CN114528875A

CN114528875A - Generator stator slot wedge tightness detection method, device and storage medium

Info

Publication number: CN114528875A
Application number: CN202210098438.2A
Authority: CN
Inventors: 周聪; 谢小平; 李雪伟; 陈伟东
Original assignee: Southwest University of Science and Technology
Current assignee: Southwest University of Science and Technology
Priority date: 2022-01-21
Filing date: 2022-01-21
Publication date: 2022-05-24

Abstract

The application belongs to the technical field of generators, and particularly relates to a method, equipment and a storage medium for detecting the tightness of a slot wedge of a generator stator, wherein the method comprises the following steps: s10, acquiring original sound wave data acquired by a sound sensor after the slot wedge to be detected is knocked; s20, preprocessing the original sound wave data to obtain knocking sound wave data; s30, performing target feature extraction on the knocking sound wave data to obtain a sound wave feature value; wherein the target features comprise a frequency band amplitude area, a spectrum centroid, a form factor, a third peak frequency, and a fifth peak frequency; and S40, inputting the sound wave characteristic value into a trained classifier to perform knocking sound wave characteristic classification, and obtaining a detection result of the tightness of the generator stator slot wedge. The method provided by the application can be used for carrying out nondestructive detection on the tightness of the generator stator slot wedge, so that the detection efficiency and accuracy are improved, and the detection cost is reduced.

Description

Generator stator slot wedge tightness detection method, device and storage medium

Technical Field

The application belongs to the technical field of generators, and particularly relates to a method, equipment and storage medium for detecting the tightness of a generator stator slot wedge.

Background

The generator is an important component of a power system and mainly comprises a stator, a rotor and other parts, wherein a stator slot wedge is a structure used for fixing a stator bar in a stator slot. In the running process of the generator, the electrified stator bar can be acted by radial electromagnetic force under the environment of a transverse magnetic field in the stator slot, so that vibration is generated. The long-term vibration of the stator bar can cause the slot wedge plate to loosen. The slot wedge plate is not flexible, and the stator bar vibrates under the effect of alternating electromagnetic force, along with the long-term operation of generator, can cause the insulating layer damage, makes the electroerosion phenomenon more violent, leads to puncturing stator bar owner insulating layer, takes place to shut down even to cause great potential safety hazard.

There are cases that show that many medium and high voltage motors suffer from magnetic wedge failure. Within 3 years of use, as much as half of the wedges are lost, so that the magnetic wedges need to be checked regularly, and the tightness detection and re-tightening of the stator slot wedges become important links for maintenance of the generator. The existing detection method comprises a manual knocking mode and a measuring hole measuring mode, but in a generator set, the number of the stator slot wedges can reach tens of thousands of blocks, the existing detection mode has great dependence on experience of operators, the judgment accuracy and the detection efficiency are not high, and meanwhile, secondary damage can be caused to the slot wedges in the detection process, so that the detection requirement cannot be effectively met.

Disclosure of Invention

Technical problem to be solved

In view of the above-mentioned shortcomings and drawbacks of the prior art, the present application provides a generator stator slot wedge tightness detection method, apparatus, and readable storage medium.

(II) technical scheme

In order to achieve the purpose, the technical scheme is as follows:

in a first aspect, an embodiment of the present application provides a method for detecting tightness of generator stator slot wedges, where the method includes:

s10, acquiring original sound wave data acquired by a sound sensor after the slot wedge to be detected is knocked;

s20, preprocessing the original sound wave data to obtain knocking sound wave data;

s30, performing target feature extraction on the knocking sound wave data to obtain a sound wave feature value; wherein the target features comprise a frequency band amplitude area, a spectrum centroid, a form factor, a third peak frequency, and a fifth peak frequency;

and S40, inputting the sound wave characteristic value into a trained classifier to perform knocking sound wave characteristic classification, and obtaining a detection result of the tightness of the generator stator slot wedge.

Optionally, S20 includes:

intercepting effective knocking sound fragments of the original sound wave data by using a double-threshold endpoint detection method to obtain knocking sound wave data;

and denoising the knocking sound wave data by adopting second-generation wavelet transform to obtain processed knocking sound wave data.

Optionally, the classifier is a support vector machine classifier, before S10, the method further includes training the support vector machine classifier, and the training step includes:

s01, classifying according to the preset tightness state of the stator slot wedges, and respectively detecting the stress of the stator slot wedges in each classified state;

s02, applying the stress of the stator slot wedge in each classification state to the corrugated plate, and performing a corrugated plate compression test to obtain the deformation amount of the corresponding corrugated plate;

s03, establishing a stator slot wedge model in each classification state based on the deformation quantity of the corrugated plate, establishing a stator slot wedge tightness test platform for a knocking test, and knocking the stator slot wedge model by using an excitation device to obtain a vibration sound signal in each classification state;

s04, preprocessing the vibration sound signal and extracting the characteristics of the vibration sound signal to obtain a vibration signal characteristic value;

and S05, training a support vector machine model by taking the vibration signal characteristic value as sample data to obtain the trained support vector machine classifier.

Optionally, the stator slot wedge tightness state classification comprises tight, slightly tight and loose; when the state is tight, the stator bar does not jump under the short-circuit condition and the non-short-circuit condition; when the state is slightly tight, the stator bar does not jump only under the condition of non-short circuit; when the state is loose, the generator is prohibited from running.

Optionally, S01 includes:

calculating the maximum value F1 of the electromagnetic force of the stator bar in normal operation when the out-of-phase current is introduced and the maximum value F2 of the electromagnetic force in short circuit;

the electromagnetic force smaller than F1 is applied to the stator slot wedge when the state is loose, the electromagnetic force equal to or larger than F2 is applied to the stator slot wedge when the state is tight, and the electromagnetic force between F1 and F2 is applied to the stator slot wedge when the state is slightly tight.

Optionally, S02 includes:

a universal material testing machine is adopted to obtain a stress-strain characteristic curve of the corrugated plate, and the relation between the load and the deformation of the corrugated plate under the pressure loading condition is obtained;

after a pressure loading test is carried out by a testing machine, drawing a compression curve of a tested corrugated plate sample;

and eliminating the deformation of the system to obtain an actual compression curve of the corrugated plate, and calculating S01 to obtain the average deformation of the corrugated plate in each classification state.

Optionally, the extracting of the vibration sound signal feature from the vibration sound signal in S04 includes:

extracting time domain characteristic parameters from the vibration sound signal to represent the tightness state of the slot wedge, wherein the time domain characteristic parameters comprise a root mean square value, a variance, a form factor, a peak factor, a kurtosis and a zero crossing rate;

extracting frequency domain characteristic parameters from the vibration sound signal to represent the tightness state of the slot wedge, wherein the frequency domain characteristic parameters comprise peak values of three frequency bands, corresponding peak frequency, a spectrum centroid of a longitudinal axis and amplitude areas of five different frequency intervals;

and carrying out characteristic screening based on an F-ratio and Pearson correlation coefficient method to obtain vibration sound signal characteristics, wherein the vibration sound signal characteristics comprise a frequency band amplitude area, a frequency spectrum centroid, a form factor, a third peak frequency and a fifth peak frequency.

Optionally, S05 includes:

taking the vibration signal characteristic value as sample data, and dividing the sample data into a training set and a test set;

carrying out normalization processing on the characteristic parameter matrixes of the training set and the test set;

dividing a training set sample into 3 groups, and optimizing the parameters of the support vector machine model by using a cross verification method;

classifying the test set by adopting a trained support vector machine model so as to verify the accuracy of the trained model;

and taking the verified support vector machine model as a trained support vector machine classifier.

In a second aspect, an embodiment of the present application provides a stator slot wedge tightness detection apparatus, including: memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the generator stator slot wedge tightness detection method according to any of the above first aspects.

In a third aspect, the present application provides a computer readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the generator stator slot wedge tightness detection method as described in any one of the above first aspect.

(III) advantageous effects

The beneficial effect of this application is: the application provides a method, equipment and a readable storage medium for detecting the tightness of a generator stator slot wedge, wherein the method comprises the following steps: s10, acquiring original sound wave data acquired by a sound sensor after the slot wedge to be detected is knocked; s20, preprocessing the original sound wave data to obtain knocking sound wave data; s30, performing target feature extraction on the knocking sound wave data to obtain a sound wave feature value; the target characteristics comprise a frequency band amplitude area, a frequency spectrum centroid, a wave form factor, a third peak frequency and a fifth peak frequency; and S40, inputting the sound wave characteristic value into a trained classifier to perform knocking sound wave characteristic classification, and obtaining a detection result of the generator stator slot wedge tightness. The method that this application provided establishes the mechanics classification standard about generator stator slot wedge elasticity, and then calculates buckled plate deformation volume classification standard to this training obtains the classification model, and the classification standard in this application is applicable to different generating set, consequently the method of this application also can be extensive be applicable to different generating set. The method extracts the slot wedge sound signals in different states, determines five pieces of characteristic parameter information through preprocessing and screening, has few characteristics and small calculated amount, and can improve the detection efficiency; the method can be used for carrying out nondestructive testing on the tightness of the slot wedge of the generator stator, so that the accuracy is improved, and the testing cost is reduced.

Drawings

The application is described with the aid of the following figures:

FIG. 1 is a schematic flow chart of a method for detecting tightness of slot wedges of a generator stator according to an embodiment of the present disclosure;

FIG. 2 is a diagram illustrating the support vector machine classifier training steps in one embodiment of the present application;

FIG. 3 is a schematic flow chart of a method for detecting tightness of slot wedges of a generator stator according to another embodiment of the present disclosure;

FIG. 4 is a schematic view of a corrugated plate fastened stator slot wedge model in another embodiment of the present application;

FIG. 5 is a graph of the actual compression of a corrugated sheet in another embodiment of the present application;

FIG. 6 is a schematic structural diagram of a stator slot wedge tightness simulation test platform according to another embodiment of the present disclosure;

FIG. 7 is a diagram illustrating the result of pattern recognition in another embodiment of the present application;

fig. 8 is a schematic diagram of an architecture of a stator slot wedge tightness detection apparatus according to another embodiment of the present application.

Description of reference numerals:

the device comprises a stator slot wedge model 1, a push-pull type electromagnetic knocking device 2, a sound sensor 3, a portable dynamic acquisition system 4 and a display 5.

Detailed Description

For the purpose of better explaining the present invention and to facilitate understanding, the present invention will be described in detail by way of specific embodiments with reference to the accompanying drawings. It is to be understood that the following specific examples are illustrative of the invention and are not to be construed as limiting the invention. In addition, it should be noted that, in the case of no conflict, the embodiments and features in the embodiments in the present application may be combined with each other; for convenience of description, only portions related to the invention are shown in the drawings.

Example one

Fig. 1 is a schematic flow chart of a method for detecting tightness of a generator stator slot wedge in an embodiment of the present application, and as shown in fig. 1, the method for detecting tightness of a generator stator slot wedge in the embodiment includes:

s30, performing target feature extraction on the knocked sound wave data to obtain a sound wave feature value; the target characteristics comprise a frequency band amplitude area, a frequency spectrum centroid, a wave form factor, a third peak frequency and a fifth peak frequency;

and S40, inputting the sound wave characteristic value into a trained classifier to perform knocking sound wave characteristic classification, and obtaining a detection result of the generator stator slot wedge tightness.

The embodiment provides a generator stator slot wedge tightness detection method based on acoustics, nondestructive detection is carried out on the generator stator slot wedge tightness, the detection efficiency and the accuracy are improved, the detection cost is reduced, and accurate identification of the stator slot wedge tightness is achieved.

In order to better understand the present invention, the steps in the present embodiment are explained below.

In this embodiment, S20 includes:

And the effective tapping sound segment is intercepted by using a double-threshold endpoint detection method, so that the later data calculation amount can be reduced.

In this embodiment, the classifier is a support vector machine classifier, the training of the support vector machine classifier is further performed before S10, fig. 2 is a schematic diagram of a training step of the support vector machine classifier in an embodiment of the present application, and as shown in fig. 2, the training step includes:

s01, classifying according to the preset tightness state of the stator slot wedges, and respectively detecting and obtaining the stress of the stator slot wedges in each classification state;

and S05, training the support vector machine model by taking the vibration signal characteristic value as sample data to obtain the trained support vector machine classifier.

The following is a description of the training procedure of the support vector machine classifier in this embodiment.

In this embodiment S01, the stator slot wedges are classified into tight, slightly tight and loose states; when the state is tight, the stator bar does not jump under the conditions of short circuit and non-short circuit; when the state is slightly tight, the stator bar does not jump under the non-short-circuit condition; when the state is loose, the generator is prohibited from running.

The method establishes three states of the stator slot wedge tightness, can help operators to know the state of the slot wedge more clearly, wherein the slot wedge in a slightly tight state can also be used as a key screening object in the next detection work, and provides early warning reference information for the next maintenance work.

This embodiment S01 may include:

starting a generator, and introducing out-of-phase current to the upper and lower layers of stator bars;

the electromagnetic force smaller than F1 is applied to the stator wedge when the state is loose, the electromagnetic force equal to or larger than F2 is applied to the stator wedge when the state is tight, and the electromagnetic force between F1 and F2 is applied to the stator wedge when the state is slightly tight.

In this embodiment, S02 includes:

In this embodiment, the method of preprocessing the vibration sound signal may be the same as the method of S20.

It should be noted that, in a test environment, the test time is generally longer than the time of the exciting device in the process of knocking the slot wedge, so that a double-threshold end point detection method is selected to intercept effective vibration sound segments, and the later data calculation amount is reduced. When the actual application of generator maintenance scene, the on-the-spot environment is noisy, and the knock sound signal who obtains contains more environmental noise, needs to carry out noise reduction processing. The second generation wavelet transform can be adopted for denoising treatment, so that the influence of noise interference is reduced. And the knocking sound signals acquired by the laboratory simulation test do not need to be subjected to noise reduction processing.

In this embodiment, the extracting of the feature of the vibration sound signal from the vibration sound signal in S04 includes:

In this embodiment, S05 includes:

The method of the embodiment classifies the test set by adopting the SVM for cross validation and optimization parameter optimization, and shows good effect by accurately identifying the tightness of three different slot wedges through testing, thereby providing an efficient and accurate detection mode for complex and difficult slot wedge detection.

Example two

The stator slot wedge tightness model is manufactured by adopting slot wedge plates, corrugated plates and gasket samples provided by the Yangtze electric power company Limited in China, and the model is trained and detected, wherein the method comprises the following steps:

step 1: and establishing a mechanical classification standard of the tightness state of the stator slot wedge.

During the operation of the generator, the current passing through the bars inside the stator slot wedge can be in phase or out of phase. The two conditions are analyzed and calculated, the electromagnetic force borne by the coil bar when the generator works normally and is in short circuit is determined, and then the mechanical classification standard of the tightness state is established.

Step 2: and converting the mechanical classification standard into a corrugated plate deformation standard.

On the basis of a known mechanical state, a corrugated plate sample is subjected to a compression experiment to obtain deformation quantities under different acting force states. The mechanical classification standard is converted into a corrugated plate deformation standard, and later-stage manual simulation of the stator slot wedge model corresponding to the three states is facilitated.

And step 3: and (5) acquiring experimental data.

And (3) building an experimental platform, knocking the slot wedge plate nodes by an electromagnetic excitation device, and collecting the slot wedge plate vibration sound signals in different states.

And 4, step 4: pre-processing of the vibration sound signal.

In order to improve the identification precision and reduce noise interference and calculation amount, pretreatment such as effective fragment interception, noise reduction and the like needs to be carried out on the knock sound signal obtained by the test.

And 5: and (5) extracting and screening features.

And extracting related characteristic parameters from the original signal to represent the elastic state information of the signal implication, and then screening out the characteristic parameters most related to the evaluation indexes, thereby reducing the number of the characteristic parameters. The calculation amount is reduced while the identification accuracy is ensured.

Step 6: and identifying the stator slot wedge tightness mode.

After feature extraction and screening are completed, a Support Vector Machine (SVM) is used for carrying out tightness state classification on the sample test set, and vibration sound signals are divided into three states to be compared with the corrugated plate deformation quantity standard.

Fig. 3 is a schematic flow chart of a method for detecting tightness of a generator stator slot wedge in another embodiment of the present application, and the following describes each step of this embodiment in detail with reference to fig. 3.

Step 1: establishing a mechanical classification standard of the tightness state of the stator slot wedge, which specifically comprises the following steps:

1) fig. 4 is a schematic structural view of a stator slot wedge model of corrugated plate fastening according to another embodiment of the present application, in which (a) is a partially enlarged view of a gasket and a corrugated plate 12, and (b) is a schematic structural view of the stator slot wedge model as a whole. As shown in fig. 4, the stator slot wedge includes a slot wedge 11, a shim 122, a corrugated plate 121, a stator bar 13, an interlayer shim 14, and a core 15. And analyzing the electromagnetic force of the stator bar, wherein when the currents introduced into the upper layer and the lower layer of the stator bar are in the same phase, the resultant electromagnetic force points to the bottom of the slot wedge. At this time, the wire rod is not affected.

2) When the current in different phases is introduced, the electromagnetic force applied to the upper-layer wire rod is directed to the acting force applied to the slot wedge plate, namely the corrugated plate.

3) The maximum value of the electromagnetic force F1 is 2.0733N/cm when the stator bar is in normal operation when the out-of-phase current is introduced, and the maximum value of the electromagnetic force F2 is 248.7960N/cm when the stator bar is in short circuit are further calculated.

4) Dividing three states of the slot wedge (more than or equal to F2, F2-F1 and less than F1) according to F1 and F2, and establishing a mechanical standard of classification.

Step 2: establishing a slot wedge deformation classification standard, 1) obtaining a stress-strain characteristic curve of the corrugated plate by adopting a universal material testing machine, and obtaining the relation between the load and the deformation of the corrugated plate under the condition of pressure loading, thereby aligning with the electromagnetic force borne by the upper layer stator bar. 2) Since the ultimate pressure load of a sample corrugated plate when being completely compressed cannot be determined, one sample is selected to estimate the ultimate load. Five additional samples were selected for testing. 3) After a pressure loading test is carried out by a testing machine, a compression curve of five tested corrugated plate samples is drawn, and the compression curve is found to meet Hooke's law, wherein the system deformation also meets Hooke's law. 4) Fig. 5 is a graph showing an actual compression curve of a corrugated plate according to another embodiment of the present application, the actual compression curve of the corrugated plate obtained by removing the deformation of the system is shown in fig. 5, and the average deformation values corresponding to the critical forces F1 and F2 calculated in step 1 are calculated to be 0.0736mm and 1.4636 mm.

And step 3: set up test platform and carry out laboratory stator slot wedge elasticity analogue test, figure 6 is the stator slot wedge elasticity analogue test platform structure sketch map of this application in another embodiment, and test platform specifically includes: the device comprises a stator slot wedge model 1, a push-pull type electromagnetic knocking device 2, a sound sensor 3, a portable dynamic acquisition system 4 and a display 5. Mainly, the electromagnetic excitation device 2 knocks the slot wedge plate to generate vibration sound signals, the knocking sound signals are collected through the sound sensor 3, and the portable dynamic collection system 4 stores and processes collected signal data. The thickness of the gasket in the slot wedge is adjusted for many times to simulate the deformation of the corrugated plate, and acoustic signals of the stator slot wedge tightness in three different states are collected. 100 test strokes were performed for each tightness type. So that a total of 300 sets of signals are generated for the 3 tightness states.

Step 4, preprocessing signals: 1) in a test environment, the test time is generally longer than the time during which the electromagnetic excitation device knocks the slot wedge. And a double-threshold endpoint detection method is selected to intercept effective knocking sound segments, so that the later data calculation amount is reduced. 2) In order to perform spectrum analysis on the signal subsequently, guarantee the spectrum resolution, extract effective frequency domain characteristics and ensure that the signal is too short to intercept. And intercepting the effective knocking sound signal by a double-threshold endpoint detection method, wherein the signal length is 0.5 s. 3) When the actual detection of the generator maintenance site is carried out, the site environment is noisy, the obtained knocking sound signal contains more environmental noises, and the noise reduction treatment is needed. The second generation wavelet transform is adopted for denoising treatment, so that the influence of noise interference is reduced. The laboratory simulation test has less environmental noise and does not need noise reduction treatment.

Step 5, signal feature extraction and screening: after the sound signal is preprocessed, feature extraction and screening are required. 1) The elastic state information which is used for extracting relevant characteristic parameters from the original signal to represent the signal implications is mainly divided into time domain characteristics and frequency domain characteristics. 2) And in the aspect of time domain characteristics, characteristic parameters are extracted from 6 aspects of root mean square value, variance, form factor, peak factor, kurtosis and zero crossing rate. 3) The spectral feature is mainly extracted from the peak values of 3 frequency bands of the signal, the corresponding peak frequency, the spectrum centroid of the longitudinal axis and the amplitude area of 5 different frequency intervals. 4) 18 characteristic signals are selected through preliminary characteristic extraction, and then the extracted characteristic parameters are evaluated and screened by using a characteristic screening combination method based on an F-ratio and Pearson correlation coefficient method. 5) And finally, screening to remove unqualified characteristic signals, and reserving five characteristic signals, namely a frequency band amplitude area, a frequency spectrum centroid, a wave form factor, a third peak frequency and a fifth peak frequency.

Step 6, characteristic pattern recognition: 1) before model training, the characteristic parameter matrixes of the training set and the test set are normalized. 2) And dividing the training samples into 3 groups, and optimizing the parameters by using a cross verification method to obtain the characteristic parameters of the model. Specifically, the three states (tight, slightly tight and loose) total 300 groups of data, the training set 240 group and the test set are divided into 60 groups. Through optimization, the optimal penalty parameter C is 147.0334, and the optimal kernel function parameter g is 0.0015. 3) The test set is classified by using the cross validation optimizing parameter optimized SVM, FIG. 7 is a schematic diagram of the result of pattern recognition in another embodiment of the present application, and as shown in FIG. 7, 60 groups of data in the test set are predicted by using a support vector machine classifier, and the prediction result shows that accurate recognition of three different slot wedge tightness shows good effect, and the accuracy reaches 93.3333%.

In conclusion, a mechanical classification standard and a corrugated plate deformation classification standard are established according to the tightness of the slot wedges of the generator stator. And then, manually simulating slot wedge models in different states to perform signal acquisition, preprocessing, feature extraction and screening, and finally adopting a cross validation optimization parameter optimization SVM method, wherein three different slot wedge tightness degrees are accurately identified to show a good effect. The invention establishes a set of complete solution from standard establishment to pattern recognition, and can be widely applied to a plurality of corrugated plate type generator sets.

EXAMPLE III

The second aspect of the present application provides a stator slot wedge tightness detection apparatus by way of a third embodiment, including: memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the generator stator slot wedge tightness detection method as described in any of the above embodiments.

Fig. 8 is a schematic diagram of an architecture of a stator slot wedge tightness detection apparatus in another embodiment of the present application.

The stator slot wedge tightness detecting apparatus shown in fig. 8 may include: at least one processor 101, at least one memory 102, at least one network interface 104, and other user interfaces 103. The various components in the electronic device are coupled together by a bus system 105. It is understood that the bus system 105 is used to enable communications among the components. The bus system 105 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 105 in FIG. 8.

The user interface 103 may include, among other things, a display, a keyboard, or a pointing device (e.g., a mouse, trackball, or touch pad, among others.

It will be appreciated that the memory 102 in this embodiment may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may be a Read-only memory (ROM), a programmable Read-only memory (PROM), an erasable programmable Read-only memory (erasabprom, EPROM), an electrically erasable programmable Read-only memory (EEPROM), or a flash memory. The volatile memory may be a Random Access Memory (RAM) which functions as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (staticiram, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (syncronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM ), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and direct memory bus RAM (DRRAM). The memory 62 described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

In some embodiments, memory 102 stores elements, executable units or data structures, or a subset thereof, or an expanded set thereof as follows: an operating system 1021 and application programs 1022.

The operating system 1021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, and is used for implementing various basic services and processing hardware-based tasks. The application 1022 includes various applications for implementing various application services. Programs that implement methods in accordance with embodiments of the invention can be included in application 1022.

In the embodiment of the present invention, the processor 101 is configured to execute the method steps provided in the first aspect by calling a program or an instruction stored in the memory 102, which may be specifically a program or an instruction stored in the application 1022.

The method disclosed by the above embodiment of the present invention can be applied to the processor 101, or implemented by the processor 101. The processor 101 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 101. The processor 101 described above may be a general purpose processor, a digital signal processor, an application specific integrated circuit, an off-the-shelf programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software elements in the decoding processor. The software elements may be located in ram, flash, rom, prom, or eprom, registers, among other storage media that are well known in the art. The storage medium is located in the memory 102, and the processor 101 reads the information in the memory 102 and completes the steps of the method in combination with the hardware thereof.

In addition, in combination with the method for detecting tightness of generator stator slot wedges in the foregoing embodiments, embodiments of the present invention may provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements any one of the methods for detecting tightness of generator stator slot wedges in the foregoing embodiments.

It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. The use of the terms first, second, third, etc. are used for convenience only and do not denote any order. These words are to be understood as part of the name of the component.

Furthermore, it should be noted that in the description of the present specification, the description of the term "one embodiment", "some embodiments", "examples", "specific examples" or "some examples", etc., means that a specific feature, structure, material or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, the claims should be construed to include preferred embodiments and all changes and modifications that fall within the scope of the invention.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention should also include such modifications and variations.

Claims

1. A method for detecting the tightness of generator stator slot wedges is characterized by comprising the following steps:

2. The generator stator slot wedge tightness detection method of claim 1, wherein S20 comprises:

3. The generator stator slot wedge tightness detection method of claim 1, wherein the classifier is a support vector machine classifier, and before the step of S10, the training step further comprises:

s02, applying the stress of the stator slot wedges in each classification state to the corrugated plate, and performing a corrugated plate compression test to obtain the corresponding deformation amount of the corrugated plate;

s03, building stator slot wedge models in each classification state based on the deformation quantity of the corrugated plate, building a stator slot wedge tightness test platform for a knocking test, and knocking the stator slot wedge models by using an excitation device to obtain vibration sound signals in each classification state;

4. The generator stator slot wedge tightness detection method according to claim 3, wherein the stator slot wedge tightness state classification includes tight, slightly tight, and loose; when the state is tight, the stator bar does not jump under the short-circuit condition and the non-short-circuit condition; when the state is slightly tight, the stator bar does not jump only under the condition of non-short circuit; when the state is loose, the generator is prohibited from running.

5. The generator stator slot wedge tightness detection method of claim 4, wherein S01 comprises:

6. The generator stator slot wedge tightness detection method of claim 3, wherein S02 comprises:

7. The generator stator slot wedge tightness detection method of claim 3, wherein the extracting of the vibration sound signal feature from the vibration sound signal in S04 comprises:

extracting frequency domain characteristic parameters from the vibration sound signal to represent the tightness state of the slot wedge, wherein the frequency domain characteristic parameters comprise peak values of three frequency bands, corresponding peak frequency, spectrum centroid of a longitudinal axis and amplitude areas of five different frequency intervals;

8. The generator stator slot wedge tightness detection method of claim 3, wherein S05 comprises:

9. A stator slot wedge tightness detection device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the generator stator slot wedge tightness detection method according to any of the preceding claims 1 to 8.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the generator stator slot wedge tightness detection method according to any one of the preceding claims 1 to 8.