A method, system, device and medium for detecting gas in transformer

Abstract

The present invention discloses a transformer gas detection method, system, device and medium. When receiving gas data to be detected corresponding to the transformer, multiple gas parameters corresponding to the gas data to be detected are obtained. Based on the gas parameters and the preset detection sensitivity principle, the detection sensor corresponding to the gas data to be detected is determined. Based on the detection sensor and the corresponding gas parameters, a target fitting polynomial corresponding to the detection sensor is constructed. Based on the target preset fitting polynomial, the detection data corresponding to the gas data to be detected is determined. Through the preset detection sensitivity principle, combined with the cross-sensitivity characteristics of the sensor, one sensor can detect multiple gas parameters, which greatly reduces the number of sensors in the system and reduces the difficulty of sensor integration.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer gas detection, and in particular to a transformer gas detection method, system, equipment and medium. Background Art

[0002] Gas protection is one of the main protections for transformers. It reflects the internal faults of transformers through changes in gas capacity and oil flow rate. It has the advantages of high sensitivity, rapid action, and simple wiring, providing effective protection for the safe and stable operation of transformers. However, in actual operation, due to the single function of traditional gas relays, it is unable to identify fault gas components and gas aggregation rates, resulting in some deficiencies in gas protection, such as the small amount of light gas alarm information, which makes it difficult to support rapid on-site operation and maintenance decisions. Therefore, a sensing technology that can be integrated with traditional gas relays to achieve rapid detection of gas components is needed.

[0003] The main components of transformer gas are methane (CH4), carbon monoxide (CO), ethane (C2H6), carbon dioxide (CO2), ethylene (C2H4), acetylene (C2H2) and hydrogen (H2). In actual application, the use of optical (such as photoacoustic spectroscopy) or chromatography technology can achieve simultaneous detection of the 7 components of gas, but the detection device is too large to be integrated with the gas relay. Therefore, a micro gas sensor is needed to achieve the above requirements. The main types of existing micro gas sensors are semiconductor type, infrared type, electrochemical type or catalytic combustion type, which can detect a certain type of gas, but there is a cross-sensitivity problem for mixed gases.

[0004] In order to improve the accuracy of transformer gas multi-parameter sensing detection, the existing transformer gas detection method uses an intelligent algorithm to suppress the sensor's sensitivity to non-target parameters, and sets a sensor for each of the transformer gas multiple parameter indicators, resulting in the multi-sensor system being difficult to control in volume and difficult to integrate. Summary of the invention

[0005] The present invention provides a transformer gas detection method, system, device and medium, which solves the technical problems that the existing transformer gas detection method adopts an intelligent algorithm to suppress the sensitivity of the sensor to non-target parameters, and sets a sensor for each of the multiple parameter indicators of the transformer gas, resulting in the difficulty in controlling the volume of the multi-sensor system and high integration difficulty.

[0006] The present invention provides a transformer gas detection method, comprising:

[0007] When receiving the gas data to be detected corresponding to the transformer, obtaining a plurality of gas parameters corresponding to the gas data to be detected;

[0008] Determine the detection sensor corresponding to the gas data to be detected according to the gas parameters and the preset detection sensitivity principle;

[0009] According to the detection sensor and the corresponding gas parameters, construct a target fitting polynomial corresponding to the detection sensor;

[0010] According to the target preset fitting polynomial, the detection data corresponding to the gas data to be detected is determined.

[0011] Optionally, the step of determining the detection sensor corresponding to the gas data to be detected according to the gas parameter and a preset detection sensitivity principle includes:

[0012] The gas parameters are grouped respectively according to a preset detection sensitivity principle to generate a plurality of initial gas groups corresponding to the gas data to be detected;

[0013] The initial gas group corresponding to the maximum value of the gas parameter quantity is used as the target gas group;

[0014] Determining a first sensor corresponding to the gas data to be detected based on the sensitivity type corresponding to the target gas group;

[0015] The detection sensor corresponding to the gas data to be detected is determined according to the first sensor and the gas parameter.

[0016] Optionally, the step of determining the detection sensor corresponding to the gas data to be detected according to the first sensor and the gas parameter includes:

[0017] Determining whether the cross-sensitive parameter source corresponding to the first sensor includes all the gas parameters;

[0018] If yes, the first sensor is used as the detection sensor corresponding to the gas data to be detected;

[0019] If not, the detection sensor corresponding to the gas data to be detected is determined according to the cross-sensitive parameter source and the gas parameter.

[0020] Optionally, the step of determining the detection sensor corresponding to the gas data to be detected according to the cross-sensitive parameter source and the gas parameter includes:

[0021] Taking the gas parameter that does not belong to the cross-sensitive parameter source as the gas parameter to be identified;

[0022] According to the preset detection sensitivity principle, determining the second sensor corresponding to the gas data to be detected;

[0023] The first sensor and the second sensor are used as detection sensors corresponding to the gas data to be detected.

[0024] Optionally, the step of constructing a target fitting polynomial corresponding to the detection sensor according to the detection sensor and the corresponding gas parameter includes:

[0025] Obtaining operating data corresponding to the transformer;

[0026] Based on the operating data, determining a gas test concentration corresponding to the detection sensor;

[0027] Using an orthogonal test method to construct a corresponding gas concentration value table based on the gas test concentration;

[0028] According to the gas concentration value table and the detection sensor, a target fitting polynomial corresponding to the detection sensor is constructed.

[0029] Optionally, the step of constructing a target fitting polynomial corresponding to the detection sensor according to the gas concentration value table and the detection sensor includes:

[0030] Acquire a response data set corresponding to the gas concentration value table through the detection sensor;

[0031] Based on the response data set and the gas concentration value table, construct a sensor response curve corresponding to the detection sensor;

[0032] Based on the sensor response curve, construct an initial fitting polynomial corresponding to the gas data to be detected;

[0033] Using the least square method to obtain the fitting coefficient corresponding to the initial fitting polynomial;

[0034] The initial fitting polynomial is updated by using the fitting coefficient to generate a target fitting polynomial corresponding to the gas data to be detected.

[0035] Optionally, the step of determining the detection data corresponding to the gas data to be detected according to the preset fitting polynomial of the target includes:

[0036] Based on the sensor response curve corresponding to the target preset fitting polynomial, a corresponding response inverse function model is constructed;

[0037] Performing an inverse operation on the target fitting polynomial through the response inverse function model to generate a response function corresponding to the detection sensor;

[0038] Substitute the gas data to be detected into the response function respectively to determine the detection data corresponding to the gas data to be detected.

[0039] The present invention also provides a transformer gas detection system, comprising:

[0040] A gas parameter acquisition module, for acquiring a plurality of gas parameters corresponding to the gas data to be detected when receiving the gas data to be detected corresponding to the transformer;

[0041] A detection sensor determination module, used to determine the detection sensor corresponding to the gas data to be detected according to the gas parameters and a preset detection sensitivity principle;

[0042] A target fitting polynomial construction module is used to construct a target fitting polynomial corresponding to the detection sensor according to the detection sensor and the corresponding gas parameters;

[0043] The detection data determination module is used to determine the detection data corresponding to the gas data to be detected according to the preset fitting polynomial of the target.

[0044] The present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of implementing any of the above-mentioned transformer gas detection methods.

[0045] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed, any of the above transformer gas detection methods is implemented.

[0046] It can be seen from the above technical solutions that the present invention has the following advantages:

[0047] The present invention obtains multiple gas parameters corresponding to the gas data to be detected when receiving the gas data to be detected corresponding to the transformer. Based on the gas parameters and the preset detection sensitivity principle, the detection sensor corresponding to the gas data to be detected is determined. Based on the detection sensor and the corresponding gas parameters, a target fitting polynomial corresponding to the detection sensor is constructed. Based on the target preset fitting polynomial, the detection data corresponding to the gas data to be detected is determined. The existing transformer gas detection method adopts an intelligent algorithm to suppress the sensitivity of the sensor to non-target parameters, and sets a sensor for each of the multiple parameter indicators of the transformer gas, resulting in the technical problem that the volume of the multi-sensor system is difficult to control and the integration difficulty is high. Through the preset detection sensitivity principle, combined with the cross-sensitivity characteristics of the sensor, one sensor can detect multiple gas parameters, which greatly reduces the number of sensors in the system and reduces the difficulty of sensor integration. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative labor.

[0049] Figure 1 A flowchart of a transformer gas detection method provided in Embodiment 1 of the present invention;

[0050] Figure 2 A flow chart of the steps of a transformer gas detection method provided in Embodiment 2 of the present invention;

[0051] Figure 3 A schematic diagram of a process for artificially preparing a gas sample to obtain a sensor response function according to the second embodiment of the present invention;

[0052] Figure 4 A flowchart of a transformer gas detection method provided in Embodiment 2 of the present invention;

[0053] Figure 5 This is a structural block diagram of a transformer gas detection system provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0054] The embodiments of the present invention provide a transformer gas detection method, system, device and medium, which are used to solve the technical problems that the existing transformer gas detection method adopts an intelligent algorithm to suppress the sensitivity of the sensor to non-target parameters, and sets a sensor for each of the multiple parameter indicators of the transformer gas, resulting in the difficulty in controlling the volume of the multi-sensor system and high integration difficulty.

[0055] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] See also Figure 1 , Figure 1 A flowchart of the steps of a transformer gas detection method provided in Embodiment 1 of the present invention.

[0057] The present invention provides a transformer gas detection method, comprising:

[0058] Step 101: when receiving the gas data to be detected corresponding to the transformer, a plurality of gas parameters corresponding to the gas data to be detected are obtained.

[0059] The gas data to be detected refers to the components corresponding to the gas of the transformer, and the gas data to be detected includes multiple gas parameters corresponding to the transformer, such as methane, carbon monoxide, ethane, carbon dioxide, ethylene, acetylene and hydrogen.

[0060] In the embodiment of the present invention, when the gas data to be detected corresponding to the transformer is received, the gas parameters that need to be detected for the transformer are determined based on the components corresponding to the gas data to be detected.

[0061] Step 102: Determine the detection sensor corresponding to the gas data to be detected according to the gas parameters and the preset detection sensitivity principle.

[0062] The preset detection sensitivity principle refers to grouping gas parameters according to the preset detection sensitivity grouping. The detection sensitivity grouping includes semiconductor type sensitive grouping, infrared type sensitive grouping, electrochemical type sensitive grouping and catalytic combustion type sensitive grouping. Among them, the semiconductor type sensitive grouping includes methane and hydrogen. The infrared type sensitive grouping includes carbon dioxide, methane, and ethylene. The electrochemical type sensitive grouping includes carbon monoxide and hydrogen. The catalytic combustion type sensitive grouping includes hydrogen, methane, ethane, and acetylene.

[0063] In an embodiment of the present invention, the gas parameters are grouped according to a preset detection sensitivity principle to generate a plurality of initial gas groups corresponding to the gas data to be detected. The initial gas group corresponding to the maximum value of the gas parameter quantity is used as the target gas group, and the first sensor corresponding to the gas data to be detected is determined based on the sensitivity type corresponding to the target gas group. Based on the first sensor and the gas parameters, the detection sensor corresponding to the gas data to be detected is determined.

[0064] Step 103: construct a target fitting polynomial corresponding to the detection sensor according to the detection sensor and the corresponding gas parameters.

[0065] In an embodiment of the present invention, the operation data corresponding to the transformer is obtained, and the gas test concentration corresponding to the detection sensor is determined based on the operation data. The orthogonal test method is used to construct a corresponding gas concentration value table based on the gas test concentration, and the target fitting polynomial corresponding to the detection sensor is constructed based on the gas concentration value table and the detection sensor.

[0066] Step 104: Determine the detection data corresponding to the gas data to be detected according to the preset fitting polynomial of the target.

[0067] In the embodiment of the present invention, a corresponding response inverse function model is constructed by using a sensor response curve corresponding to a target preset fitting polynomial. The target fitting polynomial is inversely operated by the response inverse function model to generate a response function corresponding to the detection sensor. The gas data to be detected are respectively substituted into the response function to determine the detection data corresponding to the gas data to be detected.

[0068] In an embodiment of the present invention, when receiving the gas data to be detected corresponding to the transformer, multiple gas parameters corresponding to the gas data to be detected are obtained. Based on the gas parameters and the preset detection sensitivity principle, the detection sensor corresponding to the gas data to be detected is determined. Based on the detection sensor and the corresponding gas parameters, a target fitting polynomial corresponding to the detection sensor is constructed. Based on the target preset fitting polynomial, the detection data corresponding to the gas data to be detected is determined. The existing transformer gas detection method adopts an intelligent algorithm to suppress the sensitivity of the sensor to non-target parameters, and sets a sensor for each of the multiple parameter indicators of the transformer gas, resulting in the technical problem that the volume of the multi-sensor system is difficult to control and the integration difficulty is high. Through the preset detection sensitivity principle, combined with the cross-sensitivity characteristics of the sensor, one sensor can detect multiple gas parameters, which greatly reduces the number of sensors in the system and reduces the difficulty of sensor integration.

[0069] See also Figure 2 , Figure 2 A flow chart of the steps of a transformer gas detection method provided in Embodiment 2 of the present invention.

[0070] Step 201: when receiving the gas data to be detected corresponding to the transformer, a plurality of gas parameters corresponding to the gas data to be detected are obtained.

[0071] In an embodiment of the present invention, in response to the received gas data to be detected, and based on the gas data to be detected, the physical quantity to be detected, i.e., multiple gas parameters corresponding to the gas data to be detected, such as hydrogen, methane, acetylene and other gases, are determined.

[0072] Step 202: group the gas parameters according to the preset detection sensitivity principle to generate a plurality of initial gas groups corresponding to the gas data to be detected.

[0073] In the embodiment of the present invention, the gas parameters are grouped according to the detection sensitive grouping corresponding to the detection sensitive principle, and the detection sensitive grouping to which the gas parameters belong is determined. Among them, one gas parameter can belong to multiple detection sensitive groups, and all detection sensitive groups corresponding to all gas parameters are used as multiple initial gas groups corresponding to the gas data to be detected.

[0074] Step 203: taking the initial gas group corresponding to the maximum value of the gas parameter quantity as the target gas group.

[0075] In the embodiment of the present invention, the detection sensitive group containing the largest number of gas parameters corresponding to the gas data to be detected in the detection sensitive group is used as the target gas group. Assuming that the gas parameters are hydrogen, methane, ethane, ethylene, and acetylene, based on the detection sensitivity principle, the catalytic combustion sensitive group will be selected as the target gas group.

[0076] Step 204: Determine the first sensor corresponding to the gas data to be detected based on the sensitivity type corresponding to the target gas group.

[0077] In the embodiment of the present invention, the sensitive type refers to the detection sensitive group corresponding to the target gas group. Based on the detection sensitive group corresponding to the target gas group, the type of the first sensor is determined. For example, if the sensitive type corresponding to the target gas group is a semiconductor sensitive group, the first sensor corresponding to the gas data to be detected should be a semiconductor sensor.

[0078] Step 205: Determine the detection sensor corresponding to the gas data to be detected based on the first sensor and the gas parameters.

[0079] Further, step 205 may include the following sub-steps S11-S13:

[0080] S11. Determine whether the cross-sensitive parameter source corresponding to the first sensor includes all gas parameters.

[0081] S12: If yes, use the first sensor as the detection sensor corresponding to the gas data to be detected.

[0082] S13. If not, determine the detection sensor corresponding to the gas data to be detected based on the cross-sensitive parameter source and the gas parameters.

[0083] In an embodiment of the present invention, the cross-sensitive parameter source refers to the sensitive gas corresponding to the specifically selected first sensor, which may be the same as the sensitive gas contained in the corresponding detection sensitive group, or may be different, and is determined based on the sensor model actually selected. It is determined whether the multiple gas parameters corresponding to the gas data to be detected are all cross-sensitive parameter sources corresponding to the first sensor. If so, the first sensor is used as the detection sensor corresponding to the gas data to be detected, that is, only the first sensor is used to perform gas detection on the gas data to be detected. If not, the next sensor is selected based on the gas parameters that do not belong to the cross-sensitive parameter source corresponding to the first sensor. The obtained sensor and the first sensor are used together as the detection sensor corresponding to the gas data to be detected.

[0084] Further, step S13 may include the following sub-steps S131-S133:

[0085] S131. Use gas parameters that do not belong to the cross-sensitive parameter source as gas parameters to be identified.

[0086] S132. Determine the second sensor corresponding to the gas data to be detected according to a preset detection sensitivity principle.

[0087] S133, using the first sensor and the second sensor as detection sensors corresponding to the gas data to be detected.

[0088] In the embodiment of the present invention, the gas parameter that cannot be detected by the first sensor is used as the gas parameter to be identified. Based on the preset detection sensitivity principle, the detection sensitivity group corresponding to the gas data to be detected is determined, and then based on the detection sensitivity group, the second sensor corresponding to the gas data to be detected is selected. Finally, the first sensor and the second sensor are used as the detection sensors corresponding to the gas data to be detected.

[0089] Step 206: construct a target fitting polynomial corresponding to the detection sensor according to the detection sensor and the corresponding gas parameters.

[0090] Further, step 206 may include the following sub-steps S21-S24:

[0091] S21. Obtain operating data corresponding to the transformer.

[0092] S22. Based on the operation data, determine the gas test concentration corresponding to the detection sensor.

[0093] S23. Use the orthogonal test method to construct a corresponding gas concentration value table based on the gas test concentration.

[0094] S24. According to the gas concentration value table and the detection sensor, a target fitting polynomial corresponding to the detection sensor is constructed.

[0095] In the embodiment of the present invention, the operation data refers to the actual operation data of the transformer, such as the gas concentration category and concentration range when the actual transformer fails. First, the operation data corresponding to the transformer is obtained, and based on the operation data, the gas test concentration corresponding to the detection sensor is determined. On the basis of the gas test concentration, the orthogonal test method is used to construct the corresponding gas concentration value table. Finally, based on the gas concentration value table and the detection sensor, the target fitting polynomial corresponding to the detection sensor is constructed.

[0096] Further, step S24 may include the following sub-steps S241-S245:

[0097] S241. Obtain a response data set corresponding to the gas concentration value table through a detection sensor.

[0098] S242. Based on the response data set and the gas concentration value table, construct a sensor response curve corresponding to the detection sensor.

[0099] S243. Based on the sensor response curve, construct an initial fitting polynomial corresponding to the gas data to be detected.

[0100] S244. Use the least square method to obtain the fitting coefficients corresponding to the initial fitting polynomial.

[0101] S245. Use the fitting coefficient to update the initial fitting polynomial to generate a target fitting polynomial corresponding to the gas data to be detected.

[0102] In the embodiment of the present invention, Figure 3 As shown in the figure, firstly, the orthogonal test method is used to construct the corresponding gas concentration value table based on the gas parameters, that is, N gas samples with different component concentrations are artificially prepared, where x is the target parameter, which is used as the input of the detection sensor, and y is the non-target parameter of the sensor cross-sensitivity source. The target parameter variable in this group of artificial gas samples is x 1 ~x N , the non-target parameter of the sensor cross-sensitivity source is a constant value y. Secondly, the test obtains the response data set F(x,y)={F(x 1 ,y)~F(x N ,y)}. Construct a sensor response curve with gas parameter W(x) as the horizontal coordinate and sensor output F(x,y) as the vertical coordinate. Then, based on the sensor response curve, construct the target parameter input W(x)={x 1 ,x 2 ,…,x N} and the sensor response output data set F(x,y)={F(x 1 ,y)~F(x N ,y)} between the initial fitting polynomial F(x,y) = a 1 +a 2 x+a 3 x 2 +…+a m x m-1 By using the least squares method, the fitting coefficients of the initial fitting polynomial {a 1 ,a 2 ,a 3 ,…a m}. The initial fitting polynomial is updated with the fitting coefficient to generate the target fitting polynomial corresponding to the gas data to be detected. Finally, based on the target fitting polynomial, that is, based on the convolution relationship between the input quantity, the sensor response function, and the output quantity, F(x,y)=W(x)*H(x,y), the corresponding response inverse function model is used to perform inverse operation to obtain the sensor response function H(x,y) to the input parameter x.

[0103] Step 207: Determine the detection data corresponding to the gas data to be detected according to the preset fitting polynomial of the target.

[0104] Further, step 207 may include the following sub-steps S31-S33:

[0105] S31. Based on the sensor response curve corresponding to the target preset fitting polynomial, a corresponding response inverse function model is constructed.

[0106] S32. Perform an inverse operation on the target fitting polynomial through a response inverse function model to generate a response function corresponding to the detection sensor.

[0107] S33, substituting the gas data to be detected into the response function respectively to determine the detection data corresponding to the gas data to be detected.

[0108] In the embodiment of the present invention, based on the sensor response curve corresponding to the target preset fitting polynomial, a response inverse function model corresponding to the detection sensor is constructed. The corresponding target fitting polynomial is inversely operated by the response inverse function model to generate a response function corresponding to the detection sensor. The gas data to be detected are respectively substituted into the response function to calculate the detection data corresponding to the gas data to be detected.

[0109] like Figure 4 As shown, step 1: determine the gas parameters to be detected in the gas data to be detected corresponding to the transformer. Assume that the gas parameters to be detected are three components: hydrogen, methane, and acetylene.

[0110] Step 2: Group the gas parameters according to the preset detection sensitivity principle (semiconductor sensitive grouping, infrared sensitive grouping, electrochemical sensitive grouping or catalytic combustion sensitive grouping), and determine the type of sensor (semiconductor sensor, infrared sensor, electrochemical sensor or catalytic combustion sensor) according to the grouping. The first sensor selected in this example is a catalytic combustion sensor.

[0111] Step 3: Determine the cross-sensitive parameter source of the selected sensor type according to the selected sensor type. For example, the sensitive parameters of the catalytic combustion sensor include hydrogen, methane, acetylene and propane, wherein propane is a non-target parameter.

[0112] Step 4: Select the test concentrations of hydrogen, methane and acetylene based on the actual transformer operation data:

[0113] Hydrogen concentration value x1: d1, d2, d3, d4; methane concentration value x2: b1, b2, b3, b4; acetylene concentration value x3: c1, c2, c3, c4; propane concentration value y: e1

[0114] The orthogonal experimental method was used to design a total of 17 groups of samples required for the test. The different gas concentration values ​​of each group of samples are shown in the gas concentration value table in Table 1 below.

[0115] Table 1 Gas concentration values

[0116]

[0117] Step 5: Experimentally obtain the sensor response data set F(x,y)=[F(x 1 ,y)~F(x N ,y)].

[0118] Step 6: Construct target parameter input W(x) = {x 1 ,x 2 ,…,x N} and the sensor response output data set F(x,y)={F(x 1 ,y)~F(x N ,y)} between the initial fitting polynomial F(x,y) = a 1 +a 2 x+a 3 x 2 +…+a m x m-1 By using the least squares method, the fitting coefficients of the initial fitting polynomial {a 1 ,a 2 ,a 3 ,…a m The initial fitting polynomial is updated using the fitting coefficient to generate a target fitting polynomial corresponding to the gas data to be detected.

[0119] Step 7: Based on the target fitting polynomial, that is, based on the convolution relationship between the input quantity, the sensor response function, and the output quantity, F(x,y)=W(x)*H(x,y), perform inverse operation through the corresponding response inverse function model to obtain the sensor response function H(x,y) for the input parameter x. Determine the detection data corresponding to the gas data to be detected through the response function.

[0120] By artificially preparing samples of different gas components, the response curve of the sensor is obtained, and the response inverse function model of the sensor is established. Combining the hardware and software means of comprehensive processing circuits and signal processing technology, the least square method is used to consider the input and output errors, and based on the basic properties of local linearization, the cross-sensitivity suppression is achieved, and the cross-sensitivity of the parameter sensor in the transformer gas is utilized.

[0121] In an embodiment of the present invention, when receiving the gas data to be detected corresponding to the transformer, multiple gas parameters corresponding to the gas data to be detected are obtained. The gas parameters are grouped according to the preset detection sensitivity principle to generate multiple initial gas groups corresponding to the gas data to be detected. The initial gas group corresponding to the maximum value of the gas parameter number is used as the target gas group. Based on the sensitivity type corresponding to the target gas group, the first sensor corresponding to the gas data to be detected is determined. Based on the first sensor and the gas parameter, the detection sensor corresponding to the gas data to be detected is determined. Based on the detection sensor and the corresponding gas parameter, a target fitting polynomial corresponding to the detection sensor is constructed. Based on the target preset fitting polynomial, the detection data corresponding to the gas data to be detected is determined. Based on the cross-sensitivity characteristics of the sensor, one sensor is used to detect multiple gas components, which reduces the number and types of sensors in the transformer gas multi-parameter sensing system and reduces the difficulty of system integration. The number of sensors is less than the number of detection parameters, which can achieve efficient monitoring of the operating quality of transformer gas.

[0122] See also Figure 5 , Figure 5 This is a structural block diagram of a transformer gas detection system provided in Example 3 of the present invention.

[0123] The embodiment of the present invention provides a transformer gas detection system, comprising:

[0124] The gas parameter acquisition module 501 is used to acquire a plurality of gas parameters corresponding to the gas data to be detected when receiving the gas data to be detected corresponding to the transformer.

[0125] The detection sensor determination module 502 is used to determine the detection sensor corresponding to the gas data to be detected according to the gas parameters and the preset detection sensitivity principle.

[0126] The target fitting polynomial construction module 503 is used to construct a target fitting polynomial corresponding to the detection sensor according to the detection sensor and the corresponding gas parameters.

[0127] The detection data determination module 504 is used to determine the detection data corresponding to the gas data to be detected according to the preset fitting polynomial of the target.

[0128] Optionally, the detection sensor determination module 502 includes:

[0129] The initial gas grouping generation module is used to group the gas parameters according to the preset detection sensitivity principle, and generate multiple initial gas groups corresponding to the gas data to be detected.

[0130] The target gas group determination module is used to take the initial gas group corresponding to the maximum value of the gas parameter quantity as the target gas group.

[0131] The first sensor determination module is used to determine the first sensor corresponding to the gas data to be detected based on the sensitive type corresponding to the target gas group.

[0132] The detection sensor determination submodule is used to determine the detection sensor corresponding to the gas data to be detected based on the first sensor and the gas parameters.

[0133] Optionally, the detection sensor determination submodule includes:

[0134] The cross-sensitive parameter source judgment module is used to judge whether the cross-sensitive parameter source corresponding to the first sensor contains all gas parameters.

[0135] The detection sensor determines the first submodule, and if so, uses the first sensor as the detection sensor corresponding to the gas data to be detected.

[0136] The detection sensor determines the second submodule, which is used to determine the detection sensor corresponding to the gas data to be detected based on the cross-sensitive parameter source and the gas parameters if no.

[0137] Optionally, the detection sensor determines that the second submodule may perform the following steps:

[0138] The gas parameters that do not belong to the cross-sensitive parameter source are used as the gas parameters to be identified;

[0139] According to the preset detection sensitivity principle, determine the second sensor corresponding to the gas data to be detected;

[0140] The first sensor and the second sensor are used as detection sensors corresponding to the gas data to be detected.

[0141] Optionally, the target fitting polynomial construction module 503 includes:

[0142] The operation data acquisition module is used to obtain the operation data corresponding to the transformer.

[0143] The gas test concentration determination module is used to determine the gas test concentration corresponding to the detection sensor based on the operation data.

[0144] The gas concentration value table construction module is used to construct a corresponding gas concentration value table based on the gas test concentration using an orthogonal test method.

[0145] The target fitting polynomial construction submodule is used to construct a target fitting polynomial corresponding to the detection sensor according to the gas concentration value table and the detection sensor.

[0146] Optionally, the target fitting polynomial construction submodule can perform the following steps:

[0147] Obtain a response data set corresponding to the gas concentration value table through a detection sensor;

[0148] Based on the response data set and the gas concentration value table, a sensor response curve corresponding to the detection sensor is constructed;

[0149] Based on the sensor response curve, an initial fitting polynomial corresponding to the gas data to be detected is constructed;

[0150] The least square method is used to obtain the fitting coefficients corresponding to the initial fitting polynomial;

[0151] The initial fitting polynomial is updated using the fitting coefficient to generate a target fitting polynomial corresponding to the gas data to be detected.

[0152] Optionally, the detection data determination module 504 includes:

[0153] The response inverse function model building module is used to build a corresponding response inverse function model based on the sensor response curve corresponding to the target preset fitting polynomial.

[0154] The response function generation module is used to perform inverse operation on the target fitting polynomial through the response inverse function model to generate a response function corresponding to the detection sensor.

[0155] The detection data determination submodule is used to substitute the gas data to be detected into the response function respectively to determine the detection data corresponding to the gas data to be detected.

[0156] An embodiment of the present invention further provides an electronic device, comprising: a memory and a processor, wherein a computer program is stored in the memory; when the computer program is executed by the processor, the processor executes a transformer gas detection method as described in any of the above embodiments.

[0157] The memory can be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read-only memory), an EPROM, a hard disk or a ROM. The memory has a storage space for program codes for executing any method steps in the above method. For example, the storage space for program codes can include individual program codes for implementing the various steps in the above method respectively. These program codes can be read from or written into one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards or floppy disks. The program code can be compressed, for example, in an appropriate form. When these codes are run by a computing and processing device, the computing and processing device is caused to execute the various steps in the transformer gas detection method described above.

[0158] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the transformer gas detection method as described in any of the above embodiments is implemented.

[0159] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0160] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0161] 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, that is, they 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.

[0162] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0163] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0164] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting gas in a transformer. It is characterized in that include: When receiving the gas data to be detected corresponding to the transformer, a plurality of gas parameters corresponding to the gas data to be detected are obtained; the gas data to be detected refers to the components corresponding to the gas of the transformer; the plurality of gas parameters include methane, carbon monoxide, ethane, carbon dioxide, ethylene, acetylene and hydrogen; According to the gas parameters and the preset detection sensitivity principle, the detection sensor corresponding to the gas data to be detected is determined; the preset detection sensitivity principle refers to grouping the gas parameters according to the preset detection sensitivity grouping; the detection sensitivity grouping includes semiconductor type sensitive grouping, infrared type sensitive grouping, electrochemical type sensitive grouping and catalytic combustion type sensitive grouping; According to the detection sensor and the corresponding gas parameters, construct a target fitting polynomial corresponding to the detection sensor; According to the preset fitting polynomial of the target, the detection data corresponding to the gas data to be detected is determined.

2. The transformer gas detection method according to claim 1, It is characterized in that The step of determining the detection sensor corresponding to the gas data to be detected according to the gas parameters and a preset detection sensitivity principle includes: The gas parameters are grouped respectively according to a preset detection sensitivity principle to generate a plurality of initial gas groups corresponding to the gas data to be detected; The initial gas group corresponding to the maximum value of the gas parameter quantity is used as the target gas group; Determining a first sensor corresponding to the gas data to be detected based on the sensitivity type corresponding to the target gas group; The detection sensor corresponding to the gas data to be detected is determined according to the first sensor and the gas parameter.

3. The transformer gas detection method according to claim 2, It is characterized in that The step of determining the detection sensor corresponding to the gas data to be detected according to the first sensor and the gas parameter comprises: Determining whether the cross-sensitive parameter source corresponding to the first sensor includes all the gas parameters; If yes, the first sensor is used as the detection sensor corresponding to the gas data to be detected; If not, the detection sensor corresponding to the gas data to be detected is determined according to the cross-sensitive parameter source and the gas parameter.

4. The transformer gas detection method according to claim 3, It is characterized in that The step of determining the detection sensor corresponding to the gas data to be detected according to the cross-sensitive parameter source and the gas parameter comprises: Taking the gas parameter that does not belong to the cross-sensitive parameter source as the gas parameter to be identified; According to the preset detection sensitivity principle, determining the second sensor corresponding to the gas data to be detected; The first sensor and the second sensor are used as detection sensors corresponding to the gas data to be detected.

5. The transformer gas detection method according to claim 1, It is characterized in that The step of constructing a target fitting polynomial corresponding to the detection sensor according to the detection sensor and the corresponding gas parameters includes: Obtaining operating data corresponding to the transformer; Based on the operating data, determining a gas test concentration corresponding to the detection sensor; Using an orthogonal test method to construct a corresponding gas concentration value table based on the gas test concentration; According to the gas concentration value table and the detection sensor, a target fitting polynomial corresponding to the detection sensor is constructed.

6. The transformer gas detection method according to claim 5, It is characterized in that The step of constructing a target fitting polynomial corresponding to the detection sensor according to the gas concentration value table and the detection sensor comprises: Acquire a response data set corresponding to the gas concentration value table through the detection sensor; Based on the response data set and the gas concentration value table, construct a sensor response curve corresponding to the detection sensor; Based on the sensor response curve, construct an initial fitting polynomial corresponding to the gas data to be detected; Using the least square method to obtain the fitting coefficient corresponding to the initial fitting polynomial; The initial fitting polynomial is updated by using the fitting coefficient to generate a target fitting polynomial corresponding to the gas data to be detected.

7. The transformer gas detection method according to claim 1, It is characterized in that The step of determining the detection data corresponding to the gas data to be detected according to the preset fitting polynomial of the target includes: Based on the sensor response curve corresponding to the target preset fitting polynomial, a corresponding response inverse function model is constructed; Performing an inverse operation on the target fitting polynomial through the response inverse function model to generate a response function corresponding to the detection sensor; Substitute the gas data to be detected into the response function respectively to determine the detection data corresponding to the gas data to be detected.

8. A transformer gas detection system, It is characterized in that include: A gas parameter acquisition module, for acquiring a plurality of gas parameters corresponding to the gas data to be detected when receiving the gas data to be detected corresponding to the transformer; the gas data to be detected refers to the components corresponding to the gas of the transformer; the plurality of gas parameters include methane, carbon monoxide, ethane, carbon dioxide, ethylene, acetylene and hydrogen; A detection sensor determination module, used to determine the detection sensor corresponding to the gas data to be detected according to the gas parameters and a preset detection sensitivity principle; the preset detection sensitivity principle refers to grouping the gas parameters according to preset detection sensitivity groups; the detection sensitivity groups include semiconductor sensitive groups, infrared sensitive groups, electrochemical sensitive groups and catalytic combustion sensitive groups; A target fitting polynomial construction module is used to construct a target fitting polynomial corresponding to the detection sensor according to the detection sensor and the corresponding gas parameters; The detection data determination module is used to determine the detection data corresponding to the gas data to be detected according to the preset fitting polynomial of the target.

9. An electronic device, It is characterized in that It comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the transformer gas detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed, the transformer gas detection method according to any one of claims 1 to 7 is implemented.

Images