Bucket wheel machine movable beam mechanism fault monitoring and early warning method and system

Abstract

The invention discloses a bucket wheel machine movable beam mechanism fault monitoring and early warning method and system, and relates to the related field of mechanical engineering technology, and the method comprises the steps: collecting a plurality of operation vibration signals of a target bucket wheel machine movable beam mechanism; inputting the plurality of operation vibration signals into a characteristic decomposition module to generate a vibration signal characteristic matrix; inputting the vibration signal characteristic matrix into a walking beam mechanism fault diagnosis and recognition model for diagnosis, and obtaining a fault positioning result; and generating a first early warning signal according to the fault positioning result, and performing fault early warning. The technical problems that existing bucket wheel machine movable beam fault early warning depends on regular maintenance and manual inspection, real-time monitoring cannot be conducted, and fault early warning cannot be conducted in time are solved.

Description

Technical Field

[0001] This application relates to the field of mechanical engineering technology, specifically to a method and system for fault monitoring and early warning of the movable beam mechanism of a bucket wheel excavator. Background Technology

[0002] The movable beam mechanism of a bucket wheel excavator is a key component, responsible for supporting and controlling the movement of the bucket wheel. Due to its long-term operation under heavy load and high-intensity working conditions, the movable beam mechanism is susceptible to failure due to various factors, such as wear, breakage, and loosening. These failures not only lead to equipment downtime for maintenance, affecting project progress and production efficiency, but may also cause safety accidents, resulting in personal injury and property damage. Therefore, timely monitoring and early warning of failures in the movable beam mechanism of a bucket wheel excavator are particularly important. However, traditional fault detection methods mainly rely on regular maintenance and manual inspections, which have disadvantages such as low efficiency, strong blindness, and inability to detect potential faults in a timely manner. It is crucial to detect fault signs in advance and predict potential faults.

[0003] Therefore, the current technology for early warning of faults in the movable beam of bucket wheel excavators relies on regular maintenance and manual inspection, which makes it impossible to monitor in real time and provide timely early warning of faults. Summary of the Invention

[0004] This application provides a method and system for fault monitoring and early warning of the movable beam mechanism of a bucket wheel excavator. By employing techniques such as feature decomposition, model building, and fault diagnosis and identification, it solves the technical problem that existing fault early warning systems for movable beam mechanisms of bucket wheel excavators rely on regular maintenance and manual inspections, making real-time monitoring and timely fault warning impossible. This enables real-time monitoring and analysis of the operating status of the movable beam mechanism, early detection of fault signs, prediction of potential faults, and avoidance of equipment failures affecting production.

[0005] This application provides a method for fault monitoring and early warning of the movable beam mechanism of a bucket wheel excavator. The method includes: collecting multiple operating vibration signals of the movable beam mechanism of the target bucket wheel excavator; inputting the multiple operating vibration signals into a feature decomposition module to generate a vibration signal feature matrix; inputting the vibration signal feature matrix into a fault diagnosis and identification model of the movable beam mechanism for diagnosis to obtain fault location results; generating a first early warning signal based on the fault location results; and issuing a fault warning based on the first early warning signal.

[0006] In a possible implementation, before inputting multiple operating vibration signals into the feature decomposition module to generate a vibration signal feature matrix, the following processing is performed: acquiring environmental interference signals; extracting the signal features of the environmental interference signals and establishing a signal filtering module; inputting the multiple operating vibration signals into the signal filtering module for signal filtering, and outputting the filtered multiple operating vibration signals.

[0007] In a possible implementation, the step of inputting the vibration signal feature matrix into the fault diagnosis and identification model of the movable beam mechanism for diagnosis, obtaining fault location results, and performing the following processing: establishing a vibration signal fault type mapping sample library; training the movable beam mechanism fault diagnosis and identification model based on the vibration signal fault type mapping sample library; inputting the vibration signal feature matrix into the movable beam mechanism fault diagnosis and identification model for feature matching, obtaining the matching degree between the fault type and the input value; and outputting the fault type with a matching degree greater than or equal to a preset matching degree as the vibration signal fault location result.

[0008] In a possible implementation, the fault diagnosis and identification model of the movable beam mechanism is trained according to the vibration signal fault type mapping sample library, and the following processing is also performed: extracting fault features and labeling them with corresponding fault type tags; training a first movable beam mechanism fault diagnosis and identification model based on the fault features; evaluating and optimizing the first movable beam mechanism fault diagnosis and identification model to obtain the movable beam mechanism fault diagnosis and identification model.

[0009] In a possible implementation, the step of inputting multiple operating vibration signals into the feature decomposition module to generate a vibration signal feature matrix also includes the following processing: performing signal feature change analysis on the multiple operating vibration signals and outputting the signal change intensity based on each feature index; optimizing the number of signal decomposition channels according to the signal change intensity and outputting vibration signal decomposition channels; and constructing the feature decomposition module according to the vibration signal decomposition channels.

[0010] In a possible implementation, after obtaining the fault location result, the following processing is also performed: based on the vibration signal fault location result, it is determined whether the bucket wheel excavator movable beam mechanism is in a position repetition; when the bucket wheel excavator movable beam mechanism is in a position repetition, the vibration signal fault location result is split to generate multiple early warning signals corresponding to different fault types.

[0011] In a possible implementation, when the bucket wheel excavator's movable beam mechanism is in a repetitive positioning state, the following processing is also performed: Based on the vibration signal fault location result, output a variable set; select initial variable coordinates, where the initial variable coordinates represent common fault types in the variable set; iterate through the remaining fault types based on the initial variable coordinates to obtain the identifier variable coordinates with the highest similarity in characterization features; and generate multiple early warning signals based on the identifier variable coordinates. This application also provides a fault monitoring and early warning system for the movable beam mechanism of a bucket wheel excavator, including: The mechanism operation vibration signal acquisition module is used to acquire multiple operating vibration signals of the target bucket wheel excavator movable beam mechanism; A vibration signal feature decomposition module is used to input multiple operating vibration signals into the feature decomposition module to generate a vibration signal feature matrix. The fault diagnosis and identification module is used to input the vibration signal feature matrix into the fault diagnosis and identification model of the movable beam mechanism for diagnosis and to obtain the fault location result. A fault warning module is used to generate a first warning signal based on the fault location result, and to issue a fault warning based on the first warning signal.

[0012] This application proposes a method and system for fault monitoring and early warning of the movable beam mechanism of a bucket wheel excavator. The method involves collecting multiple operational vibration signals from the movable beam mechanism of the target bucket wheel excavator; inputting these vibration signals into a feature decomposition module to generate a vibration signal feature matrix; inputting the vibration signal feature matrix into a fault diagnosis and identification model for the movable beam mechanism to obtain fault location results; and generating a first early warning signal based on the fault location results to provide a fault warning. This addresses the technical problem of existing bucket wheel excavator movable beam fault warning systems relying on periodic maintenance and manual inspections, which cannot provide real-time monitoring and timely fault warnings. The proposed method achieves real-time monitoring and analysis of the movable beam mechanism's operating status, enabling early detection of fault signs and prediction of potential faults, thus preventing equipment failures from impacting production. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0014] Figure 1 A schematic flowchart of a fault monitoring and early warning method for the movable beam mechanism of a bucket wheel excavator provided in this application embodiment; Figure 2 This is a schematic diagram of a fault monitoring and early warning system for the movable beam mechanism of a bucket wheel excavator, provided in an embodiment of this application.

[0015] Explanation of reference numerals in the attached figures: 10 for vibration signal acquisition module, 20 for vibration signal feature decomposition module, 30 for fault diagnosis and identification module, and 40 for fault early warning module. Detailed Implementation

[0016] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application.

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" can be the same or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0019] This application provides a method for fault monitoring and early warning of the movable beam mechanism of a bucket wheel excavator, such as... Figure 1 As shown, the method includes: Step S100: Collect multiple operational vibration signals from the target bucket wheel excavator's movable beam mechanism. The various vibration signal data acquired from the movable beam mechanism are used to monitor and analyze the equipment's operating status. The movable beam mechanism is a crucial component of the bucket wheel excavator, used to support and control the movement of the bucket wheel. It typically consists of multiple hydraulic cylinders and connecting parts, enabling the bucket wheel to move up and down, left and right, and tilt, thereby completing excavation and loading tasks. The design and operational status of the movable beam mechanism directly affect the bucket wheel excavator's working efficiency and stability; therefore, its monitoring and maintenance are essential. Operational vibration signals may include acceleration signals, velocity signals, displacement signals, and spectrum signals. Acceleration signals reflect the acceleration changes of the movable beam mechanism during operation and can be used to assess the equipment's vibration status and structural dynamic characteristics. Velocity signals record the changes in the movable beam mechanism's operating speed, helping to determine the equipment's stability and balance. Displacement signals record the displacement changes of the movable beam mechanism during operation and can be used to analyze the mechanism's position changes and motion trajectory. Spectrum signals, obtained through spectral analysis of the vibration signals, can obtain vibration components at different frequencies, thereby identifying potential fault characteristics. Collecting and analyzing vibration signal data helps to identify potential faults in a timely manner, thereby improving the reliability and safety of equipment.

[0020] After collecting multiple operational vibration signals, step S200 is executed to input the multiple operational vibration signals into the feature decomposition module to generate a vibration signal feature matrix. The collected vibration signal data are processed using feature extraction algorithms to extract key features of each signal and combine these features into a feature matrix. Specifically, the feature decomposition module may employ various signal processing and feature extraction techniques, such as wavelet transform, Fourier transform, time-domain analysis, and frequency-domain analysis, to process each vibration signal and extract parameters or feature values ​​that reflect the important characteristics of the signal. These features may include the signal's amplitude, frequency distribution, spectral characteristics, and time-domain characteristics. For example, by performing spectral analysis on the vibration signal, features such as frequency components and spectral energy are extracted to analyze the frequency characteristics of the vibration signal; feature parameters such as mean, variance, and peak value are extracted from the time-domain waveform of the vibration signal to describe the time-varying characteristics of the vibration signal; amplitude-frequency characteristics of the vibration signal, such as the relationship between amplitude and frequency, are extracted by combining frequency-domain and time-domain information to analyze the amplitude variation law of the vibration signal; and features extracted through statistical methods, such as mean, standard deviation, and slope, are used to describe the overall statistical characteristics of the vibration signal. The generated vibration signal feature matrix is ​​a matrix containing multiple feature vectors. Each row represents a sample (i.e., vibration signal data within a time period), and each column represents a feature. This feature matrix allows complex vibration signal data to be transformed into a feature representation with higher abstraction and interpretability, providing a foundation for subsequent data analysis and fault diagnosis.

[0021] In one possible implementation, before step S200, which involves inputting multiple operating vibration signals into the feature decomposition module to generate a vibration signal feature matrix, step S191 is included to collect environmental interference signals. During the acquisition of vibration signal data from the operating mechanism, various environmental interference signals may occur, such as electromagnetic interference, mechanical interference, temperature changes, and humidity effects. Specifically, electromagnetic interference refers to electromagnetic radiation signals from electrical equipment, cables, power lines, etc., which may interfere with the vibration signals collected by the sensor, introducing noise and errors. Mechanical interference refers to vibration signals caused by external physical factors such as mechanical vibrations generated during equipment operation, wind, and water flow, which may be mixed into the target signal. Changes in ambient temperature may affect the performance of the sensor and the accuracy of signal acquisition, especially for certain sensor types, where temperature changes can lead to signal drift or distortion. High humidity environments may affect the performance of electronic equipment, such as causing circuit board oxidation and moisture absorption of insulating materials, thus affecting signal acquisition and transmission. When collecting and analyzing vibration signals, it is necessary to identify and suppress these environmental interference signals to ensure the accuracy and reliability of the collected data. Step S192 is also included to extract the signal characteristics of the environmental interference signals and establish a signal filtering module. By extracting and analyzing the features of the collected environmental interference signals, their characteristic parameters are identified, and a signal filtering module is established using these parameters to suppress or reduce the impact of environmental interference on the target signal. By establishing a signal filtering module, the quality of the collected signals can be effectively improved, the impact of environmental interference on data analysis and fault diagnosis can be reduced, and the performance and reliability of the system can be improved. The method also includes step S193, where the multiple operating vibration signals are input into the signal filtering module for signal filtering, and the filtered multiple operating vibration signals are output. The collected multiple operating vibration signals are processed by the signal filtering module to remove or reduce environmental interference signal components, thereby obtaining clean signal data after filtering. Specifically, multiple operating vibration signals are input into the signal filtering module, which processes the input signals according to a pre-designed filtering algorithm or model. During the processing, the module identifies and removes environmental interference signals unrelated to the target signal, retaining the important features and information of the target vibration signal. After processing, the output signal data is the multiple operating vibration signals after filtering, in which the impact of environmental interference has been reduced. Signal filtering improves the quality and accuracy of vibration signal data, providing a more reliable data foundation for monitoring and analyzing equipment operating status.

[0022] In one possible implementation, step S200, which involves inputting multiple operating vibration signals into a feature decomposition module to generate a vibration signal feature matrix, further includes step S210, which analyzes the signal feature changes of the multiple operating vibration signals and outputs the signal change intensity based on various feature indices. Feature extraction is performed on multiple vibration signal samples, and the degree of change of different features among different samples is analyzed. Specifically, for each vibration signal sample, its feature vector is extracted. By comparing the feature values ​​between different vibration signal samples, the changes under various feature indices are analyzed. For each feature index, its corresponding signal change intensity value is output, reflecting the degree of change between different vibration signal samples under that feature index. Larger values ​​indicate stronger changes, while smaller values ​​indicate weaker changes. The implementation also includes step S220, which optimizes the number of signal decomposition channels according to the signal change intensity and outputs the vibration signal decomposition channels. The optimal number of signal decomposition channels is determined by analyzing the intensity of signal changes. Typically, signal decomposition techniques (such as wavelet transform and empirical mode decomposition) can decompose the original vibration signal into multiple frequency bands or components to better understand the signal's composition and characteristics. Specifically, based on the extracted vibration signal features and the intensity of changes under each feature index, the signal changes in different frequency ranges or feature dimensions are analyzed. Based on the analysis results of the signal intensity changes, the optimal number of signal decomposition channels and the decomposed signal results for each channel are determined to better identify fault characteristics and perform subsequent fault diagnosis or predictive analysis. The method also includes step S230, constructing a feature decomposition module according to the vibration signal decomposition channels. Vibration signal decomposition (e.g., wavelet transform, empirical mode decomposition, etc.) is used to decompose the vibration signal into multiple frequency bands or components, and a feature decomposition module is constructed for each decomposition channel.

[0023] After generating the vibration signal feature matrix, step S300 is executed, whereby the vibration signal feature matrix is ​​input into the fault diagnosis and identification model of the movable beam mechanism for diagnosis, and fault location results are obtained. The vibration signal feature matrix obtained through feature extraction and processing is used as input to a pre-trained fault diagnosis and identification model. The model analyzes and compares the vibration signal features to identify potential mechanical faults or abnormal states, and determines the specific location or type of the fault. Specifically, the fault diagnosis and identification model of the movable beam mechanism is a model built based on machine learning or artificial intelligence algorithms. By learning and analyzing a large amount of vibration signal data, it can identify the characteristic patterns and laws of vibration signals under different fault states. When a new vibration signal feature matrix is ​​input, the model analyzes and matches these features, and then outputs fault location results, indicating the possible fault location or type.

[0024] In one possible implementation, step S300 further includes step S310, establishing a vibration signal fault type mapping sample library. A series of vibration signal data are collected and organized, and the fault type information corresponding to each vibration signal is recorded. The mapping sample library can include various types of vibration signal data generated by the bucket wheel excavator's movable beam mechanism during operation, as well as the specific fault types corresponding to these vibration signals. Step S320 further includes training the movable beam mechanism fault diagnosis and identification model based on the vibration signal fault type mapping sample library. Data from the previously established vibration signal-fault type mapping sample library is used as a training set to train the fault diagnosis and identification model. Specifically, a portion of data is selected from the vibration signal-fault type mapping sample library as the training set, including vibration signal data and their corresponding fault type labels. Feature extraction and preprocessing are performed on the vibration signal data in the training set to prepare it for input into the fault diagnosis model, such as denoising and feature engineering. Using the vibration signal data and fault type labels from the training set, the movable beam mechanism fault diagnosis and identification model is trained using machine learning or deep learning algorithms. During training, the model learns the correlation between vibration signals and fault types and adjusts model parameters to improve diagnostic accuracy. The method also includes step S330, where the vibration signal feature matrix is ​​input into the movable beam mechanism fault diagnosis and identification model for feature matching to obtain the matching degree between the fault type and the input value. The vibration signal feature matrix obtained after feature extraction and processing is used as input and passed to the movable beam mechanism fault diagnosis and identification model. The model compares and matches the input vibration signal features with the learned fault type features, and then outputs a matching degree or similarity metric to evaluate the correlation between the input vibration signal and various fault types. Specifically, the model analyzes the feature patterns, frequency distributions, and other information in the input vibration signal feature matrix and compares them with the features of known fault types. The higher the matching degree, the more similar the input vibration signal features are to the features of a certain fault type. The method also includes step S340, where fault types with matching degrees greater than or equal to a preset matching degree are output as vibration signal fault location results. During fault diagnosis, if the matching degree between the vibration signal features calculated by the movable beam mechanism fault diagnosis and identification model and a certain fault type is higher than or equal to a preset threshold, then that fault type will be identified as a possible fault cause and output as a vibration signal fault location result.

[0025] In one possible implementation, step S320, training the fault diagnosis and identification model of the movable beam mechanism based on the vibration signal fault type mapping sample library, further includes step S321, extracting fault features and labeling them with corresponding fault type tags. Features related to potential faults are extracted from the vibration signal-fault type mapping sample library of the bucket wheel excavator's movable beam, and these features are associated with corresponding fault types. Specifically, vibration signal data is analyzed and processed to extract representative feature parameters. For each vibration signal sample, its corresponding fault type is determined, and the extracted features are associated with the corresponding fault types to form a feature-fault type correspondence. Step S322 further includes training the first movable beam mechanism fault diagnosis and identification model based on the fault features. The extracted feature data related to mechanical equipment faults is used as a training set to train the first movable beam mechanism fault diagnosis and identification model. Step S323 further includes evaluating and optimizing the first movable beam mechanism fault diagnosis and identification model to obtain the movable beam mechanism fault diagnosis and identification model. The performance of the trained fault diagnosis and identification model for the first movable beam mechanism is evaluated and adjusted to improve its accuracy and reliability. Specifically, the model is evaluated using a reserved validation set or cross-validation technique. Based on the evaluation results, the model is adjusted and optimized, such as adjusting the model's hyperparameters, improving the feature selection method, and increasing the amount of training data. The optimized model needs to be further validated using a test set. The performance of the optimized model is compared with that of the original model to ensure the effectiveness of the optimization and to ensure that the fault diagnosis and identification model for the movable beam mechanism has higher accuracy and reliability.

[0026] In one possible implementation, after obtaining the fault location result in step S300, the method further includes step S380, which determines whether the bucket wheel excavator's movable beam mechanism is experiencing repeated positioning based on the vibration signal fault location result. Based on the results of vibration signal processing and fault diagnosis, the fault location status of the bucket wheel excavator's movable beam mechanism is judged, with a particular focus on checking for repeated positioning. Specifically, by analyzing the vibration signal of the bucket wheel excavator's movable beam mechanism, possible fault types and locations are identified, and it is checked whether the same fault or the same location is located multiple times. The method also includes step S390, where, when the bucket wheel excavator's movable beam mechanism is experiencing repeated positioning, the vibration signal fault location result is split to generate multiple warning signals corresponding to different fault types. Based on the complex fault location results, they are broken down into multiple early warning signals, each corresponding to a specific fault type. Specifically, recurring fault location results are broken down, with each different location result corresponding to a specific fault type. For each different fault type, a corresponding early warning signal is generated. The early warning signal can be a binary flag or structured data containing more fault information. By breaking down the vibration signal fault location results and generating early warning signals, the different fault types and their severity that may exist in the bucket wheel excavator's movable beam mechanism can be more clearly identified, reducing the impact of faults on the movable beam mechanism.

[0027] In one possible implementation, step S380, when the bucket wheel excavator's movable beam mechanism is in a repetitive positioning state, further includes step S381, outputting a variable set based on the vibration signal fault location result. Based on the vibration signal processing and fault location results, a set of variables describing the state of the movable beam mechanism is generated, where the variable set may include fault type variables, fault location variables, fault severity variables, etc. Step S382 further includes selecting initial variable coordinates, where the initial variable coordinates are fault types common to the variable set. Variables present in all fault types are selected from the variable set and used as the initial variable coordinates. Step S383 further includes iterating over the remaining fault types based on the selected initial variable coordinates to obtain the most relevant identifier variable coordinates in terms of feature similarity. Specifically, iterating over the remaining fault types selects the identifier variable coordinates with the highest similarity to the initial variable coordinates as the variable coordinates representing the greatest feature similarity, better describing the similarity and differences between different fault types. Through this iterative process, the feature set can be gradually improved, enhancing the accuracy and robustness of the fault diagnosis model, thereby better handling complex fault situations. The process also includes step S384, which generates multiple early warning signals based on the coordinates of the identified variables. Based on the selected coordinates of the identified variables, corresponding early warning signals are generated for each specific fault type in fault diagnosis and predictive analysis. Specifically, for each coordinate of the identified variables, a corresponding early warning signal is generated based on information such as vibration signal characteristics, fault modes, and historical data. This signal is used to monitor equipment status in real time, remind operators of potential faults, guide maintenance work, and trigger automatic shutdown or protection measures. This provides a more comprehensive understanding of the status and risk level of different fault types, helping to detect problems early and reduce fault losses.

[0028] Finally, step S400 is executed, generating a first warning signal based on the fault location result, and then issuing a fault warning based on the first warning signal. Specifically, the first warning signal, containing information such as fault type, location, and severity, is generated based on the fault location result. This means that the condition of the bucket wheel excavator's movable beam mechanism is monitored and analyzed based on the content and characteristics of the warning signal, allowing for early detection of potential faults or trend changes, and enabling the implementation of corresponding preventative measures to avoid losses or impacts caused by the fault.

[0029] In the above text, refer to Figure 1 A method for fault monitoring and early warning of the movable beam mechanism of a bucket wheel excavator according to an embodiment of the present invention is described in detail. Next, reference will be made to... Figure 2 This invention describes a fault monitoring and early warning system for the movable beam mechanism of a bucket wheel excavator according to an embodiment of the present invention.

[0030] According to an embodiment of the present invention, a fault monitoring and early warning system for the movable beam mechanism of a bucket wheel excavator is provided to solve the technical problem that existing fault early warning systems for movable beam mechanisms rely on periodic maintenance and manual inspections, making real-time monitoring and timely fault warning impossible. This system enables real-time monitoring and analysis of the operating status of the movable beam mechanism, allowing for early detection of fault signs and prediction of potential faults, thus preventing equipment failures from impacting production. The bucket wheel excavator movable beam mechanism fault monitoring and early warning system includes: a mechanism operation vibration signal acquisition module 10, a vibration signal feature decomposition module 20, a fault diagnosis and identification module 30, and a fault early warning module 40.

[0031] The mechanism operation vibration signal acquisition module 10 is used to acquire multiple operation vibration signals of the target bucket wheel excavator movable beam mechanism; Vibration signal feature decomposition module 20, which is used to input multiple running vibration signals into the feature decomposition module to generate a vibration signal feature matrix; The fault diagnosis and identification module 30 is used to input the vibration signal feature matrix into the fault diagnosis and identification model of the movable beam mechanism for diagnosis and to obtain the fault location result. The fault warning module 40 is used to generate a first warning signal based on the fault location result and to issue a fault warning based on the first warning signal.

[0032] The specific configuration of the vibration signal feature decomposition module 20 will be described in detail below. As mentioned above, before inputting multiple operating vibration signals into the feature decomposition module to generate a vibration signal feature matrix, the vibration signal feature decomposition module 20 may further include: acquiring environmental interference signals; extracting the signal features of the environmental interference signals and establishing a signal filtering module; inputting the multiple operating vibration signals into the signal filtering module for signal filtering, and outputting the filtered multiple operating vibration signals.

[0033] The specific configuration of the fault diagnosis and identification module 30 will be described in detail below. As mentioned above, the fault diagnosis and identification module 30 further includes the following steps: inputting the vibration signal feature matrix into the fault diagnosis and identification model of the movable beam mechanism for diagnosis and obtaining fault location results; identifying the operating status of the sprinkler heads based on historical operating data and generating sprinkler head identification results; establishing a vibration signal fault type mapping sample library; training the movable beam mechanism fault diagnosis and identification model based on the vibration signal fault type mapping sample library; inputting the vibration signal feature matrix into the movable beam mechanism fault diagnosis and identification model for feature matching and obtaining the matching degree between the fault type and the input value; and outputting the fault types with a matching degree greater than or equal to a preset matching degree as vibration signal fault location results.

[0034] The specific configuration of the fault diagnosis and identification module 30 will be described in detail below. As mentioned above, the fault diagnosis and identification module 30 can further include: extracting fault features and labeling them with corresponding fault type tags; training a first fault diagnosis and identification model of the movable beam mechanism based on the fault features; and evaluating and optimizing the first fault diagnosis and identification model of the movable beam mechanism to obtain the fault diagnosis and identification model of the movable beam mechanism.

[0035] The specific configuration of the vibration signal feature decomposition module 20 will be described in detail below. As mentioned above, the vibration signal feature decomposition module 20 further includes: analyzing the signal feature changes of the multiple operating vibration signals and outputting the signal change intensity based on each feature index; optimizing the number of signal decomposition channels according to the signal change intensity and outputting vibration signal decomposition channels; and constructing the feature decomposition module according to the vibration signal decomposition channels.

[0036] The specific configuration of the fault diagnosis and identification module 30 will be described in detail below. As mentioned above, after obtaining the fault location result, the fault diagnosis and identification module 30 further includes: determining whether the bucket wheel excavator's movable beam mechanism is in a position repetition based on the vibration signal fault location result; when the bucket wheel excavator's movable beam mechanism is in a position repetition, splitting the vibration signal fault location result and generating multiple early warning signals corresponding to different fault types.

[0037] The specific configuration of the fault diagnosis and identification module 30 will be described in detail below. As mentioned above, when the bucket wheel excavator's movable beam mechanism is in a repetitive positioning state, the fault diagnosis and identification module 30 further includes: outputting a variable set based on the vibration signal fault location result; selecting initial variable coordinates, wherein the initial variable coordinates are the common fault types in the variable set; iterating over the remaining fault types based on the initial variable coordinates to obtain the identifier variable coordinates with the highest similarity in characterization features; and generating multiple early warning signals based on the identifier variable coordinates.

[0038] The bucket wheel excavator movable beam mechanism fault monitoring and early warning system provided in this embodiment of the invention can execute the bucket wheel excavator movable beam mechanism fault monitoring and early warning method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0039] Although this application makes various references to certain modules in the system according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0040] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for fault monitoring and early warning of a bucket wheel excavator's movable beam mechanism, characterized in that, The method includes: Collect multiple operational vibration signals from the movable beam mechanism of the target bucket wheel excavator; Multiple operating vibration signals are input into the feature decomposition module to generate a vibration signal feature matrix; The vibration signal feature matrix is ​​input into the fault diagnosis and identification model of the movable beam mechanism for diagnosis, and the fault location result is obtained. A first warning signal is generated based on the fault location result, and a fault warning is issued based on the first warning signal.

2. The method for fault monitoring and early warning of the movable beam mechanism of a bucket wheel excavator as described in claim 1, characterized in that, Before inputting multiple operating vibration signals into the feature decomposition module to generate a vibration signal feature matrix, the method further includes: Collect environmental interference signals; Extract the signal characteristics of the environmental interference signals and establish a signal filtering module; The multiple operating vibration signals are input to the signal filtering module for signal filtering, and the filtered multiple operating vibration signals are output.

3. The method for fault monitoring and early warning of the movable beam mechanism of a bucket wheel excavator as described in claim 1, characterized in that, The method of inputting the vibration signal feature matrix into the fault diagnosis and identification model of the movable beam mechanism for diagnosis and obtaining fault location results includes: Establish a sample library mapping vibration signal fault types; The fault diagnosis and identification model of the movable beam mechanism is trained based on the vibration signal fault type mapping sample library. The vibration signal feature matrix is ​​input into the fault diagnosis and identification model of the movable beam mechanism for feature matching to obtain the degree of matching between the fault type and the input value. The fault types with a matching degree greater than or equal to the preset matching degree are output as the vibration signal fault location results.

4. The method for fault monitoring and early warning of the movable beam mechanism of a bucket wheel excavator as described in claim 3, characterized in that, The method includes training a fault diagnosis and identification model for the movable beam mechanism based on the vibration signal fault type mapping sample library, the method comprising: Extract fault features and label them with the corresponding fault type. A fault diagnosis and identification model for the first movable beam mechanism is trained based on the fault characteristics. The fault diagnosis and identification model of the first movable beam mechanism is evaluated and optimized to obtain the fault diagnosis and identification model of the movable beam mechanism.

5. The method for fault monitoring and early warning of the movable beam mechanism of a bucket wheel excavator as described in claim 1, characterized in that, The method of inputting multiple operating vibration signals into a feature decomposition module to generate a vibration signal feature matrix further includes: The signal characteristic change analysis is performed on the multiple operating vibration signals, and the signal change intensity based on each characteristic index is output. The number of signal decomposition channels is optimized according to the intensity of the signal change, and the vibration signal decomposition channels are output. Based on the vibration signal decomposition channels, a feature decomposition module is constructed.

6. The method for fault monitoring and early warning of the movable beam mechanism of a bucket wheel excavator as described in claim 1, characterized in that, The method further includes: Based on the fault location results of vibration signals, determine whether the bucket wheel excavator's movable beam mechanism is in a repetitive positioning state. When the bucket wheel excavator's movable beam mechanism is in a repetitive positioning state, the vibration signal fault location results are split to generate multiple early warning signals corresponding to different fault types.

7. A method for fault monitoring and early warning of a bucket wheel excavator movable beam mechanism as described in claim 6, characterized in that, When the bucket wheel excavator's movable beam mechanism is in a repetitive positioning state, the method includes: Based on the fault location results of the vibration signal, output a set of variables; Select initial variable coordinates, wherein the initial variable coordinates are common to the fault types in the variable set; Based on the initial variable coordinates, the remaining fault types are iterated to obtain the identifier variable coordinates with the highest similarity in characterization features; Based on the coordinates of the identified variables, multiple early warning signals are generated.

8. A fault monitoring and early warning system for the movable beam mechanism of a bucket wheel excavator, characterized in that, The system is used to implement the fault monitoring and early warning method for the movable beam mechanism of a bucket wheel excavator as described in any one of claims 1-7, and the system includes: The mechanism operation vibration signal acquisition module is used to acquire multiple operating vibration signals of the target bucket wheel excavator movable beam mechanism; A vibration signal feature decomposition module is used to input multiple operating vibration signals into the feature decomposition module to generate a vibration signal feature matrix. The fault diagnosis and identification module is used to input the vibration signal feature matrix into the fault diagnosis and identification model of the movable beam mechanism for diagnosis and to obtain the fault location result. A fault warning module is used to generate a first warning signal based on the fault location result, and to issue a fault warning based on the first warning signal.

Images