A method and system for monitoring the operation and maintenance state of an unmanned system of a bucket wheel machine

Abstract

This application relates to the field of industrial equipment operation and maintenance monitoring technology, specifically to a method for monitoring the operation and maintenance status of an unmanned bucket wheel excavator system. First, a multi-source monitoring data set of the bucket wheel excavator is acquired, including data on the equipment's mechanical structure, power system, and operating environment. Next, the multi-source monitoring data set undergoes equipment status correlation analysis to obtain a description of the equipment status correlation relationships. Based on this description, abnormal status pattern recognition processing is performed to generate abnormal status pattern identifiers. Maintenance decision instructions, including maintenance priorities and operation guidelines, are generated based on the abnormal status pattern identifiers. Finally, the maintenance decision instructions are sent to the unmanned control system to trigger the corresponding equipment maintenance operation, achieving accurate monitoring and automated maintenance of the bucket wheel excavator's operation and maintenance status.

Description

Technical Field

[0001] This application relates to the field of big data technology, and more specifically, to a method and system for monitoring the operation and maintenance status of an unmanned bucket wheel excavator system. Background Technology

[0002] In industrial production, bucket wheel excavators, as important material handling equipment, are widely used in coal mines, ports, and other locations. Their stable operation is crucial for ensuring the continuity and efficiency of production processes. Traditional bucket wheel excavator maintenance mainly relies on manual periodic inspections and experience-based judgment, which have many limitations.

[0003] On the one hand, manual inspections struggle to obtain real-time and comprehensive information on the operating status of bucket wheel excavators. Due to the complex structure of bucket wheel excavators, which includes numerous mechanical components and power systems, manual inspections often only check some key parts, easily overlooking potential faults. Moreover, the frequency of manual inspections is limited, making it impossible to promptly detect sudden abnormalities that occur during equipment operation.

[0004] On the other hand, judgments based on human experience lack scientific rigor and accuracy. Different inspection personnel have varying levels of experience and judgment, leading to subjectivity and uncertainty in equipment condition assessments. This can easily result in misjudgments or omissions, impacting maintenance decisions and repair effectiveness. Furthermore, traditional maintenance methods cannot comprehensively analyze and correlate the overall operating status of equipment, making it difficult to predict equipment failures in advance. Repairs are often only carried out after obvious malfunctions occur, increasing maintenance costs and the risk of production interruptions. Therefore, existing bucket wheel excavator operation and maintenance status monitoring methods urgently need improvement to enhance equipment reliability and maintenance efficiency. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide a method and system for monitoring the operation and maintenance status of an unmanned bucket wheel excavator system.

[0006] In conjunction with the first aspect of this application, a method for monitoring the operation and maintenance status of an unmanned bucket wheel excavator system is provided, along with a system for monitoring the operation and maintenance status of an unmanned bucket wheel excavator system. The method includes:

[0007] Acquire a multi-source monitoring data set of the bucket wheel excavator, which includes equipment mechanical structure monitoring data, power system operation data, and operating environment parameter data;

[0008] The multi-source monitoring data set is subjected to equipment status association parsing processing to obtain a description of equipment status association that reflects the linkage relationship between equipment components;

[0009] Based on the device status association description, abnormal status pattern recognition processing is performed to generate an abnormal status pattern identifier that indicates the type and scope of the device abnormality.

[0010] Based on the abnormal state pattern identifier, a maintenance decision instruction containing maintenance priority and operation guidance is generated;

[0011] The maintenance decision command is sent to the unattended control system to trigger the corresponding equipment maintenance operation.

[0012] In conjunction with the second aspect of this application, a maintenance status monitoring system for an unmanned bucket wheel excavator system is provided. The maintenance status monitoring system for an unmanned bucket wheel excavator system includes a machine-readable storage medium and a processor. The machine-readable storage medium stores machine-executable instructions. When the processor executes the machine-executable instructions, the maintenance status monitoring system for an unmanned bucket wheel excavator system implements the aforementioned maintenance status monitoring method for an unmanned bucket wheel excavator system.

[0013] In conjunction with the third aspect of this application, a computer-readable storage medium is provided, wherein computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed, the aforementioned method for monitoring the operation and maintenance status of an unmanned bucket wheel excavator system is implemented.

[0014] Combining any of the above aspects, by acquiring a multi-source monitoring data set of the bucket wheel excavator, comprehensively covering equipment mechanical structure monitoring data, power system operation data, and operating environment parameter data, and performing equipment status correlation analysis on the multi-source monitoring data set, a description of equipment status correlation reflecting the linkage relationship between equipment components is obtained. This deeply explores the internal connections between various equipment components, enabling maintenance personnel to clearly understand the overall operating logic of the equipment. Based on the equipment status correlation description, abnormal state pattern recognition processing is performed to generate abnormal state pattern identifiers indicating the type and scope of equipment abnormalities. This allows for quick and accurate identification of abnormal situations and clarification of the scope of impact, helping maintenance personnel to take timely and targeted measures to prevent the escalation and spread of faults. Maintenance decision instructions containing maintenance priorities and operation guidelines are generated based on the abnormal state pattern identifiers. This allows for the rational arrangement of maintenance work according to the severity of equipment abnormalities, improving maintenance efficiency and reducing maintenance costs. Finally, the maintenance decision instructions are sent to the unattended control system to trigger the corresponding equipment maintenance operation, realizing the automation and intelligence of equipment operation and maintenance, reducing manual intervention, improving the accuracy and timeliness of operation and maintenance, and effectively enhancing the stability and reliability of the bucket wheel excavator operation. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained in conjunction with these drawings without creative effort.

[0016] Figure 1 This application provides a flowchart illustrating the operation and maintenance status monitoring method for an unmanned bucket wheel excavator system. Detailed Implementation

[0017] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or ends.

[0019] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0020] Figure 1 This document illustrates a flowchart of a method for monitoring the operation and maintenance status of an unmanned bucket wheel excavator system, as provided in an embodiment of this application. It should be understood that in other embodiments, the order of some steps in this method for monitoring the operation and maintenance status of an unmanned bucket wheel excavator system may be shared based on actual needs, or some steps may be omitted or maintained. The detailed components of this method for monitoring the operation and maintenance status of an unmanned bucket wheel excavator system include:

[0021] This embodiment discloses a method for monitoring the operation and maintenance status of an unmanned bucket wheel excavator system. This method can effectively monitor the equipment's operation and maintenance status by processing and analyzing multi-source monitoring data of the bucket wheel excavator, and generate corresponding maintenance decision instructions to ensure the stable operation of the bucket wheel excavator. The following will describe each step of the method in detail.

[0022] Step S110: Obtain a multi-source monitoring data set for the bucket wheel excavator, which includes equipment mechanical structure monitoring data, power system operation data, and operating environment parameter data.

[0023] In unmanned systems for bucket wheel excavators, comprehensive monitoring data needs to be collected from multiple sources to fully understand the equipment's operational status. This data covers various aspects, including the equipment's mechanical structure, power system, and operating environment, collectively forming a multi-source monitoring data set.

[0024] Step S110 may include steps S111-S115:

[0025] Step S111: Collect mechanical structure monitoring data by using stress sensors deployed on the cantilever of the bucket wheel excavator. The mechanical structure monitoring data includes deformation pressure distribution information at the cantilever joint.

[0026] Multiple stress sensors are deployed at specific intervals and in a specific layout on the cantilever of the bucket wheel excavator. These stress sensors can detect the stress changes experienced by various parts of the cantilever in real time during operation, thereby collecting mechanical structure monitoring data. Among them, the cantilever joint is a critical area where stress is concentrated and deformation is prone to occur. Therefore, deformation pressure distribution information is an important component of the mechanical structure monitoring data. For example, the stress sensors record the deformation pressure values ​​at different locations at the cantilever joint, forming a multi-dimensional set of deformation pressure distribution information. For instance, deformation pressure data are collected at different angles and positions of the cantilever joint, and these data together constitute the deformation pressure distribution of that part.

[0027] Step S112: Collect power system operation data by embedding temperature and current sensors of the power motor. The power system operation data includes the motor winding temperature change sequence and current fluctuation characteristics.

[0028] The power motor is the core power source for the bucket wheel excavator, and its operating status directly affects the normal operation of the entire equipment. Embedded within the power motor are temperature and current sensors. The temperature sensor monitors the temperature changes of the motor windings in real time, recording temperature values ​​at regular time intervals to form a sequence of motor winding temperature changes. This sequence is a multi-dimensional time-series data set, containing temperature information of the motor windings at different times. The current sensor collects current changes during motor operation. By analyzing the current data, current fluctuation characteristics can be extracted. These characteristics are also multi-dimensional, including information such as the amplitude and frequency of current fluctuations. All of this information collectively constitutes the operating data of the power system.

[0029] Step S113: Collect environmental parameter data of the work area by using temperature and humidity sensors and dust concentration sensors installed in the work area. The environmental parameter data of the work area includes information on the distribution of ambient temperature gradient and information on the distribution of dust particle density.

[0030] The operating environment of a bucket wheel excavator has a significant impact on its operational status and equipment lifespan, thus requiring monitoring. Multiple temperature and humidity sensors and dust concentration sensors are strategically placed within the excavator's operating area. The temperature and humidity sensors collect ambient temperature and humidity information at different locations. Processing and analyzing this information yields multi-dimensional information on the ambient temperature gradient distribution, reflecting the temperature variation gradient across different locations within the operating area. The dust concentration sensors monitor the concentration of dust particles in the operating environment. Measurements at different locations generate dust particle density distribution information, which is also multi-dimensional, including dust particle density data at various points within the operating area. These data collectively constitute the operating environment parameter data.

[0031] Step S114: Perform timestamp synchronization processing on the mechanical structure monitoring data, power system operation data, and operating environment parameter data to ensure that the collection time points of each type of data are aligned.

[0032] Since mechanical structure monitoring data, power system operation data, and operating environment parameter data are collected from different sensors at different locations, their collection times may differ. To ensure the accuracy of subsequent data processing and analysis, these data need to be timestamped. Specifically, this involves adjusting the timestamp of each data set using a unified time benchmark, ensuring that different types of data collected at the same time point can be accurately correlated. For example, by unifying the mechanical structure monitoring data, power system operation data, and operating environment parameter data to a millisecond-based time scale, for each time point t, corresponding mechanical structure monitoring data, power system operation data, and operating environment parameter data can be found, ensuring consistency of each type of data in the time dimension for subsequent correlation analysis.

[0033] Step S115: Perform integrity verification on the synchronized data of each type, remove invalid data segments with missing data or signal interference, and generate a multi-source monitoring data set containing valid mechanical structure monitoring data, valid power system operation data, and valid working environment parameter data.

[0034] After time-stamping synchronization, the data still needs to undergo integrity verification to remove data segments that are missing or invalid due to signal interference. Invalid data can affect the accuracy of subsequent analysis results. The synchronized mechanical structure monitoring data, power system operation data, and operating environment parameter data are checked separately to determine if there are any missing data segments or if external signal interference has caused data anomalies. Data segments with these problems are removed, leaving only valid data. This valid data includes valid mechanical structure monitoring data, valid power system operation data, and valid operating environment parameter data, which together constitute a multi-source monitoring data set.

[0035] Step S115 may include steps S1151-S1155:

[0036] Step S1151: Perform data continuity check processing on the mechanical structure monitoring data, count the number of missing data points within the continuous acquisition time period, and mark the time period with the number of missing data points exceeding a preset threshold as invalid mechanical data segments.

[0037] For mechanical structure monitoring data, a data continuity check is necessary. First, a continuous data collection period is determined, and then the number of missing data points within that period is counted. A preset threshold is established, determined based on actual monitoring needs and data acquisition accuracy requirements. When the number of missing data points within a certain time period exceeds this preset threshold, it indicates that the mechanical structure monitoring data for that period is incomplete and cannot be used for effective analysis; therefore, that time period is marked as an invalid mechanical data segment. For example, within a continuous ten-minute data collection period, if the number of missing data points exceeds a certain percentage of the theoretically required total number of data points for that period, then that ten-minute period will be marked as an invalid mechanical data segment.

[0038] Step S1152: Perform signal noise analysis on the power system operation data, calculate the signal-to-noise ratio parameter of the current fluctuation characteristics, and mark the time period when the signal-to-noise ratio parameter is lower than a preset threshold as invalid power data segments.

[0039] Current fluctuations in power system operating data are susceptible to various noise interferences, necessitating signal-to-noise analysis. Specific algorithms are used to analyze these current fluctuations and calculate their signal-to-noise ratio (SNR). The SNR reflects the ratio of valid information to noise in the signal; a higher SNR indicates less noise interference and more reliable data. A preset SNR threshold is established. When the SNR of the current fluctuations falls below this threshold within a certain time period, it indicates significant noise interference in the power system operating data during that period, making the data unreliable. This time period is then marked as an invalid power data segment.

[0040] Step S1153: Perform numerical rationality verification on the work environment parameter data, check whether the dust particle density distribution information exceeds the maximum concentration range allowed by the equipment, and mark the time period that exceeds the range as invalid environmental data segment.

[0041] The dust particle density distribution information in the operating environment parameter data needs to be verified for numerical reasonableness. During equipment operation, there is a maximum permissible concentration range for dust particle density in the operating environment, determined based on the equipment's design standards and operational requirements. By examining each data point in the dust particle density distribution information, it is determined whether it exceeds this maximum concentration range. If, within a certain time period, the data in the dust particle density distribution information exceeds the maximum permissible concentration range, then the operating environment parameter data for that time period does not meet the equipment's operational requirements, and that time period is marked as an invalid environmental data segment.

[0042] Step S1154: Remove the invalid mechanical data segments, invalid power data segments, and invalid environmental data segments from the synchronized data, and retain the remaining valid data segments.

[0043] After identifying invalid mechanical data segments, invalid power data segments, and invalid environmental data segments, these invalid data segments need to be completely removed from the data after timestamp synchronization. During the removal process, it is crucial to accurately identify and remove all data corresponding to these invalid segments, retaining only those complete and reliable data segments that were not marked as invalid; these are the remaining valid data segments.

[0044] Step S1155: Perform data format unification processing on the effective data fragments to ensure that the mechanical structure monitoring data, power system operation data and working environment parameter data have the same data storage format and timestamp marking rules, and generate a multi-source monitoring data set containing effective mechanical structure monitoring data, effective power system operation data and effective working environment parameter data.

[0045] Although the remaining valid data fragments are valid in content, they may originate from different sensors, and their data storage formats and timestamp rules may differ. To facilitate subsequent processing and analysis, these valid data fragments need to undergo a unified data format process. This includes standardizing the data storage format, for example, converting all data to the same file format and data structure; and standardizing the timestamp rules to ensure consistent timestamp representation and precision. After this processing, the mechanical structure monitoring data, power system operation data, and operating environment parameter data will have the same data storage format and timestamp rules, collectively forming a multi-source monitoring data set containing valid mechanical structure monitoring data, valid power system operation data, and valid operating environment parameter data.

[0046] Step S120: Perform equipment status association parsing processing on the multi-source monitoring data set to obtain a description of equipment status association that reflects the linkage relationship between equipment components.

[0047] After obtaining the multi-source monitoring data set, it is necessary to perform equipment status correlation analysis processing. The purpose of this step is to uncover the inherent correlations between various components of the equipment and between the equipment and the operating environment. By analyzing and processing the multi-source monitoring data, the correlations between different data points are identified, thereby obtaining a description of equipment status correlations that reflects the linkages between equipment components. The aforementioned description of equipment status correlations includes various parameters and models representing these correlations.

[0048] Step S120 may include steps S121-S125:

[0049] Step S121: Perform feature mapping processing on the mechanical structure monitoring data and power system operation data in the multi-source monitoring data set to establish a correspondence table between the cantilever joint deformation pressure distribution information and the motor current fluctuation characteristics.

[0050] In the multi-source monitoring dataset, mechanical structure monitoring data and power system operation data are selected for feature mapping processing. Specifically, this involves associating each feature in the cantilever joint deformation pressure distribution information with each feature in the motor current fluctuation characteristics. By analyzing the temporal and numerical changes of these two data points, the corresponding patterns are identified, and these correspondences are then compiled into a correspondence table. For example, when the deformation pressure at a certain location of the cantilever joint changes, a certain parameter in the motor current fluctuation characteristics will also change accordingly. These correspondences are recorded in the correspondence table, forming a multi-dimensional set of correspondences.

[0051] Step S122: Perform association rule matching processing on the power system operation data and the working environment parameter data in the multi-source monitoring data set to identify the correlation threshold between the motor winding temperature change sequence and the ambient temperature gradient distribution information.

[0052] Power system operation data and operating environment parameter data from a multi-source monitoring dataset were selected and processed using association rule matching. The focus was on analyzing the correlation between the motor winding temperature change sequence and the ambient temperature gradient distribution information. A specific algorithm and analysis method were used to identify the correlation threshold between the two. This correlation threshold is a multi-dimensional parameter used to measure the critical value of the correlation between the motor winding temperature change sequence and the ambient temperature gradient distribution information. When the correlation exceeds or falls below this threshold, it indicates that a specific correlation exists between them.

[0053] Step S123: Perform dynamic relationship modeling on the mechanical structure monitoring data and the working environment parameter data in the multi-source monitoring data set to construct a response curve model of the cantilever joint deformation pressure distribution information as a function of dust particle density.

[0054] Dynamic relationship modeling was performed on mechanical structure monitoring data and operational environment parameter data from a multi-source monitoring dataset. Taking the cantilever joint deformation pressure distribution information and dust particle density distribution information as research objects, the study analyzed how the cantilever joint deformation pressure distribution information changes accordingly with changes in dust particle density. Through fitting and analysis of a large number of data samples, a response curve model of the cantilever joint deformation pressure distribution information as a function of dust particle density was constructed. This model is a multi-dimensional curve model that can reflect the changing trend and law of cantilever joint deformation pressure distribution under different dust particle densities.

[0055] Step S124: Perform comprehensive analysis and processing on the correspondence table, correlation threshold and response curve model to extract the linkage influence factors between equipment mechanical structure, power system and working environment.

[0056] After obtaining the correspondence table, correlation threshold, and response curve model, they need to be comprehensively analyzed. From the information contained in these three documents, linkage influencing factors that characterize the mutual influence and interaction between the equipment's mechanical structure, power system, and operating environment are extracted. These linkage influencing factors are multi-dimensional, reflecting the linkage relationship between the three from different perspectives; for example, how changes in the mechanical structure affect the power system, and how changes in the operating environment affect both the mechanical structure and the power system.

[0057] Step S124 may include steps S1241-S1245:

[0058] Step S1241: Extract the maximum correlation value between the cantilever joint deformation pressure distribution information and the motor current fluctuation characteristics from the correspondence table, and use it as the mechanical-power linkage factor.

[0059] The correspondence table records various relationships between the cantilever joint deformation pressure distribution information and the motor current fluctuation characteristics. Among these relationships, there exists a maximum correlation value, which most significantly reflects the degree of linkage between the two. This maximum correlation value is extracted and used as the mechanical-power linkage factor. This factor is a multi-dimensional parameter that contains the maximum correlation information between different features.

[0060] Step S1242: Extract the highest correlation coefficient between the motor winding temperature change sequence and the ambient temperature gradient distribution information from the correlation threshold, and use it as the power-environment linkage factor.

[0061] Among the information included in the correlation threshold, there are multiple correlation coefficients between the motor winding temperature change sequence and the ambient temperature gradient distribution information. The highest correlation coefficient best reflects the close relationship between the two. This highest correlation coefficient is extracted as the power-environment linkage factor. This factor is also multi-dimensional, reflecting the highest correlation between different characteristics of the power system and the operating environment.

[0062] Step S1243: Extract the maximum slope value of the cantilever joint deformation pressure distribution information as a function of dust particle density from the response curve model, and use it as a mechanical-environment linkage factor.

[0063] The response curve model describes the variation of cantilever joint deformation pressure distribution with dust particle density, and the slope of the curve reflects the rate of change. Within the response curve model, there exists a maximum slope value, which represents the most drastic change in cantilever joint deformation pressure distribution with dust particle density. This maximum slope value is extracted as a mechanical-environment linkage factor. This factor is multi-dimensional and corresponds to the maximum slope information under different conditions.

[0064] Step S1244: Normalize the mechanical-power linkage factor, power-environment linkage factor and mechanical-environment linkage factor to eliminate the dimensional differences between different factors.

[0065] Since the mechanical-dynamic linkage factor, the dynamic-environment linkage factor, and the mechanical-environment linkage factor may have different dimensions, they need to be normalized to facilitate subsequent comprehensive analysis and calculation. The normalization process involves converting the values ​​of each factor to a uniform numerical range, such as between zero and one. This eliminates the dimensional differences between different factors, allowing them to be compared and analyzed on the same scale.

[0066] Step S1245: Calculate the overall linkage sensitivity index of the equipment based on the normalized linkage factors. The overall linkage sensitivity index is the weighted average of each normalized linkage factor. The weight coefficients are preset according to the degree of mutual influence between the systems in the actual operation of the equipment.

[0067] After obtaining the normalized mechanical-power linkage factor, power-environment linkage factor, and mechanical-environment linkage factor, the overall linkage sensitivity index of the equipment is calculated. This index is obtained by weighted averaging of these three normalized linkage factors. The weighting coefficients are pre-set based on the degree of mutual influence between the mechanical structure, power system, and operating environment during actual operation, with different levels of influence corresponding to different weight values. Through weighted averaging, a multi-dimensional overall linkage sensitivity index is obtained, which comprehensively reflects the overall linkage sensitivity between various parts of the equipment.

[0068] Step S125: Generate a description of equipment status correlation based on the linkage influence factor, which includes component correlation strength parameters and environmental influence weight coefficients. The component correlation strength parameters are used to characterize the linkage sensitivity between different mechanical components, and the environmental influence weight coefficients are used to characterize the degree of influence of operating environment parameters on equipment operating status.

[0069] Based on the extracted linkage influencing factors, further analysis and processing are performed to generate a description of equipment status correlation. This description includes component correlation strength parameters and environmental impact weight coefficients. The component correlation strength parameters are multi-dimensional, characterizing the sensitivity of the interaction between different mechanical components from various aspects, such as whether a small change in one component will cause a significant change in another component. The environmental impact weight coefficients are also multi-dimensional, used to characterize the degree of influence of various parameters in the operating environment on the equipment's operating status. Different environmental parameters have different degrees of influence on the equipment, and these differences are reflected through the weight coefficients.

[0070] Step S130: Perform abnormal state pattern recognition processing based on the device state association description to generate an abnormal state pattern identifier that indicates the type and scope of the device abnormality.

[0071] Once the device status relationship description is available, abnormal status pattern recognition can be performed based on it. By comparing and analyzing the current status relationship of the device with the status relationship under normal conditions, the existence of abnormal status patterns can be identified. Once an abnormality is detected, a corresponding abnormal status pattern identifier is generated, which indicates the type of abnormality and the scope of its impact.

[0072] Step S130 may include steps S131-S135:

[0073] Step S131: Call the pre-stored bucket wheel excavator normal state benchmark library, which includes the standard distribution range of mechanical structure deformation pressure, the standard amplitude range of power system current fluctuation, and the standard fluctuation threshold of environmental parameters.

[0074] The pre-stored bucket wheel excavator normal state benchmark library was established through extensive data collection, analysis, and organization during the normal operation of the bucket wheel excavator. It includes standard data ranges in multiple aspects: the standard distribution range of mechanical structure deformation pressure is multi-dimensional, covering the reasonable distribution range of deformation pressure in different mechanical structure parts during normal operation; the standard amplitude range of power system current fluctuation is also multi-dimensional, specifying the upper and lower limits of current fluctuation amplitude during normal operation; and the standard fluctuation thresholds of environmental parameters are also multi-dimensional, clearly defining the fluctuation range of various parameters in the operating environment under normal conditions.

[0075] Step S132: Match and compare the component association strength parameters in the device status association description with the standard association strength parameters in the normal status benchmark library to identify abnormal association strength parameters that exceed the standard range.

[0076] The component association strength parameters in the equipment status correlation description reflect the sensitivity of linkage between different mechanical components of the current equipment. These parameters are matched and compared with standard association strength parameters in the normal state benchmark library. Each component association strength parameter in each dimension is compared with the standard range of the corresponding standard association strength parameter to determine if the current parameter is within the standard range. If a component association strength parameter in a certain dimension exceeds the standard range, then that parameter is an abnormal association strength parameter and is identified.

[0077] Step S133: Perform deviation analysis on the environmental impact weight coefficient in the equipment status association description and the standard environmental impact weight coefficient in the normal state benchmark library, and calculate the absolute value of the difference between the actual weight coefficient and the standard weight coefficient.

[0078] For the environmental impact weight coefficients in the equipment status correlation description, a deviation analysis is performed between them and the standard environmental impact weight coefficients in the normal state benchmark library. For each dimension's environmental impact weight coefficient, the difference between the actual environmental impact weight coefficient and the standard environmental impact weight coefficient is calculated, and its absolute value is taken. This absolute value of the difference reflects the degree of deviation between the actual environmental impact weight coefficient and the standard value; the larger the absolute value of the difference, the more severe the deviation.

[0079] Step S134: Perform feature aggregation processing on the identified abnormal correlation strength parameters and the absolute value of the difference obtained from the deviation analysis to generate a comprehensive abnormal feature set containing abnormal correlation features and environmental impact abnormal features.

[0080] The identified anomaly correlation strength parameters and the absolute values ​​of the differences obtained through deviation analysis are subjected to feature aggregation processing. The anomaly correlation strength parameters constitute the anomaly correlation features, which are multi-dimensional and reflect abnormal situations in the linkage relationships between mechanical components. The absolute values ​​of the differences constitute the environmental impact anomaly features, which are also multi-dimensional and reflect the deviation of the environmental impact weight coefficient from the standard value. Combining these two types of features forms a comprehensive set of anomaly features, containing all anomaly characteristic information of the equipment in terms of component correlation and environmental impact.

[0081] Step S135: Perform pattern matching processing based on the comprehensive abnormal feature set and the predefined abnormal pattern template library to determine the corresponding equipment abnormality type and the range of mechanical components affected by the abnormality, and generate an abnormal state pattern identifier containing an abnormality type identifier and a set of affected components.

[0082] After the comprehensive anomaly feature set is generated, it is matched against a predefined anomaly pattern template library. This library stores various known anomaly pattern templates, each corresponding to a specific equipment anomaly type and the range of affected components. By comparing the similarity between the comprehensive anomaly feature set and each anomaly pattern template, the best-matching template is found, thereby determining the current anomaly type of the equipment and the range of mechanical components affected. Finally, an anomaly state pattern identifier containing an anomaly type identifier and the set of affected components is generated.

[0083] Step S135 may include steps S1351-S1356:

[0084] Step S1351: Input the comprehensive abnormal feature set into the abnormal pattern matching module. The abnormal pattern matching module stores mechanical structure jamming abnormal templates, power system overload abnormal templates, and environmental parameter exceeding limit abnormal templates.

[0085] The comprehensive set of abnormal features is input into the abnormal pattern matching module, a dedicated processing unit for abnormal pattern matching. This module stores various common abnormal pattern templates: a mechanical structure jamming abnormal template to match abnormal features indicating mechanical structure jamming; a power system overload abnormal template to match abnormal features indicating power system overload; and an environmental parameter exceeding limits abnormal template to match abnormal features indicating that operating environment parameters exceed normal ranges. These templates are multi-dimensional, containing various feature information corresponding to the corresponding abnormal type.

[0086] Step S1352: Calculate the feature similarity value between the comprehensive abnormal feature set and each abnormal pattern template, and select the abnormal pattern template with the highest similarity value as the matching template.

[0087] The anomaly pattern matching module calculates the feature similarity value between the comprehensive anomaly feature set and each anomaly pattern template. During the calculation, multiple dimensions of features in both the comprehensive anomaly feature set and each template are compared and analyzed separately, and then a comprehensive similarity value is derived. A higher similarity value indicates a higher degree of matching between the comprehensive anomaly feature set and the template. After calculating the similarity values ​​of all templates, the anomaly pattern template with the highest similarity value is selected as the matching template.

[0088] Step S1353: Parse the exception type description field in the matching template to obtain the corresponding exception type identifier.

[0089] The matching template includes an exception type description field, which details the exception type corresponding to the template. This field is parsed to extract an exception type identifier that uniquely identifies the exception type. The exception type identifier is a specific identifier; different exception types correspond to different identifiers, allowing the system to clearly identify the type of exception currently occurring on the device.

[0090] Step S1354: Extract the affected component indication field from the matching template to determine the range of mechanical components affected by the abnormality. The range of mechanical components includes the specific component name and location identifier.

[0091] The matching template also includes an "Affected Components Indicator" field, which specifies the mechanical components typically affected by this type of anomaly. By extracting information from this field and combining it with the actual structure and layout of the equipment, the range of mechanical components affected by the anomaly can be determined. This range includes not only the specific component names but also the location identifiers of each component to accurately pinpoint the affected parts.

[0092] Step S1355: Verify the consistency between the range of the affected components and the component association strength parameter in the description of the association relationship of the equipment status, and adjust the boundary of the affected components that may be expanded due to the association effect.

[0093] To ensure the accuracy of the determined scope of affected components, it is necessary to verify the consistency of the component association strength parameters with those in the equipment status correlation description. Check the reasonableness of the association strength parameters between components and with other components within the affected component scope, and determine whether the influence of inter-component associations might lead to an expansion of the anomaly's impact range. If such a situation exists, the boundaries of the affected components need to be adjusted to more accurately reflect the actual impact range of the anomaly.

[0094] Step S1356: Combine and encapsulate the anomaly type identifier and the adjusted range of affected components to generate an anomaly state pattern identifier that includes the anomaly type identifier and the set of affected components.

[0095] The acquired anomaly type identifier and the adjusted affected component range are combined and encapsulated. Following a specific format and rules, these two pieces of information are integrated to form a complete anomaly state pattern identifier. This anomaly state pattern identifier accurately indicates the type of anomaly in the device and the set of affected components.

[0096] Step S140: Generate a maintenance decision instruction containing maintenance priority and operation guidance based on the abnormal state mode identifier.

[0097] Once the abnormal state mode identifier is obtained, maintenance decision instructions can be generated based on it. These instructions need to include maintenance priorities and operational guidelines so that the unattended control system can take appropriate maintenance measures. Maintenance priorities determine the urgency and sequence of maintenance work, while operational guidelines provide specific steps and methods for the maintenance work.

[0098] Step S140 may include steps S141-S145:

[0099] Step S141: Parse the exception type identifier in the exception state pattern identifier and match it with the corresponding maintenance rule base. The maintenance rule base contains the maintenance operation type and urgency level corresponding to different exception types.

[0100] The exception type identifier in the exception status pattern is parsed, and the corresponding maintenance rule base is matched based on this identifier. The maintenance rule base stores maintenance rules for various exception types, each exception type corresponding to a specific maintenance operation type and urgency level. The maintenance operation type specifies what maintenance operation needs to be performed, such as inspection or replacement of parts; the urgency level indicates the urgency of the maintenance work, in order to determine the order of maintenance.

[0101] Step S142: Extract the set of affected components from the abnormal state mode identifier, and determine the maintenance priority order of each affected component by combining the functional importance assessment table of equipment components.

[0102] The set of affected components is extracted from the abnormal state pattern identifiers, and then the maintenance priority order of each affected component is determined by combining the functional importance assessment table of the equipment components. The functional importance assessment table evaluates the importance of each component in the operation of the equipment; the higher the importance of the component, the greater the impact of its abnormality on the overall operation of the equipment. Therefore, for the components in the affected component set, the maintenance order is determined according to their assessment results in the functional importance assessment table, with higher-importance components being maintained first.

[0103] Step S143: Based on the maintenance operation type and maintenance priority order, call the corresponding basic operation steps from the pre-stored operation guide template library.

[0104] Based on the determined maintenance operation type and priority order, the corresponding basic operation steps are retrieved from the pre-stored operation guide template library. This library contains operation step templates for different maintenance operation types and components, detailing the specific procedures and methods for performing maintenance operations. Following the maintenance operation type and priority order, an appropriate template is selected, from which the basic operation steps are extracted.

[0105] Step S144: Based on the component association strength parameters in the device status association description, perform association impact verification processing on the basic operation steps, and supplement the operation precautions for associated components that need to be monitored synchronously.

[0106] Based on the component association strength parameters in the equipment status correlation description, the extracted basic operation steps are subjected to association impact verification processing. The analysis examines whether maintenance operations within these basic operation steps will affect other components associated with the target component; these effects may include vibration transmission, load changes, etc. Based on the component association strength parameters, the associated components requiring synchronous monitoring are identified, and corresponding operational precautions are formulated and added to the basic operation steps.

[0107] Step S144 may include steps S1441-S1446:

[0108] Step S1441: Extract the identifiers of the target maintenance components involved in the basic operation steps.

[0109] The target maintenance component identifiers are extracted from the basic operating procedures. These identifiers clearly identify the components that require priority attention during maintenance. Each target maintenance component identifier corresponds to a specific component on the equipment, allowing for accurate location of the component needing maintenance.

[0110] Step S1442: Based on the component association strength parameter in the device status association description, find other components that have a strong association with the target maintenance component and generate a set of associated components.

[0111] Based on the component association strength parameters in the equipment status association description, analyze which other components have strong associations with the target maintenance component. A strong association means that these other components are more likely to be affected when the target maintenance component undergoes maintenance. Select these strongly associated components to form a set of associated components.

[0112] Step S1443: For each associated component in the set of associated components, analyze the types of impacts that maintenance operations may have on it, including vibration transmission impacts, load change impacts, and temperature diffusion impacts.

[0113] For each associated component in the set of associated components, a detailed analysis is conducted on the types of impacts that may occur when maintenance operations are performed on the target component. These impact types primarily include vibration transmission effects (vibrations generated during maintenance operations may be transmitted to associated components); load change effects (maintenance operations may cause changes in the load borne by the associated components); and temperature diffusion effects (temperature changes generated during maintenance may diffuse to the associated components). For each associated component, the type of impact it may experience is determined.

[0114] Step S1444: For each type of impact, formulate corresponding monitoring indicators and early warning thresholds. The monitoring indicators include vibration frequency, load change rate and temperature rise rate.

[0115] For each type of impact identified in the analysis, corresponding monitoring indicators and early warning thresholds were established. For the impact of vibration transmission, the monitoring indicator could be the vibration frequency, and an early warning threshold was set. When the vibration frequency of the associated component exceeds this threshold, it indicates that the vibration impact is significant. For the impact of load changes, the monitoring indicator could be the load change rate, and an early warning threshold was also set. When the load change rate exceeds the threshold, attention is required. For the impact of temperature diffusion, the monitoring indicator could be the temperature rise rate. When the temperature rise rate exceeds the early warning threshold, it indicates that the temperature impact is relatively severe.

[0116] Step S1445: Organize the associated component set, impact type, monitoring indicators and early warning threshold into associated component operation precautions, which include component identification, impact type description and monitoring requirement description.

[0117] The information, including the set of related components, the impact type of each related component, monitoring indicators, and early warning thresholds, is compiled into operational precautions for related components. These precautions include the identification of related components for accurate component recognition; explanations of impact types to inform maintenance personnel of potential effects; and descriptions of monitoring requirements, clearly defining the indicators to be monitored and their corresponding early warning thresholds.

[0118] Step S1446: Add the operation precautions for the associated components to the corresponding position of the basic operation steps to form an extended operation step that includes associated monitoring requirements.

[0119] Add the compiled operational precautions for related components to the corresponding positions in the basic operation steps. For example, before performing a maintenance action, add precautions regarding the need to monitor related components; during the maintenance action, add requirements for real-time monitoring of the status of related components, etc. Through the above processing, the basic operation steps are expanded into extended operation steps that include related monitoring requirements, making maintenance operations more comprehensive and safer.

[0120] Step S145: Integrate the urgency level, maintenance priority order, basic operation steps and related component operation precautions to generate a maintenance decision instruction containing a timestamp. The maintenance decision instruction includes a sequence of operation steps and component identification information corresponding to each step.

[0121] The system integrates urgency levels, maintenance priority sequences, basic operating procedures, and precautions for operating related components. This information is then combined according to a specific logic and format, and a timestamp is added to the maintenance decision instructions to record the time of their generation. The generated maintenance decision instructions contain a sequence of operating steps, arranged according to maintenance priority and operating flow; each step corresponds to a specific component identification information, clearly identifying the object being operated on.

[0122] Step S150: Send the maintenance decision command to the unattended control system to trigger the corresponding equipment maintenance operation.

[0123] After generating a maintenance decision command, it is sent to the unattended control system of the bucket wheel excavator. Upon receiving the maintenance decision command, the unattended control system can automatically trigger the corresponding equipment maintenance operation according to the sequence of operation steps and component identification information in the command. In this way, the automatic monitoring of the bucket wheel excavator's operation and maintenance status and the automatic triggering of maintenance operations are realized, ensuring that the equipment can be maintained in a timely manner and guaranteeing its stable operation.

[0124] In the above embodiments, the operation and maintenance status monitoring system for the bucket wheel excavator unmanned system used to perform the above method embodiments has at least one processor, a control module (chipset) coupled to at least one of the processors, a memory coupled to the control module, a non-volatile memory (NVM) / storage device coupled to the control module, at least one load to / output device coupled to the control module, and a network interface coupled to the control module.

[0125] The processor may include at least one single-core or multi-core processor, and may include any combination of general-purpose processors or special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). For some alternative implementations, the operation and maintenance status monitoring system applied to the unmanned bucket wheel excavator system can serve as an electronic device such as the gateway described in the embodiments of this application.

[0126] In some alternative implementations, the operation and maintenance status monitoring system applied to the unmanned bucket wheel excavator system may include at least one computer-readable medium (e.g., a memory or NVM / storage device) having instructions and at least one processor fused with the at least one computer-readable medium and configured to execute the instructions to implement the module thereby performing the actions described in this disclosure.

[0127] In one embodiment, the control module may include any suitable interface controller to provide any suitable interface to at least one of the processors and / or any suitable device or component communicating with the control module.

[0128] The control module may include a memory controller module to provide an interface to the memory. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0129] The memory can be used, for example, to load and store data and / or instructions for an operation and maintenance status monitoring system applied to an unmanned bucket wheel excavator system. In one embodiment, the memory may include any suitable volatile memory, such as suitable DRAM.

[0130] In one embodiment, the control module may include at least one load-to-output controller to provide an interface to the NVM / storage device and (at least one) load-to-output device.

[0131] For example, an NVM / storage device can be used to store data and / or instructions. An NVM / storage device may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable (at least one) non-volatile storage device (e.g., at least one hard disk drive (HDD), at least one optical disc (CD) drive, and / or at least one digital universal optical disc (DVD) drive).

[0132] NVM / storage devices may include storage resources that are physically part of a device installed on which an operation and maintenance status monitoring system for unmanned bucket wheel excavators is applied, or that can be accessed by that device without needing to be part of that device. For example, NVM / storage devices may be accessed over a network via (at least one) load to / output device.

[0133] At least one loading / output device provides an interface for the operation and maintenance status monitoring system applied to the unmanned bucket wheel excavator system to communicate with any other suitable device. The loading / output device may include communication components, communication components, sensor components, etc. A network interface provides an interface for the operation and maintenance status monitoring system applied to the unmanned bucket wheel excavator system to communicate based on at least one network. The operation and maintenance status monitoring system applied to the unmanned bucket wheel excavator system can wirelessly communicate with at least one component of a wireless network based on at least one wireless network prior and / or any prior and / or protocol, such as accessing a wireless network based on communication priors.

[0134] In one embodiment, at least one of the processors may be integrated with the logic of at least one controller of the control module (e.g., a memory controller module). In one embodiment, at least one of the processors may be integrated with the logic of at least one controller of the control module to form a system-level integration. In one embodiment, at least one of the processors may be fused with the logic of at least one controller of the control module on the same die. In one embodiment, at least one of the processors may be fused with the logic of at least one controller of the control module on the same die to form a system-on-a-chip (SoC).

[0135] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

[0136] This invention discloses a computer read storage medium that stores a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps in the operation and maintenance status monitoring method for an unmanned bucket wheel excavator system described in the foregoing embodiments.

[0137] This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps in the operation and maintenance status monitoring method for an unmanned bucket wheel excavator system described in the foregoing embodiments.

[0138] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any inventive effort.

[0139] Finally, it should be noted that the above-disclosed embodiments are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring the operation and maintenance state of an unattended system of a bucket wheel machine, characterized by The method includes: Acquire a multi-source monitoring data set of the bucket wheel excavator, which includes equipment mechanical structure monitoring data, power system operation data, and operating environment parameter data; The multi-source monitoring data set is subjected to equipment status correlation parsing processing to obtain a description of equipment status correlation reflecting the linkage relationship between equipment components, specifically including: The mechanical structure monitoring data and power system operation data in the multi-source monitoring data set are subjected to feature mapping processing to establish a correspondence table between the cantilever joint deformation pressure distribution information and the motor current fluctuation characteristics. The power system operation data and the working environment parameter data in the multi-source monitoring data set are subjected to association rule matching processing to identify the correlation threshold between the motor winding temperature change sequence and the ambient temperature gradient distribution information. The mechanical structure monitoring data and the working environment parameter data in the multi-source monitoring data set are dynamically modeled to construct a response curve model of the cantilever joint deformation pressure distribution information as a function of dust particle density. The corresponding relationship table, correlation threshold and response curve model are comprehensively analyzed and processed to extract the linkage influence factors between equipment mechanical structure, power system and working environment; Based on the aforementioned linkage influence factor, a description of equipment status correlation is generated, which includes component correlation strength parameters and environmental influence weight coefficients. The component correlation strength parameters are used to characterize the linkage sensitivity between different mechanical components, and the environmental influence weight coefficients are used to characterize the degree of influence of operating environment parameters on equipment operating status. Based on the device status association description, abnormal status pattern recognition processing is performed to generate an abnormal status pattern identifier indicating the type and scope of device abnormality, specifically including: Call the pre-stored bucket wheel excavator normal state benchmark library, which includes the standard distribution range of mechanical structure deformation pressure, the standard amplitude range of power system current fluctuation, and the standard fluctuation threshold of environmental parameters; The component association strength parameters in the device status association description are matched and compared with the standard association strength parameters in the normal status benchmark library to identify abnormal association strength parameters that exceed the standard range. The environmental impact weight coefficient in the equipment status association description is compared with the standard environmental impact weight coefficient in the normal status benchmark library by performing deviation analysis, and the absolute value of the difference between the actual weight coefficient and the standard weight coefficient is calculated. The identified anomaly correlation strength parameters and the absolute values ​​of the differences obtained from deviation analysis are subjected to feature aggregation processing to generate a comprehensive set of anomaly features that includes anomaly correlation features and environmental impact anomaly features; The system performs pattern matching processing based on the comprehensive set of abnormal features and the predefined abnormal pattern template library to determine the corresponding equipment abnormality type and the range of mechanical components affected by the abnormality, and generates an abnormal state pattern identifier that includes an abnormality type identifier and a set of affected components. Based on the abnormal state pattern identifier, a maintenance decision instruction containing maintenance priority and operation guidance is generated; The maintenance decision command is sent to the unattended control system to trigger the corresponding equipment maintenance operation.

2. The operation and maintenance state monitoring method applied to the unattended system of the bucket wheel machine according to claim 1, characterized in that, The acquisition of the multi-source monitoring data set for the bucket wheel excavator includes: Mechanical structure monitoring data is collected by stress sensors deployed on the cantilever of the bucket wheel excavator. The mechanical structure monitoring data includes information on the deformation pressure distribution at the cantilever joint. The power system operation data is collected by embedding temperature and current sensors in the power motor. The power system operation data includes the motor winding temperature change sequence and current fluctuation characteristics. The working environment parameter data is collected by temperature and humidity sensors and dust concentration sensors installed in the work area. The working environment parameter data includes information on the distribution of ambient temperature gradient and dust particle density. The mechanical structure monitoring data, power system operation data, and working environment parameter data are timestamped to ensure that the collection time points of each type of data are aligned. After synchronization, the data of each type are subjected to integrity verification, and invalid data segments with missing data or signal interference are removed to generate a multi-source monitoring data set containing valid mechanical structure monitoring data, valid power system operation data and valid working environment parameter data.

3. The method for monitoring the operation and maintenance status of an unmanned bucket wheel excavator system according to claim 2, characterized in that, The process involves performing integrity verification on the synchronized data of various types, removing invalid data segments with missing data or signal interference, and generating a multi-source monitoring data set containing valid mechanical structure monitoring data, valid power system operation data, and valid operating environment parameter data, including: The mechanical structure monitoring data is subjected to data continuity check processing, the number of missing data points within the continuous collection period is counted, and the time period with the number of missing data points exceeding a preset threshold is marked as invalid mechanical data segment; The power system operating data is subjected to signal and noise analysis processing to calculate the signal-to-noise ratio parameter of the current fluctuation characteristics, and the time period when the signal-to-noise ratio parameter is lower than a preset threshold is marked as invalid power data segment; The operational environment parameter data is subjected to numerical rationality verification processing. The dust particle density distribution information is checked to see if it exceeds the maximum concentration range allowed by the equipment. Time periods that exceed the range are marked as invalid environmental data segments. The invalid mechanical data segments, invalid power data segments, and invalid environmental data segments are removed from the synchronized data, and the remaining valid data segments are retained. The valid data fragments are processed to unify the data format, ensuring that the mechanical structure monitoring data, power system operation data, and working environment parameter data have the same data storage format and timestamp marking rules, thereby generating a multi-source monitoring data set containing valid mechanical structure monitoring data, valid power system operation data, and valid working environment parameter data.

4. The method for monitoring the operation and maintenance status of an unmanned bucket wheel excavator system according to claim 1, characterized in that, The corresponding relationship table, correlation threshold, and response curve model are comprehensively analyzed and processed to extract the linkage influencing factors between the equipment's mechanical structure, power system, and operating environment, including: The maximum correlation value between the cantilever joint deformation pressure distribution information and the motor current fluctuation characteristics is extracted from the correspondence table and used as the mechanical-power linkage factor. The highest correlation coefficient between the motor winding temperature change sequence and the ambient temperature gradient distribution information is extracted from the correlation threshold and used as the power-environment linkage factor. The maximum slope value of the cantilever joint deformation pressure distribution information as a function of dust particle density is extracted from the response curve model and used as a mechanical-environmental linkage factor. The mechanical-power linkage factor, the power-environment linkage factor, and the mechanical-environment linkage factor are normalized to eliminate the dimensional differences between different factors. The overall linkage sensitivity index of the equipment is calculated based on the normalized linkage factors. The overall linkage sensitivity index is the weighted average of each normalized linkage factor, and the weight coefficients are preset according to the degree of mutual influence of each system in the actual operation of the equipment.

5. The method for monitoring the operation and maintenance status of an unmanned bucket wheel excavator system according to claim 1, characterized in that, The step involves performing pattern matching processing based on the comprehensive set of abnormal features and a predefined abnormal pattern template library to determine the corresponding equipment abnormality type and the range of mechanical components affected by the abnormality, generating an abnormal state pattern identifier that includes an abnormality type identifier and a set of affected components, including: The comprehensive set of abnormal features is input into the abnormal pattern matching module, which stores templates for mechanical structure jamming abnormalities, power system overload abnormalities, and environmental parameter exceeding limits abnormalities. Calculate the feature similarity value between the comprehensive abnormal feature set and each abnormal pattern template, and select the abnormal pattern template with the highest similarity value as the matching template; Parse the exception type description field in the matching template to obtain the corresponding exception type identifier; Extract the affected component indicator field from the matching template to determine the range of mechanical components affected by the anomaly. The range of mechanical components includes the specific component name and location identifier. Verify the consistency between the affected component range and the component association strength parameter in the device state association description, and adjust the affected component boundary that may be expanded due to the association effect; The exception type identifier and the adjusted range of affected components are combined and encapsulated to generate an exception state pattern identifier that includes the exception type identifier and the set of affected components.

6. The method for monitoring the operation and maintenance status of an unmanned bucket wheel excavator system according to claim 1, characterized in that, The step of generating maintenance decision instructions containing maintenance priority and operation guidance based on the abnormal state mode identifier includes: Parse the exception type identifier in the exception state pattern identifier and match it with the corresponding maintenance rule base, which contains the maintenance operation type and urgency level corresponding to different exception types; Extract the set of affected components from the abnormal state mode identifiers, and determine the maintenance priority order of each affected component by combining the functional importance assessment table of equipment components. Based on the maintenance operation type and maintenance priority order, the corresponding basic operation steps are called from the pre-stored operation guide template library; Based on the component association strength parameters in the device status association description, the basic operation steps are subjected to association impact verification processing, and precautions for the operation of associated components that need to be monitored synchronously are added. By integrating the urgency level, maintenance priority order, basic operation steps, and operation precautions for related components, a maintenance decision instruction containing a timestamp is generated. The maintenance decision instruction includes a sequence of operation steps and component identification information corresponding to each step.

7. The method for monitoring the operation and maintenance status of an unmanned bucket wheel excavator system according to claim 6, characterized in that, The component association strength parameters in the device status association description are used to verify the association impact of the basic operation steps, and supplement the operation precautions for associated components that need to be monitored synchronously, including: Extract the identifiers of the target maintenance components involved in the basic operation steps; Based on the component association strength parameter in the equipment status association description, other components that have a strong association with the target maintenance component are found, and a set of associated components is generated. For each associated component in the set of associated components, analyze the types of impacts that maintenance operations may have on it, including vibration transmission effects, load change effects, and temperature diffusion effects; For each type of impact, corresponding monitoring indicators and early warning thresholds are established. The monitoring indicators include vibration frequency, load change rate, and temperature rise rate. The associated component set, impact type, monitoring indicators and early warning threshold are compiled into the associated component operation precautions, which include component identification, impact type description and monitoring requirement description; Add the operation precautions for the associated components to the corresponding positions of the basic operation steps to form extended operation steps that include associated monitoring requirements.

8. A maintenance status monitoring system for an unmanned bucket wheel excavator system, characterized in that, The system includes a processor and a computer-readable storage medium storing machine-executable instructions, which, when executed by a computer, implement the operation and maintenance status monitoring method for an unmanned bucket wheel excavator system as described in any one of claims 1-7.

Images