Method and system for detecting trace decomposed components of fluorine-containing insulating gas

Abstract

The invention discloses a fluorine-containing insulating gas trace decomposition component detection method and system, and relates to the technical field of trace decomposition component gas detection.The method comprises the steps that a fluorine-containing gas sample and multiple training gas data are obtained, all the training gas data are preprocessed, and a gas feature set is generated; training a preset trace decomposition component classification model by adopting the gas feature set to generate a target trace decomposition component classification model, carrying out trace decomposition component detection on the fluorine-containing gas sample through a pre-constructed double-layer sensing device to generate trace decomposition component data, and calculating the trace decomposition component data according to the trace decomposition component data. And performing component detection on the trace decomposition component data by adopting the target trace decomposition component classification model to obtain detection data corresponding to the fluorine-containing gas sample. The technical problems that trace decomposition component gas in existing electrical equipment is mainly detected through a sensor based on a nanometer material, but interference of fluorine-containing gas on the sensor is ignored, and trace decomposition components in the fluorine-containing gas cannot be accurately detected are solved.

Description

Technical Field

[0001] The invention relates to the technical field of trace decomposition component gas detection, and in particular to a method and system for detecting trace decomposition components of fluorine-containing insulating gas. Background Art

[0002] Fluorine-containing gases are widely used in various fields due to their excellent stability, chemical inertness, environmental compatibility and thermal properties. However, when fluorine-containing gases in electrical equipment are exposed to the operating environment for a long time, they will decompose to produce trace decomposition component gases (such as C4F7N will decompose to produce trace decomposition component gases such as C3F6, CO and CHF3 under fault conditions). These trace decomposition component gases will damage their inherent properties and cause electrical equipment to malfunction. Therefore, it is very important to detect trace decomposition component gases in fluorine-containing gases in electrical equipment in a timely manner.

[0003] Trace decomposition component gases in existing electrical equipment are mainly detected by sensors based on nanomaterials, but the interference of fluorine-containing gases on the sensors is ignored, and the trace decomposition components in fluorine-containing gases cannot be accurately detected, which reduces the reliability of electrical equipment operation. Summary of the invention

[0004] The present invention provides a method and system for detecting trace decomposition components of fluorine-containing insulating gas, which solves the technical problem that trace decomposition component gases in existing electrical equipment are mainly detected by sensors based on nanomaterials, but the interference of fluorine-containing gas on the sensor is ignored, and the trace decomposition components in the fluorine-containing gas cannot be accurately detected, thereby reducing the reliability of the operation of the electrical equipment.

[0005] The first aspect of the present invention provides a method for detecting trace decomposition components of fluorine-containing insulating gas, comprising:

[0006] Acquire a fluorine-containing gas sample and a plurality of training gas data, and pre-process all of the training gas data to generate a gas feature set;

[0007] The gas feature set is used to train a preset trace decomposition component classification model to generate a target trace decomposition component classification model;

[0008] Performing trace decomposition component detection on the fluorine-containing gas sample through a pre-constructed double-layer sensing device to generate trace decomposition component data;

[0009] The target trace decomposition component classification model is used to perform component detection on the trace decomposition component data to obtain detection data corresponding to the fluorine-containing gas sample.

[0010] Optionally, the step of using the gas feature set to train a preset trace decomposition component classification model to generate a target trace decomposition component classification model includes:

[0011] The gas feature set is used to input a preset trace decomposition component classification model for training to obtain training detection data, wherein the trace decomposition component classification model includes a classifier and a BP neural network;

[0012] Calculating a training loss function value of the gas feature set according to the training detection data;

[0013] When the training loss function value is greater than or equal to a preset standard loss value, a preset parameter adjustment method is used to adjust the network parameters of the trace decomposition component classification model until the training loss function value is less than the standard loss value;

[0014] When the training loss function value is less than the standard loss value, a target trace decomposition component classification model is generated.

[0015] Optionally, the step of using the gas feature set to input a preset trace decomposition component classification model for training to obtain training detection data includes:

[0016] Performing gas classification on the gas feature set by the classifier to obtain training gas classification data;

[0017] The BP neural network is used to perform concentration detection on the training gas classification data to obtain training detection data.

[0018] Optionally, the double-layer sensing device comprises a filter layer, a sensing layer and interdigital electrodes, and the step of detecting trace decomposition components of the fluorine-containing gas sample by using the pre-constructed double-layer sensing device to generate trace decomposition component data comprises:

[0019] Performing a filtering operation on the fluorine-containing gas sample through the filter layer to obtain a trace decomposition component gas sample;

[0020] adding the trace decomposition component gas sample into the sensing layer to generate a target sensing layer;

[0021] Conductivity detection of the target sensing layer is performed using interdigitated electrodes to obtain initial trace decomposition component data;

[0022] The initial trace decomposition component data are preprocessed to obtain trace decomposition component data.

[0023] Optionally, the filter layer is Co3(HITP)2 material.

[0024] Optionally, the sensing layer is at least one of SnO2 material, Pd-SnO2 material and MoS2-SnO2 material.

[0025] A second aspect of the present invention provides a system for detecting trace decomposition components of fluorine-containing insulating gas, comprising:

[0026] An acquisition module, used for acquiring a fluorine-containing gas sample and a plurality of training gas data, and preprocessing all of the training gas data to generate a gas feature set;

[0027] A training module, used to train a preset trace decomposition component classification model using the gas feature set to generate a target trace decomposition component classification model;

[0028] A trace decomposition component detection module, used to detect the trace decomposition components of the fluorine-containing gas sample through a pre-built double-layer sensing device to generate trace decomposition component data;

[0029] The component detection module is used to perform component detection on the trace decomposition component data using the target trace decomposition component classification model to obtain detection data corresponding to the fluorine-containing gas sample.

[0030] A third aspect of the present invention provides an electronic device comprising 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 the method for detecting trace decomposition components of fluorine-containing insulating gas as described in any one of the above items.

[0031] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the method for detecting trace decomposition components of fluorine-containing insulating gas as described in any one of the above items.

[0032] A fifth aspect of the present invention provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes the method for detecting trace decomposition components of fluorine-containing insulating gas as described in any one of the above items.

[0033] It can be seen from the above technical solutions that the present invention has the following advantages:

[0034] The present invention detects trace decomposition components of fluorine-containing gas samples through a pre-constructed double-layer sensing device to generate trace decomposition component data. When the double-layer sensing device detects trace decomposition components of fluorine-containing gas samples, the interference of fluorine-containing gas on the detection of trace decomposition component gas is shielded, thereby accurately collecting trace decomposition component data of the fluorine-containing gas sample through the conductivity change of the double-layer sensing device. This overcomes the technical problem that trace decomposition component gases in existing electrical equipment are mainly detected by sensors based on nanomaterials, but the interference of fluorine-containing gas on the sensor is ignored, and the trace decomposition components in the fluorine-containing gas cannot be accurately detected, which reduces the reliability of the operation of the electrical equipment. Compared with the traditional trace decomposition component gas detection method, the present invention does not need to consider the interference of fluorine-containing gas on the detection process, which not only improves the detection efficiency, but also ensures the integrity of the sample, facilitates subsequent component analysis, and improves the reliability of the operation of the electrical equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] 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.

[0036] Figure 1 A flowchart of a method for detecting trace decomposition components of fluorine-containing insulating gas provided in Example 1 of the present invention;

[0037] Figure 2 A schematic diagram of the structure of the sensing layer and the shielding layer provided in the first embodiment of the present invention;

[0038] Figure 3 A schematic diagram of the structure of a double-layer sensor device provided in Embodiment 1 of the present invention;

[0039] Figure 4 A schematic diagram of the response of the SnO2 sensor to the trace decomposition component gas provided in the first embodiment of the present invention;

[0040] Figure 5 A schematic diagram of the response of the SnO2 sensor coated with the Co3(HITP)2 covering layer to the trace decomposition component gas provided in Example 1 of the present invention;

[0041] Figure 6 A schematic diagram of the response of the Pd-SnO2 sensor provided in Example 1 of the present invention to trace decomposition component gases;

[0042] Figure 7A schematic diagram of the response of a Pd-SnO2 sensor coated with a Co3(HITP)2 covering layer to trace decomposition component gases provided in Example 1 of the present invention;

[0043] Figure 8 A schematic diagram of the response of the MoS2-SnO2 sensor coated with the Co3(HITP)2 covering layer to the trace decomposition component gas provided in Example 1 of the present invention;

[0044] Fig. 9 A schematic diagram of the response of the MoS2-SnO2 sensor provided in Example 1 of the present invention to trace decomposition component gases;

[0045] Fig.10 A flow chart of the steps of a method for detecting trace decomposition components of fluorine-containing insulating gas provided in Embodiment 2 of the present invention;

[0046] Fig.11 A structural block diagram of a system for detecting trace decomposition components of fluorine-containing insulating gas provided in Embodiment 3 of the present invention;

[0047] Fig.12 A structural block diagram of an electronic device provided in Embodiment 4 of the present invention;

[0048] The meanings of the reference numerals are as follows:

[0049] 1. Fluorine-containing gas sample; 2. Shielding layer; 3. Sensing layer; 4. Interdigital electrodes. DETAILED DESCRIPTION

[0050] The embodiments of the present invention provide a method and system for detecting trace decomposition components of fluorine-containing insulating gas, which are used to solve the technical problem that trace decomposition component gases in existing electrical equipment are mainly detected by sensors based on nanomaterials, but the interference of fluorine-containing gases on the sensors is ignored, and the trace decomposition components in the fluorine-containing gas cannot be accurately detected, thereby reducing the reliability of the operation of the electrical equipment.

[0051] 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.

[0052] See also Figure 1 , Figure 1 A flowchart of the steps of a method for detecting trace decomposition components of fluorine-containing insulating gas provided in Example 1 of the present invention.

[0053] The present invention provides a method for detecting trace decomposition components of fluorine-containing insulating gas, comprising:

[0054] Step 101, obtaining a fluorine-containing gas sample and a plurality of training gas data, and preprocessing all the training gas data to generate a gas feature set;

[0055] The training gas data refers to the trace decomposition component gas data of known components.

[0056] Preprocessing refers to cleaning and smoothing the data to generate a gas feature set consisting of multiple conductivity features.

[0057] In the embodiment of the present invention, after obtaining the fluorine-containing gas sample and a plurality of training gas data, all the training gas data are preprocessed to generate a gas feature set.

[0058] Step 102: training a preset trace decomposition component classification model using a gas feature set to generate a target trace decomposition component classification model;

[0059] In an embodiment of the present invention, a preset trace decomposition component classification model is trained using a gas feature set to generate a target trace decomposition component classification model, wherein the trace decomposition component classification model includes a classifier and a BP neural network connected in sequence.

[0060] Step 103, detecting trace decomposition components of the fluorine-containing gas sample by using a pre-constructed double-layer sensing device to generate trace decomposition component data;

[0061] In the embodiment of the present invention, a preset double-layer sensing device is used to detect trace decomposition components of the fluorine-containing gas sample 1 to obtain trace decomposition component data.

[0062] It should be noted that, see Figure 2-Figure 3As shown, the double-layer sensing device includes a sensing layer 3 and a shielding layer 2. Sensing layer 3: metal oxide nanofibers in common metal oxide sensors are used as sensing layer 3 to detect trace decomposition component gases. Compared with other gas-sensitive materials, metal oxides have the advantages of fast response, good stability and simple preparation. Shielding layer 2: A two-dimensional metal organic framework is used as a covering layer to effectively reduce the interference of high-concentration fluorine-containing gases and couple it with the highly selective gas sensing layer 3. The molecular dynamic diameters and electron affinities of fluorinated greenhouse gases and their trace decomposition components vary, which provides a unique opportunity for selective sensing through two-dimensional metal organic frameworks (2D MOFs). The active metal sites in 2D MOFs have a tendency to strongly interact with fluorinated greenhouse gas molecules and can effectively fix them on the surface. At the same time, their high-throughput microporous structure facilitates the unimpeded access of trace decomposition component molecules to the underlying sensing substrate. In addition, the planar geometry of 2D MOFs is different from that of 3D MOFs, making them ideal covering layers that retain and potentially amplify the sensing properties of the substrate while introducing selective filtering.

[0063] It is worth mentioning that the construction process of the double-layer sensing device is as follows:

[0064] 1. Prepare SnO2, Pd-SnO2, and MoS2-SnO2 solutions respectively, and after 1 hour of ultrasonic treatment, add 10 μL of each to the surface of the interdigital electrode 4, and form a gas-sensitive layer (i.e., sensing layer) after vacuum drying at 65°C for 6 hours. The concentrations of SnO2, Pd-SnO2, and MoS2-SnO2 solutions are all 1 mg / 40 μL.

[0065] 2. Add 2.5 μL of the screening layer material solution to the surface of the dried gas-sensitive layer by screen printing, and form a screening layer after vacuum drying at 65°C for 6 hours to obtain a sensor for detecting local fault decomposition components of C4F7N, wherein the screening layer material solution can be Co3(HITP)2, and the concentration of the screening layer material solution is 1 mg / 200 μL.

[0066] It is worth mentioning that, referring to Comparative Example 1: SnO2, Pd-SnO2, and MoS2-SnO2 are respectively prepared into 1 mg / 40 μL solutions. After 1 hour of ultrasound, 10 μL of each is dripped onto the surface of the interdigital electrode. After vacuum drying at 65°C for 6 hours, a sensor for detecting the local fault decomposition components of C4F7N is obtained. Under room temperature conditions, the sensors prepared by the present invention and Comparative Example 1 are respectively placed in resistance detection equipment, and a mixed gas (6% C4F7N / 94% CO2) is first introduced into the equipment for a period of time until the resistance of the sensor stabilizes. Thereafter, different types and concentrations of fault decomposition component gases (C3F6, CO, CHF3) are introduced into the equipment, and the changes in the resistance of the sensor are observed. When the response is close to saturation, the mixed gas (6% C4F7N / 94% CO2) is reintroduced. The test results are as follows: Figure 4-9 As shown. The SnO2 sensor shows a highly linear response to C3F6, CO and CHF3 in the concentration range of 10~50ppm. The response value of C3F6 to 50ppm is the highest, which is 13.1%, while the response values ​​of CO and CHF3 are lower, which are 7.3% and 6.0%, respectively; when the SnO2 coated with Co3(HITP)2 capping layer is 50ppm, the sensor responses of C3F6, CO and CHF3 increase to 43.1%, 21.4% and 25.2%, respectively. At a concentration of 50ppm, the response of Pd-SnO2 to CO is 101.77%, the response to C3F6 is 62.06%, and the response to CHF3 is 22.97%. The response values ​​of MoS2-SnO2 to CHF3 are 56.36%, the response value to CO is 38.98%, and the response value to C3F6 is 27.1%. After the introduction of Co3(HITP)2 capping layer, the sensor response is significantly improved. So from Figure 4-9 It can be seen that the presence of the Co3(HITP)2 screening layer greatly improves the sensitivity of the sensor to C3F6, CO, and CHF3.

[0067] Step 104: Use the target trace decomposition component classification model to perform component detection on the trace decomposition component data to obtain detection data corresponding to the fluorine-containing gas sample.

[0068] In an embodiment of the present invention, the trace decomposition component data is input into a target trace decomposition component classification model to perform component detection, and detection data corresponding to the fluorine-containing gas sample is obtained.

[0069] It should be noted that the detection data includes the categories of trace decomposition component gases and the concentrations of each category of trace decomposition component gases.

[0070] In an embodiment of the present invention, a trace decomposition component detection is performed on a fluorine-containing gas sample by a pre-constructed double-layer sensing device to generate trace decomposition component data. When the double-layer sensing device detects trace decomposition components of the fluorine-containing gas sample, the interference of the fluorine-containing gas on the detection of the trace decomposition component gas is shielded, thereby accurately collecting the trace decomposition component data of the fluorine-containing gas sample through the conductivity change of the double-layer sensing device. This overcomes the technical problem that trace decomposition component gases in existing electrical equipment are mainly detected by sensors based on nanomaterials, but the interference of fluorine-containing gases on sensors is ignored, and the trace decomposition components in the fluorine-containing gas cannot be accurately detected, which reduces the reliability of the operation of the electrical equipment. Compared with the traditional trace decomposition component gas detection method, the present invention does not need to consider the interference of fluorine-containing gases on the detection process, which not only improves the detection efficiency, but also ensures the integrity of the sample, facilitates subsequent component analysis, and improves the reliability of the operation of the electrical equipment.

[0071] See also Fig.10 , Fig.10 A flow chart of the steps of a method for detecting trace decomposition components of fluorine-containing insulating gas provided in Example 2 of the present invention.

[0072] The present invention provides a method for detecting trace decomposition components of fluorine-containing insulating gas, comprising:

[0073] Step 201, obtaining a fluorine-containing gas sample and a plurality of training gas data, and preprocessing all the training gas data to generate a gas feature set;

[0074] In an embodiment of the present invention, after obtaining a fluorine-containing gas sample and a plurality of training gas data, cleaning and smoothing operations are performed on all the training gas data to generate a gas feature set.

[0075] Step 202: using the gas feature set to input a preset trace decomposition component classification model for training to obtain training detection data, wherein the trace decomposition component classification model includes a classifier and a BP neural network;

[0076] Further, step 202 includes the following sub-steps:

[0077] S11, classifying the gas feature set by a classifier to obtain training gas classification data;

[0078] In the embodiment of the present invention, a classifier (k-nearest neighbor algorithm) is used to classify the gas feature set to obtain training gas classification data.

[0079] It should be noted that the classifier is a k-nearest neighbor algorithm, which performs preliminary classification of the gas feature set by comparing the gas feature set with known gas data. For example, the type of gas is identified by calculating the distance between the conductivity change and the known gas concentration.

[0080] In another embodiment, the classifier is at least one of a support vector machine SVM, a K-nearest neighbor algorithm, an XGBoost algorithm, and a LightGBM algorithm. When there are multiple classifiers, a weight is assigned to each algorithm, and a weighted operation is performed on the classification results calculated by each algorithm to obtain the final classification result.

[0081] S12. Use a BP neural network to perform concentration detection on the training gas classification data to obtain training detection data.

[0082] In the embodiment of the present invention, concentration detection is performed on the training gas classification data through a BP neural network to obtain training detection data.

[0083] It should be noted that the classifier is connected to the BP neural network in sequence, and the weight is adjusted through the back propagation algorithm of the BP neural network to minimize the error and further improve the detection accuracy.

[0084] Step 203: Calculate the training loss function value of the gas feature set according to the training detection data;

[0085] In an embodiment of the present invention, training result data associated with the training detection data in the gas feature set is obtained, a deviation value between the training detection data and the training result data is calculated, and the deviation value is used as the training loss function value of the gas feature set.

[0086] Step 204: when the training loss function value is greater than or equal to the preset standard loss value, a preset parameter adjustment method is used to adjust the network parameters of the trace decomposition component classification model until the training loss function value is less than the standard loss value;

[0087] It should be noted that the parameter adjustment method may be a gradient descent method, a grid search method or a random search method.

[0088] In an embodiment of the present invention, it is determined that the training loss function value is less than a preset standard loss value. If the training loss function value is greater than or equal to the standard loss value, the network parameters of the trace decomposition component classification model are adjusted by a gradient descent method, a grid search method, or a random search method until the training loss function value is less than the standard loss value.

[0089] Step 205: When the training loss function value is less than the standard loss value, a target trace decomposition component classification model is generated.

[0090] In an embodiment of the present invention, if the training loss function value is less than the standard loss value, a target trace decomposition component classification model is generated.

[0091] Step 206, detecting trace decomposition components of the fluorine-containing gas sample by using the pre-constructed double-layer sensing device to generate trace decomposition component data;

[0092] Further, the double-layer sensing device includes a filter layer, a sensing layer and interdigital electrodes, and step 206 includes the following sub-steps:

[0093] It should be noted that the mass ratio of the filter layer material to the sensor layer material is 20:1.

[0094] S21, filtering the fluorine-containing gas sample through the filter layer to obtain a trace decomposition component gas sample;

[0095] It should be noted that the filter layer is made of Co3(HITP)2 material.

[0096] In an embodiment of the present invention, the fluorine-containing gas molecules in the fluorine-containing gas sample are fixed on the surface of the filter layer based on the active metal sites of the filter layer (i.e., the two-dimensional metal-organic framework covering layer), and the high-throughput microporous structure of the filter layer is utilized to allow the trace decomposition component molecules to pass through unimpeded, thereby achieving filtration of the fluorine-containing gas sample and obtaining a trace decomposition component gas sample.

[0097] S22, adding a trace decomposition component gas sample into the sensing layer to generate a target sensing layer;

[0098] It should be noted that the sensing layer is at least one of SnO2 material, Pd-SnO2 material and MoS2-SnO2 material.

[0099] In an embodiment of the present invention, a trace decomposition component gas sample is added to the sensing layer, so that the trace decomposition component gas sample reacts chemically with the metal oxide gas sensitive material (such as SnO2, Pd-SnO2, MoS2-SnO2) of the sensing layer to obtain a target sensing layer.

[0100] S23, using interdigital electrodes to perform conductivity detection on the target sensing layer to obtain initial trace decomposition component data;

[0101] In an embodiment of the present invention, the conductivity change during the chemical reaction between the trace decomposition component gas sample and the metal oxide gas sensitive material (such as SnO2, Pd-SnO2, MoS2-SnO2) of the sensing layer is obtained in real time through the interdigitated electrodes to obtain the initial trace decomposition component data.

[0102] S24, performing data preprocessing on the initial trace decomposition component data to obtain trace decomposition component data.

[0103] In the embodiment of the present invention, the initial trace decomposition component data is filtered and denoised to obtain the trace decomposition component data.

[0104] It should be noted that the errors caused by background noise or internal interference of the sensor are removed by filtering and denoising the initial trace decomposition component data.

[0105] Step 207: Use the target trace decomposition component classification model to perform component detection on the trace decomposition component data to obtain detection data corresponding to the fluorine-containing gas sample.

[0106] In an embodiment of the present invention, the trace decomposition component data is input into a target trace decomposition component classification model to perform component detection, and detection data corresponding to the fluorine-containing gas sample is obtained.

[0107] It is worth mentioning that after obtaining the test data corresponding to the fluorine-containing gas sample, the test data can be loaded into the feedback component in the test page, the feedback component can be rendered, and a test page containing the test data can be generated. At the same time, when the concentration of the trace decomposition component gas in the test data exceeds the set safety threshold, an alarm will be issued through the test page.

[0108] In an embodiment of the present invention, a trace decomposition component detection is performed on a fluorine-containing gas sample by a pre-constructed double-layer sensing device to generate trace decomposition component data. When the double-layer sensing device detects trace decomposition components of the fluorine-containing gas sample, the interference of the fluorine-containing gas on the detection of the trace decomposition component gas is shielded, thereby accurately collecting the trace decomposition component data of the fluorine-containing gas sample through the conductivity change of the double-layer sensing device. This overcomes the technical problem that trace decomposition component gases in existing electrical equipment are mainly detected by sensors based on nanomaterials, but the interference of fluorine-containing gases on sensors is ignored, and the trace decomposition components in the fluorine-containing gas cannot be accurately detected, which reduces the reliability of the operation of the electrical equipment. Compared with the traditional trace decomposition component gas detection method, the present invention does not need to consider the interference of fluorine-containing gases on the detection process, which not only improves the detection efficiency, but also ensures the integrity of the sample, facilitates subsequent component analysis, and improves the reliability of the operation of the electrical equipment.

[0109] See also Fig.11 , Fig.11 This is a structural block diagram of a system for detecting trace decomposition components of fluorine-containing insulating gas provided in Example 3 of the present invention.

[0110] The present invention provides a detection system for trace decomposition components of fluorine-containing insulating gas, comprising:

[0111] The acquisition module 301 is used to obtain a fluorine-containing gas sample and a plurality of training gas data, and pre-process all the training gas data to generate a gas feature set;

[0112] A training module 302 is used to train a preset trace decomposition component classification model using a gas feature set to generate a target trace decomposition component classification model;

[0113] The trace decomposition component detection module 303 is used to detect the trace decomposition components of the fluorine-containing gas sample through a pre-built double-layer sensing device to generate trace decomposition component data;

[0114] The component detection module 304 is used to perform component detection on the trace decomposition component data using the target trace decomposition component classification model to obtain detection data corresponding to the fluorine-containing gas sample.

[0115] Furthermore, the training module 302 includes:

[0116] A training submodule is used to use a gas feature set to input a preset trace decomposition component classification model for training to obtain training detection data, wherein the trace decomposition component classification model includes a classifier and a BP neural network;

[0117] A first analysis submodule, used to calculate the training loss function value of the gas feature set according to the training detection data;

[0118] The second analysis submodule is used to adjust the network parameters of the trace decomposition component classification model by using a preset parameter adjustment method when the training loss function value is greater than or equal to a preset standard loss value until the training loss function value is less than the standard loss value;

[0119] When the training loss function value is less than the standard loss value, a target trace decomposition component classification model is generated.

[0120] Furthermore, the training submodule includes:

[0121] A classification unit, used for classifying the gas feature set through a classifier to obtain training gas classification data;

[0122] The concentration detection unit is used to perform concentration detection on the training gas classification data using a BP neural network to obtain training detection data.

[0123] Further, the double-layer sensing device includes a filtering layer, a sensing layer and interdigital electrodes, and the trace decomposition component detection module 303 includes:

[0124] A filtering submodule is used to filter the fluorine-containing gas sample through the filtering layer to obtain a trace decomposition component gas sample;

[0125] A mixing submodule, used for adding trace decomposition component gas samples into the sensing layer to generate a target sensing layer;

[0126] The conductivity detection submodule is used to perform conductivity detection on the target sensing layer using interdigitated electrodes to obtain initial trace decomposition component data;

[0127] The preprocessing submodule is used to preprocess the initial trace decomposition component data to obtain the trace decomposition component data.

[0128] Furthermore, the filter layer is made of Co3(HITP)2 material.

[0129] Furthermore, the sensing layer is at least one of SnO2 material, Pd-SnO2 material and MoS2-SnO2 material.

[0130] See also Fig.12 , Fig.12 This is a structural block diagram of an electronic device provided in Embodiment 4 of the present invention.

[0131] An electronic device according to an embodiment of the present invention includes: a memory 401 and a processor 402, wherein the memory 402 stores a computer program; when the computer program is executed by the processor 402, the processor 402 executes a method for detecting trace decomposition components of fluorine-containing insulating gas as described in any of the above embodiments.

[0132] The memory 401 may 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 401 has a storage space 403 for a program code 413 for executing any method step in the above method. For example, the storage space 403 for the program code may include individual program codes 413 for implementing the various steps in the above method, respectively. These program codes may be read from or written to one or more computer program products. These computer program products include program code carriers such as a hard disk, a compact disk (CD), a memory card or a floppy disk. The program code may 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 above-described method.

[0133] Embodiment 5 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 method for detecting trace decomposition components of fluorine-containing insulating gas as described in any of the above embodiments is implemented.

[0134] Embodiment 6 of the present invention further provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes a method for detecting trace decomposition components of fluorine-containing insulating gas as described in any of the above embodiments.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or 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, etc. Various media that can store program codes.

[0140] 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 trace decomposition components of fluorine-containing insulating gas, characterized in that: include: Acquire a fluorine-containing gas sample and a plurality of training gas data, and pre-process all of the training gas data to generate a gas feature set; The gas feature set is used to train a preset trace decomposition component classification model to generate a target trace decomposition component classification model; Performing trace decomposition component detection on the fluorine-containing gas sample through a pre-constructed double-layer sensing device to generate trace decomposition component data; The target trace decomposition component classification model is used to perform component detection on the trace decomposition component data to obtain detection data corresponding to the fluorine-containing gas sample.

2. The method for detecting trace decomposition components of fluorine-containing insulating gas according to claim 1, characterized in that: The step of using the gas feature set to train a preset trace decomposition component classification model to generate a target trace decomposition component classification model includes: The gas feature set is used to input a preset trace decomposition component classification model for training to obtain training detection data, wherein the trace decomposition component classification model includes a classifier and a BP neural network; Calculating a training loss function value of the gas feature set according to the training detection data; When the training loss function value is greater than or equal to a preset standard loss value, a preset parameter adjustment method is used to adjust the network parameters of the trace decomposition component classification model until the training loss function value is less than the standard loss value; When the training loss function value is less than the standard loss value, a target trace decomposition component classification model is generated.

3. The method for detecting trace decomposition components of fluorine-containing insulating gas according to claim 2, characterized in that: The step of using the gas feature set to input a preset trace decomposition component classification model for training to obtain training detection data includes: Performing gas classification on the gas feature set by the classifier to obtain training gas classification data; The BP neural network is used to perform concentration detection on the training gas classification data to obtain training detection data.

4. The method for detecting trace decomposition components of fluorine-containing insulating gas according to claim 1, characterized in that: The double-layer sensing device comprises a filter layer, a sensing layer and interdigital electrodes. The step of detecting trace decomposition components of the fluorine-containing gas sample by using the pre-constructed double-layer sensing device to generate trace decomposition component data comprises: Performing a filtering operation on the fluorine-containing gas sample through the filter layer to obtain a trace decomposition component gas sample; adding the trace decomposition component gas sample into the sensing layer to generate a target sensing layer; Conductivity detection of the target sensing layer is performed using interdigitated electrodes to obtain initial trace decomposition component data; The initial trace decomposition component data are preprocessed to obtain trace decomposition component data.

5. The method for detecting trace decomposition components of fluorine-containing insulating gas according to claim 4, characterized in that: The filter layer is made of Co3(HITP)2 material.

6. The method for detecting trace decomposition components of fluorine-containing insulating gas according to claim 4, characterized in that: The sensing layer is at least one of SnO2 material, Pd-SnO2 material and MoS2-SnO2 material.

7. A system for detecting trace decomposition components of fluorine-containing insulating gas, characterized in that: include: An acquisition module, used for acquiring a fluorine-containing gas sample and a plurality of training gas data, and preprocessing all of the training gas data to generate a gas feature set; A training module, used to train a preset trace decomposition component classification model using the gas feature set to generate a target trace decomposition component classification model; A trace decomposition component detection module, used to detect the trace decomposition components of the fluorine-containing gas sample through a pre-built double-layer sensing device to generate trace decomposition component data; The component detection module is used to perform component detection on the trace decomposition component data using the target trace decomposition component classification model to obtain detection data corresponding to the fluorine-containing gas sample.

8. An electronic device, characterized in that: It comprises 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 the method for detecting trace decomposition components of fluorine-containing insulating gas as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the method for detecting trace decomposition components of fluorine-containing insulating gas as described in any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes the method for detecting trace decomposition components of fluorine-containing insulating gas as described in any one of claims 1-6.

Images