A method and system for evaluating partial discharge in a generator stator

Abstract

The present invention discloses a method and system for evaluating partial discharge of a generator stator. The system collects three evaluation parameters, namely, daily average quantity, weekly average quantity, and monthly average quantity, as evaluation parameters for the severity of partial discharge and the number of discharge intensities for partial discharge trend analysis. The present invention realizes trend analysis and severity judgment of partial discharge of the generator stator by establishing a function model of the number of discharge intensities characterizing the partial discharge trend and a fuzzy logic evaluation process characterizing the severity of partial discharge. Please combine the two to achieve a more accurate comprehensive evaluation of the partial discharge level of the generator.

Description

Technical Field

[0001] The present invention relates to the technical field of generator stators, and specifically to a method and system for evaluating partial discharge of a generator stator. Background Art

[0002] There is a very close relationship between partial discharge and insulation deterioration and breakdown. The insulation medium of a generator endures heat, electricity, mechanical stress and environmental influences for a long time, resulting in insulation deterioration. This causes partial discharge in the insulation during the operation of the generator. It can be said that partial discharge is a sign of insulation deterioration. At the same time, partial discharge can also accelerate the deterioration of the generator insulation. If the partial discharge continues to expand and develop, it will ultimately lead to insulation damage. Therefore, accurate evaluation of partial discharge in the generator stator is of great significance for evaluating the overall insulation condition and predicting the life of the generator.

[0003] Research over the years has shown that the quantity, amplitude and polarity of partial discharge signals can directly reflect the condition of the motor insulation system. Using partial discharge phenomena to evaluate the insulation life of motors is still a cutting-edge discipline that closely combines basic theory and applied technology in development. At present, the test methods for partial discharge of generator stators at home and abroad are mainly divided into off-line test methods and on-line monitoring methods, and the evaluation criteria for the degree of partial discharge of generators are also different.

[0004] (1) Off-line detection method: The off-line detection of partial discharge testing of generator stator windings belongs to a special test of the generator and is generally carried out as a sub-part of the insulation aging identification test of the generator stator windings. The off-line test of partial discharge of generator stator windings generally adopts the method of measuring a single wire bar or measuring the whole phase. The schematic diagram of its test circuit is as Figure 1 、 Figure 2 shown, where U is the high-voltage power supply; CC is the connecting cable; C a is the test object; CD is the coupling device; Z is the filter; Z m is the input impedance of the measurement system; C k is the coupling capacitor; M is the measuring instrument. The test principle is to apply the test object to the target voltage using a partial discharge-free high-voltage power supply and read the partial discharge quantity of the test object at the target voltage.

[0005] The off-line test method for partial discharge of generator stators has the following disadvantages: (a) Based on the existing capacitance-coupled partial discharge measurement device, the test results are susceptible to electromagnetic interference, which affects the test results; (b) Due to the long test period, this test is generally only carried out on units that have been in operation for a long time or have experienced insulation breakdown multiple times during operation and preventive tests. There is a large time lag in detecting and trend judging partial discharge of generators in operation. When data exceeds the standard is found in the test, the partial discharge inside the generator has often developed to a relatively serious degree.

[0006] (2) Online monitoring methods: There are mainly the following types: neutral point coupling monitoring method, portable capacitive coupling monitoring method, stator slot coupler monitoring method, radio frequency monitoring method, etc. However, the existing online monitoring methods currently have the following disadvantages: (a) The cost is relatively high, and special online monitoring devices need to be installed; (b) It is difficult to distinguish interference signals from internal discharge signals, and the sensitivity is insufficient; (c) Most of the existing online monitoring devices collect the instantaneous values of partial discharge quantities. Since the deterioration of the generator insulation is a gradual process, that is, the partial discharge has a slow development process from normal to severe, the reference value of the instantaneous value of partial discharge is relatively small. Moreover, the instantaneous value at a certain moment may have a relatively large drift due to interference during the measurement and transmission process. Using the instantaneous value as an evaluation means for the severity of partial discharge has defects.

[0007] In summary, the existing detection methods in the industry all have defects in the evaluation of partial discharge trends: The offline method has a long detection period. Generally, this test is only carried out on units that have been in operation for a long time or have experienced insulation breakdowns multiple times during operation and preventive tests. There is a large lag in time for the detection and trend judgment of partial discharge in a running generator. When data exceeding the standard is found during the test, the partial discharge inside the generator has often developed to a relatively serious level; Most of the existing online monitoring devices collect the instantaneous values of partial discharge quantities. The instantaneous value at a certain moment may have a relatively large drift due to interference during the measurement and transmission process. The instantaneous value is not suitable for directly evaluating the severity of partial discharge.

[0008] The invention patent application with the publication number CN105182201A discloses a method for evaluating the insulation state of a generator stator bar based on low voltage and multiple parameters; this application measures the voltage across the insulation medium of the generator stator bar by setting the maximum charging voltage and charge-discharge time and applying a test voltage suitable for the characteristics of its insulation medium and insulation structure to the generator stator bar. This evaluation method can test and obtain multiple parameters of the insulation of the generator stator bar only by applying a non-destructive voltage to the insulation of the generator stator bar. However, the above problems are still not solved. Summary of the Invention

[0009] The technical problem to be solved by the present invention is: to provide a method and system for evaluating partial discharge of a generator stator to solve the problem of inaccurate evaluation of the partial discharge situation of the generator stator.

[0010] To solve the above technical problem, the present invention provides the following technical solutions:

[0011] A method for evaluating partial discharge of a generator stator includes the following steps:

[0012] S1. The system collects the average value of partial discharge amounts within a period of time as the evaluation parameter for the severity of partial discharge, and conducts a fuzzy logic evaluation on this evaluation parameter;

[0013] S2. If the fuzzy logic evaluation result in step S1 is within the normal range, it indicates that the partial discharge is normal and the evaluation ends;

[0014] S3. If the fuzzy logic evaluation result in step S1 is within the abnormal range, it indicates that the partial discharge is abnormal, and further analyze the trend of partial discharge;

[0015] S4. If the result of the partial discharge trend analysis in step S3 shows that the partial discharge is on an increasing trend over time, it indicates that the partial discharge exceeds the standard and corresponding treatment is carried out;

[0016] S5. If the result of the partial discharge trend analysis in step S3 shows that the partial discharge is not on an increasing trend over time, strengthen the monitoring of the partial discharge and conduct a comprehensive analysis.

[0017] Advantages: By combining the analysis of the partial discharge trend and the fuzzy logic evaluation process of the discharge severity, the present invention realizes the trend analysis and comprehensive judgment of the severity of the partial discharge of the generator stator, so as to more accurately comprehensively evaluate the partial discharge level of the generator.

[0018] Preferably, the evaluation parameters in step S1 are respectively set with daily average amount, weekly average amount and monthly average amount.

[0019] Preferably, the fuzzy variables for the fuzzy logic judgment include different fuzzy sets, namely fuzzy set low, fuzzy set medium and fuzzy set high;

[0020] Among them, the fuzzy set low is the normal range, and the fuzzy set medium and fuzzy set high are the abnormal ranges.

[0021] Preferably, the fuzzy logic evaluation process in step S1 includes the following steps:

[0022] S101. Set the daily average amount, weekly average amount and monthly average amount as the three evaluation parameters for the severity of partial discharge; the system collects the data of the three evaluation parameters;

[0023] S102. The system reads the daily average value and constructs a fuzzy fact, and matches it with the corresponding fuzzy variable. If the result is the fuzzy set low, it indicates that the partial discharge is normal and the evaluation ends; otherwise, execute step S103;

[0024] S103. The system reads the weekly average value, constructs a fuzzy fact and matches it with the corresponding fuzzy variable. If the result is the fuzzy set low, it indicates that the partial discharge is normal and the evaluation ends; otherwise, execute step S104;

[0025] S104. The system reads the monthly average quantity, constructs fuzzy facts and matches them with the corresponding fuzzy variables. If the result is the fuzzy set "low", step S201 is executed; otherwise, step S301 is executed.

[0026] Preferably, in S201, the trend of partial discharge is analyzed to determine whether the intensity times with the day as the time series unit is on the rise.

[0027] S202. If the intensity times with the day as the time series unit is not on the rise, it indicates that the partial discharge is normal and the evaluation ends.

[0028] S203. If the intensity times with the day as the time series unit is on the rise, the monitoring of partial discharge is strengthened for comprehensive analysis.

[0029] Preferably, in S301, the trend of partial discharge is analyzed to determine whether the intensity times with the day as the time series unit is on the rise.

[0030] S302. If the intensity times with the day as the time series unit is not on the rise, the monitoring of partial discharge is strengthened for comprehensive analysis.

[0031] S303. If the intensity times with the day as the time series unit is on the rise, it indicates that the partial discharge exceeds the standard and processing is carried out.

[0032] Preferably, the intensity times calculation function is:

[0033]

[0034] where t is time, U i and n i respectively represent the voltage and the discharge times of the average discharge signal with the time sequence of i (i = 2, 3, 4,..., t).

[0035] The present invention also provides a generator stator partial discharge evaluation system, including:

[0036] An acquisition module for acquiring the average value of the partial discharge quantity within a period of time as an evaluation parameter for the severity of partial discharge;

[0037] A fuzzy logic evaluation module for performing fuzzy logic evaluation on the evaluation parameter acquired by the acquisition module:

[0038] If the fuzzy logic evaluation result is within the normal range, it indicates that the partial discharge is normal and the evaluation ends;

[0039] If the fuzzy logic evaluation result is within the abnormal range, it indicates that the partial discharge is abnormal and the trend of partial discharge is further analyzed.

[0040] The partial discharge trend analysis module is used to analyze the partial discharge trend:

[0041] If the result of the partial discharge trend analysis shows that the partial discharge is on an increasing trend over time, it indicates that the partial discharge exceeds the standard and corresponding treatment is carried out;

[0042] If the result of the partial discharge trend analysis shows that the partial discharge is not on an increasing trend over time, the monitoring of the partial discharge is strengthened and comprehensive analysis is carried out.

[0043] Preferably, the evaluation parameters collected by the acquisition module are the daily average quantity, the weekly average quantity, and the monthly average quantity respectively.

[0044] Preferably, the fuzzy logic evaluation module has built-in fuzzy variables, including different fuzzy sets, namely the fuzzy set low, the fuzzy set medium, and the fuzzy set high;

[0045] Among them, the fuzzy set low is the normal range, and the fuzzy set medium and the fuzzy set high are the abnormal ranges

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] (1) By establishing a discharge intensity times function model representing the partial discharge trend and a fuzzy logic evaluation process representing the severity of the partial discharge in the present invention, the two are combined to realize trend analysis and severity judgment of the partial discharge of the generator stator, so as to more accurately comprehensively evaluate the partial discharge level of the generator.

[0048] (2) By setting the daily average quantity, the weekly average quantity, and the monthly average quantity as the three evaluation parameters of the partial discharge severity to replace the instantaneous value of the partial discharge quantity, the risk of large drift of the instantaneous value due to interference in the measurement and transmission process is avoided; at the same time, through the progressive detection of the three parameters, the severity of the partial discharge of the generator can be detected in time, and corresponding treatment can be carried out according to the severity of the partial discharge.

[0049] (3) Using the discharge intensity times of the partial discharge to replace the average discharge quantity and the discharge times, the change trend of the partial discharge can be more clearly reflected. Description of the Drawings

[0050] Figure 1 It is a schematic diagram of the partial discharge test circuit of a single wire bar in the off-line detection method of the prior art;

[0051] Figure 2 It is a schematic diagram of the partial discharge test circuit of the whole-phase winding in the off-line detection method of the prior art;

[0052] Figure 3Flow chart for comprehensive evaluation of embodiments of the present invention;

[0053] Figure 4 Graph of the average discharge signal voltage trend for embodiments of the present invention;

[0054] Figure 5 Graph of the discharge times trend for embodiments of the present invention;

[0055] Figure 6 Graph of the discharge intensity times trend for embodiments of the present invention;

[0056] Figure 7 Graph for comparing the discharge times and intensity times for embodiments of the present invention;

[0057] Figure 8 Flow chart for evaluating the severity of partial discharge for embodiments of the present invention. Detailed implementation manners

[0058] To facilitate those skilled in the art to understand the technical solution of the present invention, the technical solution of the present invention will be further described below in conjunction with the accompanying drawings of the specification.

[0059] The terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, "a plurality" means two or more, unless otherwise specifically defined.

[0060] Refer to Figure 3 , this embodiment discloses a method for evaluating partial discharge of a generator stator, including the following steps:

[0061] S1. The system collects the average value of the partial discharge amount within a period of time as an evaluation parameter for the severity of partial discharge, and performs fuzzy logic evaluation on this evaluation parameter;

[0062] S2. If the fuzzy logic evaluation result in step S1 is within the normal range, it indicates that the partial discharge is normal and the evaluation ends;

[0063] S3. If the fuzzy logic evaluation result in step S1 is within the abnormal range, it indicates that the partial discharge is abnormal, and further analyze the partial discharge trend;

[0064] S4. If the partial discharge trend analysis result in step S3 shows that the partial discharge is on an increasing trend over time, it indicates that the partial discharge exceeds the standard and processing is performed;

[0065] S5. If the partial discharge trend analysis result in step S3 shows that the partial discharge is not on the rise over time, strengthen the monitoring of the partial discharge and conduct a comprehensive analysis.

[0066] The evaluation parameters in step S1 are respectively set with daily average, weekly average and monthly average.

[0067] The fuzzy variables for the fuzzy logic judgment include different fuzzy sets, namely fuzzy set low, fuzzy set medium and fuzzy set high;

[0068] Among them, the fuzzy set low is the normal range, and the fuzzy set medium and fuzzy set high are the abnormal ranges.

[0069] The fuzzy logic evaluation process of step S1 includes the following steps:

[0070] S101. Set the daily average, weekly average and monthly average as the three evaluation parameters for the severity of partial discharge; the system collects the data of the three evaluation parameters;

[0071] S102. The system reads the daily average value and constructs a fuzzy fact, and matches it with the corresponding fuzzy variable. If the result is the fuzzy set low, it indicates that the partial discharge is normal and the evaluation ends; otherwise, execute step S103;

[0072] S103. The system reads the weekly average value, constructs a fuzzy fact and matches it with the corresponding fuzzy variable. If the result is the fuzzy set low, it indicates that the partial discharge is normal and the evaluation ends; otherwise, execute step S104;

[0073] S104. The system reads the monthly average value, constructs a fuzzy fact and matches it with the corresponding fuzzy variable.

[0074] If the matching result of step S104 is the fuzzy set low, the following operations are performed:

[0075] S201. Analyze the partial discharge trend and judge whether the intensity times with the day as the time series unit is on the rise;

[0076] S202. If the intensity times with the day as the time series unit is not on the rise, it indicates that the partial discharge is normal and the evaluation ends;

[0077] S203. If the intensity times with the day as the time series unit is on the rise, strengthen the monitoring of the partial discharge and conduct a comprehensive analysis.

[0078] If the matching result of step S104 is not the fuzzy set low, the following operations are performed:

[0079] S301. Analyze the partial discharge trend to determine whether the intensity times with the day as the time series unit is on an upward trend;

[0080] S302. If the intensity times with the day as the time series unit is not on an upward trend, strengthen the monitoring of partial discharge and conduct comprehensive analysis;

[0081] S303. If the intensity times with the day as the time series unit is on an upward trend, it indicates that the partial discharge exceeds the standard, and handle it.

[0082] The intensity times calculation function is:

[0083]

[0084] where t is time, U i and n i respectively represent the voltage and the number of discharges of the average discharge signal with the time sequence of i (i = 2, 3, 4,..., t).

[0085] In the specific implementation of this embodiment, it includes the following process:

[0086] (1) Trend analysis of partial discharge data

[0087] The main parameters of the existing partial discharge evaluation system are the average discharge amount and the number of discharges. These two parameters are used as indicators to characterize partial discharge respectively: when the average discharge amount decreases and the number of discharges decreases at the same time, it can be regarded as a trend of attenuation of partial discharge; when the average discharge amount increases and the number of discharges increases at the same time, it can be regarded as a trend of increase of partial discharge. However, in engineering practice, there are often various situations, such as the average discharge amount decreases, but the number of discharges increases, or the average discharge amount increases, but the number of discharges decreases; it is very difficult to analyze the partial discharge trend with the existing evaluation system in the above situations.

[0088] In order to clearly analyze and observe the change trend of the partial discharge amount, this paper defines a new characteristic parameter intensity times Q I (t) by referring to the characteristic function PVT function that characterizes the development trend in financial time series analysis. For the partial discharge data with the time ordinal number of t, its intensity times Q I (t) is:

[0089]

[0090] where U i and n i respectively represent the voltage and the number of discharges of the average discharge signal with the time sequence of i (i = 2, 3, 4,..., t). Let ΔU t = U t - U t-1 , then the change value ΔQ of the discharge intensity timest =(ΔU t / U t-1 )n t 。

[0091] The discharge intensity times refers to the PVT function in financial transactions. Through the parameters of discharge quantity voltage (corresponding to trading price) and discharge times (corresponding to trading volume), the change trend of partial discharge is comprehensively characterized by the accumulation of the product of the change rate and the discharge times.

[0092] It can be obtained from the above formula that:

[0093] (1) The change direction of the discharge intensity times is the same as that of the average discharge intensity, that is, when the average discharge intensity increases, the discharge intensity times also increases; when the average discharge intensity decreases, the discharge intensity times will also decrease accordingly.

[0094] (2) The change amplitude of the discharge intensity is proportional to the change amplitudes of the discharge times and the average discharge quantity.

[0095] Taking a generator as a specific example for comparison and explanation:

[0096] The data of the average discharge signal voltage and the average discharge times of the generator within a period of time are as Figure 4 and Figure 5 shown.

[0097] From Figure 4 it can be seen that the average discharge quantity signal voltage is generally low, fluctuating around 5 mV; from Figure 5 it can be seen that the discharge times as a whole show an upward trend, and this trend is more obvious after 20 weeks. Figure 4 Although it can reflect the overall level of partial discharge, in terms of the development trend of partial discharge, it fails to provide valuable information; Figure 5 Although the overall provides certain trend information, due to the large fluctuation amplitude of the data curve, this trend has certain limitations.

[0098] Figure 6 and Figure 7 are the trend chart of the discharge intensity times and the comparison chart of the intensity times and the discharge times respectively. It can be seen that compared with the average discharge quantity voltage and the discharge times, the data curve of the discharge intensity times has a smaller fluctuation amplitude. Therefore, the discharge intensity times can more clearly reflect the change trend of partial discharge.

[0099] (2) Fuzzy evaluation of partial discharge data

[0100] The deterioration of generator insulation is a gradual process, that is, there is a slow development process of partial discharge from normal to severe. In this sense, the instantaneous value of partial discharge has little reference value and is not suitable for direct use in severity assessment. The severity assessment should be based on statistical data over a period of time. In this example, the hourly average, daily average, and weekly average of partial discharge can be defined respectively.

[0101] When performing fuzzy inference, there are three statistical data, namely the hourly average, daily average, and weekly average, for the aforementioned partial discharge characteristic parameters. When performing fuzzification, each fuzzy variable contains three different fuzzy sets, namely low, medium, and high. After the system reads the corresponding partial discharge characteristic information from the database, it constructs corresponding fuzzy facts for inference to obtain relevant conclusions. During the inference process, according to the relationships between various parameters, a certain number of fuzzy rules need to be constructed. For example, if the average discharge amount is high and the discharge frequency is high, then the discharge is severe.

[0102] The basic process of evaluating partial discharge from its characteristic quantities is as Figure 8 shown. First, construct a fuzzy fact from the hourly average and match it with the fuzzy variable. If the resulting fuzzy set is low, it is considered that the discharge is normal; otherwise, read the daily average and perform similar inference. If the result is considered that the discharge is normal, the process ends; otherwise, continue to judge the weekly average.

[0103] (3) Comprehensive assessment of partial discharge severity

[0104] Combining the above two evaluation methods and using three parameters, namely the daily average, weekly average, and monthly average, for fuzzy evaluation, the comprehensive evaluation method process of this embodiment as shown in Figure 3 can be obtained:

[0105] Construct a fuzzy fact from the daily average and match it with the fuzzy variable. If the resulting fuzzy set is low, it is considered that the discharge is normal; otherwise, read the weekly average and perform similar inference. If the result is considered that the discharge is normal, the process ends; otherwise, continue to judge the monthly average.

[0106] When evaluating the monthly average, the discharge intensity times Q I (t) is introduced for comprehensive judgment:

[0107] When the monthly partial discharge amount belongs to the low fuzzy set state, if the intensity times intensity with the day as the time unit sequence unit is not in an upward trend, it is considered that the partial discharge is normal; if the intensity times intensity with the day as the time unit sequence unit is in an upward trend, the monitoring of partial discharge should be strengthened.

[0108] When the monthly partial discharge amount does not belong to the low state of the fuzzy set, if the intensity times intensity of the time unit sequence with days as the time unit is on the rise, it is considered that the partial discharge exceeds the standard and corresponding measures are taken. If the intensity times intensity of the time unit sequence with days as the time unit is not on the rise, the monitoring of partial discharge should be strengthened and comprehensive analysis should be carried out.

[0109] In summary, in this embodiment, through the establishment of the discharge intensity times function model representing the trend of partial discharge and the fuzzy logic evaluation process representing the severity of partial discharge. The two are combined to realize the trend analysis and severity judgment of the partial discharge of the generator stator, so as to more accurately comprehensively evaluate the partial discharge level of the generator.

[0110] By setting the daily average amount, weekly average amount and monthly average amount as the three evaluation parameters of the partial discharge severity to replace the instantaneous value of the partial discharge amount, the risk of large drift of the instantaneous value due to interference in the measurement and transmission process is avoided; at the same time, through the progressive detection of the three parameters, the severity of the partial discharge of the generator can be detected in time, and corresponding measures can be taken according to the severity of the partial discharge.

[0111] At the same time, the discharge intensity times of partial discharge is used to replace the average discharge amount and discharge times, so as to more clearly reflect the change trend of partial discharge.

[0112] This embodiment also discloses a partial discharge evaluation system for the generator stator, including:

[0113] A collection module for collecting the average value of the partial discharge amount within a period of time as an evaluation parameter of the partial discharge severity;

[0114] A fuzzy logic evaluation module for performing fuzzy logic evaluation on the evaluation parameters collected by the collection module:

[0115] If the fuzzy logic evaluation result is within the normal range, it indicates that the partial discharge is normal and the evaluation ends;

[0116] If the fuzzy logic evaluation result is within the abnormal range, it indicates that the partial discharge is abnormal and further analysis of the partial discharge trend is carried out;

[0117] A partial discharge trend analysis module for analyzing the partial discharge trend:

[0118] If the partial discharge trend analysis result shows that the partial discharge is on the rise over time, it indicates that the partial discharge exceeds the standard and corresponding measures are taken;

[0119] If the partial discharge trend analysis result shows that the partial discharge is not on the rise over time, the monitoring of partial discharge is strengthened and comprehensive analysis is carried out.

[0120] The evaluation parameters collected by the collection module are the daily average, weekly average, and monthly average respectively.

[0121] The fuzzy logic evaluation module has built-in fuzzy variables, including different fuzzy sets, namely the fuzzy set low, the fuzzy set medium, and the fuzzy set high;

[0122] Among them, the fuzzy set low is the normal range, and the fuzzy set medium and the fuzzy set high are the abnormal ranges.

[0123] The fuzzy logic evaluation module includes the following modules:

[0124] A data reading module, which is used to collect the daily average, weekly average, and monthly average of the three evaluation parameters used as the severity of partial discharge by the collection module;

[0125] A first judgment module, which is used to judge the daily average value. By constructing a fuzzy fact and matching it with the corresponding fuzzy variable, if the result is the fuzzy set low, it indicates that the partial discharge is normal and the evaluation ends; otherwise, the second judgment module is started;

[0126] A second judgment module, which is used to judge the weekly average value, construct a fuzzy fact and match it with the corresponding fuzzy variable. If the result is the fuzzy set low, it indicates that the partial discharge is normal and the evaluation ends; otherwise, the third judgment module is started;

[0127] A third judgment module, which is used to judge the monthly average value, construct a fuzzy fact and match it with the corresponding fuzzy variable. If the result is the fuzzy set low, the first analysis module of the partial discharge trend analysis module is started; otherwise, the second analysis module of the partial discharge trend analysis module is started.

[0128] The first analysis module is used to analyze the partial discharge trend and judge whether the intensity times in the time series unit of days is on the rise;

[0129] If the intensity times in the time series unit of days is not on the rise, it indicates that the partial discharge is normal and the evaluation ends;

[0130] If the intensity times in the time series unit of days is on the rise, the monitoring of the partial discharge is strengthened for comprehensive analysis.

[0131] The second analysis module is used to analyze the partial discharge trend and judge whether the intensity times in the time series unit of days is on the rise;

[0132] If the intensity times in the time series unit of days is not on the rise, the monitoring of the partial discharge is strengthened for comprehensive analysis;

[0133] If the intensity frequency with the day as the time series unit is on the rise, it indicates that the partial discharge exceeds the standard and needs to be processed.

[0134] The intensity frequency calculation functions adopted by the first analysis module and the second analysis module are as follows:

[0135]

[0136] where t is the time, U i and n i respectively represent the voltage and the discharge frequency of the average discharge signal at the time sequence of i (i = 2, 3, 4,..., t).

[0137] It should be noted that a generator stator partial discharge evaluation system based on a multi-parameter time series function disclosed in this embodiment corresponds to a generator stator partial discharge evaluation method disclosed in the above embodiment, and has corresponding technical features and technical effects, which will not be elaborated here.

[0138] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention, and any reference signs in the claims should not be regarded as limiting the claims involved.

[0139] The above embodiments only represent the implementation manners of the invention. The protection scope of the present invention is not limited to the above embodiments. For those skilled in the art, without departing from the concept of the present invention, several deformations and improvements can be made, and these all belong to the protection scope of the present invention.

Claims

1. A method for evaluating partial discharge in a generator stator, characterized in that: It includes: S1. The system collects the average value of the partial discharge amount within a period of time as an evaluation parameter for the severity of partial discharge, and performs fuzzy logic evaluation on this evaluation parameter; S2. If the fuzzy logic evaluation result in step S1 is within the normal range, it indicates that the partial discharge is normal and the evaluation ends; S3. If the fuzzy logic evaluation result in step S1 is within the abnormal range, it indicates that the partial discharge is abnormal, and further analyze the partial discharge trend; S4. If the result of the partial discharge trend analysis in step S3 shows that the partial discharge is on an increasing trend over time, it indicates that the partial discharge exceeds the standard and processing is carried out; S5. If the result of the partial discharge trend analysis in step S3 shows that the partial discharge is not on an increasing trend over time, strengthen the monitoring of the partial discharge and conduct comprehensive analysis; The fuzzy variables for fuzzy logic judgment include different fuzzy sets, namely fuzzy set low, fuzzy set medium, and fuzzy set high; Fuzzy set low is the normal range, and fuzzy set medium and fuzzy set high are the abnormal ranges; The fuzzy logic evaluation process of step S1 includes the following steps: S101. Set the daily average, weekly average, and monthly average as the three evaluation parameters for the severity of partial discharge; The system collects data of the three evaluation parameters; S102. The system reads the daily average value and constructs a fuzzy fact, and matches it with the corresponding fuzzy variable. If the result is fuzzy set low, it indicates that the partial discharge is normal and the evaluation ends; Otherwise, execute step S103; S103. The system reads the weekly average value, constructs a fuzzy fact and matches it with the corresponding fuzzy variable. If the result is fuzzy set low, it indicates that the partial discharge is normal and the evaluation ends; Otherwise, execute step S104; S104. The system reads the monthly average value, constructs a fuzzy fact and matches it with the corresponding fuzzy variable. If the result is fuzzy set low, execute step S201; Otherwise, execute step S301.

2. The method for evaluating partial discharge in a generator stator according to claim 1, characterized in that: The evaluation parameters in step S1 are respectively set with the daily average, weekly average, and monthly average.

3. The method for evaluating partial discharge in a generator stator according to claim 1, characterized in that: S201. Analyze the partial discharge trend and judge whether the intensity times with days as the time series unit is on an increasing trend; S202. If the intensity times with days as the time series unit is not on an increasing trend, it indicates that the partial discharge is normal and the evaluation ends; S203. If the intensity times with days as the time series unit is on an increasing trend, strengthen the monitoring of the partial discharge and conduct comprehensive analysis.

4. The method for evaluating partial discharge in a generator stator according to claim 1, characterized in that: S301. Analyze the partial discharge trend and judge whether the intensity times with days as the time series unit is on an increasing trend; S302. If the intensity times with days as the time series unit is not on an increasing trend, strengthen the monitoring of the partial discharge and conduct comprehensive analysis; S303. If the intensity times with a day as the time series unit is on an upward trend, it indicates that the partial discharge exceeds the standard, and corresponding treatment shall be carried out.

5. The method for evaluating partial discharge of a generator stator according to claim 3 or 4, characterized in that: the intensity times calculation function is: where t is time, U i and n i represent the voltage and the number of discharges of the average discharge signal at the time sequence i (i = 2, 3, 4,..., t), respectively.

6. A system for evaluating partial discharge of a generator stator, characterized in that: it includes: a collection module, configured to collect the average value of the partial discharge amount within a period of time as an evaluation parameter for the severity of the partial discharge; a fuzzy logic evaluation module, configured to perform fuzzy logic evaluation on the evaluation parameter collected by the collection module: if the fuzzy logic evaluation result is within the normal range, it indicates that the partial discharge is normal, and the evaluation ends; if the fuzzy logic evaluation result is within the abnormal range, it indicates that the partial discharge is abnormal, and further analyze the partial discharge trend; a partial discharge trend analysis module, configured to analyze the partial discharge trend: if the partial discharge trend analysis result shows that the partial discharge is on an upward trend over time, it indicates that the partial discharge exceeds the standard, and corresponding treatment shall be carried out; if the partial discharge trend analysis result shows that the partial discharge is not on an upward trend over time, strengthen the monitoring of the partial discharge and conduct comprehensive analysis; the fuzzy logic evaluation module internally sets fuzzy variables, including different fuzzy sets, namely fuzzy set low, fuzzy set medium, and fuzzy set high; wherein, the fuzzy set low is the normal range, and the fuzzy set medium and fuzzy set high are the abnormal ranges; the fuzzy logic evaluation process of the fuzzy logic evaluation module includes the following steps: S101. Set the daily average amount, weekly average amount, and monthly average amount as three evaluation parameters for the severity of the partial discharge; the system collects data of the three evaluation parameters; S102. The system reads the daily average value and constructs a fuzzy fact, and matches it with the corresponding fuzzy variable. If the result is the fuzzy set low, it indicates that the partial discharge is normal, and the evaluation ends; otherwise, execute step S103; S103. The system reads the weekly average value, constructs a fuzzy fact and matches it with the corresponding fuzzy variable. If the result is the fuzzy set low, it indicates that the partial discharge is normal, and the evaluation ends; otherwise, execute step S104; S104. The system reads the monthly average amount, constructs a fuzzy fact and matches it with the corresponding fuzzy variable. If the result is the fuzzy set low, execute step S201; otherwise, execute step S301.

7. The system for evaluating partial discharge of a generator stator according to claim 6, characterized in that: the evaluation parameters collected by the collection module are respectively the daily average amount, the weekly average amount, and the monthly average amount.

Images