A method, device, medium and product for detecting acid value of insulating oil

Abstract

The present application discloses a method, device, medium and product for detecting the acid value of insulating oil, and relates to the field of acid value detection of insulating oil. The method comprises preparing insulating oil samples with different aging degrees; performing terahertz detection on the insulating oil samples to obtain the corresponding time domain signal of the terahertz electric field; preprocessing the time domain signal of the terahertz electric field; performing a main peak extraction operation on the preprocessed time domain signal; and converting the time domain signal after the main peak extraction operation into a frequency domain spectrum; obtaining an insulating oil acid value detection model according to the terahertz characteristic parameters extracted from the frequency domain spectrum and the insulating oil acid value obtained from the insulating oil sample; and obtaining the corresponding insulating oil acid value by using the insulating oil acid value detection model according to the terahertz characteristic parameters of the insulating oil to be tested. The present application can improve the accuracy, efficiency and automation level of insulating oil acid value detection.

Description

Technical Field

[0001] The present application relates to the field of insulating oil acid value detection, and in particular to an insulating oil acid value detection method, equipment, medium and product. Background Art

[0002] Under the long-term operation of complex operating conditions such as electrical, thermal and mechanical stress, the performance of the insulating material of oil-immersed power equipment gradually deteriorates, and the probability of failure increases year by year. The functional characteristics of the insulating oil of oil-filled equipment can effectively reflect the operating risk of the equipment. According to the regulations, the above indicators of each equipment should be evaluated at least once every 1 to 3 years. The acid value of insulating oil indicates that the oil contains acidic substances, that is, the total value of organic acids and inorganic acids. It is generally expressed by the number of mg of potassium hydroxide required to neutralize the acidic substances in 1g of insulating oil. The insulating oil of a new transformer that has not been used contains almost no acidic substances, and its acid value is quite small. However, under long-term storage of oil products, especially after the oil-filled equipment is put into operation, it is inevitable that it will come into contact with oxygen in the air, and the oil products are easily aged. In the early stage of oxidation, low-molecular organic acids are mainly generated, and further oxidation produces high-molecular organic acids and acid products. When the above-mentioned acidic substances exist in the insulating oil, the conductivity of the oil will be increased, the insulation performance of the oil will be reduced, and corrosion to the metal may also occur. When the operating temperature is high (above 80℃), the solid fiber paper insulation material will age, thus shortening the service life of the equipment. According to the analysis of insulating oil based on the on-site investigation, simulation test and aging test results in the laboratory, the insulating oil of the transformer in operation generally has an acid value greater than 0.1mgKOH / g, and the possibility of sludge precipitation in the insulating oil of the transformer increases when the pH value is equal to or less than 4.0. On the contrary, the insulating oil of the transformer can basically ensure the good and reliable operation of the transformer. When the acid value rises to above 0.2mgKOH / g or the pH value is lower than 3.8, the oil quality deteriorates significantly and more sludge will be produced.

[0003] The traditional method for detecting the acid value of insulating oil is the neutralization titration method, which is easily affected by external interference, has a complex test procedure, a low level of automation, a large workload, and is greatly affected by human factors.

[0004] How to improve the accuracy, efficiency and automation level of insulating oil acid value detection is a technical problem that needs to be solved urgently. Summary of the invention

[0005] The purpose of this application is to provide a method, equipment, medium and product for detecting the acid value of insulating oil, which can improve the accuracy, efficiency and automation level of insulating oil acid value detection.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a method for detecting the acid value of insulating oil, the method comprising:

[0008] Preparation of insulating oil samples with different aging degrees;

[0009] Perform terahertz detection on the insulating oil sample to obtain the corresponding time domain signal of the terahertz electric field;

[0010] Preprocessing the time domain signal of the terahertz electric field;

[0011] The preprocessed time domain signal is subjected to a main peak extraction operation; and the time domain signal subjected to the main peak extraction operation is converted into a frequency domain spectrum;

[0012] According to the terahertz characteristic parameters extracted from the frequency domain spectrum and the insulating oil acid value obtained from the insulating oil sample, an insulating oil acid value detection model is obtained;

[0013] According to the terahertz characteristic parameters of the insulating oil to be tested, the insulating oil acid value detection model is adopted to obtain the corresponding insulating oil acid value.

[0014] Optionally, the preparing insulating oil samples with different aging degrees specifically includes:

[0015] Obtaining insulating oil and insulating paper, and drying the insulating oil and insulating paper respectively in a vacuum environment under a first set condition for a first set time; the first set condition has a temperature of 90° C. and a pressure of 5 kPa;

[0016] The dried insulating paper is immersed in insulating oil, and vacuum immersed for a second set time under a second set condition; the second set condition has a temperature of 60° C. and a pressure of 5 kPa;

[0017] The insulating paper was taken out and sealed in a glass bottle at a ratio of 10:1 oil to paper, and then an accelerated thermal aging test was performed;

[0018] During the accelerated thermal aging experiment, samples are taken at intervals, and the taken samples are sealed in containers and stored at a constant temperature, thereby obtaining insulating oil samples with different aging degrees.

[0019] Optionally, the preprocessing of the time domain signal of the terahertz electric field specifically includes:

[0020] Performing time domain signal baseline correction on the time domain signal;

[0021] Perform wavelet decomposition and noise reduction on the time domain signal after baseline correction;

[0022] Multivariate scattering correction is performed on the time domain signal after wavelet decomposition and denoising.

[0023] Optionally, the method for extracting terahertz characteristic parameters is interval partial least squares method.

[0024] Optionally, according to the terahertz characteristic parameters extracted from the frequency domain spectrum and the insulating oil acid value obtained from the insulating oil sample, an insulating oil acid value detection model is obtained, which specifically includes:

[0025] According to the terahertz characteristic parameters extracted from the frequency domain spectrum and the insulating oil acid value obtained from the insulating oil sample, a detection model for the insulating oil acid value was established using support vector machine.

[0026] Optionally, the insulating oil sample is measured using the GB / T 264-1983 petroleum product acid value determination method to obtain the corresponding insulating oil acid value.

[0027] In a second aspect, the present application provides an insulating oil acid value detection device, the insulating oil acid value detection device comprising:

[0028] Sample preparation module, used to prepare insulating oil samples with different aging degrees;

[0029] A time domain signal determination module is used to perform terahertz detection on the insulating oil sample to obtain a corresponding time domain signal of the terahertz electric field;

[0030] A preprocessing module, used for preprocessing the time domain signal of the terahertz electric field;

[0031] The frequency domain spectrum determination module is used to perform a main peak extraction operation on the preprocessed time domain signal; and convert the time domain signal after the main peak extraction operation into a frequency domain spectrum;

[0032] An insulating oil acid value detection model determination module is used to obtain an insulating oil acid value detection model based on terahertz characteristic parameters extracted from frequency domain spectra and the insulating oil acid value obtained from insulating oil samples;

[0033] The detection module is used to obtain the corresponding insulating oil acid value according to the terahertz characteristic parameters of the insulating oil to be tested and adopt the insulating oil acid value detection model.

[0034] In a third aspect, the present application provides a computer 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 insulating oil acid value detection method.

[0035] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the insulating oil acid value detection method when executed by a processor.

[0036] In a fifth aspect, the present application provides a computer program product, including a computer program, which implements the insulating oil acid value detection method when executed by a processor.

[0037] According to the specific embodiments provided in this application, this application has the following technical effects:

[0038] The present application provides an insulating oil acid value detection method, device, medium and product, which perform a main peak extraction operation on a pre-processed time domain signal; and convert the time domain signal after the main peak extraction operation into a frequency domain spectrum; obtain an insulating oil acid value detection model according to terahertz characteristic parameters extracted from the frequency domain spectrum and the insulating oil acid value obtained from the insulating oil sample; in the present application, the main peak extraction operation is performed on the time domain signal, and then in the subsequent process of determining the terahertz characteristic parameters, there is no need to consider the influence of the offset of the acid value characteristic peak on the extraction of the terahertz characteristic parameters; and in the present application, a sample is first prepared, and a quantitative relationship with the insulating oil acid value is established using the terahertz characteristic parameters, and then the terahertz spectrum of the sample to be tested is directly measured, and the insulating oil acid value is detected using the established quantitative relationship; the present application is contactless detection, simple and fast, and does not require sample extraction. While ensuring the accuracy of traditional methods, it can overcome the shortcomings of the prior art such as extraction, complexity and time consumption, and poor anti-interference, and can achieve non-destructive and rapid detection of transformer insulating oil acid value on site. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0040] Figure 1 This is a schematic flow chart of a method for detecting the acid value of insulating oil in one embodiment of the present application.

[0041] Figure 2 This is a schematic diagram of the overall process of a method for detecting the acid value of insulating oil in one embodiment of the present application.

[0042] Figure 3 Schematic diagram of insulating oil samples with different aging degrees.

[0043] Figure 4 Schematic diagram of the structure of the terahertz detection device.

[0044] Figure 5 Schematic diagram of the time domain signal after wavelet decomposition and denoising.

[0045] Figure 6 Schematic diagram of the time domain signal after taking the main peak operation.

[0046] Figure 7 Schematic diagram of terahertz absorption spectrum.

[0047] Figure 8 Schematic diagram of the separating hyperplane.

[0048] Fig. 9 Schematic diagram of the support vector machine structure. DETAILED DESCRIPTION

[0049] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0050] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0051] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0052] In an exemplary embodiment, Figure 1 and Figure 2 As shown, a method for detecting the acid value of insulating oil is provided, wherein:

[0053] Preparation of insulating oil samples with different aging degrees;

[0054] Obtain insulating oil (Karamay #25 mineral oil) and insulating paper (sulfate cellulose insulating paper, thickness of 0.12 mm), and dry the insulating oil and the insulating paper in a vacuum environment under a first set condition for a first set time; the temperature of the first set condition is 90° C., the pressure is 5 kPa; the first set time is 48 hours;

[0055] The dried insulating paper is immersed in insulating oil and vacuum immersed for a second set time under a second set condition; the temperature of the second set condition is 60° C. and the pressure is 5 kPa; the second set time is 24 hours;

[0056] The insulating paper was taken out and placed in a glass bottle with an oil-to-paper ratio of 10:1 (1L oil + 87g paper), sealed, and placed in a 130℃ aging box for accelerated thermal aging test;

[0057] The entire aging experiment lasted for 128 days. During the accelerated thermal aging experiment, samples were taken at intervals and sealed in containers at a constant temperature of 4°C to prevent the volatilization of polar substances in the oil, slow down the deterioration of the insulating oil, prevent the reaction of internal substances, and ensure that the samples taken before and after will not change. Figure 3 As shown, the remaining oil samples were tested for acid value according to national standards, and terahertz testing was performed uniformly after all samples were taken.

[0058] The insulating oil acid value of the insulating oil sample was measured according to GB / T 264-1983 petroleum product acid value determination method. The average value of multiple tests was taken as the test result, as shown in Table 1:

[0059] Table 1

[0060]

[0061] Perform terahertz detection on the insulating oil sample to obtain the corresponding time domain signal of the terahertz electric field;

[0062] Terahertz detection devices such as Figure 4 As shown, a transmission terahertz spectrometer is used to select a polystyrene standard cuvette (capacity of 4.5 mL) with a 10 mm optical path, and the terahertz spectrum of the standard sample insulating oil is non-destructively measured at 25° C. and 5% humidity.

[0063] The femtosecond laser pulse emitted by the femtosecond laser is split into two by a beam splitter, and becomes two femtosecond laser beams; the transmitted light with strong optical power is used as pump light, and the reflected light with weak optical power is used as detection light;

[0064] The pump light illuminates the terahertz radiation source. After energy conversion, the terahertz radiation source radiates terahertz waves into the free space. The terahertz waves are focused by a confocal off-axis parabolic reflector to penetrate the insulating oil sample. The collected terahertz waves containing sample information on the sample stage are then focused onto the electro-optical crystal inside the terahertz receiving end by another confocal off-axis parabolic reflector.

[0065] At the same time, the detection light passes through the time delay device and the reflector and is incident on the electro-optical crystal inside the terahertz receiving end; when the detection light coincides with the terahertz wave that arrives at the same time, the electro-optical crystal produces an electro-optical effect under the action of the terahertz bias electric field, causing the polarization state of the detection light passing through the electro-optical crystal to change; the detection light modulated by the quarter-wave plate is divided into two beams of light with mutually perpendicular polarization directions by the Wollaston prism inside the terahertz receiving end, and then passes through the phase-locked amplifier inside the terahertz receiving end and is incident on the two photoelectric probes of the terahertz differential detector; the terahertz receiving end is connected to an external computer to analyze and process the detected data; the light intensity difference between the two detection lights is proportional to the field strength of the terahertz radiation field, thereby realizing equivalent time sampling of the terahertz pulse signal and extracting the time domain signal of the terahertz electric field.

[0066] Preprocessing the time domain signal of the terahertz electric field;

[0067] Specifically include:

[0068] Performing time domain signal baseline correction on the time domain signal;

[0069] Since there are various drifts in the operation of the instrument hardware, and the appearance of drifts makes the actual spectrum obtained different from the theoretical spectrum (linear or nonlinear), baseline correction is used to approximately eliminate noise. The polynomial fitting method first performs polynomial fitting on the signal with a linear trend, fits the baseline, and then subtracts the fitting signal from the original signal to obtain the time domain signal after baseline correction.

[0070] Perform wavelet decomposition and noise reduction on the time domain signal after baseline correction;

[0071] The wavelet denoising method is an algorithm based on the multi-resolution analysis of wavelet transform. According to the characteristics that the wavelet decomposition coefficients of noise and signal in different frequency bands have different intensity distributions, the wavelet coefficients corresponding to the noise in each frequency band are removed, and the wavelet decomposition coefficients of the original signal are retained. Then, the processed coefficients are reconstructed by wavelet to obtain a pure signal. The denoising effect of wavelet transform is better in the case of low signal-to-noise ratio, and the recognition rate of the denoised signal is higher. At the same time, the denoising effect of wavelet denoising method is particularly obvious for time-varying signals and sudden signal. The time domain signal after wavelet decomposition and denoising is as follows: Figure 5 shown.

[0072] Multivariate scattering correction is performed on the time domain signal after wavelet decomposition and denoising.

[0073] An average spectrum is calculated from a series of spectral data. The average spectrum is a representative that contains the common features of all samples. It is assumed that the spectrum of each sample can be approximated to the average spectrum through a linear transformation. Linear transformation means that a sample spectrum can be adjusted by scaling (multiplying by a coefficient) and translating (adding or subtracting a constant) operations to make its shape as close to the average spectrum as possible. For each sample spectrum, the optimal scaling coefficient and translation constant are found by linear regression. These parameters are applied to the original sample spectrum and adjusted to obtain the corrected spectrum, which reduces the variation caused by scattering and better reflects the true information of the insulating oil sample.

[0074] The preprocessed time domain signal is subjected to a main peak extraction operation; and the time domain signal subjected to the main peak extraction operation is converted into a frequency domain spectrum;

[0075] The main peak operation is to select the main signal, set the signals on both sides of the main peak to zero, thereby improving the stability of the frequency domain signal, and Figure 6 shown.

[0076] The time domain signal after the main peak operation is converted into a frequency domain spectrum, and Figure 7 As shown, the specific formula includes the following:

[0077]

[0078] n(ω)=1+[φ s (ω)-φ r (ω)]c / dω

[0079]

[0080] α(ω)=2k(ω)ω / c

[0081] Where ω is the angular frequency, E(ω) is the terahertz frequency domain electric field, E(t) is the terahertz time domain electric field, A(ω) is the frequency domain amplitude, φ(ω) is the frequency domain phase; d is the thickness of the sample, c is the speed of light in vacuum, φ s (ω) is the frequency domain phase of the sample signal, φ r (ω) is the frequency domain phase of the reference signal, A s (ω) is the frequency domain amplitude of the sample signal, A r (ω) is the frequency domain amplitude of the reference signal, n is the refractive index, k is the extinction coefficient, and α is the absorption coefficient.

[0082] According to the terahertz characteristic parameters extracted from the frequency domain spectrum and the insulating oil acid value obtained from the insulating oil sample, an insulating oil acid value detection model is obtained;

[0083] For the frequency domain spectrum, the interval partial least squares method can be used to extract the characteristic band of acid value. The entire absorption spectrum area is divided into multiple sub-intervals of equal width. Partial least squares regression is performed on each sub-interval to establish a "local regression model" of the acid value of insulating oil. The mean square error (MSE) value is used as the accuracy measurement standard of each model, and the sub-interval where the local model with the highest accuracy is located is taken as the characteristic band of acid value.

[0084] As for the acid value in the oil, it is easy to observe from the absorption spectrum that the insulating oil sample has more absorption peaks in the 1.0-2.5THz frequency band. According to iPLS, the 1.0-2.5THz frequency band is divided into characteristic bands. The data of this frequency band is first divided into 15 intervals, and partial least squares regression is performed on each interval. The mean square error MSE of the established local regression model is calculated. It is preliminarily judged that the characteristic band is located in the 10th to 12th sub-intervals, and it is considered that the extracted characteristic band is located in the 2.0-2.2THz frequency band.

[0085] Multiple regression was used to establish the quantitative relationship between the absorption spectrum values ​​in the 2.0-2.2 THz frequency band and the acid value of the insulating oil.

[0086] Support vector machine is a linear classifier, which is a special perceptron. The ultimate goal of support vector machine is to find a special separation hyperplane and Figure 8 As shown in the figure, the distance between the hyperplane and the sample set is the largest. By converting it into a convex quadratic programming problem, SVM is the optimal method for solving convex quadratic programming.

[0087] For a linear and separable terahertz data set, the hyperplane selected by the model is unique, as shown in Figure 8;

[0088] like Fig. 9 As shown, the SVM input is the training data set K = {(x 1 ,y 1 )(x 2 ,y 2 ),…,(x N ,y N )}, where x i ∈R n ,y i ∈{+1,-1},i=1,2,...,N; the output is the separating hyperplane that can divide the data set; then by selecting the penalty parameter, the parameter is non-negative, and a convex optimization problem is constructed based on the parameter: Solve this problem so that Where 0≤α i ≤C,i=1,2,…,N; thus the optimal solution is obtained Then by calculating Select a component from the optimal solution To satisfy the conditions: Then calculate Finally, the required separation hyperplane with the largest interval is obtained: ω * ·x+b * = 0, and the output decision function is f(x) = sgn(ω * ·x+b * ). Support vector machine regression is a very useful technique, especially for datasets with complex feature relationships.

[0089] The value of each frequency point in the absorption spectrum of 2.0-2.2THz frequency band is used as input, and the acid value measured by the national standard of insulating oil is used as output. C=100 and γ=0.1 are preset. The mean square error is used to evaluate the prediction ability of the model. The gradient descent optimization algorithm is used to determine the optimal C and γ to improve the performance of the model until the final regression analysis is completed.

[0090] The accuracy of the training set and the test machine are both greater than 93%, indicating that the model can accurately evaluate the acid value of insulating oil based on the 2.0-2.2THz frequency band of the terahertz frequency domain absorption spectrum of the insulating oil, and the test does not require the destruction of the insulating oil itself, which has the advantages of being non-destructive and convenient.

[0091] According to the terahertz characteristic parameters of the insulating oil to be tested, the insulating oil acid value detection model is adopted to obtain the corresponding insulating oil acid value.

[0092] The terahertz spectrum of the sample to be tested is measured, and its absorption spectrum in the 2.0-2.2THz frequency band is calculated. The acid value of the insulating oil can be calculated by inputting the acid value detection model, and the measurement comparison is performed based on the GB / T 264-1983 standard. According to the comparison results, the detection results of the present application are basically consistent with the standard measurement method, and the error is less than 0.02mgKOH / g, as shown in Table 2.

[0093] Table 2

[0094]

[0095] The present application is contactless and quick to detect, and does not require sample extraction. While ensuring the accuracy of traditional methods, it overcomes the shortcomings of existing technologies such as extraction, complexity and time consumption, and poor anti-interference, and can achieve non-destructive and rapid detection of transformer insulating oil acid value on site.

[0096] Based on the same inventive concept, the embodiment of the present application also provides an insulating oil acid value detection device for implementing the insulating oil acid value detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more insulating oil acid value detection device embodiments provided below can refer to the limitations of the insulating oil acid value detection method above, and will not be repeated here.

[0097] In an exemplary embodiment, an insulating oil acid value detection device is provided, comprising:

[0098] Sample preparation module, used to prepare insulating oil samples with different aging degrees;

[0099] A time domain signal determination module is used to perform terahertz detection on the insulating oil sample to obtain a corresponding time domain signal of the terahertz electric field;

[0100] A preprocessing module, used for preprocessing the time domain signal of the terahertz electric field;

[0101] The frequency domain spectrum determination module is used to perform a main peak extraction operation on the preprocessed time domain signal; and convert the time domain signal after the main peak extraction operation into a frequency domain spectrum;

[0102] An insulating oil acid value detection model determination module is used to obtain an insulating oil acid value detection model based on terahertz characteristic parameters extracted from frequency domain spectra and the insulating oil acid value obtained from insulating oil samples;

[0103] The detection module is used to obtain the corresponding insulating oil acid value according to the terahertz characteristic parameters of the insulating oil to be tested and adopt the insulating oil acid value detection model.

[0104] In an exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, a memory, an input / output interface, and a communication interface. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for detecting the acid value of insulating oil is implemented.

[0105] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0106] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0107] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other media used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory, magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive memory, magnetic variable memory, ferroelectric memory, phase change memory, graphene memory, etc. Volatile memory may include random access memory or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory or dynamic random access memory, etc.

[0109] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0110] In this application, all actions to obtain signals, information or data are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0111] Importantly, it should be noted that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are only exemplary. Although only a few embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible (e.g., the size, scale, structure, shape and proportion of various elements, and parameter values ​​(e.g., temperature, pressure, etc.), installation arrangement, use of materials, color, directional changes, etc.) without substantially departing from the novel teachings and advantages of the subject matter described in the application. For example, the element shown as integrally formed can be composed of multiple parts or elements, the position of the element can be inverted or otherwise changed, and the nature or number or position of the discrete element can be changed or changed. Therefore, all such modifications are intended to be included in the scope of the present invention. The order or sequence of any process or method steps can be changed or reordered according to alternative embodiments. In the claims, any "device plus function" clause is intended to cover the structure of performing the function described herein, and is not only structurally equivalent but also equivalent structure. Without departing from the scope of the present invention, other replacements, modifications, changes and omissions can be made in the design, operating conditions and arrangement of the exemplary embodiments. Therefore, the invention is not limited to a specific embodiment, but extends to numerous modifications still falling within the scope of the appended claims.

[0112] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0113] It will be appreciated that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will be a routine task of design, fabrication, and production for those of ordinary skill having the benefit of this disclosure without undue experimentation.

[0114] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for detecting the acid value of insulating oil, characterized in that: include, Preparation of insulating oil samples with different aging degrees; Perform terahertz detection on the insulating oil sample to obtain the corresponding time domain signal of the terahertz electric field; Preprocessing the time domain signal of the terahertz electric field; The preprocessed time domain signal is subjected to a main peak extraction operation; and the time domain signal subjected to the main peak extraction operation is converted into a frequency domain spectrum; According to the terahertz characteristic parameters extracted from the frequency domain spectrum and the insulating oil acid value obtained from the insulating oil sample, an insulating oil acid value detection model is obtained; According to the terahertz characteristic parameters of the insulating oil to be tested, the insulating oil acid value detection model is adopted to obtain the corresponding insulating oil acid value.

2. The method for detecting the acid value of insulating oil according to claim 1, characterized in that: The method of preparing insulating oil samples with different aging degrees also includes obtaining insulating oil and insulating paper, and drying the insulating oil and insulating paper respectively in a vacuum environment under a first set condition for a first set time; the temperature of the first set condition is 90° C. and the pressure is 5 kPa; immersing the dried insulating paper in the insulating oil, and vacuum immersing the paper under a second set condition for a second set time; The second set condition has a temperature of 60°C and a pressure of 5 kPa; the insulating paper is taken out and sealed in a glass bottle with an oil-to-paper ratio of 10:1, and an accelerated thermal aging experiment is performed; during the accelerated thermal aging experiment, samples are taken at intervals, and the taken samples are sealed in a container and stored at a constant temperature, thereby obtaining insulating oil samples with different degrees of aging.

3. The method for detecting the acid value of insulating oil according to claim 1, characterized in that: The preprocessing of the time domain signal of the terahertz electric field also includes performing baseline correction on the time domain signal; performing wavelet decomposition and noise reduction on the time domain signal after the baseline correction; and performing multivariate scattering correction on the time domain signal after the wavelet decomposition and noise reduction.

4. The method for detecting the acid value of insulating oil according to claim 1, characterized in that: The method for extracting the terahertz characteristic parameters is interval partial least squares method.

5. The method for detecting the acid value of insulating oil according to claim 2, characterized in that: An insulating oil acid value detection model is obtained based on the terahertz characteristic parameters extracted from the frequency domain spectrum and the insulating oil acid value obtained from the insulating oil sample. Specifically, a support vector machine is used to establish an insulating oil acid value detection model based on the terahertz characteristic parameters extracted from the frequency domain spectrum and the insulating oil acid value obtained from the insulating oil sample.

6. The deicing blade for a wind turbine according to claim 5, characterized in that: The insulating oil sample was measured using the GB / T264-1983 petroleum product acid value determination method to obtain the corresponding insulating oil acid value.

7. An insulating oil acid value detection device, characterized in that: include, Sample preparation module, used to prepare insulating oil samples with different aging degrees; as well as, A time domain signal determination module is used to perform terahertz detection on the insulating oil sample to obtain a corresponding time domain signal of the terahertz electric field; and A preprocessing module, used for preprocessing the time domain signal of the terahertz electric field; and, The frequency domain spectrum determination module is used to perform a main peak extraction operation on the preprocessed time domain signal; and convert the time domain signal after the main peak extraction operation into a frequency domain spectrum; and, An insulating oil acid value detection model determination module is used to obtain an insulating oil acid value detection model according to terahertz characteristic parameters extracted from frequency domain spectrum and the insulating oil acid value obtained from the insulating oil sample; and The detection module is used to obtain the corresponding insulating oil acid value according to the terahertz characteristic parameters of the insulating oil to be tested and adopt the insulating oil acid value detection model.

8. A computer device comprising: 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 insulating oil acid value detection 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, the insulating oil acid value detection method described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the insulating oil acid value detection method described in any one of claims 1 to 6 is implemented.

Images