Temperature measurement diagnosis method and system based on box-type substation

Abstract

The application relates to the technical field of power equipment diagnosis, and discloses a temperature measurement diagnosis method and system based on a box-type transformer substation, which comprises the following steps: S1, acquiring partial discharge data, current data and temperature data of the box-type transformer substation; S2, establishing a partial discharge and temperature correlation model according to the partial discharge data and the temperature data; and establishing a current and temperature mapping relationship according to the current thermal effect of the current data; S3, establishing a processing model according to the partial discharge and temperature correlation model, the current and temperature mapping relationship and the temperature data; inputting the partial discharge data, the current data and the temperature data into the processing model; and the processing model outputs a diagnosis result and a linkage control signal. The application solves the problem of low temperature measurement diagnosis accuracy in the prior art.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power equipment diagnosis, and relates to a temperature measurement diagnosis method and system based on a box-type substation. BACKGROUND

[0002] Temperature measurement diagnosis of a box-type substation generally includes real-time monitoring, analysis and fault warning of temperature states of transformer windings, switch contacts and cable joints. Temperature measurement diagnosis is a key module of intelligent upgrading of a box-type substation, and the penetration rate is rapidly increasing in the box-type substation market.

[0003] The existing temperature measurement diagnosis devices or methods do not model the physical correlation between partial discharge signals and temperature field changes, and cannot realize collaborative diagnosis of insulation degradation and temperature rise. Moreover, the real-time influence of current load changes on temperature rise is not quantified, which easily leads to fault misjudgment, and therefore the accuracy of temperature measurement diagnosis is low. SUMMARY

[0004] The present application provides a temperature measurement diagnosis method and system based on a box-type substation, aiming to solve the problem of low accuracy of temperature measurement diagnosis in the prior art.

[0005] In one scheme, the temperature measurement diagnosis method based on a box-type substation is provided, comprising the following steps:

[0006] S1, obtaining partial discharge data, current data and temperature data of a box-type substation;

[0007] S2, establishing a partial discharge and temperature correlation model according to the partial discharge data and the temperature data; and establishing a current and temperature mapping relationship according to the current thermal effect of the current data;

[0008] S3, establishing a processing model according to the partial discharge and temperature correlation model, the current and temperature mapping relationship and the temperature data, inputting the partial discharge data, the current data and the temperature data into the processing model, and outputting a diagnosis result and a linkage control signal by the processing model.

[0009] In one scheme, the temperature data includes thermal imaging data and sensor temperature data; in step S2, a partial discharge and temperature correlation model is established according to the partial discharge data and the thermal imaging data; and in step S3, a processing model is established according to the partial discharge and temperature correlation model, the current and temperature mapping relationship and the sensor temperature data.

[0010] In one scheme, the box-type substation comprises a high-voltage chamber, a transformer chamber and a low-voltage chamber; temperature sensors are installed on cable head copper bars of the high-voltage chamber, windings and iron cores of the transformer chamber, and incoming and outgoing line copper bars of the transformer chamber, and incoming and outgoing line copper bars of the low-voltage chamber; current sensors are arranged on three incoming lines and four outgoing lines of the transformer chamber; a plurality of partial discharge sensors are installed on inner walls of the transformer; and a thermal imager is further arranged in the box-type substation.

[0011] Specifically, the partial discharge sensor is a TEV partial discharge sensor.

[0012] In one scheme, the temperature sensors of the high-voltage side windings and iron cores of the transformer chamber and the incoming and outgoing line copper bars of the low-voltage chamber are optical fiber single-point temperature measurement sensors; the temperature sensors of the cable head copper bars of the high-voltage chamber and the incoming and outgoing line copper bars of the transformer chamber are RFID temperature sensors; and the temperature sensors of the low-voltage side windings and iron cores of the transformer chamber are PT100 sensors.

[0013] In one scheme, the step of establishing the partial discharge and temperature correlation model comprises: collecting partial discharge characteristic quantities and thermal imaging data of a plurality of time periods and fitting a Hurst index; establishing a temperature rise mapping formula through the Hurst index; and establishing a dynamic temperature rise model according to the temperature rise mapping formula.

[0014] In one scheme, the current and temperature mapping relationship is based on current load Dynamic temperature field formula: t is achieved; wherein R is the equivalent resistance of the equipment, k is the thermal conductivity of the material, ΔT represents the temperature change amount at time t; I represents the current load changing over time.

[0015] In one scheme, after step S2 is performed, the method further comprises the steps of: taking the thermal imaging data as plane coordinates and calibrating the detection positions of each temperature sensor, calibrating the partial discharge source positions according to the partial discharge and temperature correlation model, and calibrating the detection positions of the current sensors according to the current and temperature mapping relationship.

[0016] In one scheme, the establishment of the processing model is through dynamic adjustment of weight distribution based on D-S evidence theory, dynamic adjustment of weight distribution of output confidence of the thermal imaging data, the partial discharge data, the current data and the sensor temperature data, setting of the output confidence threshold, and establishment of a dynamic weight fusion diagnosis mechanism.

[0017] In one scheme, the dynamic adjustment of weight distribution is performed through the formula: ; wherein, is the current weight of sensor i; is the last weight of sensor i; is any temperature sensor or partial discharge sensor or thermal imager; is the learning rate; is the recent prediction error of sensor i. Wherein, the recent prediction error of sensor i is roughly estimated by the covariance and prediction value of Kalman filter output.

[0018] In one scheme, the temperature measurement diagnosis system based on box-type substation is provided in another aspect, which uses the temperature measurement diagnosis method.

[0019] The beneficial effects of the present application are: the correlation model of partial discharge and temperature is established according to the partial discharge data and the temperature data, which can improve the diagnosis accuracy of insulation deterioration and improve the detection rate of instantaneous temperature anomaly. By establishing the mapping relationship between current and temperature, the real-time influence of current load change on temperature rise can be quantified, so as to reduce the fault misjudgment and improve the accuracy of temperature measurement diagnosis. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0021] Figure 1 is the temperature measurement diagnosis method flowchart in an embodiment of the present application;

[0022] Figure 2 is the comparison chart of traditional temperature measurement and the temperature measurement of the present method in an embodiment of the present application;

[0023] Figure 3 is the comparison chart of traditional temperature measurement and the temperature measurement diagnosis of the present method in an embodiment of the present application; DETAILED DESCRIPTION

[0024] The specific embodiments of the present application will be further described in detail below in combination with the drawings and embodiments. The following embodiments are used to illustrate the present application, but not to limit the scope of the present application. Similarly, the following embodiments are only some embodiments of the present application, not all embodiments, and all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0025] In this disclosure, the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" mean that a particular feature, structure, material, or characteristic is included in at least one embodiment or example of the present disclosure. Exemplary representations of the above terms in this specification are not necessarily directed to the same embodiment or example. Moreover, the described particular features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples. In addition, different embodiments or examples described in this specification and features of different embodiments or examples can be combined and combined by those skilled in the art without contradiction.

[0026] The present application makes improvements and innovations, and proposes the following embodiments.

[0027] In some embodiments, referring to Figure 1 In one aspect, a temperature measurement and diagnosis method based on a box-type substation is provided, comprising the following steps:

[0028] S1, obtaining partial discharge data, current data and temperature data of the box-type substation;

[0029] S2, establishing a partial discharge and temperature correlation model according to the partial discharge data and the temperature data; and establishing a current and temperature mapping relationship according to the current thermal effect of the current data;

[0030] S3, establishing a processing model according to the partial discharge and temperature correlation model, the current and temperature mapping relationship, and the temperature data; inputting the partial discharge data, the current data and the temperature data into the processing model; and outputting a diagnosis result and a linkage control signal by the processing model.

[0031] The partial discharge and temperature correlation model established according to the partial discharge data and the temperature data can improve the accuracy of insulation deterioration diagnosis and increase the instantaneous temperature anomaly detection rate. By establishing the current and temperature mapping relationship, the real-time influence of current load change on temperature rise can be quantified, so as to reduce fault misjudgment and improve the accuracy of temperature measurement and diagnosis.

[0032] In some embodiments, the temperature data includes thermal imaging data and sensor temperature data; in step S2, a partial discharge and temperature correlation model is established according to the partial discharge data and the thermal imaging data; and in step S3, a processing model is established according to the partial discharge and temperature correlation model, the current and temperature mapping relationship, and the sensor temperature data. The thermal imaging data can intuitively reflect the temperature condition of the box-type substation, and the sensor temperature data can obtain the temperature condition of a specific position in the box-type substation. This is used to improve the temperature detection of the box-type substation, provide more data support for subsequent diagnosis work, and improve the accuracy of diagnosis.

[0033] In some embodiments, the box-type transformer substation comprises a high-voltage chamber, a transformer chamber and a low-voltage chamber; temperature sensors are installed on cable head copper bars of the high-voltage chamber, windings and cores of the transformer chamber, and incoming and outgoing line copper bars of the transformer chamber and the low-voltage chamber; current sensors are arranged on three incoming lines and four outgoing lines of the transformer chamber; a plurality of partial discharge sensors are installed on the inner wall of the transformer chamber; and a thermal imager is further arranged in the box-type transformer substation. The temperature sensors installed on the cable head copper bars of the high-voltage chamber, the windings and cores of the transformer chamber, and the incoming and outgoing line copper bars of the transformer chamber and the low-voltage chamber can facilitate obtaining temperature data of the corresponding positions; the current sensors arranged on the three incoming lines and the four outgoing lines of the transformer chamber can facilitate obtaining current conditions of the corresponding circuits; and the plurality of partial discharge sensors installed on the inner wall of the transformer chamber can facilitate obtaining partial discharge signals of a plurality of positions. The plurality of temperature data, current data and partial discharge data can provide more data support for subsequent diagnosis work and improve the accuracy of diagnosis.

[0034] Specifically, the partial discharge sensor is a TEV partial discharge sensor. The use of the TEV partial discharge sensor can better obtain electromagnetic pulse signals of partial discharge and improve the sensitivity of detection.

[0035] In some embodiments, the temperature sensors of the high-voltage side windings and cores of the transformer chamber and the incoming and outgoing line copper bars of the low-voltage chamber are optical fiber single-point temperature measurement sensors; the temperature sensors of the cable head copper bars of the high-voltage chamber and the incoming and outgoing line copper bars of the transformer chamber are RFID temperature sensors; and the temperature sensors of the low-voltage side windings and cores of the transformer chamber are PT100 sensors.

[0036] Specifically, the optical fiber single-point temperature measurement sensor has high precision and sensitivity, the measurement precision reaches ±0.1℃, and it can capture slight temperature changes (such as 0.1℃ level fluctuations); the response speed to local overheating points is much higher than that of traditional thermocouples; and it can stably work in electromagnetic interference environments such as high-voltage transformer substations and radar stations without signal distortion risk.

[0037] The RFID temperature sensor (Radio Frequency Identification Temperature Sensor) can withstand an environmental temperature of -40℃~220℃, is suitable for high-temperature scenes such as transformer substations and metallurgy, and can eliminate the difficulty of power line layout through radio frequency signal power taking of a reader / writer, and is especially suitable for temperature measurement of high-voltage equipment (such as switch cabinet contacts) and rotating parts.

[0038] The PT100 sensor (platinum resistance temperature sensor) can compensate for wire resistance error through three-wire / two-wire connection and reduce the influence of line interference.

[0039] In some embodiments, the steps for establishing the partial discharge and temperature correlation model include: collecting partial discharge characteristic quantities and thermal imaging data over multiple time periods and fitting the Hurst exponent; establishing a temperature rise mapping formula using the Hurst exponent; and establishing a dynamic temperature rise model based on the temperature rise mapping formula.

[0040] After establishing a dynamic temperature rise model, the location of partial discharge can be accurately captured by the partial discharge sensor in conjunction with the dynamic temperature rise model, which improves the accuracy of insulation degradation diagnosis and increases the detection rate of instantaneous temperature anomalies.

[0041] Specifically, the heating mapping formula established using the Hurst exponent is based on the fact that partial discharge signals exhibit a non-uniform, self-similar scattered point distribution in the time-frequency domain (such as PRPD spectra), and its complexity can be described by the fractal dimension (box dimension). The partial discharge signal is converted into a binary image, and an improved grid covering method is used to count the number of scattered point regions covered by grids of different sizes. The fractal dimension is then obtained by fitting the slope using double logarithmic coordinates. Specifically, the formula... ,in, Grid side length The number of non-empty grids in the lower cover discharge region, It is the fractal dimension.

[0042] The Hurst exponent quantifies the long-range correlation between partial emission time series and temperature time series within a fractal grid using rescaled range analysis (R / S analysis). The length is... The original sequence (partial discharge signal and temperature time series) is divided into multiple sub-intervals, each with a length of [length missing]. ,common The data is divided into several intervals. For each sub-interval, the data is zero-mean normalized to eliminate baseline offset interference. in This is the mean of the sub-intervals. Calculate the cumulative deviation for each sub-interval. Characterizing the cumulative effect of sequence deviation from the mean: The range (R) is defined as the difference between the maximum and minimum cumulative deviations: Define S as the standard deviation, and calculate the standard deviation for each subinterval. Value, eliminating the influence of dimensions: For multiple sub-interval lengths Repeat the above steps to fit. and The linear relationship is used to obtain the formula: in The intercept; The slope is the Hurst exponent.

[0043] Finally, the formula for the local temperature rise mapping model can be obtained: in, Box dimension, Hurst index; thermal conductivity of material; .

[0044] According to the local temperature rise mapping model formula to construct a dynamic temperature rise model: Laplace , k is the thermal conductivity constant; wherein, ; wherein, (According to the current thermal effect, thermal conductivity of material, ρ is the density, c is the specific heat capacity), (Local discharge temperature rise estimation).

[0045] Using this formula can quickly obtain the local dynamic temperature rise.

[0046] In some embodiments, the current and temperature mapping relationship is based on the current load Dynamic temperature field formula: t is realized; wherein The equivalent resistance of the device, thermal conductivity of material, Indicates the temperature change at time t; Indicates the current load changes over time.

[0047] In some embodiments, after step S2, it further includes the steps of: taking the thermal imaging data as the plane coordinates and calibrating the detection positions of each temperature sensor, calibrating the local discharge source position according to the local discharge and temperature correlation model, and calibrating the detection position of the current sensor according to the current and temperature mapping relationship. By constructing a unified space reference, the coordinate system difference is eliminated. Since each sensor (such as temperature sensor, current sensor, local discharge sensor) has an independent coordinate system, it needs to be converted to the global coordinate system through calibration to establish an accurate mapping relationship between temperature data and physical position. It can avoid the situation that the thermodynamic analysis is invalid due to the split of the coordinate system.

[0048] Specifically, taking the thermal imaging data as the plane coordinates and calibrating the detection positions of each temperature sensor, calibrating the local discharge source position, and calibrating the detection position of the current sensor need to be processed as follows: taking the thermal imaging plane coordinates as the reference.

[0049] 1. Time alignment: using a sliding window mechanism to compensate for transmission delay (window size Δt = 1s) Wherein The delay time of each sensor is calibrated through NTP protocol.

[0050] 2. Time-frequency analysis of local discharge signal: extract the equivalent time width And the center frequency wherein is the partial discharge time-domain signal, is the Fourier transform thereof.

[0051] 3. Partial discharge space matching degree calculation: partial discharge correlation point coordinates and thermal imaging high-temperature area coincidence degree. wherein, by comparing the thermal imaging temperature with the high-temperature threshold , the high-temperature area is identified; the distance between the partial discharge correlation point coordinates and the high-temperature area center coordinates is calculated ) through a specific function or coefficient and temperature-related constant , the matching degree Match is calculated; when Match ≥ 0.9, it is determined as an effective correlation point is the high-temperature threshold, ); when the matching degree Match ≥ 0.9, it is considered that the partial discharge point and the high-temperature area have effective correlation, indicating that the equipment has specific faults or overheating phenomenon.

[0052] Current sensor joule heat model: dynamic temperature field based on current load ; t wherein is the equivalent resistance of the equipment, is the thermal conductivity of the material.

[0053] 4. Current space matching degree calculation: current correlation point coordinates and thermal imaging high-temperature area coincidence degree. The point coordinates are calculated using the spectrum graph normalized cross-correlation algorithm , and when Match ≥ 0.9, it is determined as an effective correlation point.

[0054] Specifically, the matching degree calculation and correlation point confirmation of other single-point temperature measurement sensors are the same as those of the current sensor.

[0055] After aligning the collection time of the sensors, spatial registration under time synchronization can be realized through coordinate calibration, avoiding the "ghost" phenomenon of fused data. Adopting dynamic window mechanism to compensate for transmission delay can eliminate the time sequence misalignment of multiple sensors, suppress network transmission jitter, and support dynamic temperature field reconstruction.

[0056] The partial discharge space matching degree calculation formula can evaluate the matching degree of the partial discharge point and the high-temperature area by comprehensively considering the thermal imaging temperature and distance factors.

[0057] In some embodiments, the establishment of the processing model is by dynamically adjusting the weight distribution of the output confidence of the thermal imaging data, partial discharge data, current data, and sensor temperature data based on the D-S evidence theory, and setting an output confidence threshold to establish a dynamic weight fusion diagnosis mechanism.

[0058] Through the improved D-S evidence theory, the weight is adaptively and dynamically adjusted, and the multi-source sensor data such as temperature, current, thermal imaging, and single-point temperature measurement are fused to output abnormal probability and perform abnormal diagnosis.

[0059] According to the data confidence, the weight is distributed, and the sensor weight is dynamically and adaptively adjusted to fuse the multi-source data output confidence and diagnosis including thermal imaging, partial discharge, current, and single-point temperature measurement: set the temperature rise greater than in a point and a time as a temperature change anomaly (code A), and the temperature greater than as an over-temperature anomaly (code B), and the point is also a single-point temperature measurement associated point, a current associated point, and a partial discharge associated point, and the evidence body calculation can be obtained at this time. , is . Wherein, K is a constant, the confidence threshold is set to 0.5, and when the abnormal confidence is greater than 0.5, a pre-warning alarm is generated, and the alarm point is highlighted.

[0060] In some embodiments, the dynamic adjustment of the weight distribution is performed by the formula: ; wherein, is the current weight of sensor i; is the last weight of sensor i; is any temperature sensor or partial discharge sensor or thermal imager; is the learning rate; is the recent prediction error of sensor i. Wherein, the recent prediction error of sensor i is estimated by the covariance and prediction value output by Kalman filtering. Taking the Kalman filtering fusion of the thermal imaging and partial discharge associated point position as an example.

[0061] The state transition process is the thermal imaging temperature measurement value at the last moment plus the partial discharge temperature rise value, and the measurement value is the thermal imaging temperature measurement value at the next moment, and the transition matrix ] state x= [ T t -∆ t , Q PD ×∆ t] T , measurement Z= , is the measurement covariance, is the thermal imaging and partial discharge covariance matrix, the Kalman gain , the Kalman state update , and the Kalman covariance update = .

[0062] After obtaining the error covariance matrix, the confidence of each sensor m can be calculated using Gaussian distribution integration , where is the error standard deviation.

[0063] Specifically, the processing model outputs three levels of conclusions of "normal", "temperature rise warning" and "over-temperature warning" after processing the input data; and outputs a linkage control signal, for example, when the alarm is triggered, the fault information is automatically uploaded to the operation and maintenance platform, and the fan is started to dissipate heat, and if the temperature does not decrease within 10 minutes, remote power-off protection is triggered.

[0064] In some embodiments, the other aspect provides a temperature measurement and diagnosis system based on a box-type substation, which adopts the temperature measurement and diagnosis method. According to the establishment of the partial discharge and temperature correlation model based on the partial discharge data and the temperature data, the accuracy of the insulation deterioration diagnosis can be improved, and the instantaneous temperature anomaly detection rate can be improved. By establishing the mapping relationship between the current and the temperature, the real-time influence of the current load change on the temperature rise can be quantified, so that the fault misjudgment can be reduced, and the accuracy of the temperature measurement and diagnosis can be improved.

[0065] As shown in Figure 2 , the blue line represents the case where only an optical fiber single-point temperature measurement sensor is arranged in the substation, and the output temperature fluctuates greatly, while the yellow line is the temperature line output after the partial discharge data, current data and temperature data are input into the processing model using the method of the present application, and the fluctuation amplitude of the temperature is smaller than that of the blue line, and the line is smooth. In combination with Figure 3 , when diagnosing the temperature condition, the accuracy of the method of the present application is higher than that of the traditional optical fiber single-point temperature measurement sensor due to the dynamic allocation of weights of multiple data.

[0066] The above are only optional embodiments of the present application and do not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. Those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A temperature measurement diagnosis method based on a box-type substation, characterized by, The method comprises the following steps: S1, obtaining partial discharge data, current data and temperature data of the box-type substation; S2, establishing a partial discharge and temperature correlation model according to the partial discharge data and the temperature data; and establishing a current and temperature mapping relationship according to the current thermal effect of the current data; The temperature data comprises thermal imaging data and sensor temperature data; and the partial discharge and temperature correlation model is established according to the partial discharge data and the thermal imaging data; The establishment of the partial discharge and temperature correlation model comprises: Collecting partial discharge characteristic quantities and thermal imaging data in multiple time periods and fitting a Hurst index; Establishing a temperature rise mapping formula through the Hurst index; Establishing a dynamic temperature rise model according to the temperature rise mapping formula; The current-temperature mapping relationship is based on current load Dynamic temperature field formula: t is achieved; wherein R is the equivalent resistance of the device, K is the thermal conductivity of the material, represents the temperature change at time t; represents the current load over time; S3, establishing a processing model according to the partial discharge and temperature correlation model, the current and temperature mapping relationship and the sensor temperature data; inputting the partial discharge data, the current data and the sensor temperature data into the processing model, and outputting a diagnosis result and a linkage control signal by the processing model; The processing model is established by dynamically adjusting the weight distribution of the output confidence of the thermal imaging data, the partial discharge data, the current data and the sensor temperature data based on the D-S evidence theory, setting a threshold value of the output confidence, and establishing a dynamic weight fusion diagnosis mechanism.

2. The temperature measurement diagnostic method according to claim 1, characterized in that, The box-type substation comprises a high-voltage chamber, a transformer chamber and a low-voltage chamber; temperature sensors are installed on cable head copper bars of the high-voltage chamber, windings and iron cores of the transformer chamber, and incoming and outgoing line copper bars of the transformer chamber and the low-voltage chamber; current sensors are arranged on three incoming lines and four outgoing lines of the transformer chamber; a plurality of partial discharge sensors are installed on the inner wall of the transformer; and a thermal imager is further arranged in the box-type substation.

3. The temperature measurement diagnostic method according to claim 2, characterized in that The temperature sensors of the high-voltage side windings and iron cores of the transformer chamber and the incoming and outgoing line copper bars of the low-voltage chamber are optical fiber single-point temperature measurement sensors; the temperature sensors of the cable head copper bars of the high-voltage chamber and the incoming and outgoing line copper bars of the transformer chamber are RFID temperature sensors; and the temperature sensors of the low-voltage side windings and iron cores of the transformer chamber are PT100 sensors.

4. The temperature measurement diagnostic method according to claim 2, characterized in that, After step S2, the following step is further included: The detection positions of the temperature sensors are calibrated with the thermal imaging data as plane coordinates, the partial discharge source positions are calibrated according to the partial discharge and temperature correlation model, and the detection positions of the current sensors are calibrated according to the current and temperature mapping relationship.

5. The temperature measurement diagnostic method according to claim 2, characterized in that, The dynamic adjustment of the weight distribution is performed by the formula: ; wherein, is the current weight for sensor i; is the previous weight for sensor i; is any temperature sensor or partial discharge sensor or thermal imager; is the learning rate; is the recent prediction error for sensor i.

6. A temperature measurement diagnosis system based on a box-type substation, characterized by, The temperature measurement and diagnosis method is performed by using any one of claims 1-5.

Images