An intelligent system and method for remote control and fault diagnosis of construction machinery

Abstract

The application discloses an intelligent system and method for remote control and fault diagnosis of engineering machinery, and the method comprises the following steps: acquiring equipment collection data information; the equipment collection data information comprises a plurality of basic collection data information; performing analysis and processing on the equipment collection data information to obtain target processing data information; and performing diagnosis and analysis processing on the target processing data information to obtain target equipment state information.

Description

Technical Field

[0001] This invention relates to the field of engineering machinery technology, and in particular to an intelligent system and method for remote control and fault diagnosis of engineering machinery. Background Technology

[0002] With the widespread application of construction machinery in fields such as construction, mining, and transportation, its operational reliability and maintenance efficiency have become key factors restricting the industry's development. Traditional construction machinery fault diagnosis mainly relies on manual experience judgment, regular maintenance inspections, or sensor alarm systems based on simple threshold judgments, resulting in significant diagnostic lag and high false alarm rates. Although remote control technology has been gradually applied to the operation of construction machinery in recent years, fault diagnosis is still limited to the initial stage of data acquisition and remote alarm, lacking intelligent analysis and prediction capabilities for equipment operating status. Among existing technologies, expert system-based diagnostic methods can handle some typical faults, but suffer from difficulties in updating the knowledge base and inability to cope with complex working conditions; vibration signal analysis-based diagnostic technologies have stringent requirements for sensor deployment and cannot effectively handle multi-source heterogeneous data; while some traditional machine learning methods have achieved certain results in specific scenarios, they face bottlenecks such as strong dependence on feature engineering and insufficient model generalization ability. In addition, existing remote monitoring systems mostly adopt fixed communication protocols and centralized data processing architectures, which are difficult to meet the real-time diagnostic needs of construction machinery in mobile operation scenarios, resulting in response delays when dealing with sudden faults, which may lead to serious safety accidents. Therefore, an intelligent system and method for remote control and fault diagnosis of construction machinery are provided to improve the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of construction machinery. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide an intelligent system and method for remote control and fault diagnosis of engineering machinery, which is conducive to improving the accuracy and efficiency of fault diagnosis, thereby improving the intelligent operation and maintenance efficiency of engineering machinery.

[0004] To address the aforementioned technical problems, a first aspect of the present invention discloses an intelligent diagnostic method, the method comprising: Acquire device-collected data information; the device-collected data information includes several basic data collection information. The data collected by the device is analyzed and processed to obtain the target processed data. The target processing data information is processed for diagnosis and analysis to obtain the target device status information.

[0005] A second aspect of this invention discloses an intelligent diagnostic system, the system comprising: The acquisition module is used to acquire device-collected data information; the device-collected data information includes several basic acquisition data information. The first processing module is used to analyze and process the data information collected by the device to obtain the target processed data information; The second processing module is used to perform diagnostic analysis on the target processing data information to obtain the target device status information.

[0006] A third aspect of the present invention discloses another intelligent diagnostic system, the system comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the intelligent diagnostic method disclosed in the first aspect of the present invention.

[0007] The fourth aspect of the present invention discloses a computer-readable storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the intelligent diagnostic method disclosed in the first aspect of the present invention. Attached Figure Description

[0008] 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.

[0009] Figure 1 This is a schematic diagram of a scenario for the intelligent diagnostic system provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating an intelligent diagnostic method disclosed in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an intelligent diagnostic system disclosed in an embodiment of the present invention; Figure 4 This is a schematic diagram of another intelligent diagnostic system disclosed in an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of a target diagnostic model disclosed in an embodiment of the present invention. Detailed Implementation

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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.

[0014] 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.

[0015] 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.

[0016] 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)."

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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.

[0025] This application provides an intelligent diagnostic method, system, computer device, and computer-readable storage medium, which will be described in detail below.

[0026] Please see Figure 1 , Figure 1 This is a schematic diagram of a scenario for the intelligent diagnostic system provided in an embodiment of this application. The intelligent diagnostic system may include a computer device 100, which integrates the intelligent diagnostic system, such as... Figure 1 Computer equipment in the country.

[0027] In this embodiment, the computer device 100 is mainly used to acquire device-collected data information; the device-collected data information includes several basic data acquisition information. The data collected by the device is analyzed and processed to obtain the target processed data. The target processing data information is processed for diagnosis and analysis to obtain the target device status information.

[0028] It can improve the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of construction machinery.

[0029] 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.

[0030] 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.

[0031] 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 document. It is understood that the intelligent diagnostic system may also include one or more other services, which are not limited here.

[0032] In addition, such as Figure 1 As shown, the intelligent diagnostic system may also include a memory 200 for storing data, such as image data and location information.

[0033] It should be noted that, Figure 1 The schematic diagram of the intelligent diagnostic system shown is merely an example. The intelligent diagnostic system and scenarios described in this application are intended to more clearly illustrate 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 intelligent diagnostic systems and the emergence of new business scenarios, the technical solutions provided in this application are also applicable to similar technical problems.

[0034] This invention discloses an intelligent system and method for remote control and fault diagnosis of construction machinery, which helps to improve the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of construction machinery. Detailed descriptions follow.

[0035] Example 1 Please see Figure 2 , Figure 2 This is a flowchart illustrating an intelligent diagnostic method disclosed in an embodiment of the present invention. Figure 2 The described intelligent diagnostic 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, this intelligent diagnostic method may include the following operations: 101. Obtain data information collected by the device.

[0036] In this embodiment of the invention, the data information collected by the device includes several basic data information.

[0037] 102. Analyze and process the data collected by the equipment to obtain the target processing data.

[0038] 103. Perform diagnostic analysis on the target processing data to obtain the target equipment status information.

[0039] It should be noted that the aforementioned basic data acquisition information consists of signal data from engineering machinery collected by sensors, which is then transmitted to a remote intelligent diagnostic system via a communication system, thereby enabling remote control and status diagnosis of the engineering machinery. This embodiment of the invention does not impose limitations on this. Furthermore, the aforementioned basic data acquisition information includes signal data information of types such as pressure, flow, temperature, and vibration. Each type of signal data information includes at least one column of data information. Furthermore, the collected data information is distributed sequentially along a time dimension, which is not limited in this embodiment of the invention.

[0040] It should be noted that due to the complexity of the working environment, the hydraulic system failures of construction machinery have a relatively high degree of randomness, and the failures are relatively complex, including comprehensive failures and ambiguities caused by multiple state problem points. As a result, the current state monitoring of hydraulic systems has not yet been fully developed, especially remote state monitoring and analysis. Therefore, this application combines traditional experience with intelligent technology (sensors + AI models) to solve the problem. Through multi-parameter correlation analysis and remote monitoring platforms, accurate state analysis is achieved, thereby improving the remote control and maintenance capabilities of construction machinery and increasing its operating efficiency. The embodiments of this invention are not limited.

[0041] It should be noted that the above-mentioned target equipment status information represents the operating status of the hydraulic system of the engineering machinery, such as normal operation, hydraulic pump failure, hydraulic valve failure, hydraulic cylinder failure, etc., and the embodiments of the present invention do not limit it.

[0042] It should be noted that the above target processing data information includes three target signal data information, and the dimensions (2D matrix data form) of the target signal data information are consistent. This embodiment of the invention does not limit the dimensions.

[0043] It is evident that implementing the intelligent diagnostic method described in the embodiments of the present invention is beneficial to improving the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of engineering machinery.

[0044] In an optional embodiment, the above-described analysis and processing of the data collected by the device to obtain target processing data includes: The data collected by the equipment is corrected to obtain the target corrected data information; the target corrected data information includes several target corrected data values. The target correction data is split and combined to obtain the target processing data.

[0045] It should be noted that before correcting the data collected by the device, the basic data collected by the device needs to be aligned. This can be done based on a large model to ensure that all collected signal data are consistent in the time dimension, thereby eliminating data gaps caused by device delays and clock differences, and providing an accurate time reference for subsequent data correction. This embodiment of the invention does not limit this.

[0046] It should be noted that the above-mentioned splitting and combining of target correction data information involves dividing the corrected target correction data value information into three equal parts (keeping the time dimension unchanged and dividing the columns from left to right), thereby forming the target signal data information in the target processing data information. This embodiment of the invention does not limit this process. For example (the data in the time dimension is determined based on actual acquisition; the four time dimensions in this example are merely illustrative), the target correction data value information is as follows:

[0047] The target correction data information can then be divided into three sequentially distributed target signal data information: First target signal data information:

[0048] Second target signal data information:

[0049] The third target signal data information:

[0050] It should be noted that after the above three sequentially distributed target signal data information are processed by the first feature extraction module of the target diagnostic model, they are sequentially input into the first sub-feature extraction module, the second sub-feature extraction module, and the third sub-feature extraction module in the second feature extraction module. That is, the first sub-feature extraction module, the second sub-feature extraction module, and the third sub-feature extraction module correspond to the three sequentially distributed target signal data information, so that different sub-feature extraction modules are used to extract the feature information of signals collected by different types of hydraulic systems. This embodiment of the invention does not limit the scope of the invention.

[0051] It is evident that implementing the intelligent diagnostic method described in the embodiments of the present invention is beneficial to improving the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of engineering machinery.

[0052] In another optional embodiment, the data information collected by the device is corrected to obtain target corrected data information, including: For any basic data information collected by the device, identify the missing data value corresponding to the basic data information to obtain the first identification data information corresponding to the basic data information. Abnormal information in the collected data values ​​corresponding to the basic collected data information is identified to obtain the second identification data information corresponding to the basic collected data information. The first and second identification data information are merged to obtain the target identification data information corresponding to the basic collected data information; the target identification data information includes several identification data values; the identification data values ​​are distributed according to the collection order. Based on the target identification data, the target correction data value information corresponding to the basic collected data information is determined.

[0053] It should be noted that the above-mentioned correction processing of the data collected by the equipment is a key step in ensuring data reliability and improving decision-making quality during the remote control and intelligent diagnosis of engineering machinery. This is mainly because the data collected by the equipment is easily affected by sensor failures, environmental interference (such as electromagnetic fields, temperature and humidity changes), or transmission errors. Uncorrected outliers (such as out-of-range temperature readings) or missing values ​​(such as missing pressure records) will directly distort the data analysis results, leading to incorrect control commands or misjudgments of equipment status. By correcting sensor outliers, equipment failures can be accurately predicted, avoiding unplanned downtime. This embodiment of the invention does not limit the scope of the invention.

[0054] It should be noted that the above-mentioned gap identification and anomaly information identification can be implemented based on a large model, or it can be identified by the user through data analysis one by one, or it can be identified according to preset data rules (such as IQR to identify outliers). This embodiment of the invention does not limit these methods.

[0055] It should be noted that the above-mentioned merging of the first and second identification data information is not only to unify and summarize all abnormal data, but also to avoid the coupling of the two types of abnormal data, eliminate the possibility of duplicate analysis, and thus improve the efficiency and reliability of data analysis. This embodiment of the invention does not limit this.

[0056] It is evident that implementing the intelligent diagnostic method described in the embodiments of the present invention is beneficial to improving the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of engineering machinery.

[0057] In another optional embodiment, based on the target identification data information, the target correction data value information corresponding to the basic collected data information is determined, including: Sequentially determine an identifier data value from the target identifier data information as a backup identifier value information, and remove the identifier data value information corresponding to the backup identifier value information from the target identifier data information; The backup identifier value information is calculated and processed using a data correction model to obtain the target identifier value information; The data correction model is as follows: ; In the formula, Characterizes target identifier value information; and These respectively represent the data value preceding the data value corresponding to the backup identifier information and its sort number in the basic data information; and These respectively represent the collected data value that is sorted after the collected data value corresponding to the backup identifier value information and is not identified as the identifier data value information, and its sort number in the basic collected data information; and These respectively characterize the first correction factor and the second correction factor; The collected data values ​​corresponding to the backup identifier values ​​are replaced and updated using the target identifier value information; Determine whether the target identification data information contains identification data value information, and obtain the existence determination result; When the judgment result is yes, the execution is triggered to sequentially determine an identifier data value from the target identifier data information as a backup identifier value information, and remove the identifier data value information corresponding to the backup identifier value information from the target identifier data information; If the judgment result is negative, the updated basic data information will be used as the target correction data value information corresponding to the basic data information.

[0058] It should be noted that the first correction coefficient and the second correction coefficient mentioned above are values ​​between [0,1], such as 0, 1, 0.5, 0.6, and the sum of the two is 1. This embodiment of the invention does not limit the values.

[0059] It should be noted that the above This is the data value collected before the backup identifier value. This is mainly because abnormal data in the target identifier data is corrected sequentially (identifier data is determined as the backup identifier value from the target identifier data in sequence). Therefore, when a later abnormal data is corrected, all data before it are considered normal. To ensure data continuity, the previous data, i.e., the data based on the nearest neighbor principle, is selected as the reference for correcting this data. This is a normal data value that follows the data value corresponding to the backup identifier information. It is not necessarily directly adjacent to the data value corresponding to the backup identifier information, but it still follows the nearest neighbor principle. This is mainly to ensure the continuity of data as much as possible while ensuring the accuracy and reliability of the data, thereby improving the availability of the collected data. This embodiment of the invention does not limit this.

[0060] It should be noted that the above-mentioned calculation and processing of the backup identifier value information using the data correction model to obtain the target identifier value information utilizes both the linear relationship of the absolute values ​​of adjacent normal collected data values ​​and the temporal order relationship (i.e., the sort number) between the absolute values ​​and the collected data values. This fully utilizes the coupling relationship between the time dimension and the absolute value dimension, thereby improving the reliability and accuracy of data correction and making it more conducive to improving the accuracy and efficiency of fault diagnosis. This embodiment of the invention does not limit the scope of the invention.

[0061] It is evident that implementing the intelligent diagnostic method described in the embodiments of the present invention is beneficial to improving the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of engineering machinery.

[0062] In another optional embodiment, diagnostic analysis is performed on the target processing data information to obtain target device status information, including: The target diagnostic model is used to analyze and process the target processing data to obtain the target diagnostic results. The target diagnostic results are transformed and processed to obtain the target device status information.

[0063] It should be noted that the above-mentioned target diagnostic model can be implemented based on Python 3.7.16 or later, trained on an NVIDIA GeForce RTX 4090 graphics card. The training samples can be obtained by users collecting various types of signals from the fault data of construction machinery and labeling them with fault types. During training, the batch size of the samples should be no less than 10, the number of iterations should be no less than 400, the optimizer should be Adam, and the learning rate should be no greater than 1×10. -4 The loss function can be the cross-entropy loss function, and the trained model can be evaluated using accuracy, recall, F1 score, and false negative rate. This embodiment of the invention does not limit the specific loss function.

[0064] It should be noted that the overall performance of the intelligent state diagnosis proposed in this application has a significant advantage over DNN and SVM algorithms. The test results of its various performance metrics under the same training samples are as follows:

[0065] It should be noted that the above-mentioned target diagnostic results information represents the classification probability value in the time dimension, and this embodiment of the invention does not limit this.

[0066] In this optional embodiment, as an optional implementation method, the above-described conversion processing of the target diagnostic result information to obtain the target device status information includes: Obtain the state relationship mapping table; Based on the state relationship mapping table, the classification probability value in the target diagnosis result information is looked up to obtain the equipment operating status information. The device's operating status information is visualized to obtain the target device's status information.

[0067] It should be noted that the above-mentioned equipment operating status information includes several equipment operating statuses, and this embodiment of the invention does not limit them.

[0068] It should be noted that the above state relationship mapping table can be:

[0069] It should be noted that the above-mentioned visualization of device operation status information involves generating the device operation status in the device operation status information in chronological order in a list form as data that can be displayed on a display terminal (such as a monitor). This can be implemented based on a large model, and this embodiment of the invention does not limit it.

[0070] It is evident that implementing the intelligent diagnostic method described in the embodiments of the present invention is beneficial to improving the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of engineering machinery.

[0071] In an optional embodiment, the target diagnostic model includes a first feature extraction module, a second feature extraction module, a third feature extraction module, and a diagnostic recognition module; wherein, The first feature extraction module is configured to perform local feature extraction on the target processing data information; The second feature extraction module is configured to enhance the salient features extracted by the first feature extraction module and suppress the non-salient features extracted by the first feature extraction module. The third feature extraction module is configured to perform global feature extraction; The diagnostic identification module is configured to classify and identify the extracted features to obtain target diagnostic result information.

[0072] It should be noted that the aforementioned first feature extraction module can be constructed based on an RNN, using convolutional layers to convolve the sequentially input target signal data information, followed by pooling layers to obtain three corresponding local feature data information. This embodiment of the invention does not impose any limitations on this. Furthermore, the convolutional kernel in the first feature extraction module can be one of 1×1, 3×1, 3×3, 5×1, 5×3, 5×5, 7×5, and 7×7, with a stride of 1 or 2. This embodiment of the invention does not impose any limitations on this.

[0073] It should be noted that the second feature extraction module uses three parallel branches to perform nonlinear feature extraction on the local features extracted by the first extraction module. By allocating weighted features, the extraction of significant features is improved while the extraction of non-significant features is suppressed, thereby improving the extraction of effective features. Each branch does not correspond to the same input data, but is for different types of signal features of the hydraulic system. Feature fusion is performed at the end of the second feature extraction module, which can improve the nonlinear feature extraction capability of the target diagnostic model, effectively improve the feature fitting of complex data such as multi-type signals of complex systems like hydraulic systems, thereby improving the ability to extract operating state information from signals, and making it more conducive to capturing the operating state regularity features in the data, thereby improving the accuracy and reliability of the system's operating state analysis. This embodiment of the invention is not limited.

[0074] It should be noted that the aforementioned third feature extraction module constructs an understanding of the whole (global) by gradually integrating and analyzing details (local). That is, through hierarchical and progressive information processing and fusion, it overcomes the limitation of processing all information at once, effectively transforming the original low-level features into high-level, semantic features, enabling distant local features to influence each other through information flow, and assigning each local feature its position and role information in the whole. It can be built based on graph neural networks, and this embodiment of the invention does not limit it.

[0075] It should be noted that the above-mentioned diagnostic identification module includes a deactivation layer, a fully connected layer and an activation function layer (softmax function) connected in sequence to accurately convert the extracted features into probability values ​​that characterize the operating state of the hydraulic system. This embodiment of the invention does not limit the scope of the invention.

[0076] It is evident that implementing the intelligent diagnostic method described in the embodiments of the present invention is beneficial to improving the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of engineering machinery.

[0077] In another optional embodiment, the second feature extraction module includes a first sub-feature extraction module, a second sub-feature extraction module, a third sub-feature extraction module, and a third fusion unit; wherein, The first sub-feature extraction module includes a first transformation unit, a first pooling unit, a first convolution unit, a first connection unit, a second connection unit, a first activation unit, a first fusion unit, and a second fusion unit; wherein, The input of the first transformation unit is configured to receive input data from the input of the first sub-feature extraction module; the output of the first transformation unit is connected to the input of the first pooling unit and the input of the second fusion unit; the first pooling unit, the first convolution unit, the first connection unit, the second connection unit, and the first activation unit are connected sequentially; the input of the first fusion unit is configured to receive input data from the input of the first sub-feature extraction module and output data from the output of the first activation unit; the output of the first fusion 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 sub-feature extraction module.

[0078] It should be noted that the model architecture of the first, second, and third sub-feature extraction modules is consistent, and this embodiment of the invention does not limit this. Furthermore, the first, second, and third sub-feature extraction modules are three independent branches. That is, after feature extraction from three independent data points by the first feature extraction module, a rotation operation is used to fuse the channel features with a specific spatial dimension (such as horizontal or vertical). The spatial dimension dependencies of each channel are handled independently (e.g., calculating the weights of different positions within the channel). Any spatial axis (determined by the first transformation unit) is selected for connection, highlighting key information. This allows the model to focus on the features most relevant to the hydraulic system's operating state, improving the target diagnostic model's ability to focus on key data signals and further enhancing the accuracy and efficiency of fault diagnosis. This embodiment of the invention does not limit this. Furthermore, the conversion operations of the first conversion units corresponding to the first sub-feature extraction module, the second sub-feature extraction module, and the third sub-feature extraction module are respectively clockwise rotation of 90°, counterclockwise rotation of 90°, and rotation of 0°, so as to focus on the correlation feature relationship between channel C and space W, channel C and space H, and space W and space H in the three-dimensional feature map extracted by the first feature extraction module. This embodiment of the invention does not limit this.

[0079] It should be noted that the above-mentioned analysis of the hydraulic system signal using three feature extraction branches is because it also takes into account that due to the complexity of the working environment of the hydraulic system of construction machinery, its pressure, flow, vibration and other signals reflect feature information in different dimensions, and each signal reflects the system's operating status with different emphases. If too much attention is paid to irrelevant signal features of the hydraulic system of construction machinery, it will not be conducive to the target diagnostic model capturing important operating status information. Therefore, each branch first uses the first transformation unit to rotate the feature map extracted by the first feature extraction module, and uses the first activation unit in each sub-feature extraction module to generate the result attention weight, thereby increasing the attention weight of the salient features of the channel in each individual channel branch, extracting more relevant signal features, and thus realizing the extraction of more relevant feature information from different dimensions. This embodiment of the invention is not limited.

[0080] It should be noted that the first pooling unit mentioned above is constructed based on the Z-pooling layer. By aggregating the maximum and mean values ​​of the channel dimensions of the input tensor in parallel, a dual-channel feature map is generated. This operation significantly reduces the channel depth to a fixed dimension while preserving the key statistical information (extreme values ​​and distribution) of the original tensor. This embodiment of the invention does not limit this.

[0081] It should be noted that the convolution kernel of the first convolution unit can be one of 1×1, 3×1, 3×3, 5×1, 5×3, 5×5, 7×5 and 7×7, with a stride of 1 or 2. This embodiment of the invention does not limit the type of kernel.

[0082] It should be noted that the first connection unit and the second connection unit mentioned above are constructed based on a fully connected layer, and this embodiment of the present invention does not limit them.

[0083] It should be noted that the first activation unit mentioned above is constructed based on the softmax activation function, and this embodiment of the present invention does not limit it.

[0084] It should be noted that the first, second, and third fusion units described above are constructed based on element-wise addition operations, and this embodiment of the invention does not impose limitations on them. Furthermore, the first and second fusion units are feature fusions of two residual structures within the same sub-feature extraction module, achieving feature fusions of different depths and feature weights, which is more conducive to focusing on feature information more relevant to the hydraulic system; this embodiment of the invention does not impose limitations on them. Furthermore, the third fusion unit can obtain more refined feature information from the average vector input from three dimensions; this embodiment of the invention does not impose limitations on it.

[0085] It is evident that implementing the intelligent diagnostic method described in the embodiments of the present invention is beneficial to improving the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of engineering machinery.

[0086] Example 2 Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of an intelligent diagnostic 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: The acquisition module 201 is used to acquire device-collected data information; the device-collected data information includes several basic data acquisition information. The first processing module 202 is used to analyze and process the data information collected by the device to obtain the target processing data information; The second processing module 203 is used to perform diagnostic analysis on the target processing data information to obtain the target device status information.

[0087] It is evident that implementation Figure 3 The described intelligent diagnostic system helps improve the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of construction machinery.

[0088] In another alternative embodiment, such as Figure 3 As shown, the data collected by the device is analyzed and processed to obtain the target processing data, including: The data collected by the equipment is corrected to obtain the target corrected data information; the target corrected data information includes several target corrected data values. The target correction data is split and combined to obtain the target processing data.

[0089] It is evident that implementation Figure 3 The described intelligent diagnostic system helps improve the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of construction machinery.

[0090] In yet another alternative embodiment, such as Figure 3 As shown, the data collected by the device is corrected to obtain the target corrected data, including: For any basic data information collected by the device, identify the missing data value corresponding to the basic data information to obtain the first identification data information corresponding to the basic data information. Abnormal information in the collected data values ​​corresponding to the basic collected data information is identified to obtain the second identification data information corresponding to the basic collected data information. The first and second identification data information are merged to obtain the target identification data information corresponding to the basic collected data information; the target identification data information includes several identification data values; the identification data values ​​are distributed according to the collection order. Based on the target identification data, the target correction data value information corresponding to the basic collected data information is determined.

[0091] It is evident that implementation Figure 3 The described intelligent diagnostic system helps improve the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of construction machinery.

[0092] In yet another alternative embodiment, such as Figure 3 As shown, based on the target identification data information, the target correction data value information corresponding to the basic collected data information is determined, including: Sequentially determine an identifier data value from the target identifier data information as a backup identifier value information, and remove the identifier data value information corresponding to the backup identifier value information from the target identifier data information; The backup identifier value information is calculated and processed using a data correction model to obtain the target identifier value information; The data correction model is as follows: ; In the formula, Characterizes target identifier value information; and These respectively represent the data value preceding the data value corresponding to the backup identifier information and its sort number in the basic data information; and These respectively represent the collected data value that is sorted after the collected data value corresponding to the backup identifier value information and is not identified as the identifier data value information, and its sort number in the basic collected data information; and These respectively characterize the first correction factor and the second correction factor; The collected data values ​​corresponding to the backup identifier values ​​are replaced and updated using the target identifier value information; Determine whether the target identification data information contains identification data value information, and obtain the existence determination result; When the judgment result is yes, the execution is triggered to sequentially determine an identifier data value from the target identifier data information as a backup identifier value information, and remove the identifier data value information corresponding to the backup identifier value information from the target identifier data information; If the judgment result is negative, the updated basic data information will be used as the target correction data value information corresponding to the basic data information.

[0093] It is evident that implementation Figure 3 The described intelligent diagnostic system helps improve the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of construction machinery.

[0094] In yet another alternative embodiment, such as Figure 3 As shown, diagnostic analysis is performed on the target processing data to obtain the target device status information, including: The target diagnostic model is used to analyze and process the target processing data to obtain the target diagnostic results. The target diagnostic results are transformed and processed to obtain the target device status information.

[0095] It is evident that implementation Figure 3 The described intelligent diagnostic system helps improve the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of construction machinery.

[0096] In yet another alternative embodiment, such as Figure 3 As shown, the target diagnostic model includes a first feature extraction module, a second feature extraction module, a third feature extraction module, and a diagnostic recognition module; among which, The first feature extraction module is configured to perform local feature extraction on the target processing data information; The second feature extraction module is configured to enhance the salient features extracted by the first feature extraction module and suppress the non-salient features extracted by the first feature extraction module. The third feature extraction module is configured to perform global feature extraction; The diagnostic identification module is configured to classify and identify the extracted features to obtain target diagnostic result information.

[0097] It is evident that implementation Figure 3 The described intelligent diagnostic system helps improve the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of construction machinery.

[0098] In yet another alternative embodiment, such as Figure 3 As shown, the second feature extraction module includes a first sub-feature extraction module, a second sub-feature extraction module, a third sub-feature extraction module, and a third fusion unit; wherein, The first sub-feature extraction module includes a first transformation unit, a first pooling unit, a first convolution unit, a first connection unit, a second connection unit, a first activation unit, a first fusion unit, and a second fusion unit; wherein, The input of the first transformation unit is configured to receive input data from the input of the first sub-feature extraction module; the output of the first transformation unit is connected to the input of the first pooling unit and the input of the second fusion unit; the first pooling unit, the first convolution unit, the first connection unit, the second connection unit, and the first activation unit are connected sequentially; the input of the first fusion unit is configured to receive input data from the input of the first sub-feature extraction module and output data from the output of the first activation unit; the output of the first fusion 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 sub-feature extraction module.

[0099] It is evident that implementation Figure 3 The described intelligent diagnostic system helps improve the accuracy and efficiency of fault diagnosis, thereby enhancing the intelligent operation and maintenance efficiency of construction machinery.

[0100] Example 3 Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of another intelligent diagnostic system disclosed in an embodiment of the present invention. Wherein, Figure 4 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 4 As shown, the system may include: Memory 301 storing executable program code; Processor 302 coupled to memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps in the intelligent diagnostic method described in Embodiment 1.

[0101] Example 4 This invention discloses a computer-readable storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to perform the steps in the intelligent diagnostic method described in Embodiment 1.

[0102] Example 5 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 intelligent diagnostic method described in Embodiment 1.

[0103] 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.

[0104] 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.

[0105] Finally, it should be noted that the intelligent system and method for remote control and fault diagnosis of engineering machinery 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; and these 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. An intelligent diagnostic method, characterized in that, The method includes: Acquire device-collected data information; the device-collected data information includes several basic data collection information. The data information collected by the device is analyzed and processed to obtain target processed data information; the analysis and processing includes correcting the data information collected by the device to obtain target corrected data information; the target corrected data information includes several target corrected data value information. The target correction data information is split and combined to obtain the target processing data information; For any of the basic data acquisition information in the data information collected by the device, based on the target identification data information corresponding to the basic data acquisition information, the target correction data value information corresponding to the basic data acquisition information is determined. Specifically, this includes: Sequentially determine an identifier data value from the target identifier data information as a backup identifier value, and remove the identifier data value corresponding to the backup identifier value from the target identifier data information; The backup identifier value information is calculated and processed using a data correction model to obtain the target identifier value information; The data correction model is as follows: ； In the formula, Characterizes the target identifier value information; and These respectively represent the data value preceding the data value corresponding to the backup identifier information and its sort number in the basic data information; and These respectively represent the collected data value that is ordered after the collected data value corresponding to the backup identifier value information and is not identified as the identifier data value information, and its sort number in the basic collected data information; and The first correction coefficient and the second correction coefficient are respectively represented; the first correction coefficient and the second correction coefficient are values ​​between [0,1], and their sum is 1; The target identifier value information is used to replace and update the collected data value corresponding to the backup identifier value information; Determine whether the identification data value information exists in the target identification data information, and obtain an existence determination result; When the existence determination result is yes, the process of sequentially determining an identifier data value from the target identifier data information as a backup identifier value information is triggered, and the identifier data value information corresponding to the backup identifier value information is removed from the target identifier data information is executed. When the determination result is negative, the updated basic data information will be used as the target correction data value information corresponding to the basic data information. The target processing data information is subjected to diagnostic analysis to obtain target device status information; the target diagnostic model used for diagnostic analysis includes a first feature extraction module, a second feature extraction module, and a third feature extraction module; The second feature extraction module includes a first sub-feature extraction module, a second sub-feature extraction module, a third sub-feature extraction module, and a third fusion unit. The first sub-feature extraction module, the second sub-feature extraction module, and the third sub-feature extraction module are respectively used to extract feature information characterizing the pressure, flow rate, and vibration of the hydraulic system of engineering machinery.

2. The intelligent diagnostic method according to claim 1, characterized in that, The step of correcting the data information collected by the device to obtain the target corrected data information includes: For any of the basic data information collected by the device, the missing data value corresponding to the basic data information is identified to obtain the first identification data information corresponding to the basic data information. Abnormal information in the collected data values ​​corresponding to the basic collected data information is identified to obtain the second identification data information corresponding to the basic collected data information. The first identification data information and the second identification data information are merged to obtain the target identification data information corresponding to the basic collected data information; the target identification data information includes several identification data value information; the identification data value information is distributed according to the collection order; Based on the target identification data information, the target correction data value information corresponding to the basic collected data information is determined.

3. The intelligent diagnostic method according to claim 1, characterized in that, The diagnostic analysis of the target processing data information to obtain target device status information includes: The target processing data is analyzed and processed using a target diagnostic model to obtain target diagnostic results. The target diagnostic result information is converted and processed to obtain the target device status information.

4. The intelligent diagnostic method according to claim 3, characterized in that, The target diagnostic model includes a first feature extraction module, a second feature extraction module, a third feature extraction module, and a diagnostic recognition module; wherein, The first feature extraction module is configured to perform local feature extraction on the target processing data information; The second feature extraction module is configured to enhance the salient features extracted by the first feature extraction module and suppress the non-salient features extracted by the first feature extraction module. The third feature extraction module is configured to perform global feature extraction; The diagnostic identification module is configured to classify and identify the extracted features to obtain the target diagnostic result information.

5. The intelligent diagnostic method according to claim 4, characterized in that, The first sub-feature extraction module includes a first transformation unit, a first pooling unit, a first convolution unit, a first connection unit, a second connection unit, a first activation unit, a first fusion unit, and a second fusion unit; wherein, The input terminal of the first conversion unit is configured to receive input data information from the input terminal of the first sub-feature extraction module; the output terminal of the first conversion unit is connected to the input terminal of the first pooling unit and the input terminal of the second fusion unit; the first pooling unit, the first convolution unit, the first connection unit, the second connection unit, and the first activation unit are connected sequentially; the input terminal of the first fusion unit is configured to receive input data information from the input terminal of the first sub-feature extraction module and output data information from the output terminal of the first activation unit; the output terminal of the first fusion unit is connected to the input terminal of the second fusion unit; the output terminal of the second fusion unit is configured as the output terminal of the first sub-feature extraction module.

6. An intelligent diagnostic system, characterized in that, The system includes: The acquisition module is used to acquire device-collected data information; the device-collected data information includes several basic acquisition data information. The first processing module is used to analyze and process the data information collected by the device to obtain target processing data information; the analysis and processing includes correcting the data information collected by the device to obtain target corrected data information; the target corrected data information includes several target corrected data value information. The target correction data information is split and combined to obtain the target processing data information; For any of the basic data acquisition information in the data information collected by the device, based on the target identification data information corresponding to the basic data acquisition information, the target correction data value information corresponding to the basic data acquisition information is determined. Specifically, this includes: Sequentially determine an identifier data value from the target identifier data information as a backup identifier value, and remove the identifier data value corresponding to the backup identifier value from the target identifier data information; The backup identifier value information is calculated and processed using a data correction model to obtain the target identifier value information; The data correction model is as follows: ； In the formula, Characterizes the target identifier value information; and These respectively represent the data value preceding the data value corresponding to the backup identifier information and its sort number in the basic data information; and These respectively represent the collected data value that is ordered after the collected data value corresponding to the backup identifier value information and is not identified as the identifier data value information, and its sort number in the basic collected data information; and The first correction coefficient and the second correction coefficient are respectively represented; the first correction coefficient and the second correction coefficient are values ​​between [0,1], and their sum is 1; The target identifier value information is used to replace and update the collected data value corresponding to the backup identifier value information; Determine whether the identification data value information exists in the target identification data information, and obtain an existence determination result; When the existence determination result is yes, the process of sequentially determining an identifier data value from the target identifier data information as a backup identifier value information is triggered, and the identifier data value information corresponding to the backup identifier value information is removed from the target identifier data information is executed. When the determination result is negative, the updated basic data information will be used as the target correction data value information corresponding to the basic data information. The second processing module is used to perform diagnostic analysis on the target processing data information to obtain target device status information; the target diagnostic model used for diagnostic analysis includes a first feature extraction module, a second feature extraction module, and a third feature extraction module. The second feature extraction module includes a first sub-feature extraction module, a second sub-feature extraction module, a third sub-feature extraction module, and a third fusion unit. The first sub-feature extraction module, the second sub-feature extraction module, and the third sub-feature extraction module are respectively used to extract feature information characterizing the pressure, flow rate, and vibration of the hydraulic system of engineering machinery.

7. An intelligent diagnostic 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 intelligent diagnostic method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which, when invoked, are used to execute the intelligent diagnostic method as described in any one of claims 1-5.

Images