Wheel bucket excavator bucket tooth operation state identification method and system and storage medium

Abstract

The invention relates to a wheel bucket excavator bucket tooth operation state recognition method and system and a storage medium, relates to the technical field of intelligent monitoring, and aims to solve the problem that the abnormal recognition false alarm rate is high due to the fact that the operation state of bucket teeth cannot be accurately recognized. The method comprises the following steps: acquiring data of a plurality of sensors of bucket teeth of a to-be-measured wheel bucket excavator at the current moment; according to the sensor type, classifying the plurality of sensor data to generate a plurality of sensor data subsets; according to the decision tree model, determining historical optimal data corresponding to each sensor data subset and a corresponding normal fluctuation range; on the basis of the historical optimal data and the normal fluctuation range corresponding to each sensor data subset, abnormal data in each sensor data in each sensor data subset is judged, and a judgment result corresponding to each sensor data subset is obtained; and determining the operation state of the bucket tooth of the wheel bucket excavator to be detected according to the plurality of judgment results.

Description

Technical Field

[0001] This application relates to the field of intelligent monitoring technology, and in particular to a method, system and storage medium for identifying the operating status of bucket teeth of a bucket wheel excavator. Background Technology

[0002] Currently, the monitoring and identification of the operating status of bucket teeth in bucket wheel excavators mostly relies on image capture. By capturing images of the bucket teeth's operating status and then analyzing and processing them, the normal operating status of the bucket teeth can be determined. However, due to the complex structure of the bucket teeth, environmental interference, and the high rotation speed of the teeth during operation, it is difficult to extract accurate tooth features from the monitoring images, which easily leads to misjudgments and a high false alarm rate. Summary of the Invention

[0003] This invention provides a method, system, and storage medium for identifying the operating status of bucket teeth in a bucket wheel excavator, to solve the problem of high false alarm rates caused by the inability to accurately identify the operating status of the bucket teeth. The technical solution of this invention is as follows: According to a first aspect of the present invention, a method for identifying the operating status of bucket teeth of a bucket excavator is provided. The method includes: acquiring multiple sensor data of the bucket teeth of the bucket excavator to be tested at the current moment; classifying the multiple sensor data according to sensor type to generate multiple sensor data subsets; the sensor types include vibration sensors, pressure sensors, angle sensors, position sensors, range sensors, and power sensors; each sensor subset corresponds to one sensor type; determining the historical best data and the corresponding normal fluctuation range corresponding to each sensor data subset according to a decision tree model; based on the historical best data and the normal fluctuation range corresponding to each sensor data subset, determining the abnormal data in each sensor data in each sensor data subset to obtain the determination result corresponding to each sensor data subset; and determining the operating status of the bucket teeth of the bucket excavator to be tested according to the multiple determination results.

[0004] As an implementation method, before determining the historical optimal data range corresponding to each subset of sensor data, the method further includes: acquiring a historical sample dataset of the bucket teeth of the bucket excavator to be tested; the historical sample dataset includes multiple historical sensor data of different sensor types corresponding to different time points within a preset time period before the current time; constructing a decision tree model based on the historical sample dataset; the decision tree model characterizes the mapping of sensor data to specific state labels based on the classification of sensor data and initial comparison benchmarks; the state labels include normal and abnormal.

[0005] In this implementation, the decision tree model can automatically learn normal operating modes based on historical data and adapt to equipment aging or environmental changes, thereby dynamically adjusting the judgment criteria. This improves the intelligence level of status recognition and enhances the system's adaptability.

[0006] As one implementation method, based on the decision tree model, the historical optimal data and corresponding normal fluctuation range corresponding to each subset of sensor data are determined. Specifically, this includes: classifying multiple historical sensor data based on sensor type to obtain multiple historical sensor data subsets; determining the state labels of historical sensor data in each historical sensor data subset according to the decision tree algorithm of the decision tree model, and determining the historical normal dataset and historical abnormal dataset in each historical sensor data subset; determining the average value of multiple historical sensor data in the historical normal dataset based on the historical normal dataset in each historical sensor data subset, thereby determining the historical optimal data; and determining the normal fluctuation range based on the boundary values ​​in the historical normal dataset and the historical abnormal dataset.

[0007] In this implementation, historical optimal data and normal fluctuation ranges for each sensor type are determined using historical sensor data, ensuring an accurate decision-making benchmark for assessing the current state of multiple sensor data. Simultaneously, "historical optimal data" is defined by calculating the average value from historical normal datasets, providing an objective benchmark for state assessment. This avoids biases caused by manually set thresholds, making the state judgment benchmark closer to the actual optimal operating conditions of the equipment, thus improving the accuracy and scientific rigor of state identification. Furthermore, the determination of the normal fluctuation range relies not only on the boundaries of historical normal data but also references historical abnormal datasets, making the delineation of the normal range more discriminative and effectively distinguishing between critical abnormal states and healthy extreme fluctuations, significantly reducing the system's false alarm and false negative rates.

[0008] As one implementation method, based on the historical best data and normal fluctuation range corresponding to each subset of sensor data, abnormal data in each sensor data within the corresponding subset of sensor data is determined, and the determination result corresponding to each subset of sensor data is obtained. Specifically, this includes: inputting multiple sensor data at the current moment into a decision tree model to obtain multiple subsets of sensor data; determining the corresponding historical best data and normal fluctuation range of the target sensor data based on the target sensor type corresponding to the target subset of sensor data; comparing each sensor data in the target subset of sensor data with the target historical best data to obtain multiple data differences; filtering out abnormal data differences from the multiple data differences that exceed the target normal fluctuation range, and identifying the sensor data associated with the abnormal data differences as abnormal data; and obtaining the determination result corresponding to the target subset of sensor data based on the number of abnormal data and the corresponding sensor type.

[0009] As one implementation method, the operating status of the bucket teeth of the bucket excavator under test is determined based on multiple judgment results, including: if the number of abnormal data in the judgment results is greater than the abnormal number threshold, the operating status of the bucket teeth of the bucket excavator under test is determined to be abnormal; if the number of abnormal data in the judgment results is less than or equal to the abnormal number threshold, the operating status of the bucket teeth of the bucket excavator under test is determined to be normal.

[0010] In this implementation, the number of abnormal data in the judgment result can be used to promptly determine whether the operating status of the bucket teeth of the bucket excavator under test has become abnormal, thus improving the timeliness of status identification.

[0011] As one approach, when it is determined that the bucket teeth of the bucket excavator under test are in an abnormal operating condition, the abnormality type of the bucket teeth is determined based on the sensor type corresponding to each abnormal data.

[0012] In this implementation, if the judgment result shows an anomaly in a single type of sensor data, the fault location can be precisely pinpointed, narrowing the fault scope to the component or physical process most relevant to that sensor, greatly shortening the diagnosis time. If the judgment result shows anomalies in multiple subsets of different types of sensors simultaneously, it may indicate a more complex composite fault, and the judgment results from different sensor data can be cross-validated. This significantly improves the reliability and confidence of the diagnostic results.

[0013] As one implementation method, when abnormal data is detected and it is determined that the bucket teeth of the bucket excavator under test are in abnormal operation, a fault warning message is issued. The warning message is used to indicate that the current sensor data is abnormal. The fault warning message includes one or more of the following: voice information, light information, and text information.

[0014] As one implementation method, multiple sensor data at various time points within a preset period are recorded in real time to generate a dynamic waveform graph. The dynamic waveform graph includes multiple waveforms, with each waveform corresponding to a sensor type. Abnormal data in the dynamic waveform graph is then highlighted.

[0015] In this implementation, the dynamic waveform graph records data within a preset period in real time. Based on the fault development process displayed in the waveform graph, it provides users with a more accurate and intuitive basis for decision-making.

[0016] According to a second aspect of the present invention, a bucket tooth operating status identification system for a bucket wheel excavator is provided. The system includes: an identification module and a sensor module; the identification module and the sensor module are connected by communication.

[0017] The sensor module is used to collect data from multiple sensors on the bucket teeth of the bucket excavator under test in real time.

[0018] The identification module acquires multiple sensor data points from the bucket teeth of the excavator under test at the current moment. Based on sensor type, it categorizes the data into multiple subsets, including vibration sensors, pressure sensors, angle sensors, position sensors, range sensors, and power sensors. Each subset corresponds to one sensor type. Using a decision tree model, it determines the historical best data and normal fluctuation range for each subset. Based on these data points, it identifies abnormal data within each subset, obtaining a judgment result for each subset. Finally, based on these judgment results, it determines the operating status of the excavator's bucket teeth.

[0019] The bucket excavator bucket tooth operating status identification system is configured to perform a bucket excavator bucket tooth operating status identification method as described in the first aspect and any possible implementation thereof.

[0020] According to a third aspect of the present invention, a bucket wheel excavator bucket tooth operating status identification device is provided, the device being configured to perform a bucket wheel excavator bucket tooth operating status identification method as described in the first aspect and any possible implementation thereof.

[0021] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which instructions are stored, such that when the instructions in the computer-readable storage medium are executed by a processor of a bucket excavator bucket tooth operating status identification device, the bucket excavator bucket tooth operating status identification device is able to perform a bucket excavator bucket tooth operating status identification method as described in the first aspect and any possible implementation thereof.

[0022] According to a fifth aspect of the present disclosure, a computer program product is provided, the computer program product including computer instructions, which, when executed on a bucket excavator bucket tooth running status identification device, cause the bucket excavator bucket tooth running status identification device to execute the bucket excavator bucket tooth running status identification method of the first aspect and any possible implementation thereof.

[0023] The technical solutions provided by the embodiments of the present invention bring at least the following beneficial effects: This application uses data from multiple sensors such as vibration, pressure, angle, position, range, and power to conduct more comprehensive state monitoring of the operating status of the bucket teeth of a bucket wheel excavator from multiple dimensions, improving the coverage and accuracy of the operating status monitoring. Furthermore, different sensor data have different characteristics and fluctuation patterns. Therefore, the collected multiple sensor data are classified according to sensor type to generate multiple sensor data subsets. The historical best data and normal fluctuation range of each sensor data subset are determined according to the decision tree model. Different sensor data subsets correspond to different anomaly judgment criteria. Anomaly judgment is performed on the data in each sensor data subset separately, which can reduce mutual interference between data and improve the accuracy of state recognition. Based on this, the judgment results of multiple sensor data subsets are combined for decision-making, avoiding the risk of false alarms caused by a single data source. Through multi-source information fusion, the reliability and robustness of the bucket tooth operating status judgment of the bucket wheel excavator are effectively improved.

[0024] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0025] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0026] Figure 1 This is a schematic diagram of a bucket excavator bucket tooth operating status identification system according to an exemplary embodiment. Figure 1 ; Figure 2 This is a schematic diagram of a bucket excavator bucket tooth operating status identification system according to an exemplary embodiment. Figure 2 ; Figure 3 This is a schematic diagram of a bucket excavator bucket tooth operating status identification system according to an exemplary embodiment. Figure 3 ; Figure 4 This is a flowchart illustrating a method for identifying the operating status of bucket teeth in a bucket wheel excavator according to an exemplary embodiment; Figure 5 This is a schematic diagram illustrating a device for identifying the operating status of bucket teeth of a bucket excavator according to an exemplary embodiment. Detailed Implementation

[0027] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0028] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0029] Before providing a detailed introduction to the method for identifying the operating status of bucket teeth in a bucket excavator provided in this application embodiment, let's briefly introduce the application scenarios and implementation environment involved in this application embodiment.

[0030] Currently, the monitoring and identification of the operating status of bucket teeth in bucket wheel excavators mostly relies on image capture. By capturing images of the bucket teeth's operating status and then analyzing and processing them, the normal operating status of the bucket teeth can be determined. However, due to the complex structure of the bucket teeth, environmental interference, and the high rotation speed of the teeth during operation, it is difficult to extract accurate tooth features from the monitoring images, which easily leads to misjudgments and a high false alarm rate.

[0031] To address the aforementioned issues, this application proposes a method for identifying the operating status of bucket teeth in a bucket wheel excavator. By utilizing data from multiple sensors, including those for vibration, pressure, angle, position, range, and power, the method provides a more comprehensive monitoring of the bucket teeth's operating status from multiple dimensions, improving the coverage and accuracy of the monitoring. Furthermore, since different sensor data exhibit different characteristics and fluctuation patterns, the method categorizes the collected sensor data according to sensor type, generating multiple sensor data subsets. A decision tree model is then used to determine the historical best data and normal fluctuation range for each sensor data subset. Different anomaly judgment criteria apply to different sensor data subsets, and anomaly judgment is applied to each subset separately, reducing mutual interference between data and improving the accuracy of status identification. Based on this, the judgment results from multiple sensor data subsets are used for comprehensive decision-making, avoiding the risk of false alarms from a single data source. Through multi-source information fusion, the reliability and robustness of the bucket tooth operating status determination method are effectively improved.

[0032] Secondly, the implementation architecture involved in this application will be briefly introduced below.

[0033] Figure 1 This is a schematic diagram of a bucket tooth operating status identification system for a bucket wheel excavator provided in this application. Figure 1 .like Figure 1 As shown, the bucket excavator's bucket tooth operating status recognition system includes a sensor module 11 and a recognition module 12.

[0034] The sensor module 11 and the identification module 12 are connected via communication.

[0035] Sensor module 11 is configured to collect multiple sensor data from the bucket teeth of the bucket excavator under test in real time.

[0036] The identification module 12 is configured to acquire multiple sensor data of the bucket teeth of the bucket excavator under test at the current moment; classify the multiple sensor data according to the sensor type to generate multiple sensor data subsets; determine the historical best data and the corresponding normal fluctuation range of each sensor data subset according to the decision tree model; based on the historical best data and normal fluctuation range of each sensor data subset, determine the abnormal data in each sensor data in each sensor data subset to obtain the judgment result corresponding to each sensor data subset; and determine the operating status of the bucket teeth of the bucket excavator under test according to the multiple judgment results.

[0037] In some embodiments, such as Figure 2 As shown, the sensor module 11 includes a controller 111, a vibration sensor 112, a pressure sensor 113, an angle sensor 114, a position sensor 115, a range sensor 116, and a power sensor 117.

[0038] Vibration sensor 112 is installed at the connection between the bucket teeth and the runner of the bucket wheel excavator. Pressure sensor 113 is installed inside the bucket teeth of the bucket wheel excavator. Angle sensor 114 is installed at the connection between the bucket teeth and the runner of the bucket wheel excavator. Position sensor 115 is installed on the outside of the bucket teeth of the bucket wheel excavator. Range sensor 116 is installed at the top inside the bucket teeth of the bucket wheel excavator. Power sensor 117 is installed at the drive unit of the bucket teeth of the bucket wheel excavator.

[0039] The controller 111 is configured to transmit commands and acquire data via wireless communication.

[0040] Vibration sensor 112 is configured to monitor the vibration values ​​that occur during the operation of the bucket teeth of a bucket excavator.

[0041] Pressure sensor 113 is configured to monitor the pressure on the bucket teeth of a bucket excavator.

[0042] Angle sensor 114 is configured to monitor the rotation angle of the bucket teeth of a bucket wheel excavator.

[0043] Position sensor 115 is configured to monitor the movement position of the bucket teeth of a bucket wheel excavator.

[0044] The range sensor 116 is configured to monitor changes in the length of the bucket teeth of a bucket excavator.

[0045] The power sensor 117 is configured to monitor the power of the bucket teeth of the bucket excavator during operation.

[0046] like Figure 3 As shown, the identification module 12 includes a data acquisition unit 121, a data analysis unit 122, a data comparison unit 123, a fault diagnosis unit 124, a data display unit 125, and a control unit 126.

[0047] The data acquisition unit 121 is configured to acquire data generated by the sensor module 11 and transmit the acquired data to the data analysis unit 122.

[0048] The data analysis unit 122 is configured to classify multiple sensor data according to sensor type and generate multiple sensor data subsets.

[0049] The data comparison unit 123 is configured to determine the historical best data and the corresponding normal fluctuation range of each sensor data subset according to the decision tree model, and based on the historical best data and the normal fluctuation range of each sensor data subset, determine the abnormal data in each sensor data in each sensor data subset, and obtain the judgment result corresponding to each sensor data subset.

[0050] The fault diagnosis unit 124 is configured to determine the abnormality type of the bucket teeth of the bucket excavator under test based on the sensor type corresponding to each abnormal data when it is determined that the bucket teeth of the bucket excavator under test are in an abnormal operation.

[0051] The data display unit 125 is configured to record data from multiple sensors at various time points within a preset period in real time, generating a dynamic waveform graph. The dynamic waveform graph includes multiple waveforms, with each waveform corresponding to a sensor type. Abnormal data in the dynamic waveform graph is highlighted, and an early warning message is issued.

[0052] The control unit 126 includes one or more processors and a memory, and is configured to control the data acquisition unit 121, the data analysis unit 122, the data comparison unit 123, the fault diagnosis unit 124 and the data display unit 125 to perform their respective functions.

[0053] This bucket excavator bucket tooth operating status identification system is configured to acquire multiple sensor data from the bucket teeth of the bucket excavator under test at the current moment; classify the multiple sensor data according to sensor type to generate multiple sensor data subsets; sensor types include vibration sensors, pressure sensors, angle sensors, position sensors, range sensors, and power sensors; one sensor subset corresponds to one sensor type; based on a decision tree model, determine the historical best data and corresponding normal fluctuation range for each sensor data subset; based on the historical best data and normal fluctuation range corresponding to each sensor data subset, identify abnormal data in each sensor data subset to obtain the judgment result corresponding to each sensor data subset; and determine the operating status of the bucket teeth of the bucket excavator under test based on multiple judgment results.

[0054] As one implementation method, the bucket tooth operating status identification system for a bucket wheel excavator is specifically configured such that, before determining the historical optimal data range corresponding to each subset of sensor data, the method further includes: acquiring a historical sample dataset of the bucket teeth of the bucket wheel excavator to be tested; the historical sample dataset includes multiple historical sensor data of different sensor types corresponding to different time points within a preset time period before the current time; constructing a decision tree model based on the historical sample dataset; the decision tree model characterizes the mapping of sensor data to specific status labels based on the classification of sensor data and an initial comparison benchmark; the status labels include normal and abnormal.

[0055] As one implementation method, the bucket tooth operating status identification system for bucket wheel excavators is specifically configured to determine the historical optimal data and corresponding normal fluctuation range for each subset of sensor data based on a decision tree model. Specifically, this includes: classifying multiple historical sensor data sets based on sensor type to obtain multiple historical sensor data subsets; determining the status labels of the historical sensor data in each subset of historical sensor data based on the decision tree algorithm of the decision tree model, and determining the historical normal dataset and historical abnormal dataset for each subset of historical sensor data; determining the average value of multiple historical sensor data sets in the historical normal dataset based on the historical normal dataset, thereby determining the historical optimal data; and determining the normal fluctuation range based on the boundary values ​​in the historical normal dataset and the historical abnormal dataset.

[0056] As one implementation method, the bucket tooth operation status recognition system for bucket wheel excavators is specifically configured to determine abnormal data in each sensor data subset based on the historical best data and normal fluctuation range corresponding to each sensor data subset, and obtain the judgment result corresponding to each sensor data subset. Specifically, this includes: inputting multiple sensor data at the current moment into a decision tree model to obtain multiple sensor data subsets; determining the corresponding target historical best data and target normal fluctuation range according to the target sensor type corresponding to the target sensor data subset; comparing each sensor data in the target sensor data subset with the target historical best data to obtain multiple data differences; filtering out abnormal data differences from the multiple data differences that exceed the target normal fluctuation range, and identifying the sensor data associated with the abnormal data differences as abnormal data; and obtaining the judgment result corresponding to the target sensor data subset based on the number of abnormal data and the corresponding sensor type.

[0057] As one implementation method, the bucket tooth operating status identification system for a bucket wheel excavator is specifically configured to determine the operating status of the bucket teeth of the bucket wheel excavator under test based on multiple judgment results, including: if the number of abnormal data in the judgment results is greater than the abnormal number threshold, the operating status of the bucket teeth of the bucket wheel excavator under test is determined to be abnormal; if the number of abnormal data in the judgment results is less than or equal to the abnormal number threshold, the operating status of the bucket teeth of the bucket wheel excavator under test is determined to be normal.

[0058] As one implementation method, the bucket tooth operation status recognition system for bucket wheel excavators is specifically configured to determine the abnormality type of the bucket teeth of the bucket wheel excavator under test based on the sensor type corresponding to each abnormal data when it is determined that the bucket teeth of the bucket wheel excavator under test are in an abnormal operation.

[0059] As one implementation method, the bucket excavator bucket tooth operation status recognition system is specifically configured to issue a fault warning message when abnormal data is detected and it is determined that the bucket teeth of the bucket excavator under test are in abnormal operation. The warning message is used to indicate that the current sensor data is abnormal. The fault warning message includes one or more of the following: voice information, light information, and text information.

[0060] As one implementation method, the bucket tooth operation status recognition system of the bucket wheel excavator is specifically configured to record data from multiple sensors at various time points within a preset period in real time, and generate a dynamic waveform diagram; the dynamic waveform diagram includes multiple waveforms, with each waveform corresponding to a sensor type; and abnormal data in the dynamic waveform diagram is highlighted.

[0061] For ease of understanding, the following description, in conjunction with the accompanying drawings, details the method for identifying the operating status of bucket teeth in a bucket excavator provided in this application.

[0062] Figure 4This is a flowchart illustrating a method for identifying the operating status of bucket teeth in a bucket excavator according to an exemplary embodiment, such as... Figure 4 As shown, the method for identifying the operating status of bucket teeth in a bucket wheel excavator includes the following steps.

[0063] S21: Acquire multiple sensor data of the bucket teeth of the bucket excavator to be tested at the current moment.

[0064] The system acquires multiple sensor data at the current moment from multiple locations of the bucket teeth of the bucket excavator under test.

[0065] In one embodiment, the multiple sensor data include vibration data monitored by a vibration sensor, pressure data monitored by a pressure sensor, rotation angle data monitored by an angle sensor, movement position data monitored by a position sensor, range data monitored by a range sensor, and power data monitored by a power sensor.

[0066] By utilizing data from multiple sensors, including those for vibration, pressure, angle, position, range, and power, the operating status of the bucket teeth of the bucket wheel excavator is monitored more comprehensively from multiple dimensions, improving the coverage and accuracy of the operating status monitoring. S22, classify multiple sensor data according to sensor type and generate multiple sensor data subsets.

[0067] Sensor types include vibration sensors, pressure sensors, angle sensors, position sensors, range sensors, and power sensors.

[0068] A subset of sensors corresponds to one sensor type.

[0069] Different sensor data have different characteristics and fluctuation patterns. The multiple sensor data currently acquired are labeled and classified according to the source sensor type, generating multiple sensor data subsets. The generated sensor data subsets form accurate judgment nodes for candidate decision trees, thereby making the final operation status judgment clearer and the abnormal status location more accurate.

[0070] Understandably, the selected subsets of sensor data form accurate decision nodes in the candidate decision tree. Based on these decision nodes, the vibration data subset is checked sequentially for anomalies, followed by the pressure data subset, and so on, until all subsets are checked. In this way, through classification and independent determination of sensor data subsets, it is possible to clearly identify which aspect of the data is abnormal, thus achieving preliminary fault localization.

[0071] For example, multiple sensor data points are collected in real time, and labels are added to each data point according to the type of the source sensor. For example, vibration data is labeled "vibration," pressure data is labeled "pressure," and angle data is labeled "angle." After labeling, data with the same label are stored in a subset of the sensor data.

[0072] S23. Based on the decision tree model, determine the historical best data and the corresponding normal fluctuation range for each subset of sensor data.

[0073] Historical best data represents the baseline reference value of a subset of sensor data corresponding to a certain sensor type under normal operating conditions.

[0074] The normal fluctuation range is characterized by the normal deviation range that sensor data can deviate from the historical best data when the equipment is operating in good health.

[0075] Historical best data and corresponding normal fluctuation range provide clear and reliable judgment rules for decision tree models, enabling accurate and intelligent identification of the operating status of bucket teeth of bucket excavators.

[0076] To accurately determine the historical best data and corresponding normal fluctuation range of the sensor data subset corresponding to each sensor type, the following two steps are involved.

[0077] First, construct a decision tree model.

[0078] Specifically, a historical sample dataset of bucket teeth from the bucket excavator to be tested is obtained. Based on the historical sample dataset, a decision tree model is constructed.

[0079] The historical sample dataset includes multiple historical sensor data of different sensor types corresponding to different time points within a preset time period prior to the current time.

[0080] The decision tree model represents sensor data by classifying it and using an initial benchmark, mapping the sensor data to specific state labels. These state labels include normal and abnormal.

[0081] The historical sample dataset includes various sensor data under normal operating conditions and various sensor data under known abnormal conditions.

[0082] Decision tree models can automatically learn normal operating modes based on historical data and adapt to equipment aging or environmental changes, thereby dynamically adjusting judgment criteria. This improves the intelligence level of status recognition and enhances the system's adaptability.

[0083] Secondly, based on the decision tree model, the historical best data and corresponding normal fluctuation range for each subset of sensor data are determined. This involves the following three steps.

[0084] First, based on sensor type, multiple historical sensor data are classified to obtain multiple subsets of historical sensor data.

[0085] Based on the historical sensor data from the aforementioned historical sample data, classification and labeling processes are performed to form multiple historical sensor subsets.

[0086] Secondly, based on the decision tree algorithm of the decision tree model, the state labels of the historical sensor data in each historical sensor data subset are determined, and the historical normal dataset and historical abnormal dataset in each historical sensor data subset are determined.

[0087] In one implementation, based on the initial decision benchmarks corresponding to different types of sensor data in the decision tree model, each historical sensor subset is judged to determine the historical normal dataset and historical abnormal dataset of each historical sensor subset.

[0088] For example, vibration data: normal range (0-10 mm / s²), abnormal (>10 mm / s²); pressure data: normal range (10-15 MPa), abnormal (>15 MPa); angle data: normal range (40°-50°), ignoring minor fluctuations.

[0089] Finally, based on the historical normal datasets in each subset of historical sensor data, the average value of multiple historical sensor data in the historical normal datasets is determined to identify the optimal historical data. The normal fluctuation range is then determined based on the boundary values ​​in the historical normal datasets and the historical abnormal datasets.

[0090] Understandably, determining the historical optimal data and normal fluctuation range for each sensor type using historical sensor data provides an accurate decision-making benchmark for assessing the current state of multiple sensor data. Simultaneously, defining "historical optimal data" by calculating the average value from historical normal datasets provides an objective benchmark for state assessment, avoiding biases from manually set thresholds. This makes the state judgment benchmark closer to the actual optimal operating conditions of the equipment, improving the accuracy and scientific rigor of state identification. Furthermore, determining the normal fluctuation range relies not only on the boundaries of historical normal data but also references historical abnormal datasets, making the delineation of the normal range more discriminative and effectively distinguishing between critical abnormal states and healthy extreme fluctuations, significantly reducing the system's false alarm and false negative rates.

[0091] S24. Based on the historical best data and normal fluctuation range corresponding to each sensor data subset, abnormal data in each sensor data in each sensor data subset are determined, and the determination result corresponding to each sensor data subset is obtained.

[0092] Specifically, multiple sensor data points at the current moment are input into a decision tree model, resulting in multiple subsets of sensor data. Based on the target sensor type corresponding to each subset, the corresponding historical best data and normal fluctuation range of the target are determined. Each sensor data point in the subset is compared with the historical best data, yielding multiple data differences. From these differences, abnormal data differences exceeding the target's normal fluctuation range are selected, and the sensor data associated with these abnormal differences are identified as anomalous data. Based on the number of anomalous data points and their corresponding sensor types, the judgment result for the subset of target sensor data is obtained.

[0093] In one implementation, multiple sensor data collected at the current moment are fed into a decision tree model. Based on the sensor type labels of the sensor data, they are divided into multiple sensor data subsets. The sensor data in each subset is then evaluated one by one. For example, first, each vibration data point in the vibration data subset is evaluated. Based on the historical best data corresponding to the vibration data subset, the difference between each vibration data point and the historical best data is calculated. These differences are then compared with their corresponding normal fluctuation ranges. Vibration data whose deviations exceed the normal fluctuation range are identified as abnormal data, and the number of abnormal data points is determined. Thus, the evaluation result for this vibration data subset is [vibration data label, number of abnormal data points]. This evaluation process is repeated for all sensor data subsets to obtain the evaluation result for each subset.

[0094] S25, based on multiple judgment results, determine the operating status of the bucket teeth of the bucket excavator under test.

[0095] The process involves evaluating each subset of sensor data separately, resulting in multiple evaluation results. Each result includes the number of abnormal data points and the corresponding sensor type.

[0096] In one implementation, if the number of abnormal data in the judgment result is greater than the abnormal number threshold, the operating status of the bucket teeth of the bucket excavator under test is determined to be abnormal; if the number of abnormal data in the judgment result is less than or equal to the abnormal number threshold, the operating status of the bucket teeth of the bucket excavator under test is determined to be normal.

[0097] In this implementation, the number of abnormal data in the judgment result can be used to promptly determine whether the operating status of the bucket teeth of the bucket excavator under test has become abnormal, thus improving the timeliness of status identification.

[0098] Optionally, if it is determined that the bucket teeth of the bucket excavator under test are in an abnormal operation, the abnormality type of the bucket teeth of the bucket excavator under test can be determined according to the sensor type corresponding to each abnormal data.

[0099] In one implementation, when acquiring historical known fault data, a fault mode library is established, which contains the mapping relationship between various typical faults and sensor data characteristics.

[0100] If the assessment results show an anomaly in a single type of sensor data, the corresponding fault type is determined based on the sensor type. For example: abnormal vibration data corresponds to an anomaly type of collision or cracking of the bucket teeth; abnormal pressure data corresponds to an anomaly type of overload or impact from a hard object; abnormal angle data corresponds to an anomaly type of mechanical structure anomaly. This narrows down the fault to the component or physical process most relevant to the sensor, greatly shortening the diagnostic time.

[0101] If the judgment results show that multiple subsets of different types of sensors are abnormal simultaneously, it may indicate a more complex compound fault, and the judgment results of different sensor data can be cross-verified. For example, when the data from the vibration sensor and the pressure sensor both show instantaneous spikes, the diagnosis is a fault of bucket teeth impacting a hard object. When the vibration sensor data is continuously abnormal while the pressure data is normal, and the angle data shows a regular deviation, the diagnosis is a fault of loose mechanical connection of bucket teeth. When the pressure and power sensor data show a slow upward trend, while other data are stable, the diagnosis is a fault of progressive wear of bucket teeth.

[0102] In this way, by comprehensively analyzing multi-dimensional anomaly data to determine the fault type, the reliability and confidence of the diagnostic results are significantly improved. Furthermore, the diagnosed anomaly type is sent to the display interface, providing staff with clear fault type prompts and handling suggestions, thereby upgrading from anomaly monitoring to fault diagnosis and reducing reliance on the experience of on-site personnel.

[0103] For example, the establishment of the fault mode library and the automatic anomaly type diagnosis process can be implemented through the following two paths.

[0104] Path 1: Diagnosis based on the fault mode library.

[0105] Embed a failure mode library with "if-then" rules within an existing decision tree or a standalone diagnostic module. Specific examples include the following three.

[0106] First, the failure mode: the bucket teeth hit a hard object / overload IF vibration value rises sharply AND pressure value rises sharply AND power value increases instantaneously.

[0107] THEN Abnormal type diagnosis conclusion: High probability of hard object impact or overload. It is recommended to immediately check whether the bucket tooth cutting edge is cracked or curled.

[0108] Second, the failure mode is as follows: loose bucket teeth or worn connecting parts. The vibration value is consistently high and has a certain regularity. The angle data shows slight jumps at specific positions. The pressure value is normal.

[0109] THEN: The diagnosis of the abnormal type is highly likely to be due to loose bucket tooth fixing structure or bearing wear.

[0110] Third, failure mode: Bucket tooth wear (progressive) IF pressure value slowly increases (in order to achieve the same digging effect) AND power value slowly increases AND vibration and angle do not change drastically.

[0111] THEN Abnormal Diagnosis Conclusion: The teeth show normal wear or dullness, and it is recommended to schedule maintenance.

[0112] Path 2: Diagnosis based on machine learning models.

[0113] Machine learning models (such as random forests and neural networks) can be used to replace or supplement fault mode libraries. These models are trained to directly learn the complex mapping between sensor data sets and fault types.

[0114] Training process: The model is trained using a large amount of labeled historical sample data. Each historical sensor data is labeled, including status labels as normal data and abnormal data, as well as fault cause labels, such as impact, loosening, wear, etc.

[0115] Diagnostic process: The abnormal data after assessment is input into the trained diagnostic model in real time. The model will directly output a probability distribution of the fault type, such as: [impact 85%, looseness 10%, normal 5%]. In this way, the abnormal type of the bucket teeth of the bucket excavator under test can be intelligently determined.

[0116] Optionally, if abnormal data is detected and it is determined that the bucket teeth of the bucket excavator under test are in abnormal operation, a fault warning message is issued. The warning message is used to indicate that the current sensor data is abnormal. The fault warning message includes one or more of the following: voice information, light information, and text information.

[0117] Optionally, multiple sensor data points at various time points within a preset period are recorded in real time to generate a dynamic waveform graph. The dynamic waveform graph includes multiple waveforms, with each waveform corresponding to a sensor type. Abnormal data in the dynamic waveform graph is then highlighted.

[0118] In one implementation, sensor data acquired at various time points is classified and determined using a decision tree model in real time. Waveform graphs of various sensor data types are displayed on the user interface, with identified abnormal data highlighted in the waveforms. The final status identification conclusion is also displayed, including: abnormal data, the time point of occurrence of the abnormal data, the sensor type of the abnormal data, the type of abnormality, and suggestions for handling the abnormality.

[0119] In this way, the dynamic waveform diagram records the data within the preset period in real time, and based on the fault development process displayed by the waveform diagram, it provides users with more accurate and intuitive decision-making basis.

[0120] Alternatively, depending on the field conditions, the combination of sensor data may also include the following two: Firstly, it is applicable to hard rock working conditions in mines, where it is necessary to monitor metal fatigue and overheating risks. It uses a monitoring combination of vibration sensors, pressure sensors, strain sensors and temperature sensors to cover multi-dimensional faults such as wear, fracture and lubrication failure.

[0121] Secondly, the applicable scenario is a bucket wheel excavator with a complex drive system. To ensure redundancy and safety, vibration sensors, pressure sensors, angle sensors, and power sensors are installed. Among them, the power sensor can help to detect abnormal motor load, so as to ensure the safe operation of the bucket wheel excavator's bucket teeth can be monitored in real time.

[0122] Figure 5 This is a schematic diagram of a device for identifying the operating status of bucket teeth in a bucket wheel excavator, as provided in this application. Figure 5 The bucket excavator bucket tooth operation status identification device 50 includes: a first processor 501, a communication bus 502, a memory 503, a communication interface 504, an output device 505, an input device 506, and a second processor 507.

[0123] The bucket wheel excavator tooth operating status identification device 50 may include at least one first processor 501 and a memory 503 for storing processor-executable instructions. The first processor 501 is configured to execute the instructions in the memory 503 to implement the bucket wheel excavator tooth operating status identification method in the following embodiments.

[0124] In addition, the bucket excavator tooth operation status identification device 50 may also include a communication bus 502, at least one communication interface 504, an input device 506, and an output device 505.

[0125] The first processor 501 may be a processor (central processing unit, CPU), a microprocessor unit, an ASIC, or one or more integrated circuits for controlling the execution of programs according to the present application.

[0126] The communication bus 502 may include a path for transmitting information between the aforementioned components.

[0127] Communication interface 504 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0128] Input device 506 is used to receive input signals and output device 505 is used to output signals.

[0129] Memory 503 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed discs, laser discs, optical discs, digital universal discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory may exist independently and be connected to the processing unit via a bus. Memory may also be integrated with the processing unit.

[0130] The memory 503 stores instructions for executing the scheme of this application, and the execution is controlled by the first processor 501. The first processor 501 executes the instructions stored in the memory 503 to realize the functions of the method of this application.

[0131] In a specific implementation, as one example, the first processor 501 may include one or more CPUs, for example... Figure 5 CPU0 and CPU1 in the CPU.

[0132] In a specific implementation, as one example, the bucket excavator tooth operating status identification device 50 may include multiple processors, such as... Figure 5 The first processor 501 and the second processor 507 are described. Each of these processors can be a single-core processor or a multi-core processor. A processor here can refer to one or more devices, circuits, and / or processing cores used to process data (such as computer program instructions).

[0133] The bucket excavator's bucket tooth operating status identification device, such as Figure 5 The diagram includes a first processor 501 and a memory 503 for storing executable instructions of the first processor 501. The first processor 501 is configured to execute executable instructions to implement the bucket tooth operating status identification method for a bucket wheel excavator as described in any of the possible embodiments above. Since the same technical effects can be achieved, further details are omitted here to avoid repetition.

[0134] This application also provides a computer-readable storage medium. When the instructions in the computer-readable storage medium are executed by the processor of the bucket excavator bucket tooth running status identification device, the bucket excavator bucket tooth running status identification device can perform the bucket excavator bucket tooth running status identification method as described in any of the above possible embodiments. And it can achieve the same technical effect; to avoid repetition, it will not be described again here.

[0135] This application also provides a computer program product, including a computer program or instructions, which are executed by a processor as described in any of the possible implementations of the bucket excavator bucket tooth operating status identification method. This achieves the same technical effect, and to avoid repetition, will not be repeated here.

[0136] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0137] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for identifying the operating status of bucket teeth in a bucket wheel excavator, characterized in that, The method includes: Acquire multiple sensor data of the bucket teeth of the bucket excavator to be tested at the current moment; Based on sensor type, the data from the multiple sensors are classified to generate multiple subsets of sensor data; the sensor types include vibration sensors, pressure sensors, angle sensors, position sensors, range sensors, and power sensors; each subset of sensors corresponds to one of the sensor types. Based on the decision tree model, the historical best data and the corresponding normal fluctuation range for each subset of sensor data are determined; Based on the historical best data and the normal fluctuation range corresponding to each of the sensor data subsets, abnormal data in each of the sensor data in each of the sensor data subsets are determined respectively, and the determination result corresponding to each of the sensor data subsets is obtained. Based on the multiple determination results, the operating status of the bucket teeth of the bucket excavator under test is determined.

2. The method for identifying the operating status of bucket teeth in a bucket wheel excavator according to claim 1, characterized in that, Before determining the historical optimal data range corresponding to each of the sensor data subsets, the method further includes: Obtain the historical sample dataset of the bucket teeth of the bucket excavator to be tested; the historical sample dataset includes multiple historical sensor data of different sensor types corresponding to different time points within a preset time period before the current time. Based on the historical sample dataset, a decision tree model is constructed; the decision tree model represents the mapping of sensor data to specific state labels based on the classification of sensor data and an initial comparison benchmark; the state labels include normal and abnormal.

3. The method for identifying the operating status of bucket teeth in a bucket wheel excavator according to claim 2, characterized in that, The step of determining the historical optimal data and corresponding normal fluctuation range for each subset of sensor data based on the decision tree model specifically includes: Based on the sensor type, the multiple historical sensor data are classified to obtain multiple subsets of historical sensor data; Based on the decision tree algorithm of the decision tree model, the state label of the historical sensor data in each historical sensor data subset is determined, and the historical normal dataset and historical abnormal dataset in each historical sensor data subset are determined. Based on the historical normal datasets in each of the historical sensor data subsets, the average value of multiple historical sensor data in the historical normal datasets is determined, thereby determining the historical optimal data; The normal fluctuation range is determined based on the boundary values ​​in the historical normal dataset and the historical abnormal dataset.

4. The method for identifying the operating status of bucket teeth in a bucket wheel excavator according to claim 3, characterized in that, The step of determining abnormal data in each sensor data set based on the historical best data and the normal fluctuation range corresponding to each of the sensor data subsets, and obtaining the determination result corresponding to each sensor data subset, specifically includes: The current sensor data is input into the decision tree model to obtain multiple subsets of the sensor data; Based on the target sensor type corresponding to the subset of target sensor data, determine the corresponding historical best data and normal fluctuation range of the target. Each sensor data in the target sensor data subset is compared with the target's historical best data to obtain multiple data differences; From multiple data differences, abnormal data differences that exceed the normal fluctuation range of the target are selected, and the sensor data associated with the abnormal data differences are identified as the abnormal data. Based on the quantity of the abnormal data and the corresponding sensor type, a determination result is obtained for the subset of target sensor data.

5. The method for identifying the operating status of bucket teeth in a bucket wheel excavator according to claim 4. Its characteristic is that, according to multiple determination results, determining the operating status of the bucket teeth of the bucket excavator under test includes: detecting that the number of abnormal data in the determination results is greater than the abnormal number threshold, and determining that the operating status of the bucket teeth of the bucket excavator under test is abnormal; detecting that the number of abnormal data in the determination results is less than or equal to the abnormal number threshold, and determining that the operating status of the bucket teeth of the bucket excavator under test is normal.

6. The method for identifying the operating status of bucket teeth in a bucket wheel excavator according to claim 5, characterized in that the method further includes: If it is determined that the bucket teeth of the bucket excavator under test are in an abnormal operation, the abnormality type of the bucket teeth of the bucket excavator under test is determined according to the sensor type corresponding to each abnormal data.

7. The method for identifying the operating status of bucket teeth in a bucket wheel excavator according to claim 5, characterized in that, The method further includes: If the abnormal data is detected and it is determined that the bucket teeth of the bucket excavator under test are in abnormal operation, a fault warning message is issued, which is used to indicate that the current sensor data is abnormal; The fault warning information includes one or more of the following: voice information, light information, and text information.

8. The method for identifying the operating status of bucket teeth in a bucket wheel excavator according to claim 5, characterized in that, The method further includes: The system records data from multiple sensors at various time points within a preset period in real time, generating a dynamic waveform graph. The dynamic waveform graph includes multiple waveforms, with each waveform corresponding to a sensor type. Abnormal data in the dynamic waveform graph is then highlighted.

9. A system for identifying the operating status of bucket teeth in a bucket wheel excavator, characterized in that, The system includes: an identification module and a sensor module; the identification module and the sensor module are connected via communication. The sensor module is used to collect data from multiple sensors on the bucket teeth of the bucket excavator under test in real time. The identification module is used to acquire multiple sensor data of the bucket teeth of the bucket excavator under test at the current moment; classify the multiple sensor data according to the sensor type to generate multiple sensor data subsets; the sensor types include vibration sensors, pressure sensors, angle sensors, position sensors, range sensors, and power sensors; one sensor subset corresponds to one of the sensor types; determine the historical best data and the corresponding normal fluctuation range for each sensor data subset according to a decision tree model; based on the historical best data and the normal fluctuation range for each sensor data subset, determine the abnormal data in each sensor data in each sensor data subset to obtain the determination result corresponding to each sensor data subset; and determine the operating status of the bucket teeth of the bucket excavator under test according to the multiple determination results. The bucket excavator bucket tooth operating status identification system is configured to perform the electricity user classification method as described in any one of claims 1-8.

10. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the bucket tooth operating status identification method of any one of claims 1-8.

Images