Generator slot wedge tightness determination method and device, electronic equipment and storage medium

Abstract

The invention discloses a generator slot wedge tightness determination method and device, electronic equipment and a storage medium. The method comprises the following steps: determining a target sound signal; determining a characteristic parameter group based on the target sound signal; constructing a feature vector based on the feature parameter group; based on a radial basis kernel function and the feature vector, determining an inner product of a high-dimensional space corresponding to the feature vector; determining a Lagrange multiplier vector and a bias term based on a pre-constructed quadratic programming objective function and an inner product of a high-dimensional space corresponding to the feature vector; and constructing a dichotomy sub-model based on a one-to-one dichotomy decomposition strategy, and determining the generator slot wedge tightness through the dichotomy sub-model, Platt scaling, a Lagrange multiplier vector and an offset term. According to the technical scheme of the invention, the method achieves the determination of the tightness of the slot wedge of the generator under the condition that the rotor of the generator does not need to be pulled out and non-contact detection is not needed, and solves the problems of subjective judgment of manual detection and excessive dependence on the experience of workers.

Description

Technical Field

[0001] This invention relates to the field of generator testing technology, and in particular to a method, apparatus, electronic device, and storage medium for determining the tightness of generator slot wedges. Background Technology

[0002] In the power industry, after long-term operation of large generator sets, stator slot wedges may loosen due to aging, vibration, and wear, leading to problems such as stator bar insulation wear and slot discharge, threatening the safe operation of the generator. Therefore, it is crucial to regularly check the tightness of the slot wedges.

[0003] Traditional methods for testing slot wedge tightness require removing the generator rotor and having experienced personnel enter the generator with testing equipment to manually tap the slot wedges, judging the tightness by listening to the sound. This method is resource-intensive, time-consuming, lacks objectivity, cannot quantitatively analyze slot wedge tightness, and cannot retain repeatable data records. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for determining the tightness of generator slot wedges, in order to solve the problem that traditional methods for determining the tightness of generator slot wedges have long detection cycles and cannot quantitatively analyze the tightness of the slot wedges.

[0005] According to one aspect of the present invention, a method for determining the tightness of a generator slot wedge is provided, the method comprising:

[0006] Identify the target sound signal; the target sound signal is the sound signal emitted when the generator slot wedge vibrates.

[0007] Based on the target sound signal, a set of characteristic parameters is determined, which includes characteristic frequency, fundamental harmonic ratio, and low frequency proportion.

[0008] Construct feature vectors based on feature parameter sets;

[0009] Based on the radial basis kernel function and eigenvectors, the inner product of the eigenvectors in the high-dimensional space is determined;

[0010] Based on the pre-constructed quadratic programming objective function and the inner product of the eigenvectors in the corresponding high-dimensional space, the Lagrange multiplier vectors and the bias term are determined.

[0011] A binary sub-model is constructed based on a one-to-one bi-classification decomposition strategy. The tightness of the generator slot wedge is determined by the binary sub-model, Pratt scaling, Lagrange multiplier vectors, and bias terms. The tightness of the generator slot wedge is the probability of different tightness conditions of the generator slot wedge.

[0012] According to another aspect of the present invention, a generator slot wedge tightness determination device is provided, the device comprising:

[0013] The sound signal determination module is used to determine the target sound signal; the target sound signal is the sound signal emitted when the generator slot wedge vibrates.

[0014] The feature parameter determination module is used to determine a set of feature parameters based on the target sound signal. The set of feature parameters includes the feature frequency, fundamental harmonic ratio, and low frequency proportion.

[0015] The feature vector determination module is used to construct feature vectors based on the feature parameter set;

[0016] The inner product determination module is used to determine the inner product of the eigenvectors in the high-dimensional space based on the radial basis kernel function and the eigenvectors.

[0017] The parameter determination module is used to determine the Lagrange multiplier vectors and bias terms based on the pre-constructed quadratic programming objective function and the inner product of the high-dimensional space corresponding to the feature vectors;

[0018] The tightness determination module is used to construct a binary sub-model based on a one-to-one bi-classification decomposition strategy, and determine the tightness of the generator slot wedge through the binary sub-model, Pratt scaling, Lagrange multiplier vectors, and bias terms; the tightness of the generator slot wedge is the probability of different tightness conditions of the generator slot wedge.

[0019] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0020] At least one processor; and

[0021] A memory that is communicatively connected to at least one processor; wherein,

[0022] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the generator slot wedge tightness determination method according to any embodiment of the present invention.

[0023] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the generator slot wedge tightness determination method of any embodiment of the present invention.

[0024] The technical solution of this invention involves: determining a target sound signal; determining a set of feature parameters based on the target sound signal; constructing a feature vector based on the feature parameter set; determining the inner product of the feature vector in the high-dimensional space based on the radial basis kernel function and the feature vector; determining the Lagrange multiplier vector and bias term based on the pre-constructed quadratic programming objective function and the inner product of the feature vector in the high-dimensional space; constructing a binary sub-model based on a one-to-one dual classification decomposition strategy; and determining the tightness of the generator slot wedges through the binary sub-model, Pratt scaling, Lagrange multiplier vectors, and bias term. This achieves the determination of the tightness of the generator slot wedges without removing the generator rotor and without contact detection, thus eliminating the problems of subjective judgment and excessive reliance on worker experience in manual inspection.

[0025] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a flowchart of a method for determining the tightness of a generator slot wedge according to Embodiment 1 of the present invention;

[0028] Figure 2 This is a diagram of the generator stator slot wedge structure to which this invention applies;

[0029] Figure 3 This is a flowchart of another method for determining the tightness of generator slot wedges according to Embodiment 2 of the present invention;

[0030] Figure 4 This is a schematic diagram of a generator slot wedge tightness determination device according to Embodiment 3 of the present invention;

[0031] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the generator slot wedge tightness determination method of the present invention. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] Example 1

[0035] Figure 1 This invention provides a flowchart of a method for determining the tightness of generator slot wedges according to Embodiment 1. This embodiment is applicable to situations where the tightness of generator slot wedges needs to be determined without disassembling the generator. This method can be executed by a generator slot wedge tightness determining device, which can be implemented in hardware and / or software and can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0036] S110. Determine the target sound signal; the target sound signal is the sound signal emitted when the generator slot wedge vibrates.

[0037] Generator slot wedges are key components embedded in the stator / rotor core slots of a generator. Located above the winding conductors, they mechanically secure the stator and rotor coils within the core slots. (See also...) Figure 2 , Figure 2 This is a diagram of the generator stator slot wedge structure to which the present invention applies, including the slot wedge, gasket, corrugated plate, core, and stator bars.

[0038] The target sound signal can be obtained by collecting sound from the target generator. The target sound signal can be acquired through acoustic sensors, and the acquired results can be processed. This application does not limit the specific model, installation location, or number of acoustic sensors.

[0039] S120. Based on the target sound signal, determine the characteristic parameter group, which includes characteristic frequency, fundamental harmonic ratio and low frequency proportion.

[0040] The target sound signal is converted into a spectrum, and feature parameters, including feature frequencies, are extracted from the spectrum. Fundamental harmonic ratio and the proportion of low frequency The low-frequency proportion can be the percentage of energy in a specific frequency band relative to the total signal energy.

[0041] Among them, characteristic frequency The expression is:

[0042] ;

[0043] in, Indicates frequency;

[0044] Fundamental harmonic ratio The calculation method is as follows:

[0045] Set compensation bandwidth ;

[0046] ;

[0047] ;

[0048] ;

[0049] ;

[0050] If non-slot wedge vibration clutter exists within the harmonic range, the energy can be corrected using the "purity factor P".

[0051]

[0052] Similarly, we can obtain P3, requiring P2 ≥ 0.8 and P3 ≥ 0.8; otherwise, we modify it to... ,

[0053] in, For fundamental wave energy, It is the energy of the second harmonic. It is the energy of the third harmonic.

[0054] Taking the percentage of energy in the 20-300Hz frequency band to the total signal energy as an example, the calculation process for the low-frequency proportion L is as follows:

[0055] ;

[0056] ;

[0057] The proportion of low frequencies, L, is calculated by the following formula:

[0058] .

[0059] S130. Construct feature vectors based on feature parameter sets.

[0060] Based on the feature parameter set, feature parameters are expanded to improve the complexity of the feature parameter set, and the supplemented feature parameter set is used as a basis.

[0061] Optionally, based on the feature parameter set, a feature vector is constructed, including:

[0062] An interactive feature set is generated based on the characteristic frequency, fundamental harmonic ratio, and low-frequency proportion; the interactive feature set contains three interactive features.

[0063] Based on the interaction feature set and feature parameter set, construct the feature vector.

[0064] Feature parameter set ;

[0065] Based on the feature parameter set, interaction features are generated, where the expression for the interaction features is:

[0066] ;

[0067] ;

[0068] ;

[0069] Indicates the first interactive feature, This indicates the second interactive feature. This represents the third interactive feature.

[0070] The expression for the constructed initial feature vector is:

[0071] .

[0072] The entropy weight method is used to quantify the information contribution of each feature, avoiding the limitations of fixed weights. The formula is as follows:

[0073] Feature standardization: ,in Let be the mean of the i-th feature. The standard deviation is denoted as .

[0074] Information entropy calculation (representing feature dispersion): , ,in Let be the probability of the k-th sample in the i-th feature.

[0075] Adaptive weight allocation: ,satisfy .

[0076] The weighted feature vectors are used to generate the final feature vectors, expressed as follows:

[0077] .

[0078] S140. Based on the radial basis kernel function and eigenvectors, determine the inner product of the eigenvectors in the high-dimensional space.

[0079] Radial basis function kernels are used to map low-dimensional linearly inseparable data to a high-dimensional feature space, thereby achieving linear separability in the high-dimensional space.

[0080] The expression for the radial basis function kernel is:

[0081] ;

[0082] In the formula, For kernel parameters, .

[0083] The radial basis kernel function maps the feature vectors to a high-dimensional feature space and generates the corresponding inner product.

[0084] S150. Based on the pre-constructed quadratic programming objective function and the inner product of the eigenvectors in the corresponding high-dimensional space, determine the Lagrange multiplier vectors and the bias term.

[0085] Construct a quadratic programming objective function to solve for the optimal classification hyperplane and generate the Lagrange multiplier vector α and the bias term b.

[0086] The expression for the quadratic programming objective function is:

[0087] ;

[0088] ;

[0089] in Let e ​​be a Lagrange multiplier vector, and let e be an all-1 vector. 'b' represents the sample label (where 1 represents the first type of loosening, 2 represents the second type of loosening, 3 represents the third type of loosening, and 4 represents the fourth type of loosening), and 'b' represents the bias term.

[0090] S160. Construct a binary sub-model based on a one-to-one bi-classification decomposition strategy, and determine the tightness of the generator slot wedge by using the binary sub-model, Pratt scaling, Lagrange multiplier vectors, and bias terms; the tightness of the generator slot wedge is the probability of different tightness conditions of the generator slot wedge.

[0091] The one-to-one binary classification decomposition strategy, also known as the one-to-one (OvO) strategy, can break down a multi-classification task into multiple paired binary classification tasks, and then obtain the final classification conclusion by integrating the prediction results.

[0092] Multiple binary sub-models are constructed using a one-to-one dual-classification decomposition strategy. Each sub-model corresponds to the optimal parameters of quadratic programming, namely the Lagrange multiplier vector and the bias term. Each sub-model can output a decision function value indicating that "the sample belongs to one of the two classes". Platt scaling is used to implement the probability output part, and finally outputs the probability of different tightness conditions of the generator slot wedge as the final tightness of the generator slot wedge.

[0093] Taking the construction of 6 binary classification sub-models as an example, the expression for the binary classification sub-model is:

[0094] ;

[0095] Where S is the support vector set, .

[0096] The formula for calculating the tightness of the generator slot wedge is as follows: ;

[0097] in, ;

[0098] In the formula, , This is the scaling parameter.

[0099] The technical solution of this application involves: determining the target sound signal; determining a set of feature parameters based on the target sound signal; constructing a feature vector based on the feature parameter set; determining the inner product of the feature vector in the high-dimensional space based on the radial basis kernel function and the feature vector; determining the Lagrange multiplier vector and bias term based on the pre-constructed quadratic programming objective function and the inner product of the feature vector in the high-dimensional space; constructing a binary sub-model based on a one-to-one dual classification decomposition strategy; and determining the tightness of the generator slot wedge through the binary sub-model, Pratt scaling, Lagrange multiplier vector, and bias term. This achieves the determination of the tightness of the generator slot wedge without removing the generator rotor and without contact testing, thus eliminating the problems of subjective judgment and excessive reliance on worker experience in manual inspection.

[0100] Example 2

[0101] Figure 3 This invention provides a flowchart of another method for determining the tightness of generator slot wedges. This embodiment further optimizes the process of determining a set of characteristic parameters based on a target sound signal, as described in the previous embodiments. This embodiment can be combined with various optional solutions from one or more of the above embodiments. Figure 3 As shown, the generator slot wedge tightness determination method of this embodiment may include the following steps:

[0102] S210. Determine the target sound signal; the target sound signal is the sound signal emitted when the generator slot wedge vibrates.

[0103] S220. Perform a fast Fourier transform on the target sound signal to generate the target frequency domain signal.

[0104] To ensure the accuracy of determining the characteristic parameters of the target sound signal, a fast Fourier transform is performed on the target sound signal to generate the target frequency domain signal.

[0105] Optionally, a fast Fourier transform is performed on the target sound signal to generate the target frequency domain signal, including:

[0106] The target sound signal is denoised to obtain the first target sound signal;

[0107] The first target sound signal is normalized to obtain the second target sound signal;

[0108] Perform a Fast Fourier Transform on the second target sound signal to generate the target frequency domain signal.

[0109] After obtaining the target sound signal, a threshold function denoising algorithm based on Daubechies 6 wavelet transform (db6 wavelet) is used to remove environmental noise and high-frequency interference from the target sound signal, generating the first target sound signal. A normalization algorithm is then used to eliminate the influence of differences in acquisition distance and excitation intensity on the signal amplitude, converting signals acquired under different conditions into a unified standard effective acoustic signal, generating the second target sound signal.

[0110] The wavelet estimation function for the denoised wedge tightness sound signal is defined as follows:

[0111]

[0112] in For symbolic functions, The wavelet decomposition coefficients of the groove wedge tightness sound signal, and the threshold N is the length of the noise signal. This represents the standard deviation of the noise.

[0113] A Fast Fourier Transform (FFT) is performed on the preprocessed, standardized, and effective acoustic signal to transform the time-domain signal, which originally varied with time, into a frequency-domain signal corresponding to frequency and amplitude.

[0114] The target frequency domain signal is generated by further calculating the power spectral density (PSD) based on the frequency domain signal.

[0115] .

[0116] S230. Determine the characteristic parameter set based on the target frequency domain signal.

[0117] S240. Construct feature vectors based on feature parameter sets.

[0118] S250. Based on the radial basis kernel function and eigenvectors, determine the inner product of the eigenvectors in the high-dimensional space.

[0119] S260. Based on the pre-constructed quadratic programming objective function and the inner product of the eigenvectors in the corresponding high-dimensional space, determine the Lagrange multiplier vectors and the bias term.

[0120] S270. Construct a binary sub-model based on a one-to-one bi-classification decomposition strategy, and determine the tightness of the generator slot wedge by using the binary sub-model, Pratt scaling, Lagrange multiplier vectors, and bias terms; the tightness of the generator slot wedge is the probability of different tightness conditions of the generator slot wedge.

[0121] By employing the technical solution of this application, a fast Fourier transform is performed on the target sound signal to generate a target frequency domain signal. Based on the target frequency domain signal, a set of characteristic parameters is determined, which can more accurately determine the characteristic parameters, thereby ensuring the accuracy of the characteristic parameters and providing a computational basis for subsequent calculations.

[0122] Example 3

[0123] Figure 4 This invention provides a structural block diagram of a generator slot wedge tightness determination device. This embodiment is applicable to situations where it is necessary to determine the tightness of the generator slot wedge without disassembling the generator. The generator slot wedge tightness determination device can be implemented in hardware and / or software, and can be configured in an electronic device with data processing capabilities. Figure 4 As shown, the generator slot wedge tightness determination device of this embodiment may include: an audio signal determination module 310, a feature parameter determination module 320, a feature vector determination module 330, an inner product determination module 340, a parameter determination module 350, and a tightness determination module 360. Wherein:

[0124] The sound signal determination module 310 is used to determine the target sound signal; the target sound signal is the sound signal emitted when the generator slot wedge vibrates.

[0125] The feature parameter determination module 320 is used to determine a set of feature parameters based on the target sound signal. The set of feature parameters includes feature frequency, fundamental harmonic ratio and low frequency proportion.

[0126] The feature vector determination module 330 is used to construct feature vectors based on the feature parameter set;

[0127] The inner product determination module 340 is used to determine the inner product of the eigenvectors in the high-dimensional space based on the radial basis kernel function and the eigenvectors.

[0128] The parameter determination module 350 is used to determine the Lagrange multiplier vector and the bias term based on the pre-constructed quadratic programming objective function and the inner product of the high-dimensional space corresponding to the feature vectors;

[0129] The tightness determination module 360 ​​is used to construct a binary sub-model based on a one-to-one bi-classification decomposition strategy, and determine the tightness of the generator slot wedge through the binary sub-model, Pratt scaling, Lagrange multiplier vectors, and bias terms; the tightness of the generator slot wedge is the probability of different tightness conditions of the generator slot wedge.

[0130] Based on the above embodiments, optionally, a feature vector is constructed based on the feature parameter set, including:

[0131] An interactive feature set is generated based on the characteristic frequency, fundamental harmonic ratio, and low-frequency proportion; the interactive feature set contains three interactive features.

[0132] Based on the interaction feature set and feature parameter set, construct the feature vector.

[0133] Based on the above embodiments, optionally, the expression for the quadratic programming objective function is:

[0134] ;

[0135] ;

[0136] in Let e ​​be a Lagrange multiplier vector, and let e be an all-1 vector. 'b' represents the sample label, where 1 indicates the first type of loosening, 2 indicates the second type of loosening, 3 indicates the third type of loosening, and 4 indicates the fourth type of loosening; 'b' represents the bias term.

[0137] The expression for the radial basis function kernel is:

[0138] ;

[0139] in, ;in For kernel parameters, ; Here, represents the weight coefficients for each feature parameter, where... This represents the weight coefficient of the i-th feature parameter. ; ; ; Let be the probability of the k-th sample in the i-th feature; ;,in Let be the mean of the i-th feature. Standard deviation; Representing characteristic frequency, Indicates the fundamental harmonic ratio This indicates the proportion of low-frequency frequencies; ; ; ; express The i-th parameter.

[0140] Based on the above embodiments, optionally, the expression for the binary classification sub-model is:

[0141] ;

[0142] Where S is the support vector set, .

[0143] Based on the above embodiments, optionally, the calculation expression for the generator slot wedge tightness is as follows: ;

[0144] in, ;

[0145] In the formula, , This is the scaling parameter.

[0146] Based on the above embodiments, optionally, determining a set of feature parameters based on the target sound signal includes:

[0147] Perform a fast Fourier transform on the target sound signal to generate the target frequency domain signal;

[0148] Based on the target frequency domain signal, determine the characteristic parameter set.

[0149] Based on the above embodiments, optionally, a fast Fourier transform is performed on the target sound signal to generate a target frequency domain signal, including:

[0150] The target sound signal is denoised to obtain the first target sound signal;

[0151] The first target sound signal is normalized to obtain the second target sound signal;

[0152] Perform a Fast Fourier Transform on the second target sound signal to generate the target frequency domain signal.

[0153] The generator slot wedge tightness determination device provided in the embodiments of the present invention can execute the generator slot wedge tightness determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0154] Example 4

[0155] Figure 5 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0156] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0157] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0158] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the generator slot wedge tightness determination method.

[0159] In some embodiments, the generator slot wedge tightness determination method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the generator slot wedge tightness determination method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the generator slot wedge tightness determination method by any other suitable means (e.g., by means of firmware).

[0160] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0161] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0162] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0163] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0164] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0165] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0166] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0167] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining the tightness of a generator slot wedge, characterized in that, include: Determine the target sound signal; the target sound signal is the sound signal emitted when the generator slot wedge vibrates. Based on the target sound signal, a set of characteristic parameters is determined, which includes characteristic frequency, fundamental harmonic ratio, and low frequency proportion. Construct feature vectors based on feature parameter sets; Based on the radial basis kernel function and the eigenvector, the inner product of the eigenvector in the high-dimensional space is determined; Based on the pre-constructed quadratic programming objective function and the inner product of the high-dimensional space corresponding to the feature vector, the Lagrange multiplier vector and the bias term are determined. A binary sub-model is constructed based on a one-to-one bi-classification decomposition strategy. The tightness of the generator slot wedge is determined by the binary sub-model, Pratt scaling, Lagrange multiplier vectors, and bias terms. The tightness of the generator slot wedge is the probability of different tightness conditions of the generator slot wedge.

2. The method according to claim 1, characterized in that, Based on the feature parameter set, a feature vector is constructed, including: An interactive feature set is generated based on the characteristic frequency, fundamental harmonic ratio, and low-frequency proportion; the interactive feature set contains three interactive features. Based on the interaction feature set and feature parameter set, construct the feature vector.

3. The method according to claim 1, characterized in that, The expression for the objective function of the quadratic programming is: ； ； in Let e ​​be a Lagrange multiplier vector, and let e be an all-1 vector. 'b' represents the sample label, where 1 indicates the first type of loosening, 2 indicates the second type of loosening, 3 indicates the third type of loosening, and 4 indicates the fourth type of loosening; 'b' represents the bias term. The expression for the radial basis kernel function is as follows: ； in, ;in For kernel parameters, ; Here, represents the weight coefficients for each feature parameter, where... This represents the weight coefficient of the i-th feature parameter. ; ; ; Let be the probability of the k-th sample in the i-th feature; ;in Let be the mean of the i-th feature. Standard deviation; Representing characteristic frequency, Indicates the fundamental harmonic ratio This indicates the proportion of low-frequency frequencies; ; ; ; express The i-th parameter.

4. The method according to claim 3, characterized in that, The expression for the binary classification sub-model is: ； Where S is the support vector set, .

5. The method according to claim 4, characterized in that, The formula for calculating the tightness of the generator slot wedge is as follows: ; in, ; In the formula, , This is the scaling parameter.

6. The method according to claim 1, characterized in that, Based on the target sound signal, determine the set of feature parameters, including: Perform a Fast Fourier Transform on the target sound signal to generate a target frequency domain signal; Based on the target frequency domain signal, a set of characteristic parameters is determined.

7. The method according to claim 6, characterized in that, Performing a Fast Fourier Transform on the target sound signal to generate a target frequency domain signal includes: The target sound signal is denoised to obtain a first target sound signal; The first target sound signal is normalized to obtain the second target sound signal; The second target sound signal is subjected to a fast Fourier transform to generate the target frequency domain signal.

8. A device for determining the tightness of a generator slot wedge, characterized in that, include: A sound signal determination module is used to determine a target sound signal; the target sound signal is the sound signal emitted when the generator slot wedge vibrates. The feature parameter determination module is used to determine a set of feature parameters based on the target sound signal. The set of feature parameters includes feature frequency, fundamental harmonic ratio, and low frequency proportion. The feature vector determination module is used to construct feature vectors based on the feature parameter set; The inner product determination module is used to determine the inner product of the eigenvector in the high-dimensional space based on the radial basis kernel function and the eigenvector; The parameter determination module is used to determine the Lagrange multiplier vector and the bias term based on the pre-constructed quadratic programming objective function and the inner product of the high-dimensional space corresponding to the feature vector; The tightness determination module is used to construct a binary sub-model based on a one-to-one bi-classification decomposition strategy, and determine the tightness of the generator slot wedge through the binary sub-model, Pratt scaling, Lagrange multiplier vectors, and bias terms; the tightness of the generator slot wedge is the probability of different tightness conditions of the generator slot wedge.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the generator slot wedge tightness determination method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the generator slot wedge tightness determination method according to any one of claims 1-7.

Images