Water turbine cavitation identification method

Abstract

The invention provides a water turbine cavitation recognition method. The water turbine cavitation recognition method comprises the steps that an audio signal A (t) and a vibration signal V (t) of a water turbine in a running state are collected; preprocessing the audio signal A (t) and the vibration signal V (t) to obtain a processed audio signal A ''(t) and a processed vibration signal V'' (t); fusing the preprocessed audio signal A ''(t) and the preprocessed vibration signal V'' (t) to obtain a fused signal Ffusion (t); empirical mode decomposition is carried out on the fusion signal Ffusion (t), an intrinsic mode function set of the fusion signal Ffusion (t) is obtained, and the intrinsic mode function set comprises a plurality of intrinsic mode functions FK (t); extracting a time-frequency feature FK of each intrinsic mode function FK (t); inputting the time-frequency feature FK into a pre-constructed support vector machine for classification to obtain a classification result; based on the classification result, whether the water turbine is subjected to cavitation or not is determined; the accuracy of identifying the cavitation of the water turbine can be improved based on the time-frequency characteristics of the fusion signal.

Description

Technical Field

[0001] The present application relates to the technical field of water turbine cavitation identification, and in particular to a water turbine cavitation identification method. Background Art

[0002] With the vigorous development of hydropower, large and medium-sized hydropower stations in China have been built and put into operation one after another. The proportion of hydropower in the power supply is increasing, and hydropower is an important part of the global energy strategy. The turbine generator set is the core equipment of the hydropower station. The stable operation of the unit is of great significance to avoid safety hazards and improve the economic benefits of power generation enterprises. Cavitation is a common destructive phenomenon inside hydraulic machinery. The existence of cavitation will reduce the efficiency of the unit, increase the vibration of the unit and the wear of the blades, resulting in a significant reduction in the working life of the turbine unit and causing huge economic losses. Therefore, the determination of cavitation is particularly important. However, in the prior art, it is usually judged by audio signals whether there is cavitation in the turbine, and the accuracy is low. Summary of the invention

[0003] In response to the above problems, the present application proposes a method for identifying cavitation in a turbine, which solves the technical problem of low accuracy in the prior art of judging whether a turbine has cavitation by using audio signals, and can improve the accuracy of identifying cavitation in a turbine based on the time-frequency characteristics of the fused signal.

[0004] The present application provides a method for identifying cavitation in a hydraulic turbine, comprising:

[0005] Step S1: collecting the audio signal A(t) and the vibration signal V(t) of the turbine in operation;

[0006] Step S2: preprocessing the audio signal A(t) and the vibration signal V(t) to obtain processed audio signal A″(t) and vibration signal V″(t);

[0007] Step S3: Fusing the preprocessed audio signal A″(t) and the vibration signal V″(t) to obtain a fused signal F fusion (t);

[0008] Step S4: fusion signal F fusion (t) Performing empirical mode decomposition to obtain the fusion signal F fusion (t) is an eigenmode function set, wherein the eigenmode function set includes several eigenmode functions F K (t);

[0009] Step S5: Extract each intrinsic mode function F K The time-frequency characteristics F of (t) K ;

[0010] Step S6: The time-frequency feature F K Input the pre-built support vector machine for classification and obtain the classification result;

[0011] Step S7: Based on the classification result, determine whether the turbine is cavitating.

[0012] In some embodiments, the step S1 includes:

[0013] Step S11: Acquire the audio signal A(t) and vibration signal V(t) of the running turbine in a synchronous and frequency manner.

[0014] In some embodiments, the step S2 comprises:

[0015] Step S21: preprocessing the audio signal A(t), including:

[0016] Step S211: Detrending the audio signal A(t) to obtain an intermediate audio signal A′(t)=A(t)-fA(t), wherein fA(t) is a trend vertex obtained by polynomial fitting;

[0017] Step S212: Remove noise from the intermediate audio signal A′(t) to obtain a processed audio signal A″(t)=filter(A′(t), h A ), where h A is a filter designed for the audio signal A′(t);

[0018] Step S22: preprocessing the vibration signal V(t), including:

[0019] Step S221: Detrend the audio signal V(t) to obtain an intermediate audio signal V′(t)=V(t)-f V (t), where f V (t) is the trend top obtained by polynomial fitting;

[0020] Step S222: Remove noise from the intermediate audio signal V′(t) to obtain a processed audio signal V″(t)=filter(V′(t), h v ), where h v It is a filter designed for the vibration signal V′(t).

[0021] In some embodiments, step S3 includes:

[0022] Step S31: The audio signal A″(t) and the vibration signal V″(t) are fused using the following formula to obtain a fused signal F fusion(t) = αA″(t) + βV″(t), where α and β are weight coefficients.

[0023] In some embodiments, the step S4 comprises:

[0024] Step S41: Determine signal F fusion All maxima and minima in (t);

[0025] Step S42: using the cubic spline interpolation method, constructing an upper envelope u(t) based on the maximum value points, and constructing a lower envelope l(t) based on the minimum value points;

[0026] Step S43: Calculate the average value m(t) of the upper and lower envelopes:

[0027]

[0028] Step S44: Subtract the average envelope from the original signal to obtain a candidate intrinsic mode function h(t): h(t)=F fusion (t)-m(t);

[0029] Step S45: Check whether h(t) satisfies the conditions of the eigenmode function;

[0030] Step S46: If h(t) does not meet the intrinsic mode function condition, treat it as a new signal and repeat the above steps until the condition is met. At this time, h(t) is considered to be an intrinsic mode function F1(t);

[0031] Step S47: Extract the intrinsic mode function F1(t) from the original signal F fusion (t) is subtracted to obtain a new residual signal r(t) = F fusion (t)-F1(t);

[0032] Step S48: taking r(t) as a new input signal, repeating the above steps to extract the next intrinsic mode function F2(t);

[0033] Step S49: When the residual signal r(t) becomes a monotonic function or a constant, the empirical mode decomposition process ends and a set of intrinsic mode functions is obtained.

[0034] In some embodiments, step S5 includes:

[0035] Step S51: For each eigenmode function F K (t) Extract time-frequency features F K , where the time-frequency feature F K ={E K , C K}, where F K is the energy characteristic, CK is the frequency center.

[0036] In some embodiments, step S6 includes:

[0037] Step S61: The time-frequency feature F K Label and obtain the data set, and divide the data set into a training set and a validation set;

[0038] Step S62: The time-frequency features F in the training set K Inputting into an initial support vector machine SVM, training the initial support vector machine SVM, and obtaining an intermediate support vector machine SVM;

[0039] Step S63: The time-frequency features F in the validation set K Input into the intermediate support vector machine SVM for verification. If the verification is passed, the training is completed and the support vector machine SVM is obtained.

[0040] Step S64: The time-frequency feature F K Input to the support vector machine SVM, the time-frequency feature F K Perform classification and obtain classification results.

[0041] In some embodiments, the step S7 includes:

[0042] Step S71: if the classification result is a negative class, determining that the turbine is cavitating;

[0043] Step S72: If the classification result is a positive class, it is determined that the turbine is operating normally.

[0044] An embodiment of the present application provides an electronic device, including:

[0045] A memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, any one of the above methods is executed.

[0046] An embodiment of the present application provides a storage medium, which stores a computer program that can be executed by one or more processors and can be used to implement any of the methods described above.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] The method comprises collecting an audio signal A(t) and a vibration signal V(t) of a turbine in operation; preprocessing the audio signal A(t) and the vibration signal V(t) to obtain a processed audio signal A″(t) and a vibration signal V″(t); fusing the preprocessed audio signal A″(t) and the vibration signal V″(t) to obtain a fused signal Ffusion (t); for the fusion signal F fusion (t) Performing empirical mode decomposition to obtain the fusion signal F fusion (t) is an eigenmode function set, wherein the eigenmode function set includes several eigenmode functions F K (t); Extract each intrinsic mode function F K The time-frequency characteristics F of (t) K ; The time-frequency feature F K Input a pre-built support vector machine for classification to obtain a classification result; determine whether the turbine is cavitating based on the classification result; and improve the accuracy of identifying turbine cavitation based on the time-frequency characteristics of the fused signal. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The embodiments of the present invention are further described below with reference to the accompanying drawings:

[0050] Figure 1 A schematic diagram of a flow chart of a method for identifying cavitation in a hydraulic turbine provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0053] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0054] If similar descriptions of "first\second\third" appear in the application documents, the following instructions will be added. In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0056] Based on the problems existing in the related art, the embodiment of the present application provides a method for identifying cavitation of a turbine, and the execution subject of the identification method can be an electronic device. The electronic device can be various types of terminals such as a laptop, a tablet computer, a desktop computer, a set-top box, a mobile device (for example, a mobile phone, a portable music player, a personal digital assistant, a dedicated messaging device, a portable gaming device), and can also be implemented as a server. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0057] In some embodiments, the functions implemented by the identification method provided in the embodiments of the present application can be implemented by a processor of an electronic device calling a program code, wherein the program code can be stored in a computer storage medium.

[0058] The present application provides a method for identifying cavitation in a hydraulic turbine. Figure 1 A schematic diagram of the implementation process of a method for identifying cavitation in a hydraulic turbine provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, including:

[0059] Step S1: collecting the audio signal A(t) and the vibration signal V(t) of the turbine in operation;

[0060] In some embodiments, the step S1 includes:

[0061] Step S11: Acquire the audio signal A(t) and vibration signal V(t) of the running turbine in a synchronous and frequency manner.

[0062] In the embodiment of the present application, the audio signal of the running turbine can be collected by a microphone, and the vibration signal of the running turbine can be collected by a vibration sensor. The audio signal and the vibration signal need to be collected synchronously and at the same frequency, that is, collected at the same time and at the same frequency, to avoid the need to align the audio signal and the vibration signal later.

[0063] Step S2: preprocessing the audio signal A(t) and the vibration signal V(t) to obtain processed audio signal A″(t) and vibration signal V″(t);

[0064] In some embodiments, the step S2 comprises:

[0065] Step S21: preprocessing the audio signal A(t), including:

[0066] Step S211: Detrending the audio signal A(t) to obtain an intermediate audio signal A′(t)=A(t)-fA(t), wherein fA(t) is a trend vertex obtained by polynomial fitting;

[0067] Step S212: Remove noise from the intermediate audio signal A′(t) to obtain a processed audio signal A″(t)=filter(A′(t), h A ), where h A is a filter designed for the audio signal A′(t);

[0068] Step S22: preprocessing the vibration signal V(t), including:

[0069] Step S221: Detrend the audio signal V(t) to obtain an intermediate audio signal V′(t)=V(t)-f V (t), where f V (t) is the trend top obtained by polynomial fitting;

[0070] Step S222: Remove noise from the intermediate audio signal V′(t) to obtain a processed audio signal V″(t)=filter(V′(t), h v ), where h v It is a filter designed for the vibration signal V′(t).

[0071] In an embodiment of the present application, by detrending the audio signal and the vibration signal, low-frequency trend components such as linear or nonlinear trends, seasonal changes, etc. can be removed from the signal. These trends are usually caused by non-periodic changes in the signal and have nothing to do with the intrinsic characteristics of the signal. Trend components may mask the periodic changes and high-frequency features in the signal, which is unfavorable for subsequent signal analysis and feature extraction. By denoising the audio signal and the vibration signal, random noise in the signal can be reduced or eliminated. These noises may come from electronic noise of the measuring equipment, environmental interference, distortion during signal transmission, etc. Noise will interfere with the true characteristics of the signal and reduce the accuracy and reliability of signal processing. By detrending and denoising the audio signal and the vibration signal, it can be beneficial to feature extraction in the later stage.

[0072] Step S3: Fusing the preprocessed audio signal A″(t) and the vibration signal V″(t) to obtain a fused signal F fusion (t);

[0073] In some embodiments, step S3 includes:

[0074] Step S31: The audio signal A″(t) and the vibration signal V″(t) are fused using the following formula to obtain a fused signal F fusion (t) = αA″(t) + βV″(t), where α and β are weight coefficients.

[0075] In the embodiment of the present application, the audio signal and the vibration signal are fused by weighted averaging, so that the fusion of the audio signal and the vibration signal can be quickly achieved. Before the fusion, the user adjusts the weight coefficients of the audio signal and the vibration signal according to actual needs.

[0076] Step S4: fusion signal F fusion (t) Performing empirical mode decomposition to obtain the fusion signal F fusion (t) is an eigenmode function set, wherein the eigenmode function set includes several eigenmode functions F K (t);

[0077] In some embodiments, the step S4 comprises:

[0078] Step S41: Determine signal F fusion All maxima and minima in (t);

[0079] Step S42: using the cubic spline interpolation method, constructing an upper envelope u(t) based on the maximum value points, and constructing a lower envelope l(t) based on the minimum value points;

[0080] Step S43: Calculate the average value m(t) of the upper and lower envelopes:

[0081]

[0082] Step S44: Subtract the average envelope from the original signal to obtain a candidate intrinsic mode function h(t): h(t)=F fusion (t)-m(t);

[0083] Step S45: Check whether h(t) satisfies the conditions of the eigenmode function;

[0084] Step S46: If h(t) does not meet the intrinsic mode function condition, treat it as a new signal and repeat the above steps until the condition is met. At this time, h(t) is considered to be an intrinsic mode function F1(t);

[0085] Step S47: Extract the intrinsic mode function F1(t) from the original signal F fusion (t) is subtracted to obtain a new residual signal r(t) = F fusion (t)-F1(t);

[0086] Step S48: taking r(t) as a new input signal, repeating the above steps to extract the next intrinsic mode function F2(t);

[0087] Step S49: When the residual signal r(t) becomes a monotonic function or a constant, the empirical mode decomposition process ends and a set of intrinsic mode functions is obtained.

[0088] In the embodiment of the present application, the complex audio signal and vibration signal can be decomposed into multiple intrinsic mode functions through empirical mode decomposition, each of which represents the local characteristics of the signal at different time scales. This decomposition makes the analysis of the signal more intuitive and effective.

[0089] Step S5: Extract each intrinsic mode function F K The time-frequency characteristics F of (t) K ;

[0090] In some embodiments, step S5 includes:

[0091] Step S51: For each eigenmode function F K (t) Extract time-frequency features F K , where the time-frequency feature F K ={E K , C K}, where F K is the energy characteristic, C K is the frequency center.

[0092] In the embodiment of the present application, the extraction of time-frequency features can help identify the intrinsic mode function F K (t), such as periodicity, trend, anomaly, etc. This facilitates the subsequent support vector machine SVM to analyze the time-frequency features F K Perform identification and classification.

[0093] Step S6: The time-frequency feature F K Input the pre-built support vector machine for classification and obtain the classification result;

[0094] In some embodiments, step S6 includes:

[0095] Step S61: The time-frequency feature F K Label and obtain the data set, and divide the data set into a training set and a validation set;

[0096] Step S62: The time-frequency features F in the training set K Inputting into an initial support vector machine SVM, training the initial support vector machine SVM, and obtaining an intermediate support vector machine SVM;

[0097] Step S63: The time-frequency features F in the validation set K Input into the intermediate support vector machine SVM for verification. If the verification is passed, the training is completed and the support vector machine SVM is obtained.

[0098] Step S64: The time-frequency feature F K Input to the support vector machine SVM, the time-frequency feature F K Perform classification and obtain classification results.

[0099] In the embodiment of the present application, the time-frequency feature F K Mark and mark the time-frequency feature F K The cavitation time-frequency features and non-cavitation time-frequency features are divided into a data set, and then the cavitation time-frequency features and non-cavitation time-frequency features in the data set are divided into a training set and a validation set according to a ratio of 7:3. The training set is used for support vector machine SVM training, and the validation set is used for support vector machine SVM validation. After the support vector machine SVM training is completed, the time-frequency feature F K Input support vector machine SVM for classification and output the classification result.

[0100] Step S7: Based on the classification result, determine whether the turbine is cavitating.

[0101] In some embodiments, the step S7 includes:

[0102] Step S71: if the classification result is a negative class, determining that the turbine is cavitating;

[0103] Step S72: If the classification result is a positive class, it is determined that the turbine is operating normally.

[0104] In the embodiment of the present application, whether the turbine in operation is cavitated can be obtained according to the classification result. If the classification result is positive, it indicates that the turbine is operating normally. If the classification result is negative, it indicates that the turbine is cavitated, and an alarm message can be generated and sent to the terminal configured by the staff, so that the staff can handle it in time.

[0105] In summary, by collecting the audio signal A(t) and the vibration signal V(t) of the turbine in operation; preprocessing the audio signal A(t) and the vibration signal V(t) to obtain the processed audio signal A″(t) and the vibration signal V″(t); fusing the preprocessed audio signal A″(t) and the vibration signal V″(t) to obtain the fused signal F fusion (t); for the fusion signal F fusion (t) Performing empirical mode decomposition to obtain the fusion signal F fusion (t) is an eigenmode function set, wherein the eigenmode function set includes several eigenmode functions F K (t); Extract each intrinsic mode function F K The time-frequency characteristics F of (t) K ; The time-frequency feature F K Input a pre-built support vector machine for classification to obtain a classification result; determine whether the turbine is cavitating based on the classification result; and improve the accuracy of identifying turbine cavitation based on the time-frequency characteristics of the fused signal.

[0106] It should be noted that in the embodiment of the present application, if the above-mentioned identification method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM, Read Only Memory), a disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0107] Accordingly, an embodiment of the present application provides a storage medium on which a computer program is stored, characterized in that when the computer program is executed by a processor, the steps in the identification method provided in the above embodiment are implemented.

[0108] An embodiment of the present application provides an electronic device; Figure 2 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown in FIG. Figure 2As shown, the electronic device 400 includes: a processor 401, at least one communication bus 402, a user interface 403, at least one external communication interface 404, and a memory 405. The communication bus 402 is configured to realize the connection and communication between these components. The user interface 403 may include a display screen, and the external communication interface 404 may include a standard wired interface and a wireless interface. The processor 401 is configured to execute the program of the identification method stored in the memory to implement the steps in the identification method provided in the above embodiment.

[0109] It should be noted here that the description of the above storage medium and electronic device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0110] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned sequence numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0111] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, object or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, object or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, object or device including the element.

[0112] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0113] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0114] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0115] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read Only Memory), disks or optical disks, etc. Various media that can store program codes.

[0116] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can essentially or in other words, the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a controller to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0117] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for identifying cavitation in a hydraulic turbine, characterized in that: include: Step S1: collecting the audio signal A(t) and the vibration signal V(t) of the turbine in operation; Step S2: preprocessing the audio signal A(t) and the vibration signal V(t) to obtain processed audio signal A″(t) and vibration signal V″(t); Step S3: Fusing the preprocessed audio signal A″(t) and the vibration signal V″(t) to obtain a fused signal F fusion (t); Step S4: fusion signal F fusion (t) Performing empirical mode decomposition to obtain the fusion signal F fusion (t) is an eigenmode function set, wherein the eigenmode function set includes several eigenmode functions F K (t); Step S5: Extract each intrinsic mode function F K The time-frequency characteristics F of (t) K ; Step S6: The time-frequency feature F K Input the pre-built support vector machine for classification and obtain the classification result; Step S7: Based on the classification result, determine whether the turbine is cavitating.

2. The method according to claim 1, characterized in that The step S1 comprises: Step S11: Acquire the audio signal A(t) and vibration signal V(t) of the running turbine in a synchronous and frequency manner.

3. The method according to claim 1, characterized in that The step S2 comprises: Step S21: preprocessing the audio signal A(t), including: Step S211: Detrending the audio signal A(t) to obtain an intermediate audio signal A ′ (t) = A(t) - f A (t), where f A (t) is the trend top obtained by polynomial fitting; Step S212: Remove noise from the intermediate audio signal A′(t) to obtain a processed audio signal A″(t)=filter(A′(t),h A ), where h A is a filter designed for the audio signal A′(t); Step S22: preprocessing the vibration signal V(t), including: Step S221: Detrend the audio signal V(t) to obtain an intermediate audio signal V ′ (t) = V(t) - f V (t), where f V (t) is the trend top obtained by polynomial fitting; Step S222: The intermediate audio signal V ′ (t) to remove noise, and obtain the processed audio signal V″(t)=filter(V′(t),h v ), where h v It is a filter designed for the vibration signal V′(t).

4. The method according to claim 3, characterized in that The step S3 comprises: Step S31: The audio signal A″(t) and the vibration signal V″(t) are fused using the following formula to obtain a fused signal F fusion (t) = αA″(t) + βV″(t), where α and β are weight coefficients.

5. The method according to claim 4, characterized in that The step S4 comprises: Step S41: Determine signal F fusion All maxima and minima in (t); Step S42: using the cubic spline interpolation method, constructing an upper envelope u(t) based on the maximum value points, and constructing a lower envelope l(t) based on the minimum value points; Step S43: Calculate the average value m(t) of the upper and lower envelopes: Step S44: Subtract the average envelope from the original signal to obtain a candidate intrinsic mode function h(t): h(t)=F fusion (t)-m(t); Step S45: Check whether h(t) satisfies the conditions of the eigenmode function; Step S46: If h(t) does not meet the intrinsic mode function condition, treat it as a new signal and repeat the above steps until the condition is met. At this time, h(t) is considered to be an intrinsic mode function F1(t); Step S47: Extract the intrinsic mode function F1(t) from the original signal F fusiou (t) is subtracted to obtain a new residual signal r(t) = F fusuon (t)-F1(t); Step S48: taking r(t) as a new input signal, repeating the above steps to extract the next intrinsic mode function F2(t); Step S49: When the residual signal r(t) becomes a monotonic function or a constant, the empirical mode decomposition process ends and a set of intrinsic mode functions is obtained.

6. The method according to claim 5, characterized in that The step S5 comprises: Step S51: For each eigenmode function F K (t) Extract time-frequency features F K , where the time-frequency feature F K ={E K , C K }, where F K is the energy characteristic, C K is the frequency center.

7. The method according to claim 6, characterized in that The step S6 comprises: Step S61: The time-frequency feature F K Label and obtain the data set, and divide the data set into a training set and a validation set; Step S62: The time-frequency features F in the training set K Inputting into an initial support vector machine SVM, training the initial support vector machine SVM, and obtaining an intermediate support vector machine SVM; Step S63: The time-frequency features F in the validation set K Input into the intermediate support vector machine SVM for verification. If the verification is passed, the training is completed and the support vector machine SVM is obtained. Step S64: The time-frequency feature F K Input to the support vector machine SVM, the time-frequency feature F K Perform classification and obtain classification results.

8. The method according to claim 7, characterized in that The step S7 comprises: Step S71: if the classification result is a negative class, determining that the turbine is cavitating; Step S72: If the classification result is a positive class, it is determined that the turbine is operating normally.

9. An electronic device, characterized in that: include: A memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the method according to any one of claims 1 to 8 is executed.

10. A storage medium, characterized in that: The computer program stored in the storage medium can be executed by one or more processors and can be used to implement the method as claimed in any one of claims 1 to 8.

Images