Axial flow pump fault diagnosis method and device, electronic equipment and medium
Patent Information
- Application Number
- CN202410998696.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-12
Smart Images

Figure CN118940118A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of mechanical fault diagnosis, and in particular to an axial flow pump fault diagnosis method, device, electronic equipment and medium. Background Art
[0002] As an important production equipment, axial flow pumps are prone to failure under long-term high-load working environment, which may cause equipment damage and system operation interruption, causing serious impact on production and water supply. Ensuring its normal production operation is of great significance to improving the economic benefits of the enterprise.
[0003] The axial flow pump has a complex coupling structure. The monitoring information of a single sensor contains a single fault feature, which is difficult to fully reflect the complex health status of the equipment. How to effectively extract and fuse the key fault information in the multi-channel sensor signal is the core of realizing axial flow pump fault diagnosis based on multi-sensor signals. To address this problem, there is a multi-sensor information fusion diagnosis method based on shallow learning in the prior art.
[0004] However, the vibration signals of axial flow pumps often exhibit non-stationary and nonlinear characteristics, and multi-sensor information fusion diagnosis methods based on shallow learning often rely on manual feature extraction and data preprocessing. Summary of the invention
[0005] In view of this, it is necessary to provide an axial flow pump fault diagnosis method, device, electronic equipment and medium to solve the problem of relying on manual feature extraction in the prior art.
[0006] In order to solve the above problems, the present application provides an axial flow pump fault diagnosis method, comprising: Acquire a sample set consisting of vibration data of an axial flow pump of a known fault type, wherein the vibration data is acquired by at least two sensors arranged on the axial flow pump; Constructing an initial multi-channel convolutional neural network model, and training the initial multi-channel convolutional neural network model based on the sample set to obtain a fully trained multi-channel convolutional neural network model, wherein the data acquired by each sensor in the vibration data corresponds to an input channel in the initial multi-channel convolutional neural network model; Fault diagnosis of the axial flow pump to be diagnosed is performed based on the fully trained multi-channel convolutional neural network model.
[0007] In some possible implementations, three sensors are provided, which are respectively used to detect vibration signals of the axial flow pump in the horizontal direction, vertical direction and axial direction.
[0008] In some possible implementations, the known fault types include normal, and at least one of a blade crack fault, a base loose fault, a rotor imbalance fault, an impeller winding fault, and a rotor misalignment fault.
[0009] In some possible implementations, the initial multi-channel convolutional neural network model includes an input layer connected in sequence, a plurality of parallel convolutional pooling layers, a local feature fusion layer and a global average pooling layer, a fully connected layer, a Softmax layer and an output layer; The multiple convolutional pooling layers are used to extract features from the data acquired by each sensor in the vibration data to obtain local features corresponding to each sensor; The local feature fusion layer is used to perform feature fusion on the local features corresponding to the sensors based on a self-attention mechanism to obtain the fault features corresponding to the sensors.
[0010] In some possible implementations, a channel feature fusion layer is further provided between the local feature fusion layer and the fully connected layer, and the channel feature fusion layer is used to perform feature fusion on the fault features corresponding to the sensors based on a self-attention mechanism.
[0011] In some possible implementations, constructing an initial multi-channel convolutional neural network model, and training the initial multi-channel convolutional neural network model based on the sample set to obtain a fully trained multi-channel convolutional neural network model, including: Constructing an initial multi-channel convolutional neural network model, inputting the vibration data of the training set in the sample set into the initial multi-channel convolutional neural network model to obtain a predicted fault type; Based on the cross entropy loss function, calculating the loss function value of the predicted fault type and the actual fault type; Based on the loss function value, a back propagation algorithm is used to iteratively optimize the training parameters of the initial multi-channel convolutional neural network model to obtain a fully trained multi-channel convolutional neural network model.
[0012] In some possible implementations, after obtaining the fully trained multi-channel convolutional neural network model, the method further includes: The fully trained multi-channel convolutional neural network model is verified and evaluated based on the test set in the sample set to obtain a final fully trained multi-channel convolutional neural network model.
[0013] The present application also provides an axial flow pump fault diagnosis device, comprising: A data acquisition unit, used to acquire a sample set consisting of vibration data of an axial flow pump of a known fault type, wherein the vibration data is acquired by at least two sensors provided on the axial flow pump; A model determination unit, used to construct an initial multi-channel convolutional neural network model, and train the initial multi-channel convolutional neural network model based on the sample set to obtain a fully trained multi-channel convolutional neural network model, wherein the data acquired by each sensor in the vibration data corresponds to an input channel in the initial multi-channel convolutional neural network model; The model diagnosis unit is used to perform fault diagnosis on the axial flow pump to be diagnosed based on the fully trained multi-channel convolutional neural network model.
[0014] The present application also provides an electronic device, including a memory and a processor; The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps of the above-mentioned axial flow pump fault diagnosis method.
[0015] The present application also provides a computer-readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the above-mentioned axial flow pump fault diagnosis method are implemented.
[0016] The beneficial effects of the present application are as follows: the axial flow pump fault diagnosis method provided by the present application automatically learns complex feature representations from raw data through a multi-channel convolutional neural network model, and then automatically extracts feature indicators, effectively integrating multi-sensor feature data, avoiding dependence on artificially designed feature indicators, overcoming the limitations of manual feature extraction, and having stronger feature extraction capabilities and generalization, and achieving accurate diagnosis of the health status of the axial flow pump. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 A schematic flow chart of an embodiment of the axial flow pump fault diagnosis method provided in the present application; Figure 2 A schematic diagram of the structure of the multi-channel convolutional neural network model provided in this application; Figure 3 For this application Figure 1 A schematic flow chart of an embodiment of step S102; Figure 4 A schematic diagram of the diagnostic results of the multi-channel convolutional neural network model provided in this application; Figure 5 A schematic diagram of the structure of an embodiment of an axial flow pump fault diagnosis device provided in the present application; Figure 6 A schematic diagram of the structure of an embodiment of an electronic device provided in this application. DETAILED DESCRIPTION
[0018] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.
[0019] It should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts may be implemented out of order, and steps without logical contextual relationships may be reversed in order or implemented simultaneously. In addition, those skilled in the art may add one or more other operations to the flowcharts, or may remove one or more operations from the flowcharts, under the guidance of the content of this application. Some of the block diagrams shown in the accompanying drawings are functional entities, and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor systems and / or microcontroller systems.
[0020] The descriptions of "first", "second", etc. involved in the embodiments of the present application are only used to describe the implicit purpose, and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" and "second" may explicitly or implicitly include at least one of the features. "And / or" describes the association relationship of the associated objects, indicating that three relationships may exist, for example: A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone.
[0021] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0022] The present application provides an axial flow pump fault diagnosis method, which is described below.
[0023] Figure 1 A schematic flow chart of an embodiment of the axial flow pump fault diagnosis method provided in this application is as follows: Figure 1 As shown, the axial flow pump fault diagnosis method includes: S101, obtaining a sample set consisting of vibration data of an axial flow pump of a known fault type, where the vibration data is obtained by at least two sensors provided on the axial flow pump; S102, constructing an initial multi-channel convolutional neural network model, and training the initial multi-channel convolutional neural network model based on the sample set to obtain a fully trained multi-channel convolutional neural network model, wherein the data acquired by each sensor in the vibration data corresponds to an input channel in the initial multi-channel convolutional neural network model; S103. Perform fault diagnosis on the axial flow pump to be diagnosed based on the fully trained multi-channel convolutional neural network model.
[0024] Compared with the prior art, the axial flow pump fault diagnosis method provided in the present application automatically learns complex feature representations from raw data through a multi-channel convolutional neural network model, and then automatically extracts feature indicators, effectively integrating multi-sensor feature data, avoiding dependence on artificially designed feature indicators, overcoming the limitations of manual feature extraction, and having stronger feature extraction capabilities and generalization, thereby achieving accurate diagnosis of the health status of the axial flow pump.
[0025] In this embodiment, a 700ZLB-70 axial flow pump is used as an experimental object for experimental verification. The rated speed of the motor of the axial flow pump is 750rpm, the power is 160kW, and the voltage is 380V. Three sensors are provided, and CTCAC102A vibration acceleration sensors are installed in the direction of the axial flow pump bearing housing, the x-axis direction of the motor, and the y-axis direction of the motor, respectively, to detect the three-directional vibration signals of the axial flow pump in the horizontal direction, the vertical direction, and the axial direction, and complete the collection of multi-sensor signals. Detecting the three-directional vibration signals of the axial flow pump can obtain richer fault characteristics and more comprehensively reflect the complexity of the equipment. Health state, improve the diagnostic accuracy; the experimental pump health state, that is, there are six known fault types, including normal, blade crack fault, base loose fault, rotor imbalance fault and impeller winding fault rotor misalignment fault. For each axial flow pump health state, the NI9234 data acquisition card is used to continuously collect the vibration signal of the axial flow pump at a sampling frequency of 5kHz. With 1024 data points as one sample, 400 samples are collected under normal state, 100 samples are collected under each of the five fault states, and a total of 900 samples are collected for the six axial flow pump health states. The detailed parameters of the axial flow pump sample set are shown in Table 1: Table 1 Detailed parameters of the axial flow pump sample set
[0026] As shown in Table 1, the sample set is divided into three different subsets: training set, validation set and test set; the training set is used to train the model, that is, to adjust the weights and biases in the model; the validation set is used to periodically test the performance of the model during training, monitor the risk of overfitting, and guide hyperparameter optimization; finally, the test set is used to evaluate the final performance of the trained and validated model. The test set data is completely unknown to the model to ensure the fairness and accuracy of the evaluation results.
[0027] In order to better fuse multi-sensor feature data according to the fault characteristics of the axial flow pump, in some embodiments, the multi-channel convolutional neural network model structure is as follows: Figure 2 The detailed network structure parameters are shown in Table 2: Table 2 Multi-channel convolutional neural network structure parameters
[0028] Where N represents the number of sensors, the convolution kernel size 32×8 represents the convolution kernel size of 32 and the number of convolution kernels of 8, and the maximum pooling window size 2×2 represents the pooling window length of 2 and the step size of 2. In addition, before the channel feature fusion layer, the actual number of layers is N and each channel is operated in parallel.
[0029] like Figure 2 As shown in Table 2, the initial multi-channel convolutional neural network model includes a sequentially connected input layer, multiple parallel convolutional pooling layers, a local feature fusion layer and a global average pooling layer, a channel feature fusion layer, a fully connected layer, a Softmax layer and an output layer, wherein the multiple convolutional pooling layers are used to extract features from the data acquired by each sensor in the vibration data to obtain the local features corresponding to each sensor, the local feature fusion layer is used to perform feature fusion on the local features corresponding to each sensor based on the self-attention mechanism to obtain the fault features corresponding to each sensor, and the channel feature fusion layer is used to perform feature fusion on the fault features corresponding to each sensor based on the self-attention mechanism.
[0030] Therefore, the overall calculation process of the multi-channel convolutional neural network model is divided into two stages: feature extraction and feature fusion and classification. In the feature extraction stage, the model processes the input multi-channel signals in parallel, and uses multi-layer convolutional pooling layers to effectively extract the local features of the signals. Subsequently, the extracted local features are input into the temporal self-attention module with residual connection and self-attention mechanism to achieve feature fusion and capture global dependencies in the temporal dimension. Finally, the extracted fault features are compressed and reduced in dimension through global average pooling to obtain the fault features of each channel. In the feature fusion and classification stage, the model dynamically assigns different attention weights to each channel feature through the spatial self-attention module, thereby effectively integrating multi-channel information. Finally, the fused features are processed by flattening and linear transformation, and the Softmax function is input to obtain the final fault diagnosis result.
[0031] It should be noted that the self-attention mechanism is used to adaptively focus on the information of different parts of the sequence, dynamically generate different attention weights, and capture the relationship between the elements within the sequence. The specific calculation formula is as follows:
[0032]
[0033] in, , and , represent different learnable weight matrices, , and Represent different linear transformation results "query", "key" and "value" respectively. is the hidden layer dimension, Used to keep the attention score stable.
[0034] It should also be noted that in order to effectively retain the signal edge information, the model adopts a zero-padding strategy before each convolution operation; due to the complexity of real data, linear models may not be able to effectively solve practical problems. In order to improve the fitting ability of the model, the model performs ReLU nonlinear activation function operations after each convolution layer and pooling layer operation. Therefore, the ReLU nonlinear activation function can help the model capture the nonlinear relationship between inputs; in order to accelerate network training and improve model performance, residual connections are added to the self-attention module. The residual connection skips some layers and passes the input to deeper layers, allowing the gradient to flow directly through the network, making the gradient easier to backpropagate.
[0035] In order to better train the model, in some embodiments, such as Figure 3 As shown, step S102 includes: S301, constructing an initial multi-channel convolutional neural network model, inputting the vibration data of the training set into the initial multi-channel convolutional neural network model, and obtaining a predicted fault type; S302, calculating the loss function value of the predicted fault type and the actual fault type based on the cross entropy loss function; S303. Based on the loss function value, a back propagation algorithm is used to iteratively optimize the training parameters of the initial multi-channel convolutional neural network model to obtain a fully trained multi-channel convolutional neural network model.
[0036] It should be noted that this application uses the Adam algorithm as the optimization algorithm to optimize the model; adopts a dynamic learning rate strategy, the initial learning rate (Learning rate) is set to 0.0001, and adjusts the learning rate in combination with a decay rate (Decay rate) of 0.9; adopts an early stopping strategy to prevent model overfitting and optimize training time. The early stopping strategy means that when the diagnostic accuracy on the validation set no longer improves or begins to decline, the training will stop.
[0037] After obtaining the fully trained multi-channel convolutional neural network model, the test set is used to verify and evaluate the fully trained multi-channel convolutional neural network model, and the performance of the model in the fault diagnosis task is analyzed. According to the test results, the model can be further adjusted and optimized to obtain the final fully trained multi-channel convolutional neural network model to ensure its high reliability and accuracy in practical applications.
[0038] In this embodiment, the model was trained and tested 20 times independently during the experiment. The diagnostic results of the final fully trained multi-channel convolutional neural network model are as follows: Figure 4 As shown, the lowest diagnostic accuracy for the axial flow pump fault state is 96.67%, the highest diagnostic accuracy is 100%, and the average diagnostic accuracy is 99.24±1.23%.
[0039] In order to better implement an axial flow pump fault diagnosis method in an embodiment of the present application, based on an axial flow pump fault diagnosis method, correspondingly, as Figure 5 As shown, the embodiment of the present application further provides an axial flow pump fault diagnosis device 500, comprising: A data acquisition unit 501 is used to acquire a sample set consisting of vibration data of an axial flow pump of a known fault type, where the vibration data is acquired by at least two sensors provided on the axial flow pump; A model determination unit 502 is used to construct an initial multi-channel convolutional neural network model, and train the initial multi-channel convolutional neural network model based on the sample set to obtain a fully trained multi-channel convolutional neural network model, wherein the data obtained by each sensor in the vibration data corresponds to an input channel in the initial multi-channel convolutional neural network model; The model diagnosis unit 503 is used to perform fault diagnosis on the axial flow pump to be diagnosed based on a fully trained multi-channel convolutional neural network model.
[0040] The axial flow pump fault diagnosis device 500 provided in the above embodiment can implement the technical solution described in the above axial flow pump fault diagnosis method embodiment. The specific implementation principles of the above units can refer to the corresponding contents in the above axial flow pump fault diagnosis method embodiment, which will not be repeated here.
[0041] like Figure 6 As shown, the present application also provides an electronic device 600. The electronic device 600 includes a processor 601, a memory 602 and a display 603. Figure 6 Only some components of the electronic device 600 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.
[0042] In some embodiments, the memory 602 may be an internal storage unit of the electronic device 600, such as a hard disk or memory of the electronic device 600. In other embodiments, the memory 602 may also be an external storage device of the electronic device 600, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 600.
[0043] Furthermore, the memory 602 may include both an internal storage unit of the electronic device 600 and an external storage device. The memory 602 is used to store application software installed in the electronic device 600 and various data.
[0044] In some embodiments, the processor 601 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 602, such as the axial flow pump fault diagnosis method in the present application.
[0045] In some embodiments, the display 603 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 603 is used to display information on the electronic device 600 and to display a visual user interface. The components 601-603 of the electronic device 600 communicate with each other via a system bus.
[0046] In some embodiments of the present application, when the processor 601 executes the axial flow pump fault diagnosis program in the memory 602, the following steps may be implemented: Acquire a sample set consisting of vibration data of an axial flow pump of a known fault type, wherein the vibration data is acquired by at least two sensors arranged on the axial flow pump; An initial multi-channel convolutional neural network model is constructed, and the initial multi-channel convolutional neural network model is trained based on the sample set to obtain a fully trained multi-channel convolutional neural network model, wherein the data obtained by each sensor in the vibration data corresponds to an input channel in the initial multi-channel convolutional neural network model; Fault diagnosis of the axial flow pump to be diagnosed is performed based on the well-trained multi-channel convolutional neural network model.
[0047] It should be understood that: when the processor 601 executes the axial flow pump fault diagnosis program in the memory 602, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.
[0048] Furthermore, the embodiment of the present application does not specifically limit the type of the electronic device 600 mentioned, and the electronic device 600 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic device may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present application, the electronic device 600 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).
[0049] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions of the axial flow pump fault diagnosis method provided in the above-mentioned method embodiments can be implemented.
[0050] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the above-mentioned program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.
[0051] The above is a detailed introduction to an axial flow pump fault diagnosis method provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
[0052] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed in the present application should be covered within the protection scope of the present application.
Claims
1. A method for diagnosing an axial flow pump fault, characterized in that: include: Acquire a sample set consisting of vibration data of an axial flow pump of a known fault type, wherein the vibration data is acquired by at least two sensors arranged on the axial flow pump; Constructing an initial multi-channel convolutional neural network model, and training the initial multi-channel convolutional neural network model based on the sample set to obtain a fully trained multi-channel convolutional neural network model, wherein the data acquired by each sensor in the vibration data corresponds to an input channel in the initial multi-channel convolutional neural network model; Fault diagnosis of the axial flow pump to be diagnosed is performed based on the fully trained multi-channel convolutional neural network model.
2. The axial flow pump fault diagnosis method according to claim 1, characterized in that: The sensors are provided in three numbers and are used to detect the vibration signals of the axial flow pump in the horizontal direction, the vertical direction and the axial direction respectively.
3. The axial flow pump fault diagnosis method according to claim 1, characterized in that: The known fault types include normal, and at least one of a blade crack fault, a base loose fault, a rotor imbalance fault, an impeller winding fault, and a rotor misalignment fault.
4. The axial flow pump fault diagnosis method according to claim 1, characterized in that: The initial multi-channel convolutional neural network model includes an input layer connected in sequence, multiple parallel convolutional pooling layers, a local feature fusion layer and a global average pooling layer, a fully connected layer, a Softmax layer and an output layer; The multiple convolutional pooling layers are used to extract features from the data acquired by each sensor in the vibration data to obtain local features corresponding to each sensor; The local feature fusion layer is used to perform feature fusion on the local features corresponding to the sensors based on a self-attention mechanism to obtain the fault features corresponding to the sensors.
5. The axial flow pump fault diagnosis method according to claim 4, characterized in that: A channel feature fusion layer is also provided between the local feature fusion layer and the fully connected layer, and the channel feature fusion layer is used to perform feature fusion on the fault features corresponding to the sensors based on a self-attention mechanism.
6. The axial flow pump fault diagnosis method according to claim 1, characterized in that: Constructing an initial multi-channel convolutional neural network model, and training the initial multi-channel convolutional neural network model based on the sample set to obtain a fully trained multi-channel convolutional neural network model, including: Constructing an initial multi-channel convolutional neural network model, inputting the vibration data of the training set in the sample set into the initial multi-channel convolutional neural network model to obtain a predicted fault type; Based on the cross entropy loss function, calculating the loss function value of the predicted fault type and the actual fault type; Based on the loss function value, a back propagation algorithm is used to iteratively optimize the training parameters of the initial multi-channel convolutional neural network model to obtain a fully trained multi-channel convolutional neural network model.
7. The axial flow pump fault diagnosis method according to claim 6, characterized in that: After obtaining the fully trained multi-channel convolutional neural network model, the method further includes: The fully trained multi-channel convolutional neural network model is verified and evaluated based on the test set in the sample set to obtain a final fully trained multi-channel convolutional neural network model.
8. An axial flow pump fault diagnosis device, characterized in that: include: A data acquisition unit, used to acquire a sample set consisting of vibration data of an axial flow pump of a known fault type, wherein the vibration data is acquired by at least two sensors provided on the axial flow pump; A model determination unit, used to construct an initial multi-channel convolutional neural network model, and train the initial multi-channel convolutional neural network model based on the sample set to obtain a fully trained multi-channel convolutional neural network model, wherein the data acquired by each sensor in the vibration data corresponds to an input channel in the initial multi-channel convolutional neural network model; The model diagnosis unit is used to perform fault diagnosis on the axial flow pump to be diagnosed based on the fully trained multi-channel convolutional neural network model.
9. An electronic device, characterized in that: including memory and processor; The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps of the axial flow pump fault diagnosis method described in any one of claims 1 to 7 above.
10. A computer-readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the axial flow pump fault diagnosis method described in any one of claims 1 to 7 are implemented.
Citation Information
Cited By
Fault detection method and device for compressor and medium
CN121452164A
