A State Assessment Method for Dry Air-Core Reactors Based on Naive Bayes Classifier

Abstract

This invention provides a method for assessing the state of dry-type air-core reactors based on a Naive Bayes classifier, comprising: establishing an equivalent circuit model of the dry-type air-core reactor and determining the equivalent inductance after a typical reactor fault; analyzing the time-frequency domain characteristics of the equivalent inductance to determine the changes in state parameters after a fault in the dry-type air-core reactor and identifying feature quantities used to assess the operating state of the dry-type air-core reactor; constructing a state assessment model for the dry-type air-core reactor based on a Naive Bayes classifier; establishing feature quantity data samples for different operating states of the dry-type air-core reactor and training the state assessment model; inputting the actual operating data of the reactor to be assessed into the trained state assessment model to obtain the fault level assessment with the highest probability. This invention can assess the operating state of dry-type air-core reactors using changes in state quantities, providing guidance for the maintenance and repair of dry-type air-core reactors in practical engineering.

Description

Technical Field

[0001] This invention relates to the field of power equipment condition assessment technology, specifically to a method for assessing the condition of dry air-core reactors based on a Naive Bayes classifier. Background Technology

[0002] With the expansion of power system scale and the increase in reactive power demand, the number of reactors put into operation is also increasing year by year. Dry-type air-core reactors have advantages such as good linearity, low loss, and convenient maintenance, and are often used as series reactors, shunt reactors, and smoothing reactors in power systems. The widespread application and development of power electronics technology has added a large number of nonlinear loads to the power supply system, leading to increasingly frequent switching of dry-type air-core reactors and a rising failure rate, posing a significant threat to the safety of the power system. Therefore, accurately assessing the operating status of dry-type air-core reactors and understanding their operating conditions is of great significance for the long-term safe and stable operation of reactors and the power system.

[0003] Current traditional fault diagnosis methods for dry-type air-core reactors mostly rely on a single parameter as the criterion, making it difficult to achieve timely fault warning and isolation. With the construction and development of the power Internet of Things, a large number of sensors and measuring devices have been put into use, and traditional single-parameter diagnostic analysis methods can hardly meet the growing demand for condition data analysis. Therefore, it is urgent to carry out research on condition assessment technology for dry-type air-core reactors to provide strong technical support for the safe operation of power systems. Summary of the Invention

[0004] To address the aforementioned problems, this invention provides the following technical solution. The purpose of this invention is to provide a method for assessing the state of dry-type air-core reactors based on a Naive Bayes classifier. This method can utilize changes in state variables to assess the operating state of dry-type air-core reactors, providing guidance for the maintenance and repair of dry-type air-core reactors in practical engineering projects. This is of great significance for the safe and stable operation of dry-type air-core reactors and power systems.

[0005] The state assessment method for dry air-core reactors based on Naive Bayes classifiers includes the following steps:

[0006] Establish an equivalent circuit model of a dry-type air-core reactor and determine the equivalent inductance after a typical reactor fault.

[0007] Analyze the time-frequency domain characteristics of the equivalent inductance to determine the changes in the state parameters of the dry-type air-core reactor after a fault, and identify the characteristic quantities used to evaluate the operating state of the dry-type air-core reactor.

[0008] A state assessment model for dry air-core reactors is constructed based on the Naive Bayes classifier.

[0009] Establish characteristic quantity data samples of dry-type air-core reactors under different operating states, and train the dry-type air-core reactor state assessment model.

[0010] The actual operating data of the reactor to be evaluated is input into the trained dry-type air-core reactor condition assessment model to obtain the fault level assessment with the highest probability.

[0011] Preferably, the step of establishing an equivalent circuit model of a dry-type air-core reactor and determining the equivalent inductance after a typical reactor fault includes the following steps:

[0012] Establish an equivalent circuit model of a dry-type air-core reactor, and set a short-circuit turn in the nth layer;

[0013] An equivalent fault model for dry-type air-core reactors is established based on transformer principles.

[0014] Write the KCL circuit equations for the fault equivalent model of the dry-type air-core reactor and calculate the equivalent inductance of the dry-type air-core reactor:

[0015]

[0016] in, This is the voltage across the dry-type air-core reactor. The currents on the primary and secondary sides are respectively, R1 and R2. n+1 The resistors are L1 and L2 on the primary and secondary sides, respectively. n+1 M represents the inductance on the primary and secondary sides, respectively, while M represents the mutual inductance between the primary and secondary sides.

[0017] Simplifying the above equation and extracting the imaginary part, we obtain the equivalent inductance of the dry-type air-core reactor as follows:

[0018]

[0019] Preferably, the short-circuit turn is equivalent to the secondary side of the equivalent circuit of a dry-type air-core reactor, and the other windings are equivalent to the primary side of the equivalent circuit of a dry-type air-core reactor.

[0020] Preferably, the determination of the characteristic quantities used to evaluate the operating state of the dry-type air-core reactor includes the following steps:

[0021] Analyze the time-frequency domain characteristics of the equivalent inductance to determine the changes in electrical parameters after a fault in the dry-type air-core reactor:

[0022]

[0023] In the formula, ω=2πf=200π, a0, a m It is a constant.

[0024] By analyzing the changes in equivalent inductance, we can analyze the changes in current amplitude and harmonics after a fault in a dry-type air-core reactor.

[0025] By analyzing the changes in equivalent inductance, we can analyze the changes in temperature parameters after a fault in a dry-type air-core reactor.

[0026] The analysis yields changes in current amplitude and harmonics, as well as temperature parameters, after a fault in the dry-type air-core reactor, providing characteristic quantities for evaluating the operating status of the dry-type air-core reactor.

[0027] Preferably, the training of the dry-type air-core reactor state assessment model based on Naive Bayes classification includes the following steps:

[0028] By adopting the assumption of attribute conditional independence, Bayes' theorem is rewritten to establish a state assessment model for dry-type air-core reactors;

[0029] Preprocessing of training sample data for different fault levels of dry-type air-core reactors;

[0030] Import test samples of dry-type air-core reactors with different fault levels, calculate the probability of each sample at different fault levels, and normalize the probabilities.

[0031] By comparing the maximum probability of different fault levels, the state level corresponding to each sample is determined, and the corresponding maintenance strategy is determined.

[0032] Preferably, the construction of the dry-type air-core reactor condition assessment model includes the following steps:

[0033] Bayes' theorem states:

[0034]

[0035] After adopting the assumption of conditional independence of attributes, the above formula can be written as:

[0036]

[0037] For different category labels, P(x) is the same, so the above formula can be further simplified to obtain the expression for Naive Bayes classification:

[0038]

[0039] Preferably, it further includes:

[0040] Preprocessing mainly includes removing outlier data, sorting data by different fault levels, and calculating conditional probabilities based on the normal distribution, as shown in the following formula:

[0041]

[0042] A dry air-core reactor state assessment system based on a Naive Bayes classifier includes:

[0043] The equivalent model building module is used to build an equivalent model of the dry-type air-core reactor circuit and determine the equivalent inductance after a typical reactor fault.

[0044] The equivalent inductance analysis module is used to analyze the time-frequency domain characteristics of the equivalent inductance, determine the changes in the state parameters of the dry-type air-core reactor after a fault, and identify the characteristic quantities used to evaluate the operating state of the dry-type air-core reactor.

[0045] The state assessment model building module constructs a state assessment model for dry air-core reactors based on the Naive Bayes classifier.

[0046] The state assessment model training module establishes characteristic quantity data samples of different operating states of dry-type air-core reactors to train the state assessment model of dry-type air-core reactors.

[0047] The fault level assessment module inputs the actual operating data of the reactor to be assessed into the trained dry-type air-core reactor state assessment model to obtain the fault level assessment with the highest probability.

[0048] A computer device includes: the computer device includes a memory and a processor, the memory storing a computer program, which, when executed by the processor, causes the processor to perform the following steps:

[0049] Establish an equivalent circuit model of a dry-type air-core reactor and determine the equivalent inductance after a typical reactor fault.

[0050] Analyze the time-frequency domain characteristics of the equivalent inductance to determine the changes in the state parameters of the dry-type air-core reactor after a fault, and identify the characteristic quantities used to evaluate the operating state of the dry-type air-core reactor.

[0051] A state assessment model for dry air-core reactors is constructed based on the Naive Bayes classifier.

[0052] Establish characteristic quantity data samples of dry-type air-core reactors under different operating states, and train the dry-type air-core reactor state assessment model.

[0053] The actual operating data of the reactor to be evaluated is input into the trained dry-type air-core reactor condition assessment model to obtain the fault level assessment with the highest probability.

[0054] A computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the following steps:

[0055] Establish an equivalent circuit model of a dry-type air-core reactor and determine the equivalent inductance after a typical reactor fault.

[0056] Analyze the time-frequency domain characteristics of the equivalent inductance to determine the changes in the state parameters of the dry-type air-core reactor after a fault, and identify the characteristic quantities used to evaluate the operating state of the dry-type air-core reactor.

[0057] A state assessment model for dry air-core reactors is constructed based on the Naive Bayes classifier.

[0058] Establish characteristic quantity data samples of dry-type air-core reactors under different operating states, and train the dry-type air-core reactor state assessment model.

[0059] The actual operating data of the reactor to be evaluated is input into the trained dry-type air-core reactor condition assessment model to obtain the fault level assessment with the highest probability.

[0060] The beneficial effects of this invention are:

[0061] This invention proposes a state assessment method for dry-type air-core reactors based on a Naive Bayes classifier. By establishing an equivalent fault model for the dry-type air-core reactor, the equivalent inductance after typical faults is calculated. Time-frequency domain analysis is used to determine the characteristic quantities that can accurately assess the state of the dry-type air-core reactor, providing a theoretical basis for accurately assessing its operating state. A state assessment model for dry-type air-core reactors based on Naive Bayes classification is established, and simulation data is used for training and testing to determine the model's feasibility and accuracy. Overall, this invention helps to study the changes in state quantities of dry-type air-core reactors under different operating conditions, facilitates state assessment of dry-type air-core reactors, and is of great significance for the safe and reliable operation of dry-type air-core reactors. Attached Figure Description

[0062] Figure 1 The flowchart shows the state assessment method for dry air-core reactors based on Naive Bayes classifier of the present invention.

[0063] Figure 2 Equivalent circuit diagram for inter-turn short-circuit fault in dry-type air-core reactor;

[0064] Figure 3 This is a flowchart of step S1 of the algorithm in an embodiment of the present invention;

[0065] Figure 4 This is a flowchart of step S2 of the algorithm in an embodiment of the present invention;

[0066] Figure 5 This is a flowchart of step S3 of the algorithm in an embodiment of the present invention. Detailed Implementation

[0067] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0068] Example 1

[0069] This invention relates to a method for assessing the state of dry air-core reactors based on a Naive Bayes classifier. For example... Figure 1-5 As shown:

[0070] S1: Establish an equivalent model of the dry-type air-core reactor and solve for the equivalent inductance after typical faults in the reactor. This provides a theoretical basis for S2 to determine the characteristic quantities of the dry-type air-core reactor under different operating states. The flowchart is as follows: Figure 3 As shown.

[0071] S1.1: Establish the equivalent circuit model of the dry-type air-core reactor.

[0072] S1.2: Set a short-circuit turn in the nth layer, that is, establish an equivalent circuit for inter-turn short-circuit faults in a dry-type air-core reactor.

[0073] S1.3: Establish an equivalent fault model for a dry-type air-core reactor based on the transformer principle; write the KCL circuit equations for the equivalent fault model of the dry-type air-core reactor, and calculate the equivalent inductance of the dry-type air-core reactor:

[0074]

[0075] in, This is the voltage across the dry-type air-core reactor. The currents on the primary and secondary sides are respectively, R1 and R2. n+1 The resistors are L1 and L2 on the primary and secondary sides, respectively. n+1 These are the inductances on the primary and secondary sides, respectively, while M is the mutual inductance between the primary and secondary sides.

[0076] S1.4: Simplifying the above equation and extracting the imaginary part, we obtain the equivalent inductance of the dry-type air-core reactor as follows:

[0077]

[0078] It can be seen that after an inter-turn short circuit fault occurs in the reactor, the inductance value decreases and shows an oscillating trend.

[0079] S2: Using time-frequency domain analysis, determine the characteristic quantities that can accurately assess the state of the dry-type air-core reactor, providing a data foundation for S3 to accurately assess the operating state of the dry-type air-core reactor. The flowchart is as follows: Figure 4 As shown.

[0080] S2.1: Analyze the time-frequency characteristics of the equivalent inductance:

[0081]

[0082] In the formula, ω=2πf=200π, a0, a m It is a constant.

[0083] As can be seen from the above formula, after a dry-type air-core reactor fails, the equivalent inductance is no longer a constant value, but a time-varying parameter containing components such as 100Hz and 200Hz.

[0084] S2.2: Analysis of the changes in equivalent inductance after a fault in a dry-type air-core reactor shows that the impedance angle decreases as the fault severity increases; the current amplitude increases as the fault severity increases; and the current harmonic content increases as the fault severity increases.

[0085] S2.3: Analyze the magnitude of the fault turn current after a fault in a dry-type air-core reactor:

[0086]

[0087] This current is much greater than the normal operating current of the reactor. The faulty turn will generate a lot of heat, causing the average temperature and hot spot temperature to rise. Furthermore, the reactor temperature and hot spot temperature will increase as the severity of the fault increases.

[0088] S2.4: The finite element method was used to simulate and calculate the changes in characteristic quantities of the reactor under different fault levels, and training samples were established using the simulation data. According to the simulation results, after a fault occurs, the reactor impedance angle decreases, the reactor current gradually increases, and the reactor current harmonic content gradually increases. Regarding temperature, as the fault level increases, the average reactor temperature rises rapidly, showing an overall linear increase, while the hot spot temperature shows an exponential increase, verifying the theoretical derivations in S2.2 and S2.3.

[0089] S3: Establish a state assessment model for dry-type air-core reactors based on Naive Bayes classification, train and test it using feature quantity data samples, and determine the feasibility and accuracy of the model. The process is as follows: Figure 5 As shown.

[0090] S3.1: By adopting the assumption of attribute conditional independence, Bayes' theorem is rewritten to establish a state assessment model for dry-type air-core reactors.

[0091] S3.2: Considering the continuous values ​​of the state characteristic samples of dry-type air-core reactors, a probability density function is used to estimate the conditional probability. Given that statistical data in actual engineering often follows a normal distribution, the conditional probability can be estimated as follows:

[0092]

[0093] Where: μl,i and σ l,i denoted as the mean and variance of the attribute values ​​of class i in class l samples.

[0094] S3.3: 200 sets of simulation data are used as training samples for the dry-type air-core reactor state assessment model based on Naive Bayes classification, including 40 sets of data for each of the different reactor operating state levels. An additional 50 sets of data are provided as test samples, including 10 sets of data for each of the different reactor operating state levels. Abnormal data in the dry-type air-core reactor operating state samples are removed. The training samples are then classified and sorted according to fault level, and the number of samples for each fault level is counted.

[0095] S3.4: Calculate the mean and variance of different types of attribute values ​​in the sample under different fault levels;

[0096] S3.5: Train the dry air-core reactor state assessment model based on Naive Bayes classification using training samples;

[0097] S3.6: Import test sample data and calculate the normalized probability of each different sample data under different state levels.

[0098] S4: The fault level assessment with the highest probability obtained by the trained dry-type air-core reactor condition assessment model is shown in Table 1 below. The accuracy of the case analysis results reaches 90%, which verifies the accuracy of the dry-type air-core reactor condition assessment method proposed in this invention patent.

[0099] Table 1 Fault Level Assessment Results

[0100]

[0101] The condition assessment method of this invention comprehensively considers the influence of multiple factors, thus achieving high accuracy and reliability in condition assessment. Furthermore, the MATLAB software upon which this invention is based can have its code stored in a computer-readable storage medium, and the schemes in the embodiments of this application can be implemented using various computer languages. Overall, this invention contributes to the research of condition assessment technology for dry-type air-core reactors and is of great significance to the safe and reliable operation of dry-type air-core reactors.

[0102] Example 2

[0103] A dry air-core reactor state assessment system based on a Naive Bayes classifier includes:

[0104] The equivalent model building module is used to build an equivalent model of the dry-type air-core reactor circuit and determine the equivalent inductance after a typical reactor fault.

[0105] The equivalent inductance analysis module is used to analyze the time-frequency domain characteristics of the equivalent inductance, determine the changes in the state parameters of the dry-type air-core reactor after a fault, and identify the characteristic quantities used to evaluate the operating state of the dry-type air-core reactor.

[0106] The state assessment model building module constructs a state assessment model for dry air-core reactors based on the Naive Bayes classifier.

[0107] The state assessment model training module establishes characteristic quantity data samples of different operating states of dry-type air-core reactors to train the state assessment model of dry-type air-core reactors.

[0108] The fault level assessment module inputs the actual operating data of the reactor to be assessed into the trained dry-type air-core reactor state assessment model to obtain the fault level assessment with the highest probability.

[0109] Example 3

[0110] A computer device includes: the computer device includes a memory and a processor, the memory storing a computer program, which, when executed by the processor, causes the processor to perform the following steps:

[0111] Establish an equivalent circuit model of a dry-type air-core reactor and determine the equivalent inductance after a typical reactor fault.

[0112] Analyze the time-frequency domain characteristics of the equivalent inductance to determine the changes in the state parameters of the dry-type air-core reactor after a fault, and identify the characteristic quantities used to evaluate the operating state of the dry-type air-core reactor.

[0113] A state assessment model for dry air-core reactors is constructed based on the Naive Bayes classifier.

[0114] Establish characteristic quantity data samples of dry-type air-core reactors under different operating states, and train the dry-type air-core reactor state assessment model.

[0115] The actual operating data of the reactor to be evaluated is input into the trained dry-type air-core reactor condition assessment model to obtain the fault level assessment with the highest probability.

[0116] Example 4

[0117] A computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the following steps:

[0118] Establish an equivalent circuit model of a dry-type air-core reactor and determine the equivalent inductance after a typical reactor fault.

[0119] Analyze the time-frequency domain characteristics of the equivalent inductance to determine the changes in the state parameters of the dry-type air-core reactor after a fault, and identify the characteristic quantities used to evaluate the operating state of the dry-type air-core reactor.

[0120] A state assessment model for dry air-core reactors is constructed based on the Naive Bayes classifier.

[0121] Establish characteristic quantity data samples of dry-type air-core reactors under different operating states, and train the dry-type air-core reactor state assessment model.

[0122] The actual operating data of the reactor to be evaluated is input into the trained dry-type air-core reactor condition assessment model to obtain the fault level assessment with the highest probability.

[0123] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0124] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0125] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0126] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0127] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0128] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for assessing the state of a dry air-core reactor based on a Naive Bayes classifier, characterized in that, Includes the following steps: Establish an equivalent circuit model of a dry-type air-core reactor and determine the equivalent inductance after a typical reactor fault. Analyze the time-frequency domain characteristics of the equivalent inductance to determine the changes in the state parameters of the dry-type air-core reactor after a fault, and identify the characteristic quantities used to evaluate the operating state of the dry-type air-core reactor. A state assessment model for dry air-core reactors is constructed based on the Naive Bayes classifier. Establish characteristic quantity data samples of dry-type air-core reactors under different operating states, and train the dry-type air-core reactor state assessment model. The actual operating data of the reactor to be evaluated is input into the trained dry-type air-core reactor condition assessment model to obtain the fault level assessment with the highest probability. The determination of the characteristic quantities used to evaluate the operating status of the dry-type air-core reactor includes the following steps: Analyze the time-frequency domain characteristics of the equivalent inductance to determine the changes in electrical parameters after a fault in the dry-type air-core reactor; By analyzing the changes in equivalent inductance, we can analyze the changes in current amplitude and harmonics after a fault in a dry-type air-core reactor. By analyzing the changes in equivalent inductance, we can analyze the changes in temperature parameters after a fault in a dry-type air-core reactor. The analysis yielded changes in current amplitude and harmonics, as well as temperature parameters, after a fault in the dry-type air-core reactor, providing characteristic quantities for evaluating the operating status of the dry-type air-core reactor. The training of the dry air-core reactor state assessment model based on Naive Bayes classification includes the following steps: By adopting the assumption of attribute conditional independence, Bayes' theorem is rewritten to establish a state assessment model for dry-type air-core reactors; Preprocessing of training sample data for different fault levels of dry-type air-core reactors; Import test samples of dry-type air-core reactors with different fault levels, calculate the probability of each sample at different fault levels, and normalize the probabilities. By comparing the maximum probability of different fault levels, the state level corresponding to each sample is determined, and the corresponding maintenance strategy is determined.

2. The method for assessing the state of a dry air-core reactor based on a Naive Bayes classifier according to claim 1, characterized in that, The process of establishing an equivalent circuit model for a dry-type air-core reactor and determining the equivalent inductance after a typical reactor fault includes the following steps: Establish the equivalent circuit model of the dry-type air-core reactor, and in the first... n Short-circuit turns are set in the layer; An equivalent fault model for dry-type air-core reactors is established based on transformer principles. Write the KCL circuit equations for the fault equivalent model of the dry-type air-core reactor and calculate the equivalent inductance of the dry-type air-core reactor: ； in, This is the voltage across the dry-type air-core reactor. , These are the currents on the primary and secondary sides, respectively. R 1. R n+1 These are the resistors on the primary and secondary sides, respectively. L 1. L n+1 The inductors are on the primary and secondary sides, respectively. M This refers to the mutual inductance between the primary and secondary sides; Simplifying the above equation and extracting the imaginary part, we obtain the equivalent inductance of the dry-type air-core reactor as follows: 。 3. The method for assessing the state of a dry air-core reactor based on a Naive Bayes classifier according to claim 2, characterized in that, The short-circuit turn is equivalent to the secondary side of the equivalent circuit of a dry-type air-core reactor, and the other windings are equivalent to the primary side of the equivalent circuit of a dry-type air-core reactor.

4. The method for assessing the state of a dry air-core reactor based on a Naive Bayes classifier according to claim 1, characterized in that, The determination of changes in electrical parameters after a fault in a dry-type air-core reactor: ； In the formula, ω =2 πf =200 π , a 0, a m It is a constant.

5. The method for assessing the state of a dry air-core reactor based on a Naive Bayes classifier according to claim 1, characterized in that, The construction of the dry-type air-core reactor condition assessment model includes the following steps: Bayes' theorem states: ； After adopting the assumption of conditional independence of attributes, the above formula can be written as: ； For different category labels P ( x Since they are all the same, we can further simplify them into the expression for Naive Bayes classification: 。 6. The method for assessing the state of a dry air-core reactor based on a Naive Bayes classifier according to claim 1, characterized in that, Also includes: Preprocessing mainly includes removing outlier data, sorting data by different fault levels, and calculating conditional probabilities based on the normal distribution. 。 7. A state assessment system for dry air-core reactors based on a Naive Bayes classifier, characterized in that, include: The equivalent model building module is used to build an equivalent model of the dry-type air-core reactor circuit and determine the equivalent inductance after a typical reactor fault. The equivalent inductance analysis module is used to analyze the time-frequency domain characteristics of the equivalent inductance, determine the changes in the state parameters of the dry-type air-core reactor after a fault, and identify the characteristic quantities used to evaluate the operating state of the dry-type air-core reactor. The state assessment model building module constructs a state assessment model for dry air-core reactors based on the Naive Bayes classifier. The state assessment model training module establishes characteristic quantity data samples of different operating states of dry-type air-core reactors to train the state assessment model of dry-type air-core reactors. The fault level assessment module inputs the actual operating data of the reactor to be assessed into the trained dry-type air-core reactor state assessment model to obtain the fault level assessment with the highest probability. The determination of the characteristic quantities used to evaluate the operating status of the dry-type air-core reactor includes the following steps: Analyze the time-frequency domain characteristics of the equivalent inductance to determine the changes in electrical parameters after a fault in the dry-type air-core reactor; By analyzing the changes in equivalent inductance, we can analyze the changes in current amplitude and harmonics after a fault in a dry-type air-core reactor. By analyzing the changes in equivalent inductance, we can analyze the changes in temperature parameters after a fault in a dry-type air-core reactor. The analysis yielded changes in current amplitude and harmonics, as well as temperature parameters, after a fault in the dry-type air-core reactor, providing characteristic quantities for evaluating the operating status of the dry-type air-core reactor. The training of the dry air-core reactor state assessment model based on Naive Bayes classification includes the following steps: By adopting the assumption of attribute conditional independence, Bayes' theorem is rewritten to establish a state assessment model for dry-type air-core reactors; Preprocessing of training sample data for different fault levels of dry-type air-core reactors; Import test samples of dry-type air-core reactors with different fault levels, calculate the probability of each sample at different fault levels, and normalize the probabilities. By comparing the maximum probability of different fault levels, the state level corresponding to each sample is determined, and the corresponding maintenance strategy is determined.

8. A computer device, characterized in that, include: The computer device includes a memory and a processor. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the dry air-core reactor state assessment method based on any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to perform the dry air-core reactor state assessment method based on a Naive Bayes classifier as described in any one of claims 1-6.

Images