Tracing method and device for coastal insulator marine high-salt pollution based on typhoon factor

Abstract

The invention provides a coastal insulator ocean high-salt pollution tracing method and device based on typhoon factors, and relates to the technical field of high-voltage external insulation, and the method comprises the steps: setting monitoring points on a coastal inland high-voltage line of a target area, and collecting insulator dirt and environmental particles; measuring the concentration value of nitrate in insulator dirt and environmental particulate matters; a nitrate nitrogen and oxygen isotope value is obtained through an isotope mass spectrometer in combination with a nitrate concentration value and is calibrated; a Bayesian mixture model is adopted to determine the contribution ratio of the insulator dirt and the nitrate from different sources in the environmental particulate matter; constructing a data set according to the contribution proportion and the nitrate nitrogen and oxygen isotope value; the construction of a linear system network is trained through a data set, a linear change proportion image of nitrogen and oxygen isotopes is obtained, the tracking of coastal insulator marine high salt pollution in a target area by considering a typhoon factor is realized, and the problem of power transmission line insulator surface pollution caused by marine salt mist in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the technical field of high-voltage external insulation, and in particular to a method and device for tracing marine high-salinity pollution of coastal insulators based on typhoon factors. Background Art

[0002] Background of Marine High Salt Pollution for Coastal Insulators The background technology relates to the challenges faced by transmission line insulators in the special environment of coastal areas.

[0003] Due to the climate characteristics of coastal areas, salt from the ocean easily accumulates on the surface of insulators, a phenomenon known as high salt pollution. High salt pollution not only increases the difficulty of insulator maintenance, but may also affect its insulation performance, thereby affecting the reliability and safety of the entire transmission system.

[0004] In coastal areas, the salt density on the surface of insulators is usually high, mainly composed of monovalent salts. These areas are mostly in the pollution zone of level II and III, and some are in the pollution zone of level IV. The increase in salt density will lead to more frequent pollution flashover on the surface of insulators. Pollution flashover refers to the accumulation of pollutants on the surface of insulators that dissolve under certain humidity conditions to form an electrolyte film, or a chemical gas with conductive properties, thereby reducing insulation performance, increasing surface leakage current, and ultimately may cause flashover accidents.

[0005] In order to deal with this problem, relevant technical research mainly focuses on analyzing the pollution characteristics. By sampling and analyzing the pollution components on the surface of the insulator, the properties of the pollution and its impact on the flashover voltage are understood. Then its source is determined by certain special points in its composition. However, this tracing method does not take into account the impact of typhoons, resulting in poor accuracy of the tracing results. Summary of the invention

[0006] The purpose of the present invention is to provide a method and device for tracing marine high-salinity pollution of coastal insulators based on typhoon factors in order to solve the problem of poor accuracy of existing methods for tracing pollutants in high-salinity pollution.

[0007] The above-mentioned purpose of the present application is achieved through the following technical solutions: S1: Set up monitoring points on the coastal to inland high-voltage lines in the target area to collect a preset number of groups of insulator dirt and environmental particles during typhoon weather and non-typhoon weather; S2: Using chemiluminescence method, measure the nitrate concentration in insulator dirt and environmental particles; S3: Isotope mass spectrometry combined with nitrate concentration values ​​in insulator dirt and environmental particles The isotopes of nitrate are measured to obtain the nitrogen and oxygen isotope values ​​of nitrate and calibrate them; S4: A Bayesian mixture model was used to determine the contribution ratio of nitrate from different sources in insulator dirt and ambient particulate matter; According to the contribution ratio and nitrate nitrogen and oxygen isotope values, a data set was constructed; S5: Construct a linear system network based on a deep feedforward network; train the linear system network through the data set to obtain a linear change proportional image of nitrogen and oxygen isotopes; through the linear change proportional image, the tracing of marine high-salinity pollution of coastal insulators in the target area taking into account typhoon factors can be achieved.

[0008] Optionally, step S2 includes: S21: High-purity nitrogen is input into the detection device as a carrier gas to detect the airtightness of the gas path; Samples included: insulator dirt and ambient particles; The nitrate solution of the sample is injected into a 0.1M acidic vanadium trichloride solution heated to a constant temperature of 95°C in a water bath through the injection port of the detection device, so that the nitrate reacts with the vanadium trichloride to generate NO gas; the sample is insulator dirt or environmental particles; NO gas was passed through a 2M sodium hydroxide solution at 0°C; S22: inputting the NO gas purified by the sodium hydroxide solution into the NOx Analyzer detector; In the NOx Analyzer, NO gas reacts with the excess ozone generated by the NOx Analyzer and is converted into an excited state. , get the signal of NOx Analyzer detector; S23: Convert the signal of the NOx Analyzer detector into a voltage signal, and combine it with a scanning spectrum method to obtain the nitrate concentration values ​​of the insulator dirt and environmental particulate matter of a preset number of groups.

[0009] Optionally, step S3 includes: International isotope standards USGS34, USGS32, USGS35 and IAEA-N3 are used to calibrate the nitrogen and oxygen isotope values ​​of nitrate.

[0010] Optionally, step S5 includes: Use the back-propagation algorithm to update the linear system network weights.

[0011] Optionally, step S5 further includes: Add input noise; The nitrate nitrogen and oxygen isotope values ​​and noise during typhoon climate and non-typhoon climate are combined into an implicit representation; Train linear system networks through latent representation.

[0012] Optionally, step S5 further includes: The Wasserstein distance loss function is used as the training loss function for the linear system network based on the deep feedforward network.

[0013] An electronic device comprises a processor, a memory, a user interface and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes a method for tracing marine high-salinity pollution of coastal insulators based on typhoon factors.

[0014] A computer-readable storage medium stores instructions, which, when executed, execute a method for tracing marine high-salinity pollution of coastal insulators based on typhoon factors.

[0015] The beneficial effects of the technical solution provided by this application are: The stable nitrogen and oxygen isotope technology and Bayesian model were used to analyze the formation path and source of nitrate in high-salt pollution of coastal insulators. This can improve the solution to the existing surface pollution problem of transmission line insulators caused by marine salt spray, and then achieve targeted and purposeful suppression and isolation protection from the source. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present application will be further described below with reference to the accompanying drawings and embodiments, in which: Figure 1 is a step diagram in an embodiment of the present application; Figure 2 It is a schematic diagram of the working principle of measuring nitrate ion concentration in the embodiment of the present application; Figure 3 is a schematic diagram of the structure of an electronic device in an embodiment of the present application; Figure 4 It is the international working standard nitrate nitrogen isotope parameter diagram in the embodiment of this application. DETAILED DESCRIPTION

[0017] In order to have a clearer understanding of the technical features, purposes and effects of the present application, the specific implementation methods of the present application are now described in detail with reference to the accompanying drawings.

[0018] An embodiment of the present application provides a method for tracing marine high-salinity pollution on coastal insulators based on typhoon factors.

[0019] Please refer to Figure 1 , Figure 1 This is a step diagram of a method for tracing high salt pollution in coastal insulators based on typhoon factors in an embodiment of the present application, including: S1: Set up monitoring points on the coastal to inland high-voltage lines in the target area to collect a preset number of groups of insulator dirt and environmental particles during typhoon weather and non-typhoon weather; In one embodiment of the present application, typical areas such as Quanzhou are selected, and multiple monitoring points are fixed along the high-voltage lines from the coast to the inland in areas with light industrial pollution. Detection is carried out in typhoon climate and non-typhoon climate to obtain multiple sets of comparative information and obtain insulator dirt. The surrounding environmental information of the high-voltage lines from the coast to the inland is collected in typhoon climate and non-typhoon climate, and multiple sets of ambient air particulate matter around the lines are collected for comparison. The significant characteristics of inland and marine pollution are analyzed, and according to the characteristics of marine high-salt pollution, nitrates that are significantly present in its composition are determined as the main research object. The components of the multiple sets of insulator dirt and environmental particulate matter collected are analyzed, and the enrichment and decay of relevant indicators in inland and marine pollution are analyzed, with a focus on the composition characteristics of marine pollution, that is, the nitrate content.

[0020] S2: Using chemiluminescence method, measure the nitrate concentration in insulator dirt and environmental particles; S3: Isotope mass spectrometry combined with nitrate concentration values ​​in insulator dirt and environmental particles The isotopes of nitrate are measured to obtain the nitrogen and oxygen isotope values ​​of nitrate and calibrate them; In one embodiment of the present application, the nitrogen isotope is mainly determined 15 N and oxygen isotopes 18 O, and then get δ 15 N-NO 3 ‒ and δ 18 O-NO 3 ‒ The value of .

[0021] In one embodiment of the present application, in order to ensure that the data has high accuracy, high-purity N2O gas (99.999%) is selected as the reference gas during the test process, and at least 10 reference gas injections are completed before the sample peak appears. After the sample measurement is completed, the reference gas should be measured again. This process can check whether the instrument has a memory effect during the measurement process, thereby better reducing the impact between samples and ensuring the accuracy of the sample isotope value.

[0022] In one embodiment of the present application, the isotope ratio determination process is divided into two steps, as follows: First, enrichment and purification are performed. There are two modes of enrichment and purification: load mode and injection mode. In load mode, the injection needle is placed in the sample bottle, and high-purity helium (99.999%) is selected as the carrier gas of the device. The flow rate is maintained at 25 mL / min to carry the N in the sample bottle. 2 O gas passes through Nafion tube (to remove water) and Mg(ClO4)2 / Ascarite tube (to remove water and CO 2 ), and then through the eight-way valve in the GasBenchⅡ device, enter the capillary (trap1) completely immersed in liquid nitrogen to transfer N 2 After 6 minutes and 40 seconds of trapping, trap 2 sinks deep into the liquid nitrogen. At this time, the eight-way valve in the GasBench II device switches, trap 1 rises, trap 1 that has captured N2O gas leaves the liquid nitrogen, and at the same time, helium removes N2O from trap 1. 2 O is transferred to trap 2 for further enrichment. After 1 minute and 40 seconds of enrichment, the eight-way valve in the GasBenchⅡ device is switched again to injection mode. During this period, another helium gas (Backflush He, flow rate 10mL / min) has been backflushed to the front half of the gas path to prevent air from entering the injection needle gas path. After trap2 is enriched for 1 minute and 40 seconds, trap2 rises and separates from liquid nitrogen. GasBenchⅡ is now switched to open spread mode, and the N enriched in trap2 2 O gas will be pushed into the GC tube by high-purity helium (temperature 30°C) to separate N 2 O and possible residual CO 2 ), and finally, after the water is removed through the Nafion tube, it enters the IRMS, thus completing the enrichment and purification process.

[0023] Isotope determination: This IRMS contains three Faraday cups, which can receive ion beams with molecular weights of 44, 45, and 46 at the same time. This allows the enriched and purified N 2 The O gas is ionized in the IRMS and split into three N atoms: 44, 45, and 46 as it passes rapidly through a magnetic field. 2 O ion beam, and then enter the corresponding Faraday cup. According to the different number of electrons received by each Faraday cup, it can be converted into different voltage signals. Finally, the software program can calculate N from the voltage signal. 2 O isotope values ​​of nitrogen and oxygen.

[0024] S4: Use a Bayesian mixture model to determine the contribution ratio of nitrate from different sources in insulator dirt and ambient particulate matter; Construct a data set based on contribution ratios and nitrate nitrogen and oxygen isotope values; In one embodiment of the present application, a Bayesian mixture model (SIAR) is used to clarify the contribution ratio of nitrate from different sources, and the uncertainty associated with multiple sources and measured isotopic characteristics can be clearly included. According to the contribution ratio of nitrate from different sources clarified by the Bayesian mixture model (SIAR) and the nitrogen and oxygen isotope content in the ambient air particulate matter around multiple groups of lines collected on the coastal to inland high-voltage lines in typhoon climate and non-typhoon climate, pre-processing is performed, and multiple groups of data sets are formed after pre-processing (mainly comparing the changes in nitrogen and oxygen isotope content in typhoon climate, which is used as an additional condition information for training the tracer network).

[0025] S5: Construct a linear system network based on a deep feedforward network; train the linear system network through the data set to obtain a linear change proportional image of nitrogen and oxygen isotopes; through the linear change proportional image, the tracing of marine high-salinity pollution of coastal insulators in the target area taking into account typhoon factors can be achieved.

[0026] In one embodiment of the present application, a linear system network based on a deep feedforward network is constructed, which is an extension of a feedforward neural network. The linear system network is trained using multiple sets of preprocessed data sets to complete network training. A linear change ratio image of nitrogen and oxygen isotopes is formed from the coast to the inland after considering the interference of typhoon factors, and the tracing of the high salt pollution of the coastal insulators in the ocean considering the typhoon factors is realized based on this linear image.

[0027] Step S2 includes: S21: High-purity nitrogen is input into the detection device as a carrier gas to detect the airtightness of the gas path; Samples included: insulator dirt and ambient particles; The nitrate solution of the sample is injected into a 0.1M acidic vanadium trichloride solution heated to a constant temperature of 95°C in a water bath through the injection port of the detection device, so that the nitrate reacts with the vanadium trichloride to generate NO gas; the sample is insulator dirt or environmental particles; NO gas was passed through a 2M sodium hydroxide solution at 0°C; S22: inputting the NO gas purified by the sodium hydroxide solution into the NOx Analyzer detector; In the NOx Analyzer, NO gas reacts with the excess ozone generated by the NOx Analyzer and is converted into an excited state. , get the signal of NOx Analyzer detector; S23: Convert the signal of the NOx Analyzer detector into a voltage signal, and combine it with a scanning spectrum method to obtain the nitrate concentration values ​​of the insulator dirt and environmental particulate matter of a preset number of groups.

[0028] In one embodiment, chemiluminescence is used to measure the nitrate concentration of saline-alkali land samples, dust samples, and ambient atmospheric particulate matter (e.g. Figure 2 As shown): High-purity nitrogen is input as the carrier gas into the entire device to test the airtightness of the gas line. Then use a disposable syringe to inject the nitrate solution through the device inlet into the 0.1M acidic vanadium trichloride solution heated to a constant temperature of 95°C in a water bath, so that the nitrate and vanadium trichloride undergo a reduction reaction to generate NO gas. NO gas will pass through a 2M sodium hydroxide solution at 0°C with the carrier gas. This step can reduce the gas temperature and the hydrochloric acid that evaporates during the absorption process, thereby preventing subsequent device components from being corroded. The NO gas purified by the sodium hydroxide solution will come to the NOx Analyzer detector. In the NOxAnalyzer detector, the NO gas will react with the excess ozone generated by the detector and convert into an excited state. The excited state generated On the way back to the ground state, photons are emitted, and chemiluminescence occurs. When the ozone content is excessive, the number of photons emitted by the reaction is proportional to the NO concentration, which also means that the signal value in the detector is also proportional to the salt concentration in the sample.

[0029] Step S3 includes: International isotope standards USGS34, USGS32, USGS35 and IAEA-N3 are used to calibrate the nitrogen and oxygen isotope values ​​of nitrate.

[0030] Step S5 includes: Use the back-propagation algorithm to update the linear system network weights.

[0031] Specifically, during training, the DFF network uses the back-propagation algorithm to update the network weights. This process involves calculating the gradient of the loss function (such as mean squared error or cross entropy) with respect to the network weights and using these gradients to adjust the weights to reduce the difference between the predicted output and the actual output.

[0032] Step S5 also includes: Add input noise; The nitrate nitrogen and oxygen isotope values ​​and noise during typhoon climate and non-typhoon climate are combined into an implicit representation; Train linear system networks through latent representation.

[0033] Specifically, in the generator module of the linear system network, the conditional information is usually combined with the input noise to form a joint implicit representation. This representation is then converted into a target image through a network layer (which can be a fully connected layer or a convolutional layer). The conditional information of the generator is compared to the interference of typhoon factors on the nitrogen and oxygen isotope content during typhoons, which is excluded in the conditional information. In the discriminator module of the linear system network, the discriminator receives the image feature parameters that meet the conditional information and judges its feasibility and authenticity based on the conditional label.

[0034] Step S5 also includes: The Wasserstein distance loss function is used as the training loss function for the linear system network based on the deep feedforward network.

[0035] Specifically, Wasserstein distance loss is a loss function used to measure the difference between two probability distributions. It is often used to measure the difference between fake samples and real samples generated by the generator in a feedforward neural network. Wasserstein distance loss is actually a problem of solving the minimum distance between two distributions, which is usually solved using linear programming or other numerical methods.

[0036] Specifically, Figure 4 This is a graph of nitrogen isotope parameters for the international working standard nitrate.

[0037] The present application also discloses an electronic device. Figure 3 , Figure 3 The electronic device 500 may include: at least one processor 501 , at least one network interface 504 , a user interface 503 , a memory 505 , and at least one communication bus 502 .

[0038] The communication bus 502 is used to realize the connection and communication between these components.

[0039] The user interface 503 may include a display screen, and the optional user interface 503 may also include a standard wired interface or a wireless interface.

[0040] The network interface 504 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0041] The present application also discloses a computer-readable storage medium storing a plurality of instructions suitable for a processor to load to execute the above-mentioned method for tracing marine high-salinity pollution of coastal insulators based on typhoon factors.

[0042] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0043] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for tracing high salt pollution in coastal insulators based on typhoon factors, characterized in that: The method comprises the following steps: S1: Set up monitoring points on the coastal to inland high-voltage lines in the target area to collect a preset number of groups of insulator dirt and environmental particles during typhoon weather and non-typhoon weather; S2: Using chemiluminescence method, measure the nitrate concentration in insulator dirt and environmental particles; S3: Isotope mass spectrometry combined with nitrate concentration values ​​in insulator dirt and environmental particles The isotopes of nitrate are measured to obtain the nitrogen and oxygen isotope values ​​of nitrate and calibrate them; S4: A Bayesian mixture model was used to determine the contribution ratio of nitrate from different sources in insulator dirt and ambient particulate matter; Construct a data set based on contribution ratios and nitrate nitrogen and oxygen isotope values; S5: Construct a linear system network based on a deep feedforward network; train the linear system network through the data set to obtain a linear change proportional image of nitrogen and oxygen isotopes; through the linear change proportional image, the tracing of marine high-salinity pollution of coastal insulators in the target area taking into account typhoon factors can be achieved.

2. A method for tracing high salt pollution in coastal insulators based on typhoon factors as claimed in claim 1, characterized in that: Step S2 includes: S21: High-purity nitrogen is input into the detection device as a carrier gas to detect the airtightness of the gas path; Samples included: insulator dirt and ambient particles; The nitrate solution of the sample is injected into a 0.1M acidic vanadium trichloride solution heated to a constant temperature of 95°C in a water bath through the injection port of the detection device, so that the nitrate reacts with the vanadium trichloride to generate NO gas; the sample is insulator dirt or environmental particles; NO gas was passed through a 2M sodium hydroxide solution at 0°C; S22: inputting the NO gas purified by the sodium hydroxide solution into the NOx Analyzer detector; In the NOx Analyzer, NO gas reacts with the excess ozone generated by the NOx Analyzer and is converted into an excited state. , get the signal of NOx Analyzer detector; S23: Convert the signal of the NOx Analyzer detector into a voltage signal, and combine it with a scanning spectrum method to obtain the nitrate concentration values ​​of the insulator dirt and environmental particulate matter of a preset number of groups.

3. A method for tracing high salt pollution in coastal insulators based on typhoon factors as claimed in claim 1, characterized in that: Step S3 includes: International isotope standards USGS34, USGS32, USGS35 and IAEA-N3 are used to calibrate the nitrogen and oxygen isotope values ​​of nitrate.

4. A method for tracing high salt pollution in coastal insulators based on typhoon factors as claimed in claim 1, characterized in that: Step S5 includes: Use the back-propagation algorithm to update the linear system network weights.

5. The method for tracing high salt pollution in coastal insulators based on typhoon factors as claimed in claim 1, characterized in that: Step S5 also includes: Adding input noise to the linear system network; The nitrate nitrogen and oxygen isotope values ​​and input noise during typhoon climate and non-typhoon climate are combined into an implicit representation; Train linear system networks through latent representation.

6. The method for tracing high salt pollution in coastal insulators based on typhoon factors as claimed in claim 1, characterized in that: Step S5 also includes: The Wasserstein distance loss function is used as the training loss function for the linear system network based on the deep feedforward network.

7. An electronic device, characterized in that: The electronic device comprises a processor (501), a memory (505), a user interface (503) and a network interface (504), wherein the memory (505) is used to store instructions, the user interface (503) and the network interface (504) are used to communicate with other devices, and the processor (501) is used to execute the instructions stored in the memory (505) so that the electronic device executes the method according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed by a computer, the method according to any one of claims 1 to 6 is executed.

Images