Transformer fire prevention evaluation method, device, equipment, storage medium and program product
By obtaining the mixing ratio and ignition point prediction model of transformer oil, the ignition point of transformer oil is determined, which solves the problem of low efficiency in transformer fire safety assessment in the existing technology, realizes rapid and accurate fire assessment, and ensures the safety of transformers.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHENZHEN POWER SUPPLY BUREAU
- Filing Date
- 2026-03-17
- Publication Date
- 2026-05-29
AI Technical Summary
In existing technologies, transformer fire safety assessment mainly relies on destructive testing, which is inefficient and cannot meet the need for rapid fire safety assessment of operating equipment.
By obtaining the mixing ratio of transformer oil, the first and second parameters are determined using the ignition point prediction model. This model characterizes the ignition point inhibition of the transformer oil by the first oil and the flame retardancy of the transformer oil by the second oil. Based on the mixing ratio and the ignition point prediction model, the ignition point of the transformer oil is determined, and the fire resistance rating of the transformer is then evaluated.
This technology enables the rapid and accurate determination of the ignition point of transformer oil, improves the efficiency of transformer fire prevention assessment, and ensures the safety of transformers.
Smart Images
Figure CN122113053A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of power equipment safety assessment technology, and in particular to a transformer fire protection assessment method, apparatus, equipment, storage medium, and program product. Background Technology
[0002] As the core hub of the power transmission and distribution network, the safe operation of transformers directly affects the stability of the power system. Existing oil-immersed transformers generally use mineral insulating oil and flammable solid insulating materials, forming a natural basis for combustion. Under the influence of factors such as internal electric arcs, external short circuits, or aging overheating, the equipment is extremely prone to accidents such as oil spraying and deflagration. Therefore, in order to identify potential hazards at the source, it is necessary to conduct transformer fire safety assessments.
[0003] In the existing technology, the fire safety assessment of transformers mainly relies on destructive tests (such as the ASTM D92 standard ignition point test), which requires sampling and testing, resulting in low efficiency and failing to meet the need for rapid fire safety assessment of operating equipment. Summary of the Invention
[0004] Therefore, it is necessary to provide a transformer fire protection assessment method, apparatus, equipment, storage medium, and program product that can improve assessment efficiency in response to the above-mentioned technical problems.
[0005] Firstly, this application provides a method for assessing the fire safety of transformers, the method comprising:
[0006] The mixing ratio of transformer oil is obtained. The transformer oil includes a first oil and a second oil, and the first ignition point of the first oil is lower than the second ignition point of the second oil.
[0007] The first parameter is determined based on the first sub-model of the mixing ratio and ignition point prediction model. The first parameter is used to characterize the inhibition of the ignition point of the transformer oil by the first oil.
[0008] The second parameter is determined based on the second sub-model of the mixing ratio and ignition point prediction model. The second parameter is used to characterize the flame retardancy of the second oil on the transformer oil.
[0009] The ignition point of the transformer oil is determined based on the first and second parameters, and the fire protection assessment result of the transformer is determined based on the ignition point of the transformer oil.
[0010] In one embodiment, both the first parameter and the second parameter exhibit an exponentially decreasing relationship with the mixing ratio.
[0011] In one embodiment, the process of determining the ignition point prediction model includes:
[0012] Obtain the sample dataset, which includes the sample mixing ratio of multiple sample oils and the sample flash point of each sample oil;
[0013] Obtain the initial ignition point prediction model, which includes a first initial sub-model and a second initial sub-model. Both the first initial sub-model and the second initial sub-model are exponential decay models.
[0014] By fitting the sample dataset using nonlinear regression analysis, the model parameter values in the initial ignition point prediction model are determined, thus obtaining the ignition point prediction model.
[0015] In one embodiment, obtaining the mixing ratio of the transformer oil includes:
[0016] The total area of the first characteristic peak of the first oil and the total area of the second characteristic peak of the second oil in the transformer oil were determined by gas chromatography analysis.
[0017] The mixing ratio is determined based on the total area of the first characteristic peak and the total area of the second characteristic peak.
[0018] In one embodiment, determining the ignition point of the transformer oil based on a first parameter and a second parameter includes:
[0019] The sum of the first and second parameters is taken as the ignition point of the transformer oil.
[0020] In one embodiment, the assessment result for transformer fire protection is determined based on the ignition point of the transformer oil, including:
[0021] When the ignition point of the transformer oil is greater than or equal to the first preset threshold, the assessment result is determined to be that the transformer's fire protection level is at the first level;
[0022] When the ignition point of the transformer oil is greater than or equal to the second preset threshold and less than the first preset threshold, the evaluation result is determined to be that the transformer fire protection level is at the second level.
[0023] When the ignition point of the transformer oil is less than the second preset threshold, the assessment result is determined to be that the transformer fire protection level is level three; the transformer fire protection level is positively correlated with the ignition point of the transformer oil.
[0024] Secondly, this application also provides a transformer fire protection assessment device, comprising:
[0025] The acquisition module is used to acquire the mixing ratio of transformer oil, which includes a first oil and a second oil, wherein the first ignition point of the first oil is lower than the second ignition point of the second oil.
[0026] The first determining module is used to determine the first parameter based on the mixing ratio and the first sub-model of the ignition point prediction model. The first parameter is used to characterize the suppression of the ignition point of the transformer oil by the first oil.
[0027] The second determining module is used to determine the second parameter based on the mixing ratio and the second sub-model of the ignition point prediction model. The second parameter is used to characterize the flame retardancy of the second oil on the transformer oil.
[0028] The third determining module is used to determine the ignition point of the transformer oil based on the first and second parameters, and to determine the assessment result of transformer fire prevention based on the ignition point of the transformer oil.
[0029] In one embodiment, both the first parameter and the second parameter exhibit an exponentially decreasing relationship with the mixing ratio.
[0030] In one embodiment, the acquisition module is further configured to acquire a sample dataset, which includes the sample mixing ratio of multiple sample oils and the sample ignition point corresponding to each sample oil; acquire an initial ignition point prediction model, which includes a first initial sub-model and a second initial sub-model, both of which are exponential decay models; and determine the model parameter values in the initial ignition point prediction model by fitting the sample dataset based on nonlinear regression analysis, thereby obtaining the ignition point prediction model.
[0031] In one embodiment, the acquisition module is specifically used to determine the total area of the first characteristic peak of the first oil and the total area of the second characteristic peak of the second oil in the transformer oil by gas chromatography analysis; and to determine the mixing ratio based on the total area of the first characteristic peak and the total area of the second characteristic peak.
[0032] In one embodiment, the third determining module is specifically used to take the sum of the first parameter and the second parameter as the ignition point of the transformer oil.
[0033] In one embodiment, the third determining module is specifically used to determine that the transformer fire resistance rating is at level one when the ignition point of the transformer oil is greater than or equal to a first preset threshold; to determine that the transformer fire resistance rating is at level two when the ignition point of the transformer oil is greater than or equal to a second preset threshold and less than the first preset threshold; and to determine that the transformer fire resistance rating is at level three when the ignition point of the transformer oil is less than the second preset threshold. The transformer fire resistance rating is positively correlated with the ignition point of the transformer oil.
[0034] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in any of the first aspects above.
[0035] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any of the first aspects above.
[0036] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the first aspects above.
[0037] The aforementioned transformer fire protection assessment method, apparatus, equipment, storage medium, and program products obtain the mixing ratio of transformer oil, which includes a first oil and a second oil, with the first oil having a lower first ignition point than the second oil. Based on the mixing ratio and a first sub-model of the ignition point prediction model, a first parameter is determined, characterizing the inhibition of the transformer oil's ignition point by the first oil. A second parameter is determined based on the mixing ratio and a second sub-model of the ignition point prediction model, characterizing the flame-retardant effect of the second oil on the transformer oil. The ignition point of the transformer oil is then determined based on the first and second parameters, and the transformer fire protection assessment result is determined based on the ignition point. By inputting the mixing ratio into a pre-constructed ignition point prediction model, the ignition point of the transformer oil is accurately and quickly determined, thereby improving assessment efficiency. Attached Figure Description
[0038] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0039] Figure 1 This is a flowchart illustrating a transformer fire protection assessment method in one embodiment;
[0040] Figure 2 This is a flowchart illustrating the steps for determining the ignition point prediction model in one embodiment;
[0041] Figure 3 This is a flowchart illustrating the steps for obtaining the mixing ratio of transformer oil in one embodiment;
[0042] Figure 4 This is a flowchart illustrating the steps for determining the assessment results of transformer fire protection in one embodiment;
[0043] Figure 5 This is a flowchart illustrating a transformer fire protection assessment method in another embodiment;
[0044] Figure 6 This is a structural block diagram of a transformer fire assessment device in one embodiment;
[0045] Figure 7This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation
[0046] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.
[0047] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.
[0048] As the core hub of the power transmission and distribution network, the safe operation of transformers directly affects the stability of the power system. Existing oil-immersed transformers generally use mineral insulating oil and flammable solid insulating materials, forming a natural basis for combustion. Under the influence of factors such as internal electric arcs, external short circuits, or aging overheating, the equipment is extremely prone to accidents such as oil spraying and deflagration. Therefore, in order to identify potential hazards at the source, it is necessary to conduct transformer fire safety assessments.
[0049] In the existing technology, the fire safety assessment of transformers mainly relies on destructive tests (such as the ASTM D92 standard ignition point test), which requires sampling and testing, resulting in low efficiency and failing to meet the need for rapid fire safety assessment of operating equipment.
[0050] In view of this, this application provides a transformer fire protection assessment method that can effectively improve assessment efficiency.
[0051] In one exemplary embodiment, such as Figure 1 As shown, a method for assessing the fire safety of transformers is provided. Taking the application of this method to computer equipment as an example, the computer equipment can be a server or a terminal. The method includes steps 101 to 104. Wherein:
[0052] Step 101: Obtain the mixing ratio of transformer oil.
[0053] The transformer oil includes a first oil and a second oil, wherein the first ignition point of the first oil is lower than the second ignition point of the second oil.
[0054] The first oil can be a low-flash-point mineral oil with a flash point of approximately 160°C, and the second oil can be a high-flash-point natural ester insulating oil with a flash point of approximately 300°C or higher.
[0055] Optionally, the mixing ratio of the transformer oil can be the ratio between the mass of the first oil and the mass of the second oil in the transformer oil.
[0056] It should be noted that the IEEE C57.147 standard has tested the fire resistance of pure natural ester insulating oil (ignition point ≥300℃) and mineral oil (ignition point approximately 160℃). However, these data only apply to single oils or simple high-proportion mixtures (e.g., 50% / 50%), lacking a systematic study of the small proportion of mineral oil (e.g., ≤11%) that may remain after transformer refilling and the mixture with natural ester. Therefore, the ignition point of transformer oil with any mixing ratio can also be determined through the embodiments of this application. Furthermore, transformer refilling can replace traditional mineral oil transformers with natural ester insulating oil, representing an environmentally friendly technology that reduces carbon emissions.
[0057] Optionally, if the mixing ratio of the transformer oil is predetermined, it can be obtained from a database or from user input data; alternatively, it can be determined based on the predetermined masses of the first and second oils. If the mixing ratio of the transformer oil is uncertain beforehand, it can be determined by gas chromatography analysis or dielectric parameter methods.
[0058] Step 102: Determine the first parameter based on the mixing ratio and the first sub-model of the ignition point prediction model. The first parameter is used to characterize the suppression of the ignition point of the transformer oil by the first oil.
[0059] It is understandable that the ignition point prediction model includes a first sub-model and a second sub-model. By inputting the mixing ratio into the ignition point prediction model, the first sub-model in the ignition point prediction model determines the first parameter based on the mixing ratio.
[0060] The first oil is a low-ignition-point component. Since the low-ignition-point component can evaporate a sufficient concentration of flammable vapor at a lower temperature, the transformer oil can be ignited at a temperature much lower than that of the high-ignition-point component, thereby suppressing and lowering the ignition point of the transformer oil.
[0061] In one possible implementation, the ignition point prediction model can be a neural network model. The structure of this neural network model includes two sub-neural network models, which can be obtained by training the initial model parameters based on a training dataset. The training dataset can include multiple mixed-ratio samples and the ignition point labels corresponding to each mixed-ratio sample. In this way, during the training of the ignition point prediction model based on the training dataset, the ignition point prediction model can fully mix the mapping relationship between the mixed-ratio samples and the corresponding ignition point labels, thereby obtaining the first sub-model and the second sub-model.
[0062] In another possible implementation, the ignition point prediction model can be a traditional mathematical model. This involves determining a specific mathematical model (i.e., the mathematical model has a clear formula and a clear physical meaning), then fitting the mathematical model to a sample dataset to determine the coefficients in the mathematical model, thereby obtaining the ignition point prediction model, which is also known as the first sub-model and the second sub-model.
[0063] Step 103: Determine the second parameter based on the mixing ratio and the second sub-model of the ignition point prediction model. The second parameter is used to characterize the flame retardancy of the second oil on the transformer oil.
[0064] Similarly, after the mixing ratio is input into the ignition point prediction model, the second sub-model in the ignition point prediction model determines the second parameter based on the mixing ratio.
[0065] The second oil is a high flash point component. The flame retardant effect of the high flash point component is completely opposite to the flame retardant effect of the low flash point component. It can be understood that the high flash point component has a significant flame retardant effect in the mixed transformer oil: it has low volatility and high latent heat of vaporization. When heated, it can dilute the concentration of combustible vapor, absorb the heat of the system, and form a liquid phase barrier layer to isolate oxygen, thereby increasing the overall flash point and ignition point of the transformer oil, inhibiting the occurrence and spread of combustion, and improving the fire safety performance of the transformer oil.
[0066] Step 104: Determine the ignition point of the transformer oil based on the first and second parameters, and determine the assessment result of transformer fire prevention based on the ignition point of the transformer oil.
[0067] Optionally, the ignition point of the transformer oil can be obtained by numerically processing the first and second parameters.
[0068] For example, the sum of the first and second parameters can be used as the ignition point of the transformer oil. Alternatively, the ignition point of the transformer oil can be obtained by weighted summation of the first and second parameters.
[0069] The assessment results for transformer fire protection include transformers with a fire protection rating of Level 1, Level 2, and Level 3. Among these, Level 1 has better fire protection performance than Level 2, and Level 2 has better fire protection performance than Level 3.
[0070] After determining the ignition point of the transformer oil, the ignition point of the transformer oil can be compared with the preset threshold corresponding to each level. Based on the range of the ignition point of the transformer oil, the assessment result of transformer fire prevention can be determined. Alternatively, the transformer oil can be input into a pre-trained classification model, and the assessment result of transformer fire prevention can be determined based on the output of the classification model.
[0071] The aforementioned transformer fire protection assessment method obtains the mixing ratio of the transformer oil, which includes a first oil and a second oil. The first oil has a lower first ignition point than the second oil. A first parameter is determined based on the mixing ratio and a first sub-model of the ignition point prediction model. This first parameter characterizes the inhibition of the transformer oil's ignition point by the first oil. A second parameter is determined based on the mixing ratio and a second sub-model of the ignition point prediction model. This second parameter characterizes the flame-retardant effect of the second oil on the transformer oil. The ignition point of the transformer oil is determined based on the first and second parameters, and the fire protection assessment result is then determined based on the ignition point. By inputting the mixing ratio into a pre-constructed ignition point prediction model, the ignition point of the transformer oil is accurately and quickly determined, thereby improving assessment efficiency.
[0072] In one exemplary embodiment, both the first parameter and the second parameter exhibit an exponentially decreasing relationship with the mixing ratio.
[0073] Optionally, the first parameter exhibits an exponential decay relationship with the mixing ratio, and the first sub-model can be an exponential decay model, which can be expressed as:
[0074]
[0075] in, As the first parameter, The mixing ratio is given, A and B are model parameters, and B represents the inhibition rate.
[0076] Similarly, the second sub-model can be an exponential decay model, which can be expressed as:
[0077]
[0078] in, For the second parameter, The mixing ratio is given by C and D, which are model parameters. D represents the concentration decay coefficient of the second oil.
[0079] Based on the above embodiments, such as Figure 2 As shown, the process of determining the ignition point prediction model includes steps 201 to 203. Wherein:
[0080] Step 201: Obtain the sample dataset, which includes the sample mixing ratio of multiple sample oils and the sample ignition point of each sample oil.
[0081] Optionally, when determining the sample dataset, multiple sample oils and their corresponding mixing ratios can be obtained by mixing the first oil and the second oil in different proportions. For example, the proportion gradient of the first oil in the sample oils can be 0%, 1%, 3%, 5%, 7%, 9%, or 11%, etc. The first oil can be mineral oil, such as 25# Karamay mineral insulating oil, and the second oil can be natural ester insulating oil, such as FR3 plant-based transformer insulating oil.
[0082] After obtaining a sample oil, it is filtered through a microporous membrane and stirred using a high-speed mixer at a preset speed for a preset time, then allowed to stand for 24 hours. For example, the microporous membrane has a pore size of 0.45 μm, the high-speed mixer has a preset speed of 800 rpm, and the preset time is 30 minutes. Next, the test cup is cleaned with acetone and heated to 300°C without air, while the environmental conditions are controlled at 23±2°C and 45±5%RH. Then, the Cleveland open cup method according to ASTM D92 is used for testing. The sample oil (e.g., 65 ml) is poured into a standard brass cup and heated at a preset temperature rise rate. When a flame appears and lasts for 5 seconds, the current temperature is recorded as the corresponding sample ignition point. For example, the preset temperature rise rate is 5-6°C / min.
[0083] Therefore, by repeating the above experimental process multiple times and obtaining the sample ignition point corresponding to the mixing ratio of each sample, a sample dataset is obtained.
[0084] Step 202: Obtain the initial ignition point prediction model. The initial ignition point prediction model includes a first initial sub-model and a second initial sub-model. Both the first initial sub-model and the second initial sub-model are exponential decay models.
[0085] The exponential decay model was chosen as both the first and second initial sub-models because the ignition point of the mixed oil is dominated by the nonlinear contribution of the low ignition point component (mineral oil). Experiments show that as the proportion of mineral oil increases, the concentration of its volatile combustible vapors does not increase nonlinearly. This nonlinear characteristic of "weak inhibition at low concentrations and significantly enhanced inhibition at high concentrations" is highly consistent with the exponential decay model. This model structure directly reflects the nonlinear inhibition mechanism of the low ignition point component on the ignition point through mathematical form, which is consistent with the nonlinear decrease in the ignition point of the mixed oil with increasing mineral oil proportion observed in experimental data.
[0086] Step 203: Based on nonlinear regression analysis and fitting of the sample dataset, determine the model parameter values in the initial ignition point prediction model, thereby obtaining the ignition point prediction model.
[0087] Optionally, after determining the specific formula of the initial ignition point prediction model, a nonlinear regression can be used to fit the decay relationship between the mixing ratio and the ignition point to obtain the ignition point prediction model, which can be expressed as: Where Y is the ignition point, and the specific values of A, B, C, and D can be determined through nonlinear regression.
[0088] For example, the ignition point prediction model can be expressed as: .
[0089] Optionally, a validation dataset can also be obtained to validate the accuracy of the ignition point prediction model, ensuring that the prediction error of the ignition point prediction model is ≤ ±10℃.
[0090] The above-mentioned sample dataset is obtained, which includes the sample mixing ratios of multiple sample oils and the corresponding flash points of each sample oil. An initial flash point prediction model is then obtained, comprising a first initial sub-model and a second initial sub-model, both of which are exponential decay models. The model parameter values in the initial flash point prediction model are determined by fitting the sample dataset using nonlinear regression analysis, thus obtaining the flash point prediction model. In this way, by determining a flash point prediction model that conforms to the nonlinear suppression mechanism of low flash point components on the flash point, and by fitting it using nonlinear regression analysis and the sample dataset to determine the specific model parameter values, an accurate flash point prediction model is obtained. Furthermore, the flash point prediction model is based on the flash point decay law of small proportion mineral oil (≤11%), with a prediction error ≤±10℃, overcoming the shortcomings of traditional empirical threshold methods (e.g., flash point ≥300℃) that ignore the influence of mixing ratios, and avoiding safety misjudgments.
[0091] In one exemplary embodiment, such as Figure 3 As shown, optionally, obtaining the mixing ratio of transformer oil includes the following steps 301 to 302. Wherein:
[0092] Step 301: Determine the total area of the first characteristic peak of the first oil and the total area of the second characteristic peak of the second oil in the transformer oil by gas chromatography analysis.
[0093] Optionally, the transformer oil can be diluted with n-hexane, filtered through an organic filter membrane, and then analyzed using a gas chromatograph equipped with a flame ionization detector (FID). Based on the analysis results, the total area of the first characteristic peak of the first oil and the total area of the second characteristic peak of the second oil in the transformer oil can be determined.
[0094] For example, the total area of the first characteristic peak of the first oil is A1, which can be the total area corresponding to the n-alkane characteristic peak (based on C14) in the interval of 14.5 minutes to 16.2 minutes in the analysis results, and the total area of the second peak of the second oil is A2, which is the total area corresponding to the triglyceride characteristic peak (based on trioleic acid glyceride) in the interval of 25.5 minutes to 27.5 minutes in the analysis results.
[0095] For example, in gas chromatography analysis, the pore size of the organic filter membrane is 0.22 μm, and the chromatographic conditions of the gas chromatograph are as follows: the column is a DB-23 (60m×0.25mm×0.25μm) or a column of equivalent polarity (such as a DB-5MS column which needs to be paired with a 50% phenyl column), the carrier gas is high-purity nitrogen with a purity ≥99.999%, the flow rate is 1.0 mL / min, and the temperature program is used: the initial temperature is 120℃ and held for 5 minutes, then increased to 200℃ at a rate of 5℃ / min, and then increased to 280℃ at a rate of 10℃ / min and held for 15 minutes; the injection port temperature is 280℃, the detector temperature is 320℃, the split ratio is 20:1, and the injection volume is 1 μL.
[0096] Step 302: Determine the mixing ratio based on the total area of the first characteristic peak and the total area of the second characteristic peak.
[0097] In one possible implementation, the ratio of the total area of the first characteristic peak to the total area of the second characteristic peak can be used as the mixing ratio, i.e., mixing ratio = A1 / A2.
[0098] In another possible approach, after obtaining the transformer oil, a first mass of a third oil can be added as an internal standard to eliminate matrix interference. For example, the third oil could be deuterated octadecane (C18D36). In this case, gas chromatography analysis can be performed on the transformer oil with the added third oil to obtain the total area A1 of the first characteristic peak of the first oil, the total area A2 of the second characteristic peak of the second oil, and the total area As of the third characteristic peak of the third oil. Quantitative calculations can then be performed using the ratio of the characteristic peak area to the internal standard peak area to offset the matrix interference throughout the volatilization, separation, and detection processes, thereby accurately obtaining the mixing ratio, i.e., mixing ratio = .
[0099] Optionally, after determining the total area A1 of the first characteristic peak of the first oil, the total area A2 of the second characteristic peak of the second oil, and the total area As of the third characteristic peak of the third oil, the mass of the first oil can be determined according to the product of a first ratio, a first mass, and a preset correction factor, where the first ratio is the ratio of the total area of the first characteristic peak to the total area of the third characteristic peak; the mass of the second oil can be determined according to the product of a second ratio, a first mass, and a preset correction factor, where the second ratio is the ratio of the total area of the second characteristic peak to the total area of the third characteristic peak; and then, the mixing ratio can be determined according to the ratio of the mass of the first oil to the mass of the second oil.
[0100] It should be noted that when determining the mixing ratio through the method in the embodiments of this application, the detection limit of the mixing ratio is less than or equal to 0.5%. When the mass fraction of the component to be detected is not less than 0.5%, accurate identification can be achieved. In other words, the lowest content of mineral oil that gas chromatography can reliably detect is 0.5% of the total volume of the mixed oil. That is, when the mineral oil content is lower than this threshold, the detection result will not have statistical reliability.
[0101] The above method uses gas chromatography to determine the total area of the first characteristic peak of the first oil and the total area of the second characteristic peak of the second oil in the transformer oil; the mixing ratio is determined based on the total area of the first and second characteristic peaks, which can accurately determine the mixing ratio of the transformer oil.
[0102] In one exemplary embodiment, optionally, as Figure 4 As shown, the assessment results for transformer fire prevention are determined based on the ignition point of the transformer oil, including the following steps 401 to 403. Wherein:
[0103] Step 401: When the ignition point of the transformer oil is greater than or equal to the first preset threshold, the evaluation result is determined to be that the transformer fire protection level is at the first level.
[0104] The first preset threshold can be 300℃. After determining the ignition point of the transformer oil according to the above embodiment, when the ignition point is ≥300℃, the evaluation result is that the transformer fire protection level is at the second level, and the fire protection level is excellent.
[0105] Step 402: When the ignition point of the transformer oil is greater than or equal to the second preset threshold and the ignition point of the transformer oil is less than the first preset threshold, the evaluation result is determined to be that the transformer fire protection level is at the second level.
[0106] The second preset threshold is 250℃. When 250℃≤ignition point<300℃, the evaluation result is that the transformer's fire protection level is at the second level, and the fire protection level is good.
[0107] Step 403: When the ignition point of the transformer oil is less than the second preset threshold, the evaluation result is determined to be that the transformer fire protection level is at level three.
[0108] Among them, the fire resistance rating of a transformer is positively correlated with the ignition point of the transformer oil.
[0109] When the ignition point is ≤250℃, the evaluation result is that the fire protection level of the transformer is the third level, which is poor.
[0110] Optionally, the assessment results can be sent to the user terminal in the form of push messages or screen display. At the same time, if the assessment result shows that the transformer fire protection level is the second level, it can also be recommended that the user strengthen temperature monitoring or shorten the testing cycle. If the assessment result shows that the transformer fire protection level is the third level, it is recommended to clean the transformer again or replace the insulating oil to ensure the fire safety of the transformer.
[0111] For ease of understanding, such as Figure 5 As shown below, a complete embodiment of the transformer fire protection assessment method provided in this application will be described in the following description.
[0112] Step 501: Obtain the sample dataset, which includes the sample mixing ratio of multiple sample oils and the sample flash point of each sample oil.
[0113] Step 502: Obtain the initial ignition point prediction model. The initial ignition point prediction model includes a first initial sub-model and a second initial sub-model. Both the first initial sub-model and the second initial sub-model are exponential decay models.
[0114] Step 503: Fit the nonlinear regression analysis and sample dataset to determine the model parameter values in the initial ignition point prediction model, thereby obtaining the ignition point prediction model;
[0115] Step 504: Determine the total area of the first characteristic peak of the first oil and the total area of the second characteristic peak of the second oil in the transformer oil by gas chromatography analysis;
[0116] Step 505: Determine the mixing ratio based on the total area of the first characteristic peak and the total area of the second characteristic peak;
[0117] Step 506: Determine the first parameter based on the mixing ratio and the first sub-model of the ignition point prediction model. The first parameter is used to characterize the suppression of the ignition point of the transformer oil by the first oil.
[0118] Step 507: Determine the second parameter based on the mixing ratio and the second sub-model of the ignition point prediction model. The second parameter is used to characterize the flame retardancy of the second oil on the transformer oil.
[0119] Step 508: Take the sum of the first parameter and the second parameter as the ignition point of the transformer oil;
[0120] Step 509: When the ignition point of the transformer oil is greater than or equal to the first preset threshold, the evaluation result is determined to be that the transformer's fire resistance level is at the first level;
[0121] Step 510: When the ignition point of the transformer oil is greater than or equal to the second preset threshold and the ignition point of the transformer oil is less than the first preset threshold, the evaluation result is determined to be that the fire resistance level of the transformer is at the second level.
[0122] Step 511: When the ignition point of the transformer oil is less than the second preset threshold, the evaluation result is determined to be that the transformer fire protection level is at level three.
[0123] Among them, the fire resistance rating of a transformer is positively correlated with the ignition point of the transformer oil.
[0124] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.
[0125] Based on the same inventive concept, this application also provides a transformer fire protection assessment device for implementing the above-mentioned transformer fire protection assessment method. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the transformer fire protection assessment device provided below can be found in the limitations of the transformer fire protection assessment method above, and will not be repeated here.
[0126] In one exemplary embodiment, such as Figure 6 As shown, a transformer fire protection assessment device 600 is provided, comprising: an acquisition module 601, a first determination module 602, a second determination module 603, and a third determination module 604, wherein:
[0127] The acquisition module 601 is used to acquire the mixing ratio of transformer oil, which includes a first oil and a second oil, wherein the first ignition point of the first oil is lower than the second ignition point of the second oil.
[0128] The first determining module 602 is used to determine the first parameter based on the mixing ratio and the first sub-model of the ignition point prediction model. The first parameter is used to characterize the suppression of the ignition point of the transformer oil by the first oil.
[0129] The second determining module 603 is used to determine the second parameter based on the mixing ratio and the second sub-model of the ignition point prediction model. The second parameter is used to characterize the flame retardancy of the second oil on the transformer oil.
[0130] The third determining module 604 is used to determine the ignition point of the transformer oil based on the first parameter and the second parameter, and to determine the assessment result of transformer fire prevention based on the ignition point of the transformer oil.
[0131] In one embodiment, both the first parameter and the second parameter exhibit an exponentially decreasing relationship with the mixing ratio.
[0132] In one embodiment, the acquisition module 601 is further configured to acquire a sample dataset, which includes the sample mixing ratio of multiple sample oils and the sample ignition point of each sample oil; acquire an initial ignition point prediction model, which includes a first initial sub-model and a second initial sub-model, both of which are exponential decay models; and determine the model parameter values in the initial ignition point prediction model by fitting the sample dataset based on nonlinear regression analysis, thereby obtaining the ignition point prediction model.
[0133] In one embodiment, the acquisition module 601 is specifically used to determine the total area of the first characteristic peak of the first oil and the total area of the second characteristic peak of the second oil in the transformer oil by gas chromatography analysis, and to determine the mixing ratio based on the total area of the first characteristic peak and the total area of the second characteristic peak.
[0134] In one embodiment, the third determining module 604 is specifically used to take the sum of the first parameter and the second parameter as the ignition point of the transformer oil.
[0135] In one embodiment, the third determining module 604 is specifically used to determine that the transformer fire resistance rating is at level one when the ignition point of the transformer oil is greater than or equal to a first preset threshold; to determine that the transformer fire resistance rating is at level two when the ignition point of the transformer oil is greater than or equal to a second preset threshold and less than the first preset threshold; and to determine that the transformer fire resistance rating is at level three when the ignition point of the transformer oil is less than the second preset threshold. The transformer fire resistance rating is positively correlated with the ignition point of the transformer oil.
[0136] Each module in the aforementioned transformer fire protection assessment device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.
[0137] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data related to transformer fire protection assessment methods. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a transformer fire protection assessment method.
[0138] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0139] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.
[0140] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.
[0141] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.
[0142] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.
[0143] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.
[0144] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.
Claims
1. A method for assessing the fire safety of transformers, characterized in that, The method includes: The mixing ratio of transformer oil is obtained, wherein the transformer oil includes a first oil and a second oil, and the first ignition point of the first oil is lower than the second ignition point of the second oil. A first parameter is determined based on the mixing ratio and the first sub-model of the ignition point prediction model. The first parameter is used to characterize the suppression of the ignition point of the transformer oil by the first oil. The second parameter is determined based on the second sub-model of the mixing ratio and ignition point prediction model. The second parameter is used to characterize the flame retardancy of the second oil on the transformer oil. The ignition point of the transformer oil is determined based on the first parameter and the second parameter, and the fire prevention assessment result of the transformer is determined based on the ignition point of the transformer oil.
2. The method according to claim 1, characterized in that, Both the first parameter and the second parameter exhibit an exponentially decreasing relationship with the mixing ratio.
3. The method according to claim 1 or 2, characterized in that, The process of determining the ignition point prediction model includes: Obtain a sample dataset, which includes the sample mixing ratio of multiple sample oils and the sample flash point of each sample oil; An initial ignition point prediction model is obtained, which includes a first initial sub-model and a second initial sub-model, both of which are exponential decay models. The model parameter values in the initial ignition point prediction model are determined by fitting the sample dataset using nonlinear regression analysis, thereby obtaining the ignition point prediction model.
4. The method according to claim 1, characterized in that, The process of obtaining the mixing ratio of the transformer oil includes: The total area of the first characteristic peak of the first oil and the total area of the second characteristic peak of the second oil in the transformer oil were determined by gas chromatography analysis. The mixing ratio is determined based on the total area of the first characteristic peak and the total area of the second characteristic peak.
5. The method according to claim 1, characterized in that, Determining the ignition point of the transformer oil based on the first parameter and the second parameter includes: The sum of the first parameter and the second parameter is taken as the ignition point of the transformer oil.
6. The method according to claim 1, characterized in that, The assessment results for transformer fire protection are determined based on the ignition point of the transformer oil, including: When the ignition point of the transformer oil is greater than or equal to a first preset threshold, the evaluation result is determined to be that the transformer's fire resistance level is at the first level. When the ignition point of the transformer oil is greater than or equal to the second preset threshold and the ignition point of the transformer oil is less than the first preset threshold, the evaluation result is determined to be that the fire resistance level of the transformer is at the second level. When the ignition point of the transformer oil is less than a second preset threshold, the evaluation result is determined to be that the fire resistance level of the transformer is at level three; the fire resistance level of the transformer is positively correlated with the ignition point of the transformer oil.
7. A transformer fire safety assessment device, characterized in that, The device includes: The acquisition module is used to acquire the mixing ratio of transformer oil, wherein the transformer oil includes a first oil and a second oil, and the first ignition point of the first oil is lower than the second ignition point of the second oil. The first determining module is used to determine a first parameter based on the mixing ratio and the first sub-model of the ignition point prediction model. The first parameter is used to characterize the suppression of the ignition point of the transformer oil by the first oil. The second determining module is used to determine a second parameter based on the mixing ratio and the second sub-model of the ignition point prediction model. The second parameter is used to characterize the flame retardancy of the second oil on the transformer oil. The third determining module is used to determine the ignition point of the transformer oil based on the first parameter and the second parameter, and to determine the assessment result of transformer fire prevention based on the ignition point of the transformer oil.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to 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 by a processor, it implements the steps of the method according to any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.