and minimized by the gradient descent method to obtain the adjusted calibration parameters.

[0028] As a preferred solution of the micro-sensor-based GIS internal humidity detection method of the present invention, the generating of the compensation data set includes:

[0029] According to the calculated environmental compensation parameter E c (t) Correct the real-time environmental data to obtain the compensated humidity detection result H f (t), the calculation formula is as follows:

[0030] H f (t) = H r (t)+k 1 ·E c (t)

[0031] T f (t) = T r (t)+k 2 ·E c (t)

[0032] P f (t) = P r (t)+k3 ·E c (t)

[0033] Among them, H f (t) is the humidity detection result after compensation, k 1 is the humidity compensation coefficient, H r (t) is the real-time humidity data at time t, T f (t) is the temperature detection result after compensation, T r (t) is the real-time temperature data at time t, k 2 is the temperature compensation coefficient, P f (t) is the air pressure detection result after compensation, T r (t) is the real-time air pressure data at time t, k 3 is the air pressure compensation coefficient;

[0034] The compensated dataset is fused with the original historical dataset to generate a complete compensated dataset.

[0035] As a preferred solution of the microsensor-based GIS internal humidity detection method of the present invention, the calculation formula of the error function is as follows:

[0036]

[0037] Among them, H c (t i ) is the compensation data set with time point t i Humidity compensation data, T c (t i ) is the temperature compensation data at time point ti in the compensation data set, P c (t i ) is the air pressure compensation data at time point ti in the compensation data set, H m (t i , Θ) is the humidity prediction value based on the calibration model, T m (t i , Θ) is the temperature prediction value based on the calibration model, P m (t i , Θ) is the predicted value of air pressure based on the calibration model, and n is the number of data points.

[0038] As a preferred solution of the micro-sensor-based GIS internal humidity detection method of the present invention, the adjusted calibration parameters include:

[0039] Construct a calibration parameter adjustment model. The calculation formula of the calibration parameter adjustment model is as follows:

[0040] H m (t,Θ)=fr ·H c (t)+Q·T c (t)+S·P c (t)

[0041] T m (t,Θ)=f r ·T c (t)+Q·H c (t)+S·P c (t)

[0042] P m (t,Θ)=f r ·P c (t)+Q·H c (t)+S·T c (t)

[0043] Where, Θ is the initial calibration parameter;

[0044] The error function L(θ) is minimized using the gradient descent method, and the initial calibration parameters are updated. The update formula is as follows:

[0045]

[0046] Among them, Θ new is the updated calibration parameter, η is the learning rate, is the gradient of the error function;

[0047] The calibration parameters are optimized and iteratively updated by gradient descent until the error function L(θ) converges to obtain the adjusted calibration parameters.

[0048] In a second aspect, the present invention provides a GIS internal humidity detection system based on a microsensor, which includes: a data acquisition preprocessing module, a dynamic environment compensation module and a parameter training module;

[0049] The data acquisition preprocessing module is used to record GIS internal environment data and initial calibration parameters using micro sensors, and perform data preprocessing on the GIS internal environment data, wherein the GIS internal environment data includes GIS real-time environment data and GIS historical environment data;

[0050] The dynamic environment compensation module is used to construct a dynamic environment compensation model according to the internal environment data of the GIS, and input the real-time environment data of the GIS into the dynamic environment compensation model to obtain dynamic environment compensation parameters;

[0051] The parameter training module is used to train the initial calibration parameters to obtain adjusted calibration parameters, feed the adjusted calibration parameters back to the microsensor, update the working state of the sensor, and re-detect to obtain the internal humidity of the GIS.

[0052] In a third aspect, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, the steps of a GIS internal humidity detection method based on a microsensor are implemented.

[0053] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, the steps of a method for detecting humidity inside a GIS based on a microsensor are implemented.

[0054] Compared with the prior art, the beneficial effect of the present invention is that the GIS internal humidity detection method based on microsensors records the GIS internal environmental data and initial calibration parameters by using microsensors, and preprocesses these data, thereby realizing comprehensive and accurate monitoring of the GIS internal environment. The data preprocessing link includes data cleaning and data filling to ensure the integrity and accuracy of the data; a dynamic environmental compensation model is constructed based on the GIS internal environmental data, and real-time environmental data is input into the model to calculate the dynamic environmental compensation parameters. This model generates environmental parameters for compensation through comprehensive analysis of real-time and historical environmental data. During the calculation process, the real-time and historical data of humidity, temperature, and air pressure are vectorized, and the compensation amount at each time point is calculated, thereby realizing dynamic compensation of environmental data. The dynamic environmental compensation model can effectively correct the errors of real-time environmental data and improve the accuracy of humidity detection; by calculating the environmental compensation parameters , correct the real-time environmental data and generate a compensation data set, define the error function, build a calibration parameter adjustment model, and iteratively optimize the error function through the gradient descent method, and finally get the adjusted calibration parameters, which are fed back to the microsensor to update the working status of the sensor, thereby achieving more accurate GIS internal humidity detection. The whole method realizes high-precision detection of GIS internal humidity through three main steps: data recording and preprocessing, dynamic environmental compensation model construction, and calibration parameter training and adjustment. Each step has its unique role and use, and brings significant beneficial effects. Through the comprehensive application of these steps, the accuracy and reliability of humidity detection results are ensured, and the operating efficiency and safety of GIS equipment are improved. This method not only innovatively combines real-time and historical data, but also overcomes the shortcomings of traditional humidity detection methods through dynamic compensation and optimization of calibration parameters, and significantly improves the detection effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0056] Figure 1 A method flow chart of a GIS internal humidity detection method and system based on a microsensor provided in one embodiment of the present invention;

[0057] Figure 2 An internal structural diagram of a computer device of a GIS internal humidity detection method and system based on a microsensor provided in one embodiment of the present invention;

[0058] Figure 3 An equivalent circuit diagram of a GIS internal humidity detection device of a GIS internal humidity detection method and system based on a microsensor provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0059] In order to make the above-mentioned purposes, features and advantages of the present invention more understandable, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0060] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0061] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0062] Example 1

[0063] Reference Figure 1-Figure 3 , which is the first embodiment of the present invention, provides a method for detecting humidity inside a GIS based on a microsensor, comprising:

[0064] This application provides a method that can effectively solve the above-mentioned problems. Next, multiple embodiments will be combined to explain in detail how to implement the GIS internal humidity detection method based on microsensors;

[0065] Figure 1 A method flow chart of a GIS internal humidity detection method and system based on a microsensor is shown, including:

[0066] S1: Use micro sensors to record GIS internal environmental data and initial calibration parameters, and preprocess the GIS internal environmental data. The GIS internal environmental data includes GIS real-time environmental data and GIS historical environmental data.

[0067] Furthermore, the microsensor is an LC wireless passive sensor;

[0068] GIS real-time environmental data includes real-time GIS internal humidity, real-time GIS internal temperature and real-time GIS internal air pressure;

[0069] GIS historical environmental data include historical GIS internal humidity, historical GIS internal temperature and historical GIS internal air pressure;

[0070] The initial calibration parameters include the resonant frequency f r , Q value Q and sensitivity coefficient S;

[0071] Data preprocessing includes data cleaning and data filling.

[0072] S2: construct a dynamic environmental compensation model according to the internal environmental data of GIS, and input the real-time environmental data of GIS into the dynamic environmental compensation model to obtain dynamic environmental compensation parameters;

[0073] Furthermore, the construction of dynamic environmental compensation model includes:

[0074] Use the initial calibration parameters to preliminarily calibrate the collected data to ensure the accuracy of the data;

[0075] Construct vector matrix functions for real-time environmental data and historical environmental data respectively;

[0076] Calculate the integral from the initial moment to the current moment t, accumulate the compensation amount at each time point, and obtain the environmental compensation parameter. The calculation formula is as follows:

[0077] E c (t) = ∫ 0 (M(H r (τ), T r (τ),P r (τ))-M(H h (τ), T h (τ), Ph (τ)))dτ

[0078] Among them, E c (t) represents the compensation amount of environmental data, reflecting the difference between real-time data and historical data, τ is the integral variable, H r (τ) is the real-time humidity data at the current time τ, T r (τ) is the real-time temperature data at the current time τ, P r (τ) is the real-time air pressure data at the current time τ, H h (τ) is the historical humidity data at the historical time τ, T h (τ) is the historical temperature data of the historical time τ, P h (τ) is the historical air pressure data at the historical time τ, M(H, T, P) is the vector matrix function based on humidity, temperature and air pressure; the calculation formula of M(H, T, P) is as follows:

[0079]

[0080] Among them, α i is the humidity coefficient, β i is the temperature coefficient, γ i is the air pressure coefficient, i = 1, 2, 3, H is humidity, T is temperature, and P is air pressure;

[0081] Due to E c (t) is the integral function, the environmental compensation E c The value range of (t) depends on the fluctuation range of environmental data and the length of integration time.

[0082] Furthermore, we determine α i , β i and γ i The steps include,

[0083] Collect the real-time humidity, temperature and air pressure data inside the GIS over a period of time, denoted as H r (t), T r (t) and P r (t);

[0084] Collect historical humidity, temperature and air pressure data in the same time period, denoted as H h (t), T h (t) and P h (t);

[0085] Using the initial calibration parameters (resonant frequency f r , Q value Q and sensitivity coefficient S) to perform preliminary calibration on the collected data to ensure the accuracy of the data;

[0086] Use linear regression or other data fitting methods and perform parameter fitting to determine α i , β i and γ i Vector-matrix function of ;

[0087] By using the least squares method or other optimization algorithms, the parameters are solved to minimize the fitting error, that is,

[0088]

[0089] Use partial data for validation to check the accuracy and reliability of the model;

[0090] Based on the verification results, the parameters are fine-tuned to ensure that the model can accurately reflect environmental changes.

[0091] Specifically, assume that n sets of data are collected, each set of data includes real-time and historical humidity, temperature and air pressure, which are specifically expressed in matrix form:

[0092]

[0093] Use the linear regression model to fit the following formula to get α i , β i and γ i :

[0094] y=Xθ 1

[0095] Among them, y is the observed result vector, θ 1 is the parameter vector to be solved, including α i , β i and γ i ;

[0096] The objective function is set to minimize the mean square error, and the optimal parameter value is obtained by minimizing the objective function, that is,

[0097]

[0098] Use the normal equation to solve the optimal parameters. The calculation formula is as follows:

[0099] θ 1 =(X T X) -1 X T y

[0100] Among them, X T is the transposed matrix of matrix X;

[0101] You can also use the gradient descent method to gradually adjust Θ through iteration 1 , until the objective function value converges.

[0102] Furthermore, step S2 compensates the GIS real-time environmental data by constructing a dynamic environmental compensation model to ensure the accuracy and reliability of humidity, temperature and air pressure data; preliminary calibration uses initial calibration parameters to perform preliminary calibration on the data to reduce initial data errors; constructs vector matrix functions of real-time and historical environmental data, and improves the efficiency and accuracy of data processing by comprehensively considering the three factors of humidity, temperature and air pressure; the environmental compensation parameter Ec(t) dynamically adjusts the environmental data through an integral function to ensure the stability and reliability of real-time data; parameter fitting and optimization use linear regression or other methods to determine the vector matrix functions of humidity, temperature and air pressure, and use the least squares method or other optimization algorithms to ensure the optimality of the model parameters and improve the accuracy and reliability of the model; model verification and fine-tuning are verified by partial data to check the model Accuracy and reliability, fine-tune the parameters according to the verification results, and further improve the effectiveness and stability of the model in practical applications; through these steps, the present invention realizes dynamic compensation and real-time calibration of environmental data in concept, and solves technical problems such as large data errors and poor real-time performance in traditional methods; preliminary calibration and vector matrix function construction make environmental data processing more systematic and accurate, the calculation of environmental compensation parameters ensures the stability of real-time data through the integral method, parameter fitting and optimization ensure the optimality of model parameters through scientific methods, and model verification and fine-tuning further improve the practical application effect of the model; in summary, the present invention realizes the accurate calibration of environmental data inside the GIS system through the construction and optimization of the dynamic environmental compensation model, improves the reliability and stability of the data, and has significant innovation and practicality in technology.

[0103] S3: compensating the GIS real-time environmental data according to the dynamic environmental compensation parameters, generating a compensation data set, constructing a calibration parameter adjustment model, and training the initial calibration parameters using the calibration parameter adjustment model and the compensation data set to obtain adjusted calibration parameters;

[0104] Further, generating a compensation data set includes,

[0105] According to the calculated environmental compensation parameter E c (t), correct the real-time environmental data and obtain the compensated humidity detection result H f (t), the calculation formula is as follows:

[0106] H f (t) = H r (t)+k 1 ·E c (t)

[0107] T f (t) = T r (t)+k 2·E c (t)

[0108] P f (t) = P r (t))+k 3 ·E c (t)

[0109] Among them, H f (t) is the humidity detection result after compensation, k 1 is the humidity compensation coefficient, H r (t) is the real-time humidity data at time t, T f (t) is the temperature detection result after compensation, T r (t) is the real-time temperature data at time t, k 2 is the temperature compensation coefficient, P f (t) is the air pressure detection result after compensation, P r (t) is the real-time air pressure data at time t, k 3 is the air pressure compensation coefficient;

[0110] The compensated data set {H f (t), T f (t), P f (t)} and the original historical data set {H h (t), T h (t), P h (t)} fusion to generate a complete compensation dataset {H c (t), T c (t), P c (t)}.

[0111] Further, training the initial calibration parameters includes:

[0112] Define the error function L, which is used to train the calibration parameters and represents the error between the compensation data and the calibration model. The calculation formula of the error function is as follows:

[0113]

[0114] Among them, H c (t i ) is the compensation data set with time point t i Humidity compensation data, T c (t i ) is the temperature compensation data at time point ti in the compensation data set, P c (t i ) is the air pressure compensation data at time point ti in the compensation data set, H m (t i, Θ) is the humidity prediction value based on the calibration model, T m (t i , Θ) is the temperature prediction value based on the calibration model, P m (t i , Θ) is the predicted value of air pressure based on the calibration model, and n is the number of data points;

[0115] A calibration parameter adjustment model is constructed and adjusted based on the initial calibration parameter Θ. The calculation formula of the calibration parameter adjustment model is as follows:

[0116] H m (t,Θ)=f r ·H c (t)+Q·T c (t)+S·P c (t)

[0117] T m (t,Θ)=f r ·T c (t)+Q·H c (t)+S·P c (t)

[0118] P m (t,Θ)=f r ·P c (t)+Q·H c (t)+S·T c (t)

[0119] Where, Θ is the initial calibration parameter;

[0120] Use the gradient descent method to minimize the error function L(Θ) and update the initial calibration parameter Θ. The update formula is as follows:

[0121]

[0122] Among them, Θ new is the updated calibration parameter, η is the learning rate, is the gradient of the error function; the calculation formula is as follows:

[0123]

[0124] The specific calculation of the gradient can be obtained by the chain rule, that is,

[0125]

[0126] The above formula is used to perform gradient descent optimization, and the calibration parameters are iteratively updated until the error function L(θ) converges, and finally the adjusted calibration parameters are obtained, that is,

[0127]

[0128] Specifically, assume that the collected experimental data is as shown in the following table:

[0129] Table 1 Collection data table

[0130]

[0131] Calculate the compensated data according to the compensation formula. For example, for time t=1, there are the following data:

[0132] H f (1) = 45.0 + 0.05 1.5 = 45.075

[0133] T f (1) = 22.0 + 0.02 1.5 = 22.03

[0134] P f (1) = 1010 + 0.01 1.5 = 1010.015

[0135] The compensated data is fused with the original data to generate a compensated data set. The original data set is shown in the following table.

[0136] Table 2 Original data table

[0137] Time (t) <![CDATA[Original humidity data H h (t)]]> <![CDATA[Original temperature data T h (t)]]> <![CDATA[Original barometric pressure data P h (t) <!-- 8 -->]]> 1 45.0 22.0 1010 2 46.0 23.0 1008 3 44.5 21.5 1012

[0138] The fused compensation data set is shown in the following table.

[0139] Table 3 Compensation data table

[0140] Time (t) <![CDATA[Compensated humidity data H f (t)]]> <![CDATA[Compensated temperature data T f (t)]]> <![CDATA[Compensated barometric pressure data P f (t)]]> 1 45.075 22.03 1010.015 2 46.078 23.039 1008.026 3 44.068 21.015 1012.051

[0141] The calibration parameters are trained according to the defined error function and the adjusted calibration parameters are obtained through repeated iterations.

[0142] Furthermore, the dynamic environment compensation parameter E cThe introduction of (t) is significantly reasonable. This parameter is used to correct real-time environmental data to reduce the impact of environmental changes on measurement results. In the complex and changeable GIS system environment, the compensation parameters can significantly improve the accuracy and reliability of the data. In the process of generating the compensated data set, the real-time environmental data is corrected according to the calculated environmental compensation parameters to obtain the compensated humidity detection results, temperature detection results and air pressure detection results. In this way, the impact of environmental changes on the measurement results can be effectively reduced, and the reliability and accuracy of the data can be significantly improved. The compensated data set integrates real-time and historical data, and the generated complete compensated data set is more comprehensive and accurate, and can better reflect the actual situation. The introduction of environmental compensation parameters solves the problem of real-time environmental data being affected by environmental factors, ensuring the accuracy and stability of the data. In the process of training the initial calibration parameters, an error function is defined to train the calibration parameters, and the error function is minimized by the gradient descent method to update the initial calibration parameters. In this way, the calibration parameters can be optimized and the calibration model can be more accurate. After iterative optimization, the adjusted calibration parameters can better match the actual environment, thereby improving the detection accuracy of the sensor; traditional calibration methods usually require a lot of manual intervention and have low accuracy, while the present invention introduces error function and gradient descent method to automate the calibration process, thereby improving calibration accuracy and efficiency; in summary, the present invention innovatively improves the detection accuracy and reliability of the GIS system through dynamic environmental compensation and calibration parameter optimization, and has significant technical advantages and practical value; through the combination of mathematical models and optimization algorithms, environmental compensation parameters and calibration parameter adjustment models, not only the accuracy and reliability of the data are ensured, but also the automation and efficiency of the calibration process are realized; in this way, the present invention has outstanding advantages in improving detection accuracy and adapting to complex environmental changes, solves multiple key problems in traditional technologies, and provides strong support for the detection of GIS systems.

[0143] S4: Feedback the adjusted calibration parameters to the microsensor, update the working status of the sensor, re-test, and obtain the internal humidity of the GIS.

[0144] Monitor sensor health status, automatically detect and repair sensor anomalies, ensure sensors continue to work under new calibration parameters, and maintain high-precision humidity detection.

[0145] Furthermore, the present embodiment also provides a GIS internal humidity detection system based on a microsensor, comprising: a data acquisition preprocessing module, a dynamic environment compensation module and a parameter training module;

[0146] The data acquisition preprocessing module is used to record GIS internal environment data and initial calibration parameters using micro sensors, and perform data preprocessing on the GIS internal environment data, wherein the GIS internal environment data includes GIS real-time environment data and GIS historical environment data;

[0147] The dynamic environment compensation module is used to construct a dynamic environment compensation model according to the internal environment data of the GIS, and input the real-time environment data of the GIS into the dynamic environment compensation model to obtain dynamic environment compensation parameters;

[0148] The parameter training module is used to train the initial calibration parameters to obtain adjusted calibration parameters, feed back the adjusted calibration parameters to the microsensor, update the working state of the sensor, and re-detect to obtain the internal humidity of the GIS.

[0149] This embodiment also provides a computer device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 2 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a comprehensive evaluation method suitable for orderly access of large-scale distributed power sources is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.

[0150] This embodiment also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: using a micro sensor to record GIS internal environment data and initial calibration parameters, and performing data preprocessing on the GIS internal environment data, wherein the GIS internal environment data includes GIS real-time environment data and GIS historical environment data;

[0151] Constructing a dynamic environmental compensation model according to the internal environmental data of the GIS, and inputting the real-time environmental data of the GIS into the dynamic environmental compensation model to obtain dynamic environmental compensation parameters;

[0152] The initial calibration parameters are trained to obtain adjusted calibration parameters, the adjusted calibration parameters are fed back to the microsensor, the working state of the sensor is updated, and the internal humidity of the GIS is re-detected.

[0153] Example 2

[0154] Reference Figure 1 - Figure 2 , which is the second embodiment of the present invention, and this embodiment provides a method for detecting humidity inside a GIS based on a microsensor. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0155] In this experiment, LC wireless passive microsensors were used to record the internal environmental data and initial calibration parameters of the GIS, and these data were preprocessed to ensure the integrity and accuracy of the data. The experimental environment was a GIS device of a certain power company, and the sensor was installed in the internal monitoring area of ​​the GIS device. The test objects included real-time environmental data (real-time humidity, real-time temperature, real-time air pressure) and historical environmental data (historical humidity, historical temperature, historical air pressure). The initial calibration parameters included resonant frequency, Q value, and sensitivity coefficient.

[0156] First, the microsensor is installed at the monitoring point of the GIS equipment, and the real-time environmental data and initial calibration parameters inside the GIS are collected wirelessly. Data preprocessing includes data cleaning and data filling. The main steps are as follows:

[0157] Data cleaning: remove noise data and invalid data to ensure data accuracy.

[0158] Data filling: Use historical data and interpolation algorithms to fill in missing data to ensure data integrity.

[0159] After completing the data preprocessing, the collected data is preliminarily calibrated using the initial calibration parameters, and vector matrix functions of real-time environmental data and historical environmental data are constructed respectively. The integral from the initial moment to the current moment t is calculated, and the compensation amount at each time point is accumulated to obtain the environmental compensation parameter E c (t),

[0160] The real-time environmental data is corrected by calculating the environmental compensation parameters, and a compensation data set is generated. The error function is defined and a calibration parameter adjustment model is constructed to adjust the initial calibration parameters.

[0161] Finally, the adjusted calibration parameters are fed back to the microsensor, the working status of the sensor is updated, and the humidity test is performed again to obtain more accurate GIS internal humidity data. The specific data is shown in the following table:

[0162] Table 4 Experimental comparison table

[0163]

[0164] By analyzing the experimental data table, it can be seen that after adopting the GIS internal humidity detection method based on microsensors, the humidity, temperature and air pressure data of each test object tend to be in a more reasonable range after adjustment. For example, the initial humidity of test object 1 was 60%, and after adjustment, the humidity dropped to 58%, and the temperature and air pressure were also fine-tuned accordingly, showing the effectiveness of the environmental compensation model.

[0165] Compared with the prior art, the traditional humidity detection method is easily affected by temperature and air pressure changes in complex environments, resulting in poor accuracy and stability of the detection data. The present invention effectively corrects the errors in real-time environmental data by introducing a dynamic environmental compensation model and data preprocessing steps, making the humidity detection results more accurate and reliable. For example, the initial humidity of test object 3 was 55%, and after adjustment, the humidity dropped to 54%, showing that the compensation model accurately corrected the humidity detection results.

[0166] In addition, the calibration parameter adjustment model in the present invention is iteratively optimized by the gradient descent method, which significantly improves the calibration accuracy of the sensor. For example, the initial air pressure of the test object 5 is 1009hPa, and the air pressure after adjustment is 1008hPa. This subtle adjustment effectively improves the detection accuracy of the sensor and ensures the accuracy of the data.

[0167] In summary, through the data analysis of this embodiment, it can be seen that the GIS internal humidity detection method based on microsensors has significant innovation and advantages, and can provide high-precision humidity detection results in complex environments. Compared with traditional methods, the present invention not only effectively overcomes the influence of environmental factors on the detection results, but also significantly improves the accuracy and reliability of humidity detection through dynamic compensation and calibration parameter optimization, and improves the operating efficiency and safety of GIS equipment.

[0168] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0169] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0170] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0171] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0172] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0173] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0174] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for detecting humidity inside a GIS based on a microsensor, characterized in that: include, Using micro sensors to record GIS internal environmental data and initial calibration parameters, and performing data preprocessing on the GIS internal environmental data, wherein the GIS internal environmental data includes GIS real-time environmental data and GIS historical environmental data; Constructing a dynamic environmental compensation model according to the internal environmental data of the GIS, and inputting the real-time environmental data of the GIS into the dynamic environmental compensation model to obtain dynamic environmental compensation parameters; The initial calibration parameters are trained to obtain adjusted calibration parameters, the adjusted calibration parameters are fed back to the microsensor, the working state of the sensor is updated, and the internal humidity of the GIS is re-detected.

2. The microsensor-based GIS internal humidity detection method according to claim 1, characterized in that: The micro sensor is an LC wireless passive sensor; The GIS real-time environmental data includes real-time GIS internal humidity, real-time GIS internal temperature and real-time GIS internal air pressure; The GIS historical environmental data includes historical GIS internal humidity, historical GIS internal temperature and historical GIS internal air pressure; The initial calibration parameters include resonant frequency, Q value and sensitivity coefficient; The data preprocessing includes data cleaning and data filling.

3. The microsensor-based GIS internal humidity detection method as claimed in claim 2, characterized in that: The construction of the dynamic environment compensation model comprises: Use the initial calibration parameters to preliminarily calibrate the collected data, and construct vector matrix functions of real-time environmental data and historical environmental data respectively; Calculate the integral from the initial moment to the current moment t, accumulate the compensation amount at each time point, and obtain the environmental compensation parameter. The calculation formula is as follows: Among them, E c (t) represents the compensation amount of environmental data, τ is the integral variable, H r (τ) is the real-time humidity data at the current time τ, T r (τ) is the real-time temperature data at the current time τ, P r (τ) is the real-time air pressure data at the current time τ, H h (τ) is the historical humidity data at the historical time τ, T h (τ) is the historical temperature data of the historical time τ, P h (τ) is the historical air pressure data at historical time τ, M(H, T, P) is the vector matrix function based on humidity, temperature and air pressure, and the calculation formula is as follows: Among them, α i is the humidity coefficient, β i is the temperature coefficient, γ i is the air pressure coefficient, i=1, 2, 3, H is humidity, T is temperature, and P is air pressure.

4. The microsensor-based GIS internal humidity detection method as claimed in claim 3, characterized in that: The training of the initial calibration parameters comprises: Correct the real-time environmental data by calculating environmental compensation parameters and generate a compensation data set; Define the error function and build a calibration parameter adjustment model to adjust the initial calibration parameters; The error function is iterated and minimized by the gradient descent method to obtain the adjusted calibration parameters.

5. The microsensor-based GIS internal humidity detection method as claimed in claim 4, characterized in that: Generating a compensation data set comprises: According to the calculated environmental compensation parameter E c (t) Correct the real-time environmental data to obtain the compensated humidity detection result H f (t), the calculation formula is as follows: H f (t)=H r (t)+k1·E c (t) T f (t)=T r (t)+k2·E c (t) P f (t)=P r (t)+k3·E c (t) Among them, H f (t) is the humidity detection result after compensation, k1 is the humidity compensation coefficient, H r (t) is the real-time humidity data at time t, T f (t) is the temperature detection result after compensation, T r (t) is the real-time temperature data at time t, k2 is the temperature compensation coefficient, P f (t) is the air pressure detection result after compensation, P r (t) is the real-time air pressure data at time t, k3 is the air pressure compensation coefficient; The compensated dataset is fused with the original historical dataset to generate a complete compensated dataset.

6. The method for detecting humidity inside a GIS based on a microsensor as claimed in claim 5, characterized in that: The calculation formula of the error function is as follows: Among them, H c (t i ) is the compensation data set with time point t i Humidity compensation data, T c (t i ) is the temperature compensation data at time point ti in the compensation data set, P c (t i ) is the air pressure compensation data at time point ti in the compensation data set, H m (t i , Θ) is the humidity prediction value based on the calibration model, T m (t i , Θ) is the temperature prediction value based on the calibration model, P m (t i , Θ) is the predicted value of air pressure based on the calibration model, and n is the number of data points.

7. The microsensor-based GIS internal humidity detection method according to claim 6, characterized in that: The adjusted calibration parameters include: Construct a calibration parameter adjustment model. The calculation formula of the calibration parameter adjustment model is as follows: H m (t,Θ)=f r ·H c (t)+Q·T c (t)+S·P c (t) T m (t,Θ)=f r ·T c (t)+Q·H c (t)+S·P c (t) P m (t,Θ)=f r ·P c (t)+Q·H c (t)+S·T c (t) Where, Θ is the initial calibration parameter; The error function L(θ) is minimized using the gradient descent method, and the initial calibration parameters are updated. The update formula is as follows: Among them, Θ new is the updated calibration parameter, η is the learning rate, is the gradient of the error function; The calibration parameters are optimized and iteratively updated by gradient descent until the error function L(θ) converges to obtain the adjusted calibration parameters.

8. A GIS internal humidity detection system based on a microsensor, based on the GIS internal humidity detection method based on a microsensor according to any one of claims 1 to 7, characterized in that: Including data acquisition preprocessing module, dynamic environment compensation module and parameter training module; The data acquisition preprocessing module is used to record GIS internal environment data and initial calibration parameters using micro sensors, and perform data preprocessing on the GIS internal environment data, wherein the GIS internal environment data includes GIS real-time environment data and GIS historical environment data; The dynamic environment compensation module is used to construct a dynamic environment compensation model according to the internal environment data of the GIS, and input the real-time environment data of the GIS into the dynamic environment compensation model to obtain dynamic environment compensation parameters; The parameter training module is used to train the initial calibration parameters to obtain adjusted calibration parameters, feed the adjusted calibration parameters back to the microsensor, update the working state of the sensor, and re-detect to obtain the internal humidity of the GIS.

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 microsensor-based GIS internal humidity detection method according to any one of claims 1 to 7 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 microsensor-based GIS internal humidity detection method according to any one of claims 1 to 7 are implemented.

Images