Insulating oil state multi-parameter intelligent health assessment method and device and storage medium

Abstract

The invention relates to the technical field of power equipment state monitoring, in particular to an insulating oil state multi-parameter intelligent health assessment method and device and a storage medium, and the method comprises the steps: obtaining a measured value sequence of a plurality of key electrical parameters of an insulating oil sample under at least two different temperature conditions; based on the measured value sequence and the initial value of each parameter, calculating to obtain a change rate sequence of each parameter under different aging time and different temperature conditions; according to a preset directional definition, identifying the change rate of the relative dielectric constant as a positive index, and identifying the change rate of the partial discharge initial voltage and the change rate of the breakdown field strength as negative indexes; inputting the change rate of each identified parameter into a health index model, and calculating to obtain a health index value; and comparing the health index value with a preset threshold interval, and outputting the state grade of the insulating oil. Through the setting, the evaluation mechanism is clear, the model is scientific, and the intelligent evaluation of the state of the insulating oil in early warning can be realized.

Description

Technical Field

[0001] This application relates to the field of power equipment condition monitoring technology, and in particular to a method, device and storage medium for intelligent health assessment of insulating oil condition using multiple parameters. Background Technology

[0002] As a core piece of equipment in the power system, the condition of the insulating oil in transformers directly affects the safe and stable operation of the entire power grid. Timely and accurate assessment of the insulating oil condition is key to achieving predictive maintenance of transformers.

[0003] Currently, methods for assessing the condition of insulating oil can be mainly divided into two categories: offline testing and online monitoring. Offline testing methods (such as electrical strength testing, acid value titration, and oil chromatography analysis) have high measurement accuracy, but require manual on-site sampling, which is cumbersome and takes weeks or even months to complete. They cannot achieve real-time condition perception and early fault warning, and the sampling process may introduce representativeness errors. Online monitoring technology is the future direction. Current online monitoring solutions mainly use multi-parameter neural network assessment methods, ultrasonic or resistance online monitoring methods, and spectral analysis methods. However, multi-parameter neural network models have problems such as unclear mechanisms and reliance on a large number of samples. Ultrasonic or resistance methods have problems such as a single assessment dimension and insufficient accuracy. Spectroscopic analysis methods fail to quantify the effect of temperature and do not consider the directional significance of parameter changes.

[0004] In other words, current insulating oil condition assessment technologies either cannot achieve real-time online assessment, or although they can monitor online, they still have the following limitations: they fail to systematically reveal the evolution law of key parameters under the coupled effect of temperature and aging time, and at the same time, they lack a scientific definition of the directionality of parameter changes, resulting in insufficient physical basis for assessment models, difficulty in capturing early deterioration signals, and limited early warning capabilities. Summary of the Invention

[0005] To address the aforementioned technical problems, this application provides a multi-parameter intelligent health assessment method, device, and storage medium for insulating oil condition. The assessment mechanism is clear, the model is scientific, and it can achieve early warning intelligent assessment of insulating oil condition.

[0006] In a first aspect, embodiments of this application provide a multi-parameter intelligent health assessment method for insulating oil condition, the multi-parameter intelligent health assessment method for insulating oil condition comprising: Obtain a sequence of measured values ​​for multiple key electrical parameters of an insulating oil sample under at least two different temperature conditions. The sequence of measured values ​​varies with thermal aging time. The key electrical parameters include partial discharge initiation voltage, breakdown field strength, and relative permittivity. Based on the measured value sequence and the initial values ​​of the partial discharge initiation voltage, the breakdown field strength, and the relative permittivity, the rate of change sequence of the partial discharge initiation voltage, the breakdown field strength, and the relative permittivity under different aging times and different temperature conditions is calculated; For a specific aging state, the rate of change of the partial discharge initiation voltage, the rate of change of the breakdown field strength, and the rate of change of the relative permittivity corresponding to a specific aging time and a specific temperature condition are determined from the rate of change sequence. According to the preset directional definition, the rate of change of the relative permittivity is identified as a positive index, and the rate of change of the partial discharge initiation voltage and the rate of change of the breakdown field strength are identified as negative indexes. The rate of change of the identified partial discharge initiation voltage, the rate of change of the breakdown field strength, and the rate of change of the relative permittivity are input into the health index model to calculate the health index value. The health index model is configured to positively weight the positive indicators and negatively weight the negative indicators. The health index value is compared with a preset threshold range to output the state level of the insulating oil. The preset threshold range is a continuous range of health index values ​​that divides the health state of the insulating oil.

[0007] According to some embodiments of the first aspect of this application, at least two different temperature conditions include a first temperature condition and a second temperature condition, and the acquisition of a sequence of measured values ​​of multiple key electrical parameters of the insulating oil sample under at least two different temperature conditions includes: For insulating oil samples at the same aging time point, the key electrical parameters were measured sequentially under the first temperature condition and the second temperature condition. The initial value is a reference value measured by the insulating oil sample in an unaged state under the first temperature condition.

[0008] According to some embodiments of the first aspect of this application, the first temperature condition is one of 23°C to 27°C, and the second temperature condition is greater than or equal to 70°C.

[0009] According to some embodiments of the first aspect of this application, the thermal aging time includes a plurality of discrete time points starting from the initial state, and the thermal aging time includes at least day 1, day 7, day 21, day 28 and day 35.

[0010] According to some embodiments of the first aspect of this application, the expression of the health index model is as follows: in, Represents the rate of change of the relative permittivity. This represents the rate of change of the partial discharge initiation voltage. This represents the rate of change of the breakdown field strength. , and These represent the weighting coefficients corresponding to the rate of change of the relative permittivity, the rate of change of the partial discharge initiation voltage, and the rate of change of the breakdown field strength, respectively.

[0011] According to some embodiments of the first aspect of this application, the weighting coefficient , and It is obtained by combining the entropy weight method or the analytic hierarchy process with the entropy weight method.

[0012] According to some embodiments of the first aspect of this application, the status levels include a normal state, a noticeable state, a vigilant state, and a failure state. The health index corresponding to the normal state is less than or equal to 0.3, the health index corresponding to the noticeable state is greater than 0.3 and less than or equal to 0.6, the health index corresponding to the vigilant state is greater than 0.6 and less than or equal to 0.9, and the health index corresponding to the failure state is greater than 0.9.

[0013] According to some embodiments of the first aspect of this application, before inputting the rate of change of the identified partial discharge initiation voltage, the rate of change of the breakdown field strength, and the rate of change of the relative permittivity into the health index model, the following is included: The rate of change of the partial discharge initiation voltage and the rate of change of the breakdown field strength, which are identified as negative indicators, are converted into absolute values ​​and then input into the health index model.

[0014] Secondly, embodiments of this application provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement: the multi-parameter intelligent health assessment method for insulating oil condition as described in the first aspect above.

[0015] Thirdly, embodiments of this application also provide a computer-readable storage medium storing computer-executable instructions for executing the multi-parameter intelligent health assessment method for insulating oil as described in the first aspect above.

[0016] The beneficial effects of this application are reflected in the following: by obtaining a sequence of measured values ​​of multiple key electrical parameters of an insulating oil sample under at least two different temperature conditions, wherein the measured value sequence changes with thermal aging time, and the key electrical parameters include partial discharge initiation voltage, breakdown field strength, and relative permittivity; based on the measured value sequence and the initial values ​​of the partial discharge initiation voltage, breakdown field strength, and relative permittivity, a sequence of the rate of change of the partial discharge initiation voltage, breakdown field strength, and relative permittivity under different aging times and different temperature conditions is calculated; for a specific aging state, the rate of change of the partial discharge initiation voltage and the rate of change of the breakdown field strength corresponding to a specific aging time and a specific temperature condition are determined from the rate of change sequence. The rate of change of the relative permittivity is defined as follows: Based on a preset directional definition, the rate of change of the relative permittivity is identified as a positive indicator, while the rates of change of the partial discharge initiation voltage and the breakdown field strength are identified as negative indicators. These identified rates of change of the partial discharge initiation voltage, the breakdown field strength, and the relative permittivity are input into a health index model to calculate a health index value. The health index model is configured to positively weight the positive indicators and negatively weight the negative indicators. The health index value is compared with a preset threshold range to output the state level of the insulating oil. The preset threshold range is a continuous range of health index values ​​that divides the health state of the insulating oil. This application, through this setup, provides a clear evaluation mechanism, a scientific model, and enables intelligent assessment of the insulating oil's state with early warning capabilities. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the multi-parameter intelligent health assessment method for insulating oil provided in the first aspect of this application. Figure 2 This is a schematic flowchart of the process for obtaining a sequence of measurement values ​​provided in the first aspect embodiment of this application; Figure 3 This is a schematic diagram of the overall workflow of the insulating oil condition assessment system provided in the first aspect embodiment of this application; Figure 4 This is a schematic diagram of the flow of the parameter change rate directionality definition and health index model calculation provided in the first aspect embodiment of this application; Figure 5 This is a flowchart illustrating the process before the rate of change of the identified partial discharge initiation voltage, the rate of change of the breakdown field strength, and the rate of change of the relative permittivity are input into the health index model, as provided in the first aspect embodiment of this application. Figure 6 This is a schematic diagram of the structure of the electronic device provided in the third aspect embodiment of this application. Detailed Implementation

[0018] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0019] In the description of this application, it should be understood that the orientation descriptions, such as up, down, front, back, left, right, etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0020] In the description of this application, the use of "first" and "second" is for the purpose of distinguishing technical features only, and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or the order of the technical features indicated.

[0021] In the description of this application, unless otherwise expressly defined, terms such as "setup," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this application in conjunction with the specific content of the technical solution.

[0022] As a core piece of equipment in the power system, the condition of the insulating oil in transformers directly affects the safe and stable operation of the entire power grid. Timely and accurate assessment of the insulating oil condition is key to achieving predictive maintenance of transformers.

[0023] Currently, methods for assessing the condition of insulating oil can be mainly divided into two categories: offline testing and online monitoring. Offline testing methods (such as electrical strength testing, acid value titration, and oil chromatography analysis) have high measurement accuracy, but require manual on-site sampling, which is cumbersome and takes weeks or even months to complete. They cannot achieve real-time condition perception and early fault warning, and the sampling process may introduce representativeness errors. Online monitoring technology is the future direction. Current online monitoring solutions mainly use multi-parameter neural network assessment methods, ultrasonic or resistance online monitoring methods, and spectral analysis methods. However, multi-parameter neural network models have problems such as unclear mechanisms and reliance on a large number of samples. Ultrasonic or resistance methods have problems such as a single assessment dimension and insufficient accuracy. Spectroscopic analysis methods fail to quantify the effect of temperature and do not consider the directional significance of parameter changes.

[0024] In other words, current insulating oil condition assessment technologies either cannot achieve real-time online assessment, or although they can monitor online, they still have the following limitations: they fail to systematically reveal the evolution law of key parameters under the coupled effect of temperature and aging time, and at the same time, they lack a scientific definition of the directionality of parameter changes, resulting in insufficient physical basis for assessment models, difficulty in capturing early deterioration signals, and limited early warning capabilities.

[0025] To address the aforementioned problems, this application proposes a multi-parameter intelligent health assessment method, device, and storage medium for insulating oil. The embodiments of this application will be further described below with reference to the accompanying drawings.

[0026] Reference Figure 1 , Figures 3 to 4 , Figure 1 This application illustrates a multi-parameter intelligent health assessment method for insulating oil condition according to an embodiment of the first aspect of this application. This method is also applied to electronic devices and executed by the electronic devices. In other words, the method can be executed by software or hardware installed in the device, and the method includes the following steps: Step S100: Obtain a sequence of measured values ​​for multiple key electrical parameters of the insulating oil sample under at least two different temperature conditions.

[0027] In this step, the measured value sequence changes with thermal aging time, and the key electrical parameters include partial discharge initiation voltage, breakdown field strength, and relative permittivity.

[0028] It should be noted that three parameters were selected that can comprehensively reflect the state of insulating oil from three different but complementary physical dimensions: insulation strength (breakdown field strength), discharge characteristics (partial discharge initiation voltage), and polarization characteristics (relative permittivity). This combination avoids the randomness of single-parameter evaluation and is different from the difficult-to-interpret neural network black box model, making the evaluation dimensions comprehensive and the physical meaning clear.

[0029] In one possible implementation, the thermal aging time includes multiple discrete time points starting from the initial state, with the thermal aging time including at least day 1, day 7, day 21, day 28, and day 35.

[0030] Step S200: Based on the measured value sequence and the initial values ​​of partial discharge initiation voltage, breakdown field strength and relative permittivity, calculate the rate of change sequence of partial discharge initiation voltage, breakdown field strength and relative permittivity under different aging times and different temperature conditions.

[0031] It should be noted that by treating temperature as a core variable alongside aging time, and by systematically collecting data at multiple temperature and time points and calculating the rate of change sequence, the co-evolution law of key electrical parameters in the temperature-time dual-factor coupled field is forcibly and quantitatively revealed, thus establishing the assessment on a clear physical basis.

[0032] Step S300: For a specific aging state, determine from the rate of change sequence the rate of change of partial discharge initiation voltage, the rate of change of breakdown field strength, and the rate of change of relative permittivity corresponding to a specific aging time and a specific temperature condition.

[0033] It should be noted that when used online, the system only needs to measure the parameters of the insulating oil at a specific temperature to retrieve the corresponding data points from the preset "rate of change sequence" knowledge base for calculation. This ensures that the method is based on comprehensive historical patterns and can perform fast and accurate real-time evaluation of the current state.

[0034] It should be noted that the formulas for calculating the rate of change of partial discharge initiation voltage, the rate of change of breakdown field strength, and the rate of change of relative permittivity are as follows: Rate of change (Δ) = (Aging value - Initial value) / Initial value 100%.

[0035] Step S400: According to the preset directionality definition, the rate of change of the relative permittivity is identified as a positive index, and the rate of change of the partial discharge initiation voltage and the rate of change of the breakdown field strength are identified as negative indexes.

[0036] In this step, the contribution directions of different parameters to the aging state are scientifically defined: an increase in the rate of change of the relative permittivity is bad (positive indicator), while a decrease in the rate of change of the partial discharge initiation voltage and the rate of change of the breakdown field strength is bad (negative indicator). This effectively solves the problem of confusion between positive and negative contributions when multiple parameters are fused, and provides a key logical premise for building a scientific and unified evaluation model.

[0037] In step S500, the rate of change of the marked partial discharge initiation voltage, the rate of change of the breakdown field strength, and the rate of change of the relative permittivity are input into the health index model to calculate the health index value.

[0038] In this step, the health index model is configured to positively weight positive indicators and negatively weight negative indicators.

[0039] It should be noted that the configuration of positive and negative weighting faithfully reflects the physical meaning of the parameters mathematically. This enables the model to sensitively capture the subtle but consistent degradation trends of multiple parameters in the early stages of aging (such as a slight increase in the rate of change of the relative permittivity while a slight decrease in the rate of change of the partial discharge initiation voltage), thereby achieving early warning and overcoming the lag of traditional methods that only alarm when performance deteriorates significantly.

[0040] In one possible implementation, the health index model can be understood to be expressed as follows: in, Represents the rate of change of the relative permittivity. This represents the rate of change of the partial discharge initiation voltage. This represents the rate of change of the breakdown field strength. , and These represent the weighting coefficients corresponding to the rate of change of relative permittivity, the rate of change of partial discharge initiation voltage, and the rate of change of breakdown field strength, respectively.

[0041] In one possible implementation, the weighting coefficients , and It is obtained by combining the entropy weight method or the analytic hierarchy process with the entropy weight method.

[0042] It should be noted that when using the entropy weight method, the information entropy of the rate of change of each parameter is calculated based on a data matrix composed of a large amount of historical experimental data, thereby determining the objective weight; when using the analytic hierarchy process, the importance of the parameters is compared pairwise based on expert experience to construct a judgment matrix, and the subjective weight is calculated. Finally, the subjective and objective weights are weighted and integrated.

[0043] Step S600: Compare the health index value with the preset threshold range and output the state level of the insulating oil.

[0044] In this step, the preset threshold range is the numerical range of continuous health index values ​​that divide the health status of insulating oil.

[0045] In one possible implementation, the status levels include normal state, attention state, alert state, and failure state. The health index corresponding to the normal state is less than or equal to 0.3, the health index corresponding to the attention state is greater than 0.3 and less than or equal to 0.6, the health index corresponding to the alert state is greater than 0.6 and less than or equal to 0.9, and the health index corresponding to the failure state is greater than 0.9.

[0046] It should be noted that this application constructs a standardized evaluation process: data acquisition → calculation of rate of change → model calculation → output of results. This process is naturally suitable for automated execution, providing a core methodology for developing online monitoring systems, eliminating the reliance on manual sampling and offline testing, and realizing real-time or near-real-time status awareness.

[0047] It should be noted that the health index corresponding to a normal state This indicates that the insulating oil is in good condition and can continue to operate normally; pay attention to the corresponding health index. This indicates that the insulating oil has begun to deteriorate, requiring increased monitoring and a shorter testing cycle; the health index corresponding to the alert state. This indicates a significant decline in the performance of the insulating oil, requiring a maintenance plan and preparation for oil replacement; the health index corresponding to the failure state. This indicates that the insulating oil has lost its basic insulating properties and poses a high risk; it should be shut down immediately.

[0048] It should be noted that by directly linking the assessment results with the operation and maintenance action guidelines, the specific thresholds (0.3, 0.6, 0.9) and corresponding status levels make the assessment results no longer abstract values, but clear and actionable warnings and decision instructions.

[0049] Specifically, existing online monitoring technologies mainly include: Multi-parameter neural network evaluation method: This method acquires multiple parameters of insulating oil (such as water content, dielectric loss factor, etc.) and inputs them into a trained neural network model for evaluation. However, the generalization ability of this method heavily relies on a large number of labeled samples, and its "black box" nature leads to a lack of clear physical mechanism explanations in the evaluation results. More importantly, this method fails to deeply reveal the quantitative evolution law of key electrical parameters under the coupled effect of "temperature" and "aging time," resulting in limited reliability and guiding significance of the evaluation model; Ultrasonic or resistance online monitoring method: This method measures the ultrasonic waves in the oil... While using propagation characteristics or changes in the resistance of insulating oil to indirectly reflect oil quality is easy to implement online, the assessment dimension is singular, usually relying on only one or a few indirect parameters. It is difficult to comprehensively and accurately capture the complex aging state of insulating oil, and the assessment results are easily affected by accidental factors, resulting in insufficient accuracy. Spectroscopic analysis methods, such as predicting parameters like acid value and interfacial tension of insulating oil based on the characteristic wavelengths of ultraviolet spectra, provide a rapid detection means, but their assessment models do not clearly quantify the direct impact of temperature changes on key electrical performance parameters of insulating oil, nor do they systematically explain the contribution of different parameter change directions (i.e., whether their indication of aging state is positive or negative) to the comprehensive assessment.

[0050] It should be noted that, referring to Figure 3 The multi-parameter intelligent health assessment method for insulating oil in this application is generally divided into two layers: a data acquisition layer and a data processing layer. The data acquisition layer includes insulating oil sample preparation, multi-parameter detection at room temperature and high temperature (partial discharge initiation voltage, breakdown field strength, relative permittivity), and the data processing layer includes the entire process of insulating oil parameter data preprocessing and change rate calculation, health index calculation, state classification, and finally outputting the results. (Refer to...) Figure 4 The diagram illustrates how the measured parameter values ​​are converted into a rate of change, and how the health index value is finally obtained by combining the preset positive / negative indicator definitions with weight calculation.

[0051] Based on this, the multi-parameter intelligent health assessment method for insulating oil provided in this application acquires the measurement sequence of multiple key electrical parameters of the insulating oil sample under at least two different temperature conditions. The measurement sequence changes with thermal aging time, and the key electrical parameters include partial discharge initiation voltage, breakdown field strength, and relative permittivity. Based on the measurement sequence and the initial values ​​of partial discharge initiation voltage, breakdown field strength, and relative permittivity, the method calculates the rate of change sequence of partial discharge initiation voltage, breakdown field strength, and relative permittivity under different aging times and different temperature conditions. For a specific aging state, the method determines the rate of change of partial discharge initiation voltage, breakdown field strength, and relative permittivity corresponding to a specific aging time and specific temperature condition from the rate of change sequence. The rate of change of the breakdown field strength and the rate of change of the relative permittivity are used. Based on a preset directional definition, the rate of change of the relative permittivity is identified as a positive indicator, while the rates of change of the partial discharge initiation voltage and the breakdown field strength are identified as negative indicators. These identified rates of change are input into a health index model to calculate the health index value. The health index model is configured to positively weight positive indicators and negatively weight negative indicators. The health index value is compared with a preset threshold range to output the state level of the insulating oil. The preset threshold range is a continuous range of health index values ​​that defines the health state of the insulating oil. This application, through this setup, provides a clear evaluation mechanism, a scientific model, and enables intelligent assessment of the insulating oil's state with early warning capabilities.

[0052] Understandably, referring to Figure 2 At least two different temperature conditions, including a first temperature condition and a second temperature condition, are involved. Step S100 includes, but is not limited to, the following steps: Step S110: For insulating oil samples at the same aging time point, key electrical parameters are measured sequentially under the first temperature condition and the second temperature condition.

[0053] In this step, the initial value is the baseline value measured by the insulating oil sample in an unaged state at the first temperature condition.

[0054] It should be noted that defining the initial value as the value under the first temperature condition (room temperature) without aging establishes a unified and scientific calculation benchmark for the entire evaluation system.

[0055] In one possible implementation, the first temperature condition is one of 23°C to 27°C, and the second temperature condition is greater than or equal to 70°C.

[0056] In some embodiments, the first temperature condition is 25℃±2℃, used to simulate normal temperature operating conditions; the second temperature condition is 90℃±5℃, used to simulate the hot spot temperature of the transformer during operation or to accelerate thermal aging.

[0057] It should be noted that when measuring under the first and second temperature conditions, including after switching temperatures, the insulating oil sample should be kept at the target temperature for at least 30 minutes to ensure that the internal temperature of the oil sample is uniform and stable before measurement.

[0058] Understandably, referring to Figure 5 Before inputting the rate of change of the identified partial discharge initiation voltage, the rate of change of the breakdown field strength, and the rate of change of the relative permittivity into the health index model in step S500, the following steps are included, but are not limited to: Step S510: Convert the rate of change of partial discharge initiation voltage and the rate of change of breakdown field strength, which are identified as negative indicators, into absolute values ​​and input them into the health index model.

[0059] In this step, the rate of change of the relative permittivity of the positive index is directly input into the health index model using its calculated value.

[0060] It should be noted that the preprocessing step of taking the absolute value of the negative indicators before model calculation ensures that the data format input to the model is consistent.

[0061] For example, taking KI50X as an example, the parameters of insulating oil under different conditions are obtained through the insulating oil multi-parameter detection platform. Under normal temperature conditions, the specific data are shown in the table below: normal temperature Partial discharge initiation voltage (kV) Breakdown electric field strength (kV / mm) Relative permittivity normal 13.5 51.2 3.506 Notice 12.9 51 3.619 Warning 12.2 50.1 3.652 warn 11.9 49.8 3.691 Failure 11.6 49.5 3.722 The specific data for high-temperature conditions are shown in the table below: high temperature Partial discharge initiation voltage (kV) Breakdown electric field strength (kV / mm) Relative permittivity normal 10.7 40.2 3.516 Notice 10.6 39.5 3.635 Warning 9.8 38.3 3.672 warn 9.2 37.9 3.71 Failure 8.9 37.1 3.727 Based on the measured parameters, extract the parameters. , , The corresponding weighting coefficients, calculated based on the differences between high and low temperatures, are shown in the table below: Weighting coefficient value <![CDATA[w1]]> 0.0401 <![CDATA[w2]]> 0.2152 <![CDATA[w3]]> 0.2448 After substituting the weighting coefficients into the HI calculation formula and considering the effect of temperature, the quality of insulating oil is divided into five levels: HI value Status evaluation Maintenance Recommendations HI≥0.95 excellent The insulating oil has good performance and can operate safely; 0.90≤HI<0.95 good The insulating oil is in normal condition and requires routine monitoring. 0.85≤HI<0.90 Notice The insulating oil has slightly deteriorated; it is recommended to strengthen monitoring. 0.75≤HI<0.85 Warning The insulating oil has deteriorated significantly and a maintenance plan is needed. HI<0.75 warn The insulating oil is severely deteriorated and should be treated immediately. As shown in the table above, high temperature significantly affects the performance of insulating oil, and the HI value generally decreases in all states.

[0062] Optionally, such as Figure 6As shown, the second aspect of this application also provides an electronic device 10, including a processor 11 and a memory 12. The memory 12 stores a program or instructions that can run on the processor 11. When the program or instructions are executed by the processor 11, they implement the various processes of the first aspect of the intelligent health assessment method for multi-parameter state of insulating oil, and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0063] It should be noted that the devices in the embodiments of this application include: servers, terminals, or other devices besides terminals.

[0064] The above device structure does not constitute a limitation on the device. The device may include more or fewer components than illustrated, or combine certain components, or arrange different components. For example, the input unit may include a graphics processing unit (GPU) and a microphone, and the display unit may use a liquid crystal display, organic light-emitting diode, or other forms to configure the display panel. The user input unit includes at least one of a touch panel and other input devices. A touch panel is also called a touch screen. Other input devices may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.

[0065] Memory can be used to store software programs and various data. Memory can primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area can store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, memory can include volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0066] The processor may include one or more processing units; optionally, the processor integrates an application processor and a modem processor, wherein the application processor mainly handles operations related to the operating system, user interface, and applications, while the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor.

[0067] This application also provides a readable storage medium storing a program or instructions. When executed by a processor, the program or instructions implement the various processes of the first aspect of the intelligent health assessment method for multi-parameter status of insulating oil, achieving the same technical effect. To avoid repetition, these will not be described again here. The processor is the processor in the device described above. The readable storage medium includes computer-readable storage media such as ROM, RAM, magnetic disk, or optical disk. It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in an order different from that described. In addition, features described with reference to certain examples may be combined in other examples.

[0068] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0069] In the description of the embodiments of this application, the terms "first," "second," "third," and "fourth" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," "third," or "fourth" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0070] In the description of the embodiments of this application, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0071] Although embodiments of this application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An insulating oil state multi-parameter intelligent health evaluation method, characterized in that, The method comprises: obtaining a plurality of measurement value sequences of a plurality of key electrical parameters of an insulating oil sample under at least two different temperature conditions, the measurement value sequences varying with thermal aging time, the key electrical parameters comprising partial discharge inception voltage, breakdown field strength and relative dielectric constant; based on the measurement value sequences and initial values of the partial discharge inception voltage, the breakdown field strength and the relative dielectric constant, calculating a plurality of rate of change sequences of the partial discharge inception voltage, the breakdown field strength and the relative dielectric constant under different aging times and different temperature conditions; for a specific aging state, determining the rate of change of the partial discharge inception voltage, the rate of change of the breakdown field strength and the rate of change of the relative dielectric constant corresponding to the specific aging time and the specific temperature condition from the rate of change sequences; according to a preset directionality definition, identifying the rate of change of the relative dielectric constant as a positive indicator, and identifying the rate of change of the partial discharge inception voltage and the rate of change of the breakdown field strength as negative indicators; inputting the identified rate of change of the partial discharge inception voltage, the rate of change of the breakdown field strength and the rate of change of the relative dielectric constant into a health index model to calculate a health index value, wherein the health index model is configured to positively weight the positive indicators and negatively weight the negative indicators; comparing the health index value with a preset threshold interval to output a state grade of the insulating oil, wherein the preset threshold interval is a numerical range of continuous health index values that divides the health state of the insulating oil.

2. The method of claim 1, wherein, The at least two different temperature conditions comprise a first temperature condition and a second temperature condition, and the obtaining a plurality of measurement value sequences of a plurality of key electrical parameters of an insulating oil sample under at least two different temperature conditions comprises: for an insulating oil sample at the same aging time point, sequentially performing measurement of the key electrical parameters under the first temperature condition and the second temperature condition; wherein the initial values are reference values measured under the first temperature condition in an unaged state of the insulating oil sample.

3. The method of claim 2, wherein, The first temperature condition is one of 23℃ to 27℃, and the second temperature condition is greater than or equal to 70℃.

4. The method of claim 1, wherein, The thermal aging time comprises a plurality of discrete time points starting from an initial state, and the thermal aging time at least comprises the 1st day, the 7th day, the 21st day, the 28th day and the 35th day.

5. The method of claim 1, wherein, The expression of the health index model is as follows: wherein represents a rate of change of relative dielectric constant, represents a rate of change of partial discharge inception voltage, represents a rate of change of breakdown field strength, , and respectively represent weight coefficients corresponding to the rate of change of relative dielectric constant, the rate of change of partial discharge inception voltage and the rate of change of breakdown field strength.

6. The method of claim 5, wherein, The weight coefficient , and is obtained by entropy weight method or a combination of analytic hierarchy process and entropy weight method.

7. The method of claim 1, wherein, The state grade comprises a normal state, an attention state, a warning state and a failure state, the health index corresponding to the normal state is less than or equal to 0.3, the health index corresponding to the attention state is greater than 0.3 and less than or equal to 0.6, the health index corresponding to the warning state is greater than 0.6 and less than or equal to 0.9, and the health index corresponding to the failure state is greater than 0.

9.

8. The method of claim 1, wherein, Before the inputting the identified rate of change of the partial discharge inception voltage, the rate of change of the breakdown field strength and the rate of change of the relative dielectric constant into the health index model, the method comprises: The rate of change of the partial discharge inception voltage and the rate of change of the breakdown field strength, identified as negative indicators, are converted to absolute values and input to the health index model.

9. An electronic device, comprising: The application relates to a method for multi-parameter intelligent health evaluation of insulating oil state. The memory, the processor and the computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to realize the method for multi-parameter intelligent health evaluation of insulating oil state according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer executable instructions for the method for multi-parameter intelligent health evaluation of insulating oil state according to any one of claims 1 to 8.

Images