An electronic pump fault diagnosis system and method

Abstract

The application discloses an electronic pump fault diagnosis system and method, and the method comprises the following steps: obtaining to-be-transmitted electronic pump signal information; the to-be-transmitted electronic pump signal information comprises first electronic pump signal information and second electronic pump signal information; pre-processing the to-be-transmitted electronic pump signal information to obtain target processing signal information; and analyzing and processing the target processing signal information to obtain fault diagnosis result information.

Description

Technical Field

[0001] This invention relates to the field of electronic pump technology, and in particular to an electronic pump fault diagnosis system and method. Background Technology

[0002] With the rapid development of new energy vehicles, industrial automation, and other fields, electric pumps, as core components of power transmission and fluid control, directly impact system safety and energy efficiency due to their operational reliability. However, existing electric pump fault diagnosis technologies still face technical challenges such as diagnostic blind spots from single-signal analysis and insufficient static thresholds and adaptability. Therefore, this paper proposes an electric pump fault diagnosis system and method that utilizes feature mining and analysis of multi-source signal information collected by the electric pump to overcome problems such as multi-source signal coupling, noise interference, and feature drift, thereby improving the accuracy and reliability of electric pump fault diagnosis. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide an electronic pump fault diagnosis system and method that facilitates feature mining and analysis of multi-source signal information collected by electronic pumps, so as to overcome problems such as multi-source signal coupling, noise interference and feature drift, and improve the fault diagnosis accuracy and reliability of electronic pumps.

[0004] To address the aforementioned technical problems, a first aspect of the present invention discloses a method for diagnosing electronic pump faults, the method comprising:

[0005] Acquire the electronic pump signal information to be transmitted; the electronic pump signal information to be transmitted includes first electronic pump signal information and second electronic pump signal information;

[0006] The electronic pump signal information to be transmitted is preprocessed to obtain the target processing signal information;

[0007] The target processing signal information is analyzed and processed to obtain fault diagnosis result information.

[0008] A second aspect of this invention discloses an electronic pump fault diagnosis system, the system comprising:

[0009] The acquisition module is used to acquire electronic pump signal information to be transmitted; the electronic pump signal information to be transmitted includes first electronic pump signal information and second electronic pump signal information.

[0010] The first processing module is used to preprocess the electronic pump signal information to be transmitted to obtain the target processing signal information;

[0011] The second processing module is used to analyze and process the target processing signal information to obtain fault diagnosis result information.

[0012] A third aspect of the present invention discloses another electronic pump fault diagnosis system, the system comprising:

[0013] Memory containing executable program code;

[0014] A processor coupled to the memory;

[0015] The processor calls the executable program code stored in the memory to execute some or all of the steps in the electronic pump fault diagnosis method disclosed in the first aspect of the present invention.

[0016] The fourth aspect of the present invention discloses a computer-readable storage medium storing computer instructions, which, when invoked, are used to perform some or all of the steps in the electronic pump fault diagnosis method disclosed in the first aspect of the present invention. Attached Figure Description

[0017] 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.

[0018] Figure 1 This is a schematic diagram of a scenario for the electronic pump fault diagnosis system provided in an embodiment of the present invention;

[0019] Figure 2 This is a flowchart illustrating an electronic pump fault diagnosis method disclosed in an embodiment of the present invention;

[0020] Figure 3 This is a schematic diagram of the structure of an electronic pump fault diagnosis system disclosed in an embodiment of the present invention;

[0021] Figure 4 This is a schematic diagram of another electronic pump fault diagnosis system disclosed in an embodiment of the present invention;

[0022] Figure 5 This is a schematic diagram of the structure of a target fault diagnosis model disclosed in an embodiment of the present invention;

[0023] Figure 6 This is a schematic diagram of the structure of a feature diagnosis module disclosed in an embodiment of the present invention. Detailed Implementation

[0024] 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 are within the scope of protection of the present invention.

[0025] It should be noted that the terminology used in the embodiments of this application is for the purpose of describing specific embodiments only and is not intended to limit the application. The singular forms "a," "the," and "the" used in the embodiments of this application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0027] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0028] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0029] It should be noted that the term "and / or" used in this application is merely a description of the same field in the related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0030] It should be noted that, depending on the context, the word "if" as used herein can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0031] It should be noted that in the description of this application, the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", and "outer" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the system or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0032] It should be noted that the phrase "within the range" used in this application, unless otherwise specified, includes both endpoints of the range by default. For example, in the range of 1 to 5, it includes the values ​​1 and 5.

[0033] It should be noted that since the method in this application embodiment is executed in a computer device, the processing objects of each computer device exist in the form of data or information, such as time, which is essentially time information. It is understood that if size, quantity, position, etc. are mentioned in subsequent embodiments, they are all corresponding data that exist so that the computer device can process them. Specific details will not be elaborated here.

[0034] It should be noted that the artificial intelligence-related technologies that may be involved in this application will be briefly described. Artificial intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new kind of intelligent machine that can react in a way similar to human intelligence. Artificial intelligence is the study of the design principles and implementation methods of various intelligent machines, enabling machines to have the functions of perception, reasoning, and decision-making.

[0035] Artificial intelligence (AI) is a comprehensive discipline encompassing a wide range of fields, including both hardware and software technologies. Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies primarily include computer vision, speech processing, natural language processing, and machine learning / deep learning.

[0036] Computer vision (CV) is a science that studies how to enable machines to "see." More specifically, it refers to machine vision, which uses cameras and computers to replace human eyes in recognizing and measuring targets, and then performs image processing to create images more suitable for human observation or transmission to instruments. As a scientific discipline, computer vision studies related theories and technologies, attempting to build artificial intelligence systems capable of extracting information from images or multidimensional data. Computer vision technologies typically include image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, 3D object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping (SLAM), and common biometric recognition technologies such as facial recognition and fingerprint recognition.

[0037] Monomodal information refers to data of only one type, such as text, images, audio, video, or electromagnetic signals. Multimodal information refers to data that includes at least two types of monomodal information. Furthermore, multimodal information is suitable for complex tasks that require the integration of multiple information sources, such as sentiment analysis, robot interaction, and autonomous driving. By integrating information from multiple modalities, higher performance and accuracy can usually be achieved in these tasks.

[0038] Large models refer to artificial neural network models with a very large number of parameters. In the field of artificial intelligence, large models typically refer to models with hundreds of millions to trillions of parameters. These models usually need to be trained on large-scale datasets and require a significant amount of computing resources for optimization and tuning. Large models are commonly used to solve complex tasks such as natural language processing, computer vision, and speech recognition. Generative AI is a type of AI that can create new content and ideas, including dialogues, stories, images, videos, and music. In this embodiment, the large model can be a large-scale pre-trained model such as the ChatGPT series, BERT, XLNet, Zhipu model, Claude, Moonshot AI model, ChatGLM model, Tongwen Qianyi model, MiniMax model, Xinghuo model, Llama model, 360GPT model, Qwen model, Baichuan model, Yunque model, vivoLM model, deepseek, Tencent Yuanbao, and Wenxin Yiyan, etc., and this embodiment does not limit the scope of the large model.

[0039] This application provides an electronic pump fault diagnosis method, system, computer device, and computer-readable storage medium, which will be described in detail below.

[0040] Please see Figure 1 , Figure 1 This is a schematic diagram of a scenario for an electronic pump fault diagnosis system provided in an embodiment of this application. The electronic pump fault diagnosis system may include a computer device 100, which integrates the electronic pump fault diagnosis system. Figure 1 Computer equipment in the country.

[0041] In this embodiment of the application, the computer device 100 is mainly used to acquire electronic pump signal information to be transmitted; the electronic pump signal information to be transmitted includes first electronic pump signal information and second electronic pump signal information; the electronic pump signal information to be transmitted is preprocessed to obtain target processing signal information; the target processing signal information is analyzed and processed to obtain fault diagnosis result information.

[0042] It can overcome problems such as multi-source signal coupling, noise interference, and feature drift by using feature mining and analysis of multi-source signal information collected by electronic pumps, thereby improving the fault diagnosis accuracy and reliability of electronic pumps.

[0043] In this embodiment, the computer device 100 can be a standalone server, a server network, or a server cluster. For example, the computer device 100 described in this embodiment includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. The cloud server is composed of a large number of computers or network servers based on cloud computing.

[0044] It is understood that the computer device 100 used in the embodiments of this application can be a device that includes both receiving and transmitting hardware, that is, a device having receiving and transmitting hardware capable of performing bidirectional communication on a bidirectional communication link. Such a device may include: cellular or other communication devices having a single-line display, a multi-line display, or a cellular or other communication device without a multi-line display. Specifically, the computer device 100 may be a desktop terminal or a mobile terminal, and may also be one of a mobile phone, tablet computer, laptop computer, etc.

[0045] Those skilled in the art will understand that Figure 1 The application environment shown is merely one application scenario of the solution in this application and does not constitute a limitation on the application scenario of the solution in this application. Other application environments may include those that are more specific to this application. Figure 1 The number of computer devices shown is more or less, for example Figure 1 Only one computer device is shown in the diagram. It is understood that the electronic pump fault diagnosis system may also include one or more other services, which are not limited here.

[0046] In addition, such as Figure 1 As shown, the electronic pump fault diagnosis system may also include a memory 200 for storing data, such as image data and location information.

[0047] It should be noted that, Figure 1 The schematic diagram of the electronic pump fault diagnosis system shown is merely an example. The electronic pump fault diagnosis system and scenario described in this application are for the purpose of more clearly illustrating the technical solutions of this application and do not constitute a limitation on the technical solutions provided in this application. As those skilled in the art will know, with the evolution of electronic pump fault diagnosis systems and the emergence of new business scenarios, the technical solutions provided in this application are also applicable to similar technical problems.

[0048] This invention discloses an electronic pump fault diagnosis system and method that facilitates feature mining and analysis of multi-source signal information acquired by the electronic pump, overcoming problems such as multi-source signal coupling, noise interference, and feature drift, thereby improving the accuracy and reliability of electronic pump fault diagnosis. Detailed descriptions follow.

[0049] Example 1

[0050] Please see Figure 2 , Figure 2 This is a schematic flowchart of an electronic pump fault diagnosis method disclosed in an embodiment of the present invention. Wherein, Figure 2 The described electronic pump fault diagnosis method is applied in management systems, such as local servers or cloud servers used for management, and this embodiment of the invention is not limited thereto. Figure 2 As shown, the electronic pump fault diagnosis method may include the following operations:

[0051] 101. Obtain the electronic pump signal information to be transmitted.

[0052] In this embodiment of the invention, the electronic pump signal information to be transmitted includes first electronic pump signal information and second electronic pump signal information.

[0053] 102. Preprocess the electronic pump signal information to be transmitted to obtain the target processing signal information.

[0054] 103. Analyze and process the target processing signal information to obtain fault diagnosis results.

[0055] It should be noted that the above-mentioned first electronic pump signal information represents a vibration signal, which can be acquired by a vibration sensor, and this embodiment of the present invention does not limit it.

[0056] It should be noted that the above-mentioned second electronic pump signal information represents either current or voltage, which can be acquired by current or voltage sensors, and this embodiment of the invention does not limit the scope of the signal.

[0057] It should be noted that due to the complexity of the operating conditions, the aforementioned electronic pumps exhibit various signal characteristics during malfunctions, such as abnormal vibration and temperature, and are also subject to noise interference. Therefore, a single signal is usually insufficient for effectively analyzing the malfunction. Furthermore, these signals encompass temporal and spatial characteristics, necessitating the fusion analysis of these two types of features to improve the accuracy of identifying the electronic pump's operating status. This application combines these fusion features of different signal types to efficiently identify the electronic pump's state type. Moreover, the method presented in this application has significant advantages over traditional CNN and CNN-GRU identification methods. The table below shows a comparison of the comprehensive test identification results from five tests conducted under the same sample conditions:

[0058]

[0059] It is evident that implementing the electronic pump fault diagnosis method described in this embodiment of the invention is beneficial for feature mining and analysis of multi-source signal information collected by the electronic pump, thereby overcoming problems such as multi-source signal coupling, noise interference, and feature drift, and improving the fault diagnosis accuracy and reliability of the electronic pump.

[0060] In an optional embodiment, the preprocessing of the electronic pump signal information to be transmitted to obtain the target processed signal information includes:

[0061] Alignment processing is performed on the first electronic pump signal information and the second electronic pump signal information in the electronic pump signal information to be transmitted to obtain the first processed signal information and the second processed signal information.

[0062] The first processed signal information and the second processed signal information are normalized to obtain the first target signal information and the second target signal information;

[0063] The first target signal information and the second target signal information are spliced ​​together to obtain the target processing signal information.

[0064] It should be noted that the normalization process of the first and second processed signal information described above maps the two signals to the interval between [0,1] to eliminate the dimensional differences between different types of signals and facilitate the unified data processing of the model. This embodiment of the invention does not limit this process.

[0065] It should be noted that the above-mentioned splicing process of the first target signal information and the second target signal information involves splicing the second target signal information after the first target signal information to form a two-dimensional time-series data information. This embodiment of the invention does not limit this process.

[0066] In this optional embodiment, as an optional implementation, the above-described alignment processing of the first electronic pump signal information and the second electronic pump signal information in the electronic pump signal information to be transmitted to obtain first processed signal information and second processed signal information includes:

[0067] The first electronic pump signal information in the electronic pump signal information to be transmitted is subjected to time delay correction processing to obtain the corrected electronic pump signal information;

[0068] Acquire signal time interval information; the signal time interval information includes the start signal time and the end signal time.

[0069] Determine whether there are two sampling periods before the start signal time for the corrected electronic pump signal information and the second electronic pump signal information to obtain the first signal judgment result;

[0070] When the first signal judgment result is yes, the time before the start signal time and with an interval of 2 sampling periods is used as the initial signal time for correcting the electronic pump signal information and the second electronic pump signal information.

[0071] When the first signal judgment result is negative, the later start time of the corrected electronic pump signal information and the second electronic pump signal information will be used as the initial signal time of the corrected electronic pump signal information and the second electronic pump signal information.

[0072] Determine whether there are two sampling periods after the termination signal time for the corrected electronic pump signal information and the second electronic pump signal information, and obtain the second signal judgment result.

[0073] When the second signal judgment result is yes, the time after the termination signal time and after an interval of 2 sampling periods is taken as the cutoff signal time of the corrected electronic pump signal information and the second electronic pump signal information.

[0074] When the second signal judgment result is negative, the earlier cutoff time between the corrected electronic pump signal information and the second electronic pump signal information will be used as the cutoff signal time of the corrected electronic pump signal information and the second electronic pump signal information.

[0075] Data extracted from the corrected electronic pump signal information and the second electronic pump signal information at the initial signal time and the cutoff signal time are used as the first processed signal information and the second processed signal information.

[0076] It should be noted that the above sampling period is the sampling period of the sensor, which can be a time value such as 0.1 seconds, and can be set by the user. This embodiment of the invention does not limit it.

[0077] It should be noted that the above-mentioned time delay correction processing of the first electronic pump signal information in the electronic pump signal information to be transmitted takes into account that the acquisition of vibration signal will have a certain time delay relative to current / voltage. Therefore, in order to ensure the consistency of data in the time dimension, it is necessary to eliminate the influence of this time delay, that is, it is necessary to advance the signal value of the first electronic pump signal information to a certain extent. This advance amount can be obtained through experimental analysis. In this application, the signal value can be shifted forward, but the time delay must be eliminated to ensure the accuracy of electronic pump working status analysis and identification. This embodiment of the invention does not limit this.

[0078] It should be noted that the aforementioned signal time interval information represents the time period for analyzing the operating status of the electronic pump. Furthermore, the determination of the initial signal time and the cutoff signal time is to ensure a certain degree of data continuity during signal value analysis, while avoiding excessive data redundancy; that is, to ensure both the accuracy and efficiency of the data analysis. This embodiment of the invention does not impose limitations on this. Furthermore, the initial signal time is no later than the start signal time, and the cutoff signal time is no earlier than the termination signal time. For example, when the start signal time and the termination signal time are [t4, t9], the corrected electronic pump signal information and the second electronic pump signal information are as follows:

[0079]

[0080] Before t4, both the corrected electronic pump signal information and the second electronic pump signal information have two sampling periods, so t2 is selected as the initial signal time. However, after t9, the second electronic pump signal information only has one sampling period, so t10 is selected as the cutoff signal time. The first processed signal information and the second processed signal information are as follows:

[0081]

[0082] It is evident that implementing the electronic pump fault diagnosis method described in this embodiment of the invention is beneficial for feature mining and analysis of multi-source signal information collected by the electronic pump, thereby overcoming problems such as multi-source signal coupling, noise interference, and feature drift, and improving the fault diagnosis accuracy and reliability of the electronic pump.

[0083] In another optional embodiment, the target processing signal information is analyzed and processed to obtain fault diagnosis result information, including:

[0084] The target fault diagnosis model is used to perform diagnostic analysis on the target processing signal information to obtain signal diagnosis results.

[0085] The signal diagnostic results are processed by time-series visualization to obtain the fault diagnosis results.

[0086] It should be noted that the above signal diagnostic results represent the identification results of the working status of the electronic pump in a time-series distribution. The time-series distribution is based on the time interval distribution corresponding to the sampling frequency of the electronic pump signal information to be transmitted. This embodiment of the invention does not limit this distribution.

[0087] It should be noted that the above-mentioned fault diagnosis result information is represented by a line graph of the time series, and the embodiments of the present invention are not limited thereto.

[0088] It should be noted that the above-mentioned time-series visualization processing of signal diagnostic results information is to present the identified working status identification results graphically according to the numerical type (e.g., 1 for normal electronic pump status, 2 for motor failure, and 3 for impeller failure) in time sequence to achieve visualization. This embodiment of the invention does not limit this.

[0089] It is evident that implementing the electronic pump fault diagnosis method described in this embodiment of the invention is beneficial for feature mining and analysis of multi-source signal information collected by the electronic pump, thereby overcoming problems such as multi-source signal coupling, noise interference, and feature drift, and improving the fault diagnosis accuracy and reliability of the electronic pump.

[0090] In yet another optional embodiment, the target fault diagnosis model includes a first feature extraction module, a second feature extraction module, a feature fusion module, and a feature diagnosis module; wherein,

[0091] The first feature extraction module is used to perform hierarchical spatial feature extraction on the target processing signal information;

[0092] The second feature extraction module is used to extract temporal features from the target processing signal information;

[0093] The feature fusion module is used to fuse multiple feature information.

[0094] The feature diagnosis module is used to perform nonlinear feature analysis on feature information in order to analyze and identify the state type of the electronic pump.

[0095] It should be noted that the above-mentioned electronic pump status types include normal electronic pump status, motor failure, and impeller failure, and the embodiments of the present invention do not limit this.

[0096] It should be noted that the above feature fusion module is built based on the self-attention mechanism. It has multiple feature channels and can learn the spatiotemporal correlation of each channel independently. Finally, it enhances key features through weighted fusion. This embodiment of the invention does not limit the scope of the invention.

[0097] It should be noted that the second feature extraction module mentioned above can be built based on the LSTM model to extract the time-series features of medium- and long sequences in the signal collected by the electronic pump. This embodiment of the invention does not impose any limitations.

[0098] It should be noted that the aforementioned feature diagnosis module includes a third convolutional unit, a first feature extraction unit, a second feature extraction unit, a third feature extraction unit, a fourth feature extraction unit, a fifth feature extraction unit, a sixth feature extraction unit, a seventh feature extraction unit, an eighth feature extraction unit, a second pooling unit, a second connection unit, and a third activation unit; wherein, the first feature extraction unit includes a fourth convolutional unit, a fifth convolutional unit, a fifth normalization unit, a sixth normalization unit, a third activation unit, a fourth activation unit, and a second fusion unit; wherein,

[0099] The input of the third convolutional unit is configured as the input of the feature diagnosis module. The third convolutional unit, the first feature extraction unit, the second feature extraction unit, the third feature extraction unit, the fourth feature extraction unit, the fifth feature extraction unit, the sixth feature extraction unit, the seventh feature extraction unit, the eighth feature extraction unit, the second pooling unit, the second connection unit, and the third activation unit are connected sequentially. The output of the third activation unit is configured as the output of the feature diagnosis module.

[0100] The input of the fourth convolutional unit and the input of the second fusion unit are configured as the input of the first feature extraction unit; the fourth convolutional unit, the fifth normalization unit, the third activation unit, the fifth convolutional unit, the sixth normalization unit, and the fourth activation unit are connected in sequence; the output of the fourth activation unit is connected to the input of the second fusion unit; the output of the second fusion unit is configured as the output of the first feature extraction unit.

[0101] It should be noted that the model architecture of the first feature extraction unit, the second feature extraction unit, the third feature extraction unit, the fourth feature extraction unit, the fifth feature extraction unit, the sixth feature extraction unit, the seventh feature extraction unit, and the eighth feature extraction unit are consistent, and the embodiments of the present invention do not limit them.

[0102] It should be noted that the second fusion unit of the aforementioned first feature extraction unit fuses features extracted from the input of the first feature extraction unit and features extracted from multiple convolution-normalization-activation links. This enables the first feature extraction unit to address the gradient vanishing and gradient exploding problems at deeper depths. This embodiment of the invention does not impose limitations on this. Furthermore, the kernel sizes of the convolution units in the aforementioned first feature extraction unit are consistent. Furthermore, the number of channels in the convolution units of the first, second, third, fourth, fifth, sixth, seventh, and eighth feature extraction units is increased exponentially to achieve progressively deeper feature extraction from the output data information of the feature fusion module, resulting in richer abstract feature representations and improving the accuracy of identifying the electronic pump state type. This embodiment of the invention does not impose limitations on this.

[0103] Furthermore, the above-mentioned low-level features are directly transmitted to the deep layer through multiple (first to eighth) feature extraction units in sequence, forming a fused feature with shallow and deep layers in each feature extraction unit. This alleviates the gradient vanishing problem when multi-level feature fusion extraction is performed in each feature extraction unit, and extracts high-order nonlinear combinations. Finally, the working state of the electronic pump can be more accurately identified through the classification and recognition of fully connected layers and activation functions. This embodiment of the invention is not limited.

[0104] It should be noted that the kernel size of the third, fourth, and fifth convolutional units mentioned above is either 3×3 or 5×5, the stride is 2, and the number of channels is 32 or 64. This embodiment of the invention does not limit the specific number of channels.

[0105] It should be noted that the fifth and sixth normalization units mentioned above are constructed based on the average pooling layer, and this embodiment of the invention does not limit them.

[0106] It should be noted that the third and fourth activation units mentioned above are constructed based on the ReLU activation function, and this embodiment of the invention does not limit them.

[0107] It should be noted that the second fusion unit described above is constructed based on element-wise addition operations, and this embodiment of the invention does not limit it.

[0108] It is evident that implementing the electronic pump fault diagnosis method described in this embodiment of the invention is beneficial for feature mining and analysis of multi-source signal information collected by the electronic pump, thereby overcoming problems such as multi-source signal coupling, noise interference, and feature drift, and improving the fault diagnosis accuracy and reliability of the electronic pump.

[0109] In another optional embodiment, the input terminals of both the first feature extraction module and the second feature extraction module are configured to receive target processing signal information; the output terminals of both the first and second feature extraction modules are connected to the input terminal of the feature fusion module; the output terminal of the feature fusion module is connected to the input terminal of the feature diagnosis module; and the output terminal of the feature diagnosis module is configured to output signal diagnosis result information.

[0110] It should be noted that the above-mentioned feature fusion module can overcome the difficulty of capturing long-distance spatiotemporal features simultaneously by fusing the outputs of the first feature extraction module and the second feature extraction module. By modeling attention weights for multiple feature channels of the input signal, it can accurately capture key spatiotemporal features, eliminate interference that occurs during signal acquisition, and achieve accurate extraction of multiple types of signals. This embodiment of the invention is not limited.

[0111] It is evident that implementing the electronic pump fault diagnosis method described in this embodiment of the invention is beneficial for feature mining and analysis of multi-source signal information collected by the electronic pump, thereby overcoming problems such as multi-source signal coupling, noise interference, and feature drift, and improving the fault diagnosis accuracy and reliability of the electronic pump.

[0112] In an optional embodiment, the first feature extraction module includes a first convolutional unit, a second convolutional unit, a first normalization unit, a second normalization unit, a third normalization unit, a fourth normalization unit, a first activation unit, a second activation unit, a first random deactivation unit, a second random deactivation unit, a third random deactivation unit, a first pooling unit, a first connection unit, a first fusion unit, and a first neural network; wherein,

[0113] The input of the first convolutional unit is configured as the input of the first feature extraction module; the first convolutional unit, the first normalization unit, the first activation unit, the first random deactivation unit, the second convolutional unit, the second normalization unit, the second activation unit, and the second random deactivation unit are connected sequentially; the output of the second random deactivation unit is connected to the input of the first pooling unit and the input of the first neural network; the output of the first pooling unit is connected to the input of the first connection unit; the output of the first connection unit is connected to the input of the fourth normalization unit; the output of the fourth normalization unit is connected to the input of the first fusion unit; the output of the first neural network is connected to the input of the third normalization unit; the output of the third normalization unit is connected to the input of the first fusion unit; the output of the first fusion unit is connected to the input of the third random deactivation unit; the output of the third random deactivation unit is configured as the output of the first feature extraction module.

[0114] It should be noted that the kernel size of the first convolutional unit and the second convolutional unit mentioned above is either 3×3 or 5×5, the stride is 2, and the number of channels is 256. This embodiment of the invention does not limit the size of the kernel.

[0115] It should be noted that the first normalization unit, the second normalization unit, the third normalization unit, and the fourth normalization unit mentioned above are constructed based on the batch normalization layer, and this embodiment of the invention does not limit them.

[0116] It should be noted that the first activation unit and the second activation unit mentioned above are constructed based on the ReLU activation function, and this embodiment of the invention does not limit them.

[0117] It should be noted that the first random deactivation unit, the second random deactivation unit, and the third random deactivation unit mentioned above are constructed based on the random deactivation layer to prevent overfitting. This embodiment of the invention does not limit the scope of the invention.

[0118] It should be noted that the first pooling unit described above is constructed based on the average pooling layer, and this embodiment of the present invention does not limit it.

[0119] It should be noted that the first connection unit mentioned above is constructed based on a fully connected layer, and this embodiment of the present invention does not limit it.

[0120] It should be noted that the first fusion unit described above is constructed based on element-wise addition operations, and this embodiment of the invention does not limit it.

[0121] It should be noted that the first neural network described above is constructed based on a gated recurrent network, and this embodiment of the invention does not limit it.

[0122] It should be noted that the first feature extraction module first uses convolutional layers to extract local time-frequency features through filters of different sizes. After the convolutional layers, random deactivation units are inserted to force the network to learn redundant feature expressions by randomly shielding some neurons, thus preventing over-reliance on specific local features. Then, the first neural network (which handles temporal dependencies) and the first pooling unit (which compresses the two-dimensional feature map into a one-dimensional vector while retaining global statistical features) are used for processing. The temporal features (dynamic characteristics) of the single modality are then concatenated with the pooled global features (static characteristics) along the channel dimension to form a hybrid feature vector. Finally, the dual-modal features are concatenated a second time to form a comprehensive feature space, thereby achieving cross-modal feature interaction and preserving the implicit correlation between electronic pump parameters. This avoids the problem of feature correlation loss caused by the independent processing of vibration and other types of signals in traditional methods, and is more conducive to accurately identifying the working state of the electronic pump. This embodiment of the invention is not limited.

[0123] It is evident that implementing the electronic pump fault diagnosis method described in this embodiment of the invention is beneficial for feature mining and analysis of multi-source signal information collected by the electronic pump, thereby overcoming problems such as multi-source signal coupling, noise interference, and feature drift, and improving the fault diagnosis accuracy and reliability of the electronic pump.

[0124] In another alternative embodiment, the target fault diagnosis model is obtained based on the following:

[0125] Obtain a fault signal training sample set; the fault signal training sample set includes several fault signal training samples;

[0126] Based on the fault signal training samples in the fault signal training sample set, a backup training sample set is determined; the backup training sample set includes K backup training samples.

[0127] The basic fault diagnosis model is trained using a spare training sample set to obtain intermediate training results.

[0128] The intermediate training results are processed using a loss function model to obtain loss function values; the loss function values ​​include K loss function values.

[0129] Determine whether the loss function value information meets the first termination condition to obtain the first determination result; the first termination condition includes that the number of training times in the intermediate training result information is greater than or equal to the number of training times threshold, and / or that all loss function values ​​in the loss function value information are located in the loss function value range;

[0130] When the first judgment result is negative, the training fault diagnosis model in the intermediate training result information is determined as the new basic fault diagnosis model, and the execution of the fault signal training sample based on the fault signal training sample set is triggered to determine the backup training sample set.

[0131] When the first judgment result is yes, the trained fault diagnosis model is determined as the target fault diagnosis model.

[0132] It should be noted that the above loss function model is the cross-entropy loss function, and this embodiment of the invention is not limited thereto.

[0133] It should be noted that the above threshold number is an integer value between [50, 60], and this embodiment of the invention does not limit it.

[0134] It should be noted that the above loss function value range is [0.1, 0.2], and this embodiment of the invention does not limit it.

[0135] It should be noted that K is an integer value between [10, 15], and this embodiment of the invention does not limit it.

[0136] It should be noted that the initial value of the above training times is 0. Each time the basic fault diagnosis model is trained using a spare training sample, its value is automatically incremented by 1. This embodiment of the invention does not limit this.

[0137] It should be noted that the above training can be performed on a device with a 2080ti GPU, an Intel Core i7 processor, and an SSD with a capacity of 512GB or more, with a learning rate of no more than 0.001. Such a computer device can provide powerful parallel computing capabilities, which can significantly speed up the training of the model.

[0138] It should be noted that the model architecture of the basic fault diagnosis model, the trained fault diagnosis model and the target fault diagnosis model mentioned above is consistent, and the embodiments of the present invention do not limit it.

[0139] It should be noted that the above-mentioned determination of the backup training sample set based on the fault signal training sample set is to randomly select K fault signal training samples from the fault signal training sample set as backup training samples, and this embodiment of the present invention does not limit this.

[0140] It should be noted that the above-mentioned training of the basic fault diagnosis model using the spare training sample set to obtain intermediate training result information is achieved by training the basic fault diagnosis model K times in sequence using K spare training samples. The subsequent spare training sample trains the basic fault diagnosis model trained by the previous spare training sample, and the basic fault diagnosis model trained by the last spare training sample is used as the training fault diagnosis model. This embodiment of the invention does not limit this.

[0141] It should be noted that the above-mentioned fault signal training samples are obtained by selecting data collection of electronic pumps that fail at different times and locations and then labeling them. There are no fewer than 100 samples of different types of faults and no fewer than 1,000 fault signal training samples in total. This embodiment of the invention does not limit the number of samples.

[0142] It is evident that implementing the electronic pump fault diagnosis method described in this embodiment of the invention is beneficial for feature mining and analysis of multi-source signal information collected by the electronic pump, thereby overcoming problems such as multi-source signal coupling, noise interference, and feature drift, and improving the fault diagnosis accuracy and reliability of the electronic pump.

[0143] Example 2

[0144] Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of an electronic pump fault diagnosis system disclosed in an embodiment of the present invention. Figure 3 The described system can be applied to management systems, such as local servers or cloud servers, and this invention does not limit its application. Figure 3 As shown, the system may include:

[0145] The acquisition module 201 is used to acquire electronic pump signal information to be transmitted; the electronic pump signal information to be transmitted includes first electronic pump signal information and second electronic pump signal information.

[0146] The first processing module 202 is used to preprocess the electronic pump signal information to be transmitted to obtain the target processed signal information;

[0147] The second processing module 203 is used to analyze and process the target processing signal information to obtain fault diagnosis result information.

[0148] It is evident that implementation Figure 3 The described electronic pump fault diagnosis system is beneficial for feature mining and analysis of multi-source signal information collected by electronic pumps, so as to overcome problems such as multi-source signal coupling, noise interference and feature drift, and improve the fault diagnosis accuracy and reliability of electronic pumps.

[0149] In another alternative embodiment, such as Figure 3 As shown, the electronic pump signal information to be transmitted is preprocessed to obtain the target processing signal information, including:

[0150] Alignment processing is performed on the first electronic pump signal information and the second electronic pump signal information in the electronic pump signal information to be transmitted to obtain the first processed signal information and the second processed signal information.

[0151] The first processed signal information and the second processed signal information are normalized to obtain the first target signal information and the second target signal information;

[0152] The first target signal information and the second target signal information are spliced ​​together to obtain the target processing signal information.

[0153] It is evident that implementation Figure 3 The described electronic pump fault diagnosis system is beneficial for feature mining and analysis of multi-source signal information collected by electronic pumps, so as to overcome problems such as multi-source signal coupling, noise interference and feature drift, and improve the fault diagnosis accuracy and reliability of electronic pumps.

[0154] In yet another alternative embodiment, such as Figure 3 As shown, the target processing signal information is analyzed and processed to obtain fault diagnosis results, including:

[0155] The target fault diagnosis model is used to perform diagnostic analysis on the target processing signal information to obtain signal diagnosis results.

[0156] The signal diagnostic results are processed by time-series visualization to obtain the fault diagnosis results.

[0157] It is evident that implementation Figure 3 The described electronic pump fault diagnosis system is beneficial for feature mining and analysis of multi-source signal information collected by electronic pumps, so as to overcome problems such as multi-source signal coupling, noise interference and feature drift, and improve the fault diagnosis accuracy and reliability of electronic pumps.

[0158] In yet another alternative embodiment, such as Figure 3 As shown, the target fault diagnosis model includes a first feature extraction module, a second feature extraction module, a feature fusion module, and a feature diagnosis module; among which,

[0159] The first feature extraction module is used to perform hierarchical spatial feature extraction on the target processing signal information;

[0160] The second feature extraction module is used to extract temporal features from the target processing signal information;

[0161] The feature fusion module is used to fuse multiple feature information.

[0162] The feature diagnosis module is used to perform nonlinear feature analysis on feature information in order to analyze and identify the state type of the electronic pump.

[0163] It is evident that implementation Figure 3The described electronic pump fault diagnosis system is beneficial for feature mining and analysis of multi-source signal information collected by electronic pumps, so as to overcome problems such as multi-source signal coupling, noise interference and feature drift, and improve the fault diagnosis accuracy and reliability of electronic pumps.

[0164] In yet another alternative embodiment, such as Figure 3 As shown, the input terminals of the first feature extraction module and the second feature extraction module are both configured to receive target processing signal information; the output terminals of the first feature extraction module and the second feature extraction module are both connected to the input terminal of the feature fusion module; the output terminal of the feature fusion module is connected to the input terminal of the feature diagnosis module; and the output terminal of the feature diagnosis module is configured to output signal diagnosis result information.

[0165] It is evident that implementation Figure 3 The described electronic pump fault diagnosis system is beneficial for feature mining and analysis of multi-source signal information collected by electronic pumps, so as to overcome problems such as multi-source signal coupling, noise interference and feature drift, and improve the fault diagnosis accuracy and reliability of electronic pumps.

[0166] In yet another alternative embodiment, such as Figure 3 As shown, the first feature extraction module includes a first convolutional unit, a second convolutional unit, a first normalization unit, a second normalization unit, a third normalization unit, a fourth normalization unit, a first activation unit, a second activation unit, a first random deactivation unit, a second random deactivation unit, a third random deactivation unit, a first pooling unit, a first connection unit, a first fusion unit, and a first neural network; wherein,

[0167] The input of the first convolutional unit is configured as the input of the first feature extraction module; the first convolutional unit, the first normalization unit, the first activation unit, the first random deactivation unit, the second convolutional unit, the second normalization unit, the second activation unit, and the second random deactivation unit are connected sequentially; the output of the second random deactivation unit is connected to the input of the first pooling unit and the input of the first neural network; the output of the first pooling unit is connected to the input of the first connection unit; the output of the first connection unit is connected to the input of the fourth normalization unit; the output of the fourth normalization unit is connected to the input of the first fusion unit; the output of the first neural network is connected to the input of the third normalization unit; the output of the third normalization unit is connected to the input of the first fusion unit; the output of the first fusion unit is connected to the input of the third random deactivation unit; the output of the third random deactivation unit is configured as the output of the first feature extraction module.

[0168] It is evident that implementation Figure 3The described electronic pump fault diagnosis system is beneficial for feature mining and analysis of multi-source signal information collected by electronic pumps, so as to overcome problems such as multi-source signal coupling, noise interference and feature drift, and improve the fault diagnosis accuracy and reliability of electronic pumps.

[0169] In yet another alternative embodiment, such as Figure 3 As shown, the target fault diagnosis model is obtained based on the following method:

[0170] Obtain a fault signal training sample set; the fault signal training sample set includes several fault signal training samples;

[0171] Based on the fault signal training samples in the fault signal training sample set, a backup training sample set is determined; the backup training sample set includes K backup training samples.

[0172] The basic fault diagnosis model is trained using a spare training sample set to obtain intermediate training results.

[0173] The intermediate training results are processed using a loss function model to obtain loss function values; the loss function values ​​include K loss function values.

[0174] Determine whether the loss function value information meets the first termination condition to obtain the first determination result; the first termination condition includes that the number of training times in the intermediate training result information is greater than or equal to the number of training times threshold, and / or that all loss function values ​​in the loss function value information are located in the loss function value range;

[0175] When the first judgment result is negative, the training fault diagnosis model in the intermediate training result information is determined as the new basic fault diagnosis model, and the execution of the fault signal training sample based on the fault signal training sample set is triggered to determine the backup training sample set.

[0176] When the first judgment result is yes, the trained fault diagnosis model is determined as the target fault diagnosis model.

[0177] It is evident that implementation Figure 3 The described electronic pump fault diagnosis system is beneficial for feature mining and analysis of multi-source signal information collected by electronic pumps, so as to overcome problems such as multi-source signal coupling, noise interference and feature drift, and improve the fault diagnosis accuracy and reliability of electronic pumps.

[0178] Example 3

[0179] Please see Figure 4 , Figure 4 This is a schematic diagram of another electronic pump fault diagnosis system disclosed in an embodiment of the present invention. Figure 4The described system can be applied to management systems, such as local servers or cloud servers, and this invention does not limit its application. Figure 4 As shown, the system may include:

[0180] Memory 301 storing executable program code;

[0181] Processor 302 coupled to memory 301;

[0182] The processor 302 calls the executable program code stored in the memory 301 to execute the steps in the electronic pump fault diagnosis method described in Embodiment 1.

[0183] Example 4

[0184] This invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps in the electronic pump fault diagnosis method described in Embodiment 1.

[0185] Example 5

[0186] This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps in the electronic pump fault diagnosis method described in Embodiment 1.

[0187] The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0188] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0189] Finally, it should be noted that the electronic pump fault diagnosis system and method disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for diagnosing faults in an electronic pump, characterized in that, The method includes: Acquire the electronic pump signal information to be transmitted; the electronic pump signal information to be transmitted includes first electronic pump signal information and second electronic pump signal information; The electronic pump signal information to be transmitted is preprocessed to obtain the target processing signal information; The target processing signal information is analyzed and processed to obtain fault diagnosis result information; The step of preprocessing the electronic pump signal information to be transmitted to obtain the target processing signal information includes: The first electronic pump signal information and the second electronic pump signal information in the electronic pump signal information to be transmitted are aligned to obtain first processed signal information and second processed signal information. The first processed signal information and the second processed signal information are normalized to obtain the first target signal information and the second target signal information; The first target signal information and the second target signal information are spliced ​​together to obtain target processing signal information; The step of analyzing and processing the target processing signal information to obtain fault diagnosis result information includes: The target processing signal information is diagnosed and analyzed using a target fault diagnosis model to obtain signal diagnosis result information. The signal diagnostic results are processed by time-series visualization to obtain fault diagnostic results. The target fault diagnosis model includes a first feature extraction module, a second feature extraction module, a feature fusion module, and a feature diagnosis module; wherein, The first feature extraction module is used to perform hierarchical spatial feature extraction on the target processing signal information; The second feature extraction module is used to extract temporal features from the target processing signal information; The feature fusion module is used to fuse multiple feature information; The feature diagnosis module is used to perform nonlinear feature analysis on feature information in order to analyze and identify the state type of the electronic pump; The input terminals of the first feature extraction module and the second feature extraction module are both configured to receive the target processing signal information; the output terminals of the first feature extraction module and the second feature extraction module are both connected to the input terminal of the feature fusion module; the output terminal of the feature fusion module is connected to the input terminal of the feature diagnosis module; and the output terminal of the feature diagnosis module is configured to output the signal diagnosis result information.

2. The electronic pump fault diagnosis method according to claim 1, characterized in that, The first feature extraction module includes a first convolutional unit, a second convolutional unit, a first normalization unit, a second normalization unit, a third normalization unit, a fourth normalization unit, a first activation unit, a second activation unit, a first random deactivation unit, a second random deactivation unit, a third random deactivation unit, a first pooling unit, a first connection unit, a first fusion unit, and a first neural network; wherein, The input of the first convolutional unit is configured as the input of the first feature extraction module; the first convolutional unit, the first normalization unit, the first activation unit, the first random deactivation unit, the second convolutional unit, the second normalization unit, the second activation unit, and the second random deactivation unit are connected sequentially; the output of the second random deactivation unit is connected to the input of the first pooling unit and the input of the first neural network; the output of the first pooling unit is connected to the input of the first connection unit; the output of the first connection unit is connected to the input of the fourth normalization unit; the output of the fourth normalization unit is connected to the input of the first fusion unit; the output of the first neural network is connected to the input of the third normalization unit; the output of the third normalization unit is connected to the input of the first fusion unit; the output of the first fusion unit is connected to the input of the third random deactivation unit; the output of the third random deactivation unit is configured as the output of the first feature extraction module.

3. The electronic pump fault diagnosis method according to claim 1, characterized in that, The target fault diagnosis model was obtained based on the following method: Obtain a fault signal training sample set; the fault signal training sample set includes several fault signal training samples; Based on the fault signal training samples in the fault signal training sample set, a backup training sample set is determined; the backup training sample set includes K backup training samples. The basic fault diagnosis model is trained using the backup training sample set to obtain intermediate training results. The intermediate training results are processed using a loss function model to obtain loss function value information; the loss function value information includes K loss function values. Determine whether the loss function value information meets the first termination condition to obtain a first determination result; the first termination condition includes that the number of training times in the intermediate training result information is greater than or equal to the number of training times threshold, and / or that all loss function values ​​in the loss function value information are located in the loss function value range; When the first judgment result is negative, the training fault diagnosis model in the intermediate training result information is determined as the new basic fault diagnosis model, and the execution of the fault signal training samples based on the fault signal training sample set is triggered to determine the backup training sample set. When the first judgment result is yes, the trained fault diagnosis model is determined to be the target fault diagnosis model.

4. An electronic pump fault diagnosis system, characterized in that, The system includes: The acquisition module is used to acquire electronic pump signal information to be transmitted; the electronic pump signal information to be transmitted includes first electronic pump signal information and second electronic pump signal information. The first processing module is used to preprocess the electronic pump signal information to be transmitted to obtain the target processing signal information; The second processing module is used to analyze and process the target processing signal information to obtain fault diagnosis result information; The step of preprocessing the electronic pump signal information to be transmitted to obtain the target processing signal information includes: The first electronic pump signal information and the second electronic pump signal information in the electronic pump signal information to be transmitted are aligned to obtain first processed signal information and second processed signal information. The first processed signal information and the second processed signal information are normalized to obtain the first target signal information and the second target signal information; The first target signal information and the second target signal information are spliced ​​together to obtain target processing signal information; The step of analyzing and processing the target processing signal information to obtain fault diagnosis result information includes: The target processing signal information is diagnosed and analyzed using a target fault diagnosis model to obtain signal diagnosis result information. The signal diagnostic results are processed by time-series visualization to obtain fault diagnostic results. The target fault diagnosis model includes a first feature extraction module, a second feature extraction module, a feature fusion module, and a feature diagnosis module; wherein, The first feature extraction module is used to perform hierarchical spatial feature extraction on the target processing signal information; The second feature extraction module is used to extract temporal features from the target processing signal information; The feature fusion module is used to fuse multiple feature information; The feature diagnosis module is used to perform nonlinear feature analysis on feature information in order to analyze and identify the state type of the electronic pump; The input terminals of the first feature extraction module and the second feature extraction module are both configured to receive the target processing signal information; the output terminals of the first feature extraction module and the second feature extraction module are both connected to the input terminal of the feature fusion module; the output terminal of the feature fusion module is connected to the input terminal of the feature diagnosis module; and the output terminal of the feature diagnosis module is configured to output the signal diagnosis result information.

5. An electronic pump fault diagnosis system, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the electronic pump fault diagnosis method as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which, when invoked, are used to execute the electronic pump fault diagnosis method as described in any one of claims 1-3.

Images