Bucket-wheel reclaimer cantilever gyroscopic moment protection method and system based on intelligent monitoring

Abstract

The invention discloses a bucket-wheel reclaimer cantilever gyroscopic moment protection method and system based on intelligent monitoring, and relates to the technical field of moment data processing. The bucket-wheel reclaimer cantilever gyroscopic moment protection method and system based on intelligent monitoring comprise the steps that S1, cantilever gyroscopic working condition data are periodically collected, and the cantilever gyroscopic working condition data are preprocessed; s2, calculating a cantilever rotation moment value, performing sliding window division by taking a sampling period as a unit, evaluating the stability of a cantilever rotation working condition, and marking an abnormal window; s3, evaluating the abnormal strength under the cantilever rotation working condition, judging the operation risk level in the current abnormal window, and triggering a hierarchical protection strategy; and S4, the recovery trend of the cantilever rotation working condition is evaluated, and the protection strategy is dynamically adjusted. The problem that in the prior art, due to the fact that a bucket-wheel material taking machine cantilever is difficult to recognize local resistance mutation in time in the rotation process, cantilever rotation moment anomaly detection lags behind is solved.

Description

Technical Field

[0001] This invention relates to the field of torque data processing technology, specifically to a method and system for protecting the cantilever rotation torque of a bucket wheel reclaimer based on intelligent monitoring. Background Technology

[0002] As a continuous loading and unloading device for bulk materials, the bucket wheel reclaimer's cantilever rotation mechanism is subjected to complex driving torques and load disturbances during operation, making it susceptible to the influence of multiple coupled factors from the motor, electrical control, hydraulics, and structure. When abnormal fluctuations or overloads occur in the rotation torque, failure to monitor and intervene in a timely manner can easily lead to equipment shutdown, structural damage, or even safety accidents. Therefore, how to achieve real-time monitoring and graded protection of the cantilever rotation torque has become a key issue in ensuring the safe and stable operation of the bucket wheel reclaimer.

[0003] For example, the invention disclosed in CN116992223A proposes a method, device, terminal equipment, and storage medium for protecting a drive mechanism, relating to the field of collision detection technology. It automatically identifies and attenuates corresponding high-frequency signals, simplifying the complex process of requiring different thresholds to trigger protection mechanisms for different operating states into a process that only requires a safety threshold to trigger the protection mechanism under non-impact conditions. The method includes: acquiring a first torque signal output by the drive mechanism; attenuating the corresponding high-frequency signals in the first torque signal according to the rate of change of the first torque signal to obtain a second torque signal; and triggering a protection mechanism for the drive mechanism based on a comparison between the second torque signal and a first threshold, where the first threshold characterizes the maximum force intensity of the driving mechanism's active component under non-impact conditions.

[0004] For example, the invention with announcement number CN109558659B provides a design method for cantilever support structures based on deformation control, including: S1, determining the profile parameters of the foundation pit and the physical and mechanical parameters of the soil; S2, determining the displacement mode of the support structure and establishing a simplified model diagram; S3, calculating the active and passive earth pressures of the foundation pit support structure respectively, and determining the critical embedment depth of the support structure against overturning based on the principle of moment balance; S4, calculating the maximum bending moment and maximum shear force of the support structure respectively, and determining the material and reinforcement of the support structure based on the maximum bending moment and maximum shear force; S5, performing overall stability verification and heave stability verification. This invention overcomes the inability to consider the deformation of the support structure in conventional foundation pit design methods. It controls the design calculation by controlling the deformation of the cantilever support structure. The calculation method is simple and feasible, and can effectively save engineering costs and reduce construction volume while ensuring safety, thus having great potential for widespread application.

[0005] However, the aforementioned existing technical solutions mainly target single signal processing of the drive mechanism or structural mechanics analysis in civil engineering. They fail to integrate multi-source data from the cantilever rotation condition of the bucket wheel reclaimer for fusion modeling, and also lack a dynamic control mechanism for graded protection and recovery trend of abnormal states. Therefore, they are difficult to meet the needs of real-time monitoring, intelligent identification and closed-loop protection of cantilever rotation torque under complex working conditions.

[0006] Therefore, in order to address the above problems, there is an urgent need for a method and system for protecting the cantilever rotation torque of a bucket wheel reclaimer based on intelligent monitoring. Summary of the Invention

[0007] Technical problems to be solved

[0008] To address the shortcomings of existing technologies, this invention provides a method and system for protecting the cantilever rotation torque of a bucket wheel reclaimer based on intelligent monitoring. This solves the problem in existing technologies where it is difficult to identify sudden changes in local resistance during the rotation of the bucket wheel reclaimer's cantilever, leading to a lag in the detection of abnormal cantilever rotation torque.

[0009] Technical solution

[0010] To achieve the above objectives, the present invention provides the following technical solution: a method and system for protecting the cantilever slewing torque of a bucket wheel reclaimer based on intelligent monitoring, comprising: S1, periodically collecting cantilever slewing condition data, and obtaining pre-processed cantilever slewing condition data through execution time synchronization, abnormal data removal, missing data completion, and standardization normalization processing; S2, calculating the cantilever slewing torque value based on the pre-processed cantilever slewing condition data, dividing the window according to the sampling period, evaluating the stability of the cantilever slewing condition, and based on... S3: Mark the abnormal window based on the evaluation results; S4: Extract the slewing stability evaluation value and cantilever slewing torque data within the abnormal window, evaluate the abnormal intensity under the cantilever slewing condition, determine the operational risk level within the current abnormal window, and trigger the graded protection strategy; S5: Extract the cantilever slewing condition data within K sampling periods after the graded protection strategy is executed, evaluate the recovery trend of the cantilever slewing condition, construct the slewing trend recovery change curve, and dynamically adjust the protection strategy based on the recovery trend evaluation results and the curve slope to achieve closed-loop control of the cantilever slewing condition.

[0011] Furthermore, the specific steps for periodically collecting cantilever slewing condition data and obtaining preprocessed cantilever slewing condition data through time synchronization, abnormal data removal, missing data completion, and standardization are as follows: A fixed sliding time window is used as a sampling period to periodically collect cantilever slewing condition data, including motor current, motor voltage, hydraulic pressure, hydraulic flow, hydraulic motor speed, cantilever slewing angle, cantilever axial force, cantilever tangential force, slewing support force, slewing angular acceleration, slewing angular velocity, and cantilever vibration offset. A time synchronization mechanism based on timestamp alignment and sampling interval verification is constructed to perform multi-channel processing on the cantilever slewing condition data. The data processing steps include: time-series registration; using a sliding window-based steady-state segment extraction algorithm to distinguish between stable operating intervals and load variation intervals in the cantilever slewing data; suppressing short-period disturbances in the cantilever slewing data by combining a first-order low-pass filter and sliding range analysis; identifying and marking anomalous values ​​using sliding Z-score detection and range limiting rules, and replacing data using the mean method; completing data completion for missing sampling segments using a time-neighborhood-based linear interpolation method; and finally, performing dimensionless processing and normalization on the cantilever slewing data of different dimensions by combining scaling and mean normalization.

[0012] Furthermore, based on the preprocessed cantilever slewing condition data, the specific steps for calculating the cantilever slewing torque value are as follows: Extract the preprocessed cantilever slewing condition data, obtain the drive power by multiplying the motor current and motor voltage, and calculate the drive-side torque in combination with the slewing angular velocity; obtain the hydraulic power by multiplying the hydraulic pressure by the hydraulic flow rate, and calculate the hydraulic-side torque in combination with the hydraulic motor speed; further extract the cantilever axial force, tangential force, and slewing angle, and calculate the load-side resistance torque based on the relationship between the force and the slewing arm length; superimpose the drive-side torque, hydraulic-side torque, and load-side resistance torque to obtain the cantilever slewing torque value.

[0013] Furthermore, the specific steps for evaluating the stability of the cantilever slewing condition by dividing the sliding window according to the sampling period are as follows: Arrange the cantilever slewing torque values ​​in chronological order to form a continuous torque time series, and divide the time series into sliding windows according to the sampling period. Calculate the change in cantilever slewing torque, the change in slewing angular velocity, the change in cantilever vibration offset, and the mean value of the slewing support force within each window; divide the change in cantilever slewing torque by the sum of the change in slewing angular velocity and the minimum term, and take the absolute value of the result to obtain the driving disturbance index; divide the change in cantilever vibration offset by the actual value... The ratio of the sum of the real-time angular velocity and the minimum term is taken as the base, and the absolute value is used as the base. The real-time angular acceleration is divided by the maximum angular acceleration within the window, and one is added. The sum is used as the exponent, and the exponential function value is calculated to obtain the vibration response index. The difference between the real-time cantilever slewing angle and the cantilever slewing angle of the previous sampling period is calculated. The absolute value is divided by the sum of the difference between the real-time slewing support force and the mean of the slewing support force and the minimum term, and one is added to the ratio to obtain the support disturbance coefficient. The driving disturbance index, the vibration response index and the support disturbance coefficient are multiplied in sequence to obtain the slewing stability evaluation value.

[0014] Furthermore, the specific steps for marking abnormal windows based on the evaluation results are as follows: Real-time comparison of the gyrostability evaluation value and the gyrostability threshold; when the gyrostability evaluation value is less than or equal to the gyrostability threshold, no action is taken; when the gyrostability evaluation value is greater than the gyrostability threshold, the current sampling period is marked as an abnormal sampling period; the number of abnormal sampling periods within the window is calculated, and a window gyrostability density curve is constructed based on the sliding window history; the mean gyrostability evaluation value within the window is further calculated. If both the number of abnormal sampling periods and the mean gyrostability evaluation value exceed the corresponding threshold, an abnormal warning signal is triggered, and the current window is marked as an abnormal window.

[0015] Further, the specific steps for extracting the slewing stability assessment value and cantilever slewing moment data within the anomaly window and evaluating the anomaly intensity under cantilever slewing conditions are as follows: Extract the slewing stability assessment value and cantilever slewing condition data within the anomaly window, and calculate the mean, standard deviation, standard deviation, and mean of the slewing stability assessment value, all within the window; add the square of the mean of the slewing stability assessment value to the standard deviation, and then divide by the sum of the number of anomaly sampling periods and a constant to obtain the anomaly intensity factor; add the constant to the change in cantilever vibration offset and take the natural logarithm to obtain the vibration influence factor; multiply the change in cantilever slewing moment by the standard deviation of the cantilever slewing moment, divide by the sum of the mean and minimum terms of the cantilever slewing moment, and then take the square root of the product to obtain the structural disturbance factor; add the product of the anomaly intensity factor and the vibration influence factor and the structural disturbance factor to obtain the slewing operation risk assessment value.

[0016] Further, the specific steps for determining the running risk level within the current abnormal window and triggering the hierarchical protection strategy are as follows: Compare the rotary running risk assessment value S with the multi-level rotary risk thresholds S1 and S2 in real time, and determine the running risk level within the current abnormal window and trigger the hierarchical protection strategy: When S ≤ S1, it is determined as a first-level risk, maintain the current rotary angular velocity, and increase the sampling frequency; when S1 < S < S2, it is determined as a second-level risk, dynamically adjust the rotary angular velocity according to the difference between S and S1, while reducing the motor output power and restricting the continuous torque output on the driving side; when S ≥ S2, it is determined as a third-level risk, abort the electronic control torque output of the driving device, and pause the rotary motion on the motor side; synchronously activate the hydraulic flow compensation path, and implement rotary angular velocity limitation and attitude stability control on the cantilever by limiting the hydraulic pressure difference adjustment range and response step; and send a risk alarm signal to the main control unit. <00OO035>

[0017] Further, the specific steps for extracting the cantilever rotary working condition data within K sampling periods after the execution of the hierarchical protection strategy and evaluating the recovery trend of the cantilever rotary working condition are as follows: Extract the rotary angular velocity and rotary support force within K sampling periods after the execution of the hierarchical protection strategy, calculate the change in rotary angular velocity and the average value of rotary support force within K sampling periods, and recalculate the current rotary running risk assessment value based on the real-time cantilever rotary working condition data; Add one to the absolute value of the change in rotary angular velocity, and then divide it by the sum of the absolute value of the difference between the current rotary support force and the average value of rotary support force within K sampling periods and a minimum term, and take the natural logarithm of the obtained ratio to get the support disturbance adjustment term; Subtract the initial rotary running risk assessment value from the current rotary running risk assessment value, and then divide it by the sum of the current rotary running risk assessment value and a minimum term, and square the obtained ratio to get the risk fluctuation term; Add the support disturbance adjustment term and the risk fluctuation term to get the rotary trend recovery value.

[0018] Furthermore, the following steps are taken to construct a slewing trend recovery curve, combine the recovery trend assessment results and the curve slope, and dynamically adjust the protection strategy to achieve closed-loop control of the cantilever slewing condition: Calculate the slewing trend recovery value from the first sampling period after the protection strategy is executed to the Kth sampling period, construct the slewing trend recovery curve, and extract the curve slope using the moving average and differential trend methods; when the curve slope is positive and the slewing trend recovery value is below the recovery threshold and continues to rise, the angular velocity limitation range is gradually released, and the hydraulic differential pressure adjustment step size is widened; when the curve slope is positive... If the curve slope is positive and the recovery value of the slewing trend is lower than the recovery threshold and there is a downward wave, the current protection strategy continues to be executed. If the curve slope is zero or negative and the recovery value of the slewing trend is lower than the recovery threshold, the protection strategy level is automatically upgraded. If the current protection state is already at level three, the cantilever power supply is cut off and an audible and visual alarm is triggered. If the difference between the curve slope and zero is less than the recovery slope threshold and the recovery value of the slewing trend is greater than the recovery threshold, the protection strategy is exited and the slewing anomaly assessment and risk monitoring are re-entered to realize the closed-loop monitoring and adaptive control mechanism for the slewing condition of the cantilever.

[0019] The second aspect of this invention provides a cantilever slewing torque protection system for a bucket wheel reclaimer based on intelligent monitoring, comprising: a data acquisition and preprocessing module, a cantilever torque anomaly identification module, a risk assessment and hierarchical control module, and an anomaly recovery adaptive control module. The data acquisition and preprocessing module is used to periodically acquire cantilever slewing condition data and obtain preprocessed cantilever slewing condition data through execution time synchronization, anomaly data removal, missing data completion, and standardization normalization. The cantilever torque anomaly identification module is used to calculate the cantilever slewing torque value based on the preprocessed cantilever slewing condition data and divide the window into sliding windows based on the sampling period. The system evaluates the stability of the cantilever slewing condition and marks abnormal windows based on the evaluation results. The risk assessment and graded control module extracts the slewing stability evaluation value and cantilever slewing torque data within the abnormal window, assesses the intensity of the anomaly under the cantilever slewing condition, determines the operational risk level within the current abnormal window, and triggers a graded protection strategy. The anomaly recovery adaptive control module extracts the cantilever slewing condition data within K sampling periods after the graded protection strategy is executed, evaluates the recovery trend of the cantilever slewing condition, constructs a slewing trend recovery curve, and dynamically adjusts the protection strategy based on the recovery trend evaluation results and the curve slope to achieve closed-loop control of the cantilever slewing condition.

[0020] Beneficial effects

[0021] The present invention has the following beneficial effects: (1) The bucket wheel reclaimer cantilever rotation torque protection method and system based on intelligent monitoring introduces multi-dimensional parameters such as torque change, angular velocity change, vibration offset change and average support force into the sliding window of the cantilever rotation working condition data, and constructs composite disturbance index and response index. This can more comprehensively and dynamically depict the force characteristics of the bucket wheel reclaimer during the rotation process, and overcomes the shortcomings of the existing technology where a single torque signal is difficult to accurately reflect abnormalities.

[0022] (2) The bucket wheel reclaimer cantilever slewing torque protection method and system based on intelligent monitoring can not only identify short-term torque anomalies caused by sudden changes in local resistance, but also assess the impact of continuous mechanical disturbances on system stability by calculating the slewing anomaly assessment value and the number of anomaly sampling cycles, and combining the multi-threshold judgment mechanism, thereby achieving higher precision anomaly window identification and early warning.

[0023] (3) The bucket wheel reclaimer cantilever rotation torque protection method and system based on intelligent monitoring, by designing multi-dimensional quantitative indicators such as abnormal intensity factor, vibration influence factor and structural disturbance factor, and integrating them into the rotation operation risk assessment value, can automatically trigger the graded protection strategy according to the risk level. Compared with the traditional protection method that relies on fixed thresholds, it is more adaptable and flexible, and can effectively avoid false triggering and missed triggering.

[0024] (4) The bucket wheel reclaimer cantilever rotation torque protection method and system based on intelligent monitoring realizes real-time quantitative evaluation of the performance of graded protection strategy by introducing the rotation trend recovery value, and dynamically adjusts the protection level by analyzing the recovery change curve and slope. When the working condition is restored to stability, the protection is automatically withdrawn, realizing the adaptive balance between protection and operation, and overcoming the problem of lack of restorative judgment and closed-loop control after the protection measures are implemented in the prior art. Attached Figure Description

[0025] Figure 1 The flowchart shows the method for protecting the cantilever rotation torque of a bucket wheel reclaimer based on intelligent monitoring. Figure 2 This is a structural diagram of a bucket wheel reclaimer cantilever rotation torque protection system based on intelligent monitoring. Figure 3 The window rotation anomaly density curve; Figure 4 A bar chart to classify the risk levels of slewing operations. Detailed Implementation

[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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.

[0027] Please see Figures 1-4 This invention provides a technical solution: a method and system for protecting the slewing torque of a bucket wheel reclaimer based on intelligent monitoring, comprising: S1, periodically collecting slewing condition data of the cantilever, and obtaining preprocessed slewing condition data by performing time synchronization, abnormal data removal, missing data completion, and standardization; S2, calculating the slewing torque value of the cantilever based on the preprocessed slewing condition data, dividing the slewing condition into sliding windows based on the sampling period, evaluating the stability of the slewing condition, and marking abnormal windows based on the evaluation results; S3, extracting the slewing stability evaluation value and slewing torque data within the abnormal windows, evaluating the abnormal intensity under the slewing condition, determining the operational risk level within the current abnormal window, and triggering a graded protection strategy; S4, extracting the slewing condition data of the cantilever within K sampling periods after the execution of the graded protection strategy, evaluating the recovery trend of the slewing condition, constructing a slewing trend recovery curve, and dynamically adjusting the protection strategy based on the recovery trend evaluation results and the curve slope to achieve closed-loop control of the slewing condition.

[0028] Specifically, the following steps are taken to periodically collect cantilever rotation condition data and obtain preprocessed cantilever rotation condition data through time synchronization, abnormal data removal, missing data completion, and standardization normalization: A fixed sliding time window is used as a sampling period to periodically collect cantilever rotation condition data. Within each sampling period, the cantilever rotation condition data involved in the operation of the bucket wheel reclaimer's cantilever rotation mechanism is completely recorded. The cantilever rotation condition data includes twelve categories of variables: motor current, motor voltage, hydraulic pressure, hydraulic flow rate, hydraulic motor speed, cantilever rotation angle, cantilever axial force, cantilever tangential force, rotation support force, rotation angular acceleration, rotation angular velocity, and cantilever vibration offset. All variables are sampled with a uniform time resolution to ensure temporal integrity. The data collection process involves several key parameters: motor current is continuously acquired via a current sensor installed in the power supply circuit; motor voltage is measured and recorded in real time via a voltage detection device; hydraulic pressure is synchronously sampled using pressure sensors arranged in the hydraulic circuit; hydraulic flow is acquired by a flow meter installed in the hydraulic channel; hydraulic motor speed is sampled at high frequency by an encoder connected to the motor shaft; cantilever rotation angle is continuously monitored by an angle sensor based on rotational displacement; cantilever axial force is acquired in real time by force-sensitive elements deployed on the load-bearing structure; cantilever tangential force is accurately measured by a force-measuring component at the contact point with the working surface; rotational support force is periodically acquired using a distributed strain gauge array; rotational angular acceleration is calculated by an acceleration sensor installed at the rotation axis; rotational angular velocity is continuously acquired by an angular velocity sensor; and cantilever vibration offset is obtained by recording displacement offset using a vibration detector at a high sampling rate. Finally, a time synchronization mechanism based on timestamp alignment and sampling interval verification is constructed to perform inter-channel time correction on the cantilever rotation data to eliminate data misalignment caused by sampling delays. A steady-state segment extraction algorithm based on a sliding window, combined with a fixed window length and sliding step size design, is used to segmentally identify and classify the stable operating intervals and load variation intervals in the cantilever slewing data. The start and end positions of the stable and variation segments are marked to ensure local consistency in subsequent processing. Combining a first-order low-pass filter and sliding range analysis, the cantilever slewing data of each channel is first filtered using a first-order low-pass filter optimized for cutoff frequency. Then, the sliding range index within each window is calculated to accurately identify and suppress short-period disturbances caused by sampling fluctuations of electrical system pulses and vibration signals in the cantilever slewing data, improving data stability. Using sliding Z-score detection and range limiting rules, a standardized Z-value is calculated point-by-point for the cantilever slewing data of each channel and compared with the corresponding threshold to automatically identify abrupt outliers. For the identified abrupt outliers, an interpolation strategy using the mean of equal-width windows is employed to ensure the continuity and physical rationality of the values ​​after removing outliers.To address the missing sampling segments caused by sampling signal interruptions and communication packet loss, a linear interpolation method based on time neighborhood is employed to recover the complete data sequence. Finally, the cantilever slewing data is dimensionless through a combination of scaling and mean normalization. First, linear scaling is performed using the maximum and minimum values ​​of each channel. Then, Z-score normalization is performed using the channel mean and standard deviation as the standard, mapping data from different physical quantity scales to a unified numerical space, facilitating multivariate fusion analysis and subsequent modeling.

[0029] This implementation plan achieves efficient acquisition and standardized processing of cantilever rotation operation data by constructing a comprehensive data acquisition and preprocessing workflow. A fixed sliding time window is employed to ensure temporal consistency and full coverage of twelve characterizing variables. By combining time synchronization mechanisms, steady-state segment extraction algorithms, short-cycle disturbance suppression, outlier identification and repair, and sampling gap filling methods, the integrity, continuity, and stability of the data are effectively improved. A unified normalization strategy enables standardized representation of multi-channel cantilever rotation operation data, providing stable and reliable data support for subsequent risk assessment and modeling.

[0030] Specifically, based on the preprocessed cantilever slewing condition data, the specific steps for calculating the cantilever slewing torque value are as follows: First, extract the cantilever slewing condition data after time synchronization, anomaly removal, missing data completion, and normalization processing to ensure that the sampled data of each channel are strictly aligned in the time dimension, have a unified numerical range, and consistent physical units, possessing input characteristics that can be directly used for torque calculation. Second, construct the instantaneous drive power curve of the drive system by multiplying the sampled value of the motor voltage at each time point in the motor current channel with the sampled value of the motor voltage at the corresponding time. Based on the conversion relationship between drive power and slewing angular velocity, calculate the drive-side torque at each sampling point using the slewing angular velocity as the conversion quantity. Simultaneously, extract the synchronized sampled values ​​of the hydraulic pressure channel and the hydraulic flow channel, and multiply them point by point at the corresponding time to construct the hydraulic power sequence of the hydraulic system. By integrating the hydraulic motor speed, and based on the nonlinear relationship between hydraulic power and speed, establish a hydraulic system efficiency correction model to ensure that the hydraulic side torque calculation results are accurate and comparable under different operating conditions. The nonlinear relationship between hydraulic power and hydraulic motor speed was established using measured data from multiple sets of different pressure and flow conditions to create a calibration curve. A hydraulic system efficiency correction model was constructed using polynomial fitting and interpolation correction methods. During operation, real-time hydraulic power and hydraulic motor speed were input into this model, and the hydraulic side torque was calculated through interpolation. Further, three sets of synchronous data—the cantilever axial force channel, the cantilever tangential force channel, and the cantilever rotation angle channel—were extracted. Combined with the geometric characteristic parameters of the bucket wheel reclaimer's cantilever structure, a rotating lever arm model between the force application point and the rotation axis center was constructed. The effective lever arm length was calculated in real-time based on the rotation angle. Combining the force decomposition of the cantilever axial force and cantilever tangential force, the component force effects under the current posture were calculated, thus deriving the load-side resistance torque. Finally, the drive-side torque, hydraulic-side torque, and load-side resistance torque were synchronously superimposed at each sampling point to obtain the comprehensive cantilever rotation torque value.

[0031] In this implementation plan, the step of calculating the cantilever rotation torque value based on preprocessed cantilever rotation data achieves accurate decomposition and fusion of multi-source driving forces and load resistance during the rotation of the bucket wheel reclaimer cantilever. This method combines key variables such as motor current, motor voltage, hydraulic pressure, hydraulic flow rate, hydraulic motor speed, cantilever axial force, cantilever tangential force, and cantilever rotation angle to accurately quantify the independent contributions of the driving-side torque, hydraulic-side torque, and load-side resistance torque. This effectively improves the completeness and reliability of the cantilever rotation torque calculation, providing high-precision data support for subsequent rotation stability assessment and risk identification.

[0032] Specifically, the steps for evaluating the stability of the cantilever slewing condition by dividing the sliding window according to the sampling period are as follows: The standardized and normalized cantilever slewing torque values ​​are arranged in chronological order to form a complete and continuous cantilever slewing torque time series. Combining the sampling time resolution, the series is divided into sliding windows according to the sampling period. Each sliding window contains a fixed N sampling periods, where N is a positive integer, ensuring that the data within the window covers a continuous and stable time interval. Subsequently, the changes in cantilever slewing torque, cantilever slewing angular velocity, cantilever vibration offset, and the mean slewing support force are calculated within each sliding window. The changes in each item are obtained by calculating the absolute value of the difference between the corresponding variables at the beginning and end of the sampling period of the window. The change in cantilever slewing torque is divided by the sum of the change in cantilever slewing angular velocity and the minimum term, and the absolute value of the resulting ratio is used as a driving disturbance index to measure the degree of influence of driving-side energy fluctuations on system stability. Further, the change in cantilever vibration offset is divided by the sum of the cantilever rotation angular velocity and the minimum term corresponding to the current sampling period, and the absolute value of the resulting ratio is used as the base. The cantilever rotation angular acceleration of the current sampling period is divided by the maximum rotation angular acceleration within the current window, and one is added to the result. The sum is used as the exponent, and the vibration response index is calculated using an exponential function. Subsequently, the absolute value of the difference between the cantilever rotation angle of the current sampling period and the cantilever rotation angle of the previous sampling period is calculated, and then divided by the sum of the difference between the rotation support force of the current sampling period and the mean rotation support force of the current window, and the minimum term. The ratio is added to the result and defined as the support disturbance coefficient, which is used to quantify the degree of disturbance caused by the fluctuation of the stressed structure. Finally, the driving disturbance index, the vibration response index, and the support disturbance coefficient are multiplied sequentially to obtain the rotational stability evaluation value. Among them, the minimum term is a non-zero minimum positive real number used to ensure the numerical stability and logical completeness of the algorithm.

[0033] The specific formula for calculating the gyration stability assessment value is as follows: ; In the formula, This represents the gyratory stability assessment value. This indicates the change in the swing torque of the cantilever. This represents the change in angular velocity. This indicates the change in cantilever vibration offset. Indicates real-time angular acceleration. Indicates real-time rotational angular velocity. This indicates the maximum angular acceleration within the window. This indicates the real-time cantilever rotation angle. This indicates the cantilever rotation angle in the previous sampling period. Indicates the real-time rotational support force. This represents the average value of the slewing support force. Indicates a minus term.

[0034] In this implementation scheme, a sliding window mechanism based on the sampling period is constructed, and key variables such as the change in cantilever rotation torque, the change in cantilever rotation angular velocity, the change in cantilever vibration offset, and the mean value of rotation support force are introduced in each sliding window. This enables a comprehensive quantification of the multidimensional coupling effect of driving disturbance, vibration response, and support fluctuation during the cantilever rotation process, thereby accurately calculating the rotation stability assessment value and realizing the dynamic identification of the stability state of the bucket wheel reclaimer's cantilever rotation. This provides a timely and high-resolution decision-making basis for subsequent risk classification control and adaptive regulation.

[0035] Specifically, the steps for marking abnormal windows based on the evaluation results are as follows: First, the gyration stability evaluation value and the gyration stability threshold are compared in real time, and the current gyration stability state is determined cycle by cycle. When the gyration stability evaluation value corresponding to the current sampling cycle is less than or equal to the gyration stability threshold, the current gyration condition is determined to be in a stable state, no action is taken, and the data for the next sampling cycle is recorded. When the gyration stability evaluation value of the current sampling cycle is greater than the gyration stability threshold, it is determined that there is an instability risk in that cycle, and the sampling cycle is marked as an abnormal sampling cycle. Subsequently, the number of abnormal sampling cycles within the window is calculated, and a gyration anomaly density curve is constructed based on the sliding window history. Further, the gyration stability evaluation value sequence within the sliding window is averaged to calculate the mean gyration stability evaluation value within the window. If the number of abnormal sampling cycles in the current window exceeds the anomaly density threshold, and the mean gyration stability evaluation value exceeds the mean gyration stability evaluation value threshold, then the dual threshold judgment condition is met simultaneously, triggering a gyration anomaly warning signal, and the current sliding window is marked as an abnormal window.

[0036] like Figure 3 The figure shows the number of abnormal sampling cycles and the anomaly window labeling results within 10 windows, used to analyze the dynamic evolution characteristics of abnormal density during the cantilever rotation process of the bucket wheel reclaimer. The horizontal axis represents the window number, and the vertical axis represents the number of abnormal sampling cycles corresponding to each window. The curves, connected by blue broken lines, show the number of abnormal sampling cycles for each window, reflecting the trend of density change over time. The black dashed line is set as the abnormal density threshold, with a value of 2, serving as a reference benchmark for identifying high-risk windows. When the number of abnormal sampling cycles in a window exceeds the abnormal density threshold, it is marked as an abnormal window with a red broken line dot. As can be seen from the figure, windows 6, 7, 8, 9, and 10 significantly exceed the abnormal density threshold and are highlighted with red dots as abnormal windows. This indicates that during the operation phases corresponding to these windows, the cantilever rotation torque changes frequently, requiring timely triggering of a graded protection strategy to reduce equipment operation risks.

[0037] In this implementation scheme, by comparing the slewing stability assessment value and the slewing stability threshold in real time, and constructing a windowed slewing anomaly density curve using a sliding window mechanism, and comprehensively judging whether the number of abnormal sampling periods and the average slewing stability assessment value simultaneously exceed the corresponding threshold, a multi-dimensional joint judgment method based on continuous sampling periods is realized. This method can effectively identify unstable slewing states caused by local mutations, thereby accurately marking abnormal windows. This method enhances the sensitivity and anti-interference capability of slewing anomaly identification, improves the accuracy of perception of the dynamic evolution process of the bucket wheel reclaimer's cantilever slewing condition, and provides a reliable basis for the triggering and execution of subsequent graded response control strategies.

[0038] Specifically, the steps for extracting slewing stability assessment values ​​and cantilever slewing condition data within the anomaly window and evaluating the anomaly intensity under the cantilever slewing condition are as follows: First, extract the slewing stability assessment value sequence and the cantilever slewing condition data sequence within the corresponding time period from the marked anomaly window. Statistically process the slewing stability assessment value sequence, calculating the mean and standard deviation of the slewing stability assessment values ​​within the anomaly window to reflect the concentration and fluctuation level of the assessment indicators. Simultaneously, calculate the standard deviation and mean of the cantilever slewing torque time series. Then, sum the square of the mean of the slewing stability assessment values ​​and the standard deviation of the slewing stability assessment values, and divide this sum by the sum of the number of anomaly sampling periods and a constant to construct an anomaly intensity factor, which is used as a comprehensive indicator reflecting the degree of stability deviation and anomaly clustering within the current anomaly window. Further, obtain the cantilever vibration offset change corresponding to the last sampling period of the anomaly window, add a constant to it, and take the natural logarithm to construct a vibration influence factor, reflecting the dynamic response characteristics of local disturbances. Simultaneously, the change in cantilever slewing moment within the abnormal window is multiplied by the standard deviation of the cantilever slewing moment, and then divided by the sum of the mean and minimum terms of the cantilever slewing moment. The square root of the resulting ratio is then used to construct a structural disturbance factor, which measures the amplitude of structural response fluctuations caused by moment changes. Finally, the abnormal intensity factor is added to the product of the vibration influence factor and the structural disturbance factor to obtain the slewing operation risk assessment value.

[0039] The specific formula for calculating the risk assessment value of slewing operation is as follows: ; In the formula, This indicates the risk assessment value for slewing operation. This represents the mean of the gyration stability assessment values. This represents the standard deviation of the gyration stability assessment value. This indicates the change in cantilever vibration offset. Indicates the number of abnormal sampling periods. This indicates the change in the swing torque of the cantilever. This indicates the standard deviation of the cantilever slewing torque. This represents the average swing moment of the cantilever. Indicates a minus term.

[0040] In this embodiment, Table 1 is a data table of slewing operation risk assessment values, listing the key variables and corresponding slewing operation risk assessment values ​​under five abnormal cycles. The key variables used include: mean slewing stability assessment value, standard deviation of slewing stability assessment, change in cantilever vibration offset, number of abnormal sampling cycles, change in cantilever slewing torque, standard deviation of cantilever slewing torque, and mean cantilever slewing torque.

[0041] Table 1. Risk Assessment Values ​​for Slewing Operation

[0042] In this implementation plan, a quantitative calculation process for the slewing operation risk assessment value is constructed by extracting the slewing stability assessment value and cantilever slewing condition data within the abnormal window, thus achieving a multi-dimensional fusion assessment of the operating characteristics of abnormal sections. This method collaboratively incorporates the mean slewing stability assessment value, the standard deviation of the slewing stability assessment value, the standard deviation of the cantilever slewing moment, the mean cantilever slewing moment, the change in cantilever vibration offset, and the change in cantilever slewing moment into the risk judgment model. It comprehensively considers the degree of stability deviation, the intensity of structural disturbance, and the degree of local vibration influence, effectively quantifying the dynamic risk level within the abnormal window under the constraint of the number of abnormal sampling periods. This technical approach improves the accuracy of identifying local abnormal behaviors under complex slewing conditions, enhances the sensitivity and pertinence of abnormal risk identification, and provides a key basis for the graded response and linkage control strategy of slewing operation status.

[0043] Specifically, the steps for determining the operational risk level within the current abnormal window and triggering the graded protection strategy are as follows: The slewing operation risk assessment value S is compared in real time with the multi-level slewing risk thresholds S1 and S2. Based on the assessment results, the operational risk level corresponding to the current abnormal window is determined, and the corresponding slewing protection control strategy is executed. Specifically: When the slewing operation risk assessment value S is less than or equal to the first-level slewing risk threshold S1, it is determined to be a first-level risk. In this case, the current slewing angular velocity is kept stable, and the sampling frequency of the cantilever slewing condition data is increased to enhance the real-time performance and granularity of the operational status monitoring. When the slewing operation risk assessment value S is greater than the first-level slewing risk threshold S1 and less than the second-level slewing risk threshold S2, it is determined to be a second-level risk. The current slewing angular velocity is dynamically adjusted based on the difference between the slewing operation risk assessment value S and the first-level slewing risk threshold S1, and the motor output power is controlled to decrease, limiting the continuous torque output level on the drive side and reducing the driving force. The load pressure of the drive system is monitored; when the slewing risk assessment value S is greater than or equal to the secondary slewing risk threshold S2, it is judged as a level 3 risk, and the electronic torque output of the drive device is immediately stopped, and the slewing on the motor side is suspended to avoid further aggravation of the operational risk; at the same time, the hydraulic flow compensation path is activated, and while maintaining the continuity of hydraulic power transmission, the adjustment range and response step of the hydraulic pressure difference are limited to effectively limit the slewing angular velocity of the cantilever, and attitude stability control based on dynamic response adjustment is implemented; finally, a slewing risk alarm signal is sent to the main control unit to realize the graded response control and safety linkage handling of multi-level operational risks within the abnormal window.

[0044] like Figure 4 As shown, the graph displays the rotation operation risk assessment values ​​and risk level determination results corresponding to five abnormal windows, used to identify the operational risk classification status of the bucket wheel reclaimer cantilever under different rotation conditions. The graph uses a color-coded bar chart to represent the rotation operation risk assessment value S for each abnormal window, where green represents Level 1 risk, blue represents Level 2 risk, and red represents Level 3 risk, visually clearly distinguishing the risk level change trends under each abnormal window. Two dashed threshold lines are set in the graph as reference criteria for risk level classification: the orange dashed line represents the Level 1 risk assessment threshold S1, and the purple dashed line represents the Level 2 risk assessment threshold S2. Figure 4 It effectively depicts the dynamic evolution of slewing operation risks within each abnormal window, providing intuitive risk distribution data support for cantilever slewing anomaly identification, risk assessment, and graded control, thereby supporting the generation and execution of intelligent graded protection strategies under the cantilever slewing condition of the bucket wheel reclaimer.

[0045] In this implementation plan, the risk level determination and graded protection strategy for slewing operation enables accurate identification and dynamic response adjustment of the cantilever slewing condition within the abnormal window. By introducing multi-level slewing risk thresholds S1 and S2, combined with the real-time determination result of the slewing operation risk assessment value S, the graded execution of the slewing angular velocity, motor output power, and hydraulic flow control strategies under different risk levels is ensured, thereby effectively avoiding potential safety hazards such as slewing torque overload, attitude instability, and drive runaway. This strategy not only improves the sensitivity and targeting of abnormal response but also enhances the operational stability and safety redundancy of the cantilever slewing condition, providing a highly reliable safety guarantee for the continuous and stable operation of the bucket wheel reclaimer.

[0046] Specifically, the steps for extracting cantilever slewing condition data within K sampling periods after the implementation of the graded protection strategy and evaluating the recovery trend of the cantilever slewing condition are as follows: Starting from the first sampling period after the implementation of the graded protection strategy, continuously extract the slewing angular velocity and slewing support force within K sampling periods to construct a subsequence of cantilever slewing condition data for the corresponding time period, where K is a positive integer. Based on this subsequence of data, calculate the change in slewing angular velocity and the mean value of slewing support force within K sampling periods to ensure that the calculation results fully reflect the dynamic response characteristics after the control strategy is applied. Furthermore, combining the real-time collected cantilever slewing condition data, recalculate the slewing operation risk assessment value for the current sampling period. Add a constant one to the absolute value of the change in slewing angular velocity within K sampling periods and use this as the numerator. The denominator is the absolute value of the difference between the slewing support force in the current sampling period and the mean value of the slewing support force within K sampling periods, plus a minimum term. Take the natural logarithm of the ratio obtained and use it as the support disturbance adjustment term. Simultaneously, the risk assessment value of the current cyclical operation is subtracted from the initial cyclical operation risk assessment value, and then divided by the sum of the current cyclical operation risk assessment value and the minimum term. The square of the resulting ratio yields the risk fluctuation term, which reflects the relative intensity of change in the risk level. Finally, the support disturbance adjustment term and the risk fluctuation term are added together to obtain the cyclical trend recovery value.

[0047] The specific formula for calculating the trend recovery value is as follows: ; In the formula, Indicates the recovery value of the trend reversal. This represents the change in angular velocity over K sampling periods. Indicates the current retracement support level. This represents the average slewing support force over K sampling periods. This indicates the current risk assessment value for slewing operation. This represents the initial risk assessment value for slewing operation. Indicates a minus term.

[0048] This implementation scheme can dynamically characterize the stable recovery process of the cantilever slewing condition within a specified K sampling periods after the execution of the graded protection strategy, based on multi-dimensional key indicators such as slewing angular velocity, slewing support force, and slewing operation risk assessment value. By constructing support disturbance adjustment terms and risk fluctuation terms and calculating slewing trend recovery values, the response effect of the graded protection strategy can be quantitatively tracked, which helps to identify changes in the slewing system state in a timely manner, improves the accuracy of abnormal control and the responsiveness of operation condition assessment, and provides reliable criterion support for the closed-loop optimization of slewing operation safety strategies.

[0049] Specifically, the following steps are taken to construct a slewing trend recovery curve, combine the recovery trend assessment results and the curve slope, and dynamically adjust the protection strategy to achieve closed-loop control of the cantilever slewing condition: First, continuously extract the slewing trend recovery values ​​from the first sampling period after the execution of the graded protection strategy to the Kth sampling period, and construct a complete slewing trend recovery curve based on the sampling period sequence; then, use a weighted moving average method to smooth the slewing trend recovery curve, and combine it with first-order differential trend extraction technology to accurately obtain the slope change trend of the slewing trend recovery curve in the continuous sampling period; when the slope of the slewing trend recovery curve is greater than zero, and the slewing trend recovery values ​​in the continuous sampling period are all below the recovery threshold and show a continuous upward trend, automatically release the limitation adjustment range of the slewing angular velocity, and correspondingly widen the hydraulic differential pressure adjustment step size to improve the recovery response efficiency; when the slope of the slewing trend recovery curve is greater than zero, the protection strategy is adjusted dynamically based on the recovery trend assessment results and the curve slope, and ... protection strategy is adjusted dynamically based on the recovery trend assessment results and the protection strategy is adjusted dynamically based on the recovery trend assessment results and the protection strategy is adjusted dynamically based on the recovery trend assessment results and the protection strategy is adjusted dynamically based on the recovery trend assessment results When the slope of the slewing trend recovery curve is zero, and although the recovery value is below the recovery threshold, there is a downward wave, the current protection strategy remains unchanged, and the established control strategy continues to be executed. When the slope of the slewing trend recovery curve is zero or less than zero, and the slewing trend recovery value never reaches the recovery threshold, it is determined that there is a continuous abnormal fluctuation in the current cantilever slewing condition, and the protection strategy is upgraded to a higher level of protection. If it is already in a level three protection state, the power output of the cantilever drive side is further interrupted, and an audible and visual alarm is activated simultaneously to remind the operators to intervene and investigate in a timely manner. When the difference between the slope of the slewing trend recovery curve and zero is less than the recovery slope threshold, and the slewing trend recovery value is greater than the recovery threshold, it is determined that the current cantilever slewing condition has recovered to a safe range, the protection strategy control process is automatically exited, and the slewing anomaly assessment and operation risk monitoring path is reconnected, realizing a complete mechanism for full-cycle closed-loop monitoring, continuous tracking, and adaptive dynamic control of the cantilever slewing condition.

[0050] In this implementation plan, by constructing a slewing trend recovery curve and dynamically extracting the slope of the slewing trend recovery value, combined with the recovery trend assessment results, the risk evolution trend of the cantilever slewing condition can be accurately identified. By adjusting the slewing angular velocity limit range and the hydraulic differential pressure adjustment step size, the response sensitivity and adjustment accuracy during the anomaly recovery process are effectively improved. In the case of insufficient or deteriorating recovery trend, the protection strategy level is automatically upgraded and the cantilever drive power is cut off to ensure operational safety under high-risk conditions. After the recovery trend steadily rises and exceeds the recovery threshold, the system can intelligently exit the protection state and return to the slewing anomaly assessment and operational risk monitoring process, thereby realizing full-cycle closed-loop monitoring and adaptive control of the cantilever slewing condition, improving the real-time performance, continuity, and safety of anomaly management.

[0051] like Figure 2 As shown, the second aspect of the present invention provides a cantilever slewing torque protection system for a bucket wheel reclaimer based on intelligent monitoring, comprising: a data acquisition and preprocessing module, a cantilever torque anomaly identification module, a risk assessment and hierarchical control module, and an anomaly recovery adaptive control module. The data acquisition and preprocessing module is used to periodically acquire cantilever slewing condition data and obtain preprocessed cantilever slewing condition data through execution time synchronization, anomaly data removal, missing data completion, and standardization normalization. The cantilever torque anomaly identification module is used to calculate the cantilever slewing torque value based on the preprocessed cantilever slewing condition data and divide the data into sliding windows based on the sampling period. The system evaluates the stability of the cantilever slewing condition and marks the abnormal window based on the evaluation results. The risk assessment and graded control module is used to extract the slewing stability evaluation value and cantilever slewing torque data within the abnormal window, evaluate the abnormal intensity under the cantilever slewing condition, determine the operational risk level within the current abnormal window, and trigger the graded protection strategy. The abnormal recovery adaptive control module is used to extract the cantilever slewing condition data within K sampling periods after the graded protection strategy is executed, evaluate the recovery trend of the cantilever slewing condition, construct the slewing trend recovery change curve, and dynamically adjust the protection strategy based on the recovery trend evaluation results and the curve slope to achieve closed-loop control of the cantilever slewing condition.

[0052] This implementation plan constructs a bucket wheel reclaimer cantilever slewing torque protection system, comprising a data acquisition and preprocessing module, a cantilever torque anomaly identification module, a risk assessment and graded control module, and an anomaly recovery adaptive adjustment module. This system achieves closed-loop management of the entire cantilever slewing condition data process. The system ensures data reliability by performing time synchronization, anomaly data removal, missing data completion, and standardization of the cantilever slewing condition data. It assesses the stability of the cantilever slewing condition through a sliding window, identifying anomaly windows during operation. Furthermore, it comprehensively analyzes the slewing stability assessment value and cantilever slewing torque data within the anomaly window, quantifying the anomaly intensity, clarifying the risk level, and executing a matching graded protection strategy. After the protection strategy is executed, the system dynamically tracks the slewing trend recovery curve and precisely adjusts the protection strategy based on the recovery trend assessment results and curve slope, achieving intelligent, real-time, and adaptive operation of the entire process of cantilever slewing condition risk identification, control, and recovery.

[0053] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0054] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for protecting the cantilever rotation torque of a bucket wheel reclaimer based on intelligent monitoring, characterized in that, Includes the following steps: S1 periodically collects cantilever slewing condition data and obtains preprocessed cantilever slewing condition data through execution time synchronization, abnormal data removal, missing data filling and standardization normalization. S2, based on the preprocessed cantilever slewing condition data, calculate the cantilever slewing torque value, divide the sliding window according to the sampling period, evaluate the stability of the cantilever slewing condition, and mark the abnormal window based on the evaluation results; S3, extract the slewing stability assessment value and cantilever slewing torque data within the abnormal window, assess the abnormal intensity under the cantilever slewing condition, determine the operational risk level within the current abnormal window, and trigger the graded protection strategy. S4. Extract the cantilever slewing condition data within K sampling periods after the execution of the graded protection strategy, evaluate the recovery trend of the cantilever slewing condition, construct the slewing trend recovery change curve, and dynamically adjust the protection strategy based on the recovery trend evaluation results and the curve slope to achieve closed-loop control of the cantilever slewing condition.

2. The method for protecting the cantilever rotation torque of a bucket wheel reclaimer based on intelligent monitoring according to claim 1, characterized in that: The specific steps for periodically collecting cantilever slewing condition data and obtaining preprocessed cantilever slewing condition data through time synchronization, abnormal data removal, missing data completion, and standardization normalization are as follows: A fixed sliding time window is used as a sampling period to periodically collect cantilever slewing condition data, which includes motor current, motor voltage, hydraulic pressure, hydraulic flow, hydraulic motor speed, cantilever slewing angle, cantilever axial force, cantilever tangential force, slewing support force, slewing angular acceleration, slewing angular velocity, and cantilever vibration offset. By constructing a time synchronization mechanism based on timestamp alignment and sampling interval verification, multi-channel time-series registration is performed on cantilever slewing condition data. A steady-state segment extraction algorithm based on a sliding window is used to distinguish between stable operating intervals and loading variation intervals in the cantilever slewing condition data. Short-period disturbances in the cantilever slewing condition data are suppressed by combining a first-order low-pass filter and sliding range analysis. Abnormal abrupt changes are identified and marked using sliding Z-score detection and range limiting rules, and data replacement is completed using the mean method. For missing sampling segments, a linear interpolation method based on time neighborhood is used to complete the data. Finally, dimensionless processing and normalization are performed on cantilever slewing condition data of different dimensions by combining scaling and mean normalization.

3. The method for protecting the cantilever rotation torque of a bucket wheel reclaimer based on intelligent monitoring according to claim 1, characterized in that: The specific steps for calculating the cantilever slewing torque value based on the preprocessed cantilever slewing condition data are as follows: The preprocessed cantilever rotation data is extracted, and the drive power is obtained by multiplying the motor current and motor voltage. The drive-side torque is calculated by combining the rotation angular velocity. The hydraulic power is obtained by multiplying the hydraulic pressure and hydraulic flow rate. The hydraulic-side torque is calculated by combining the hydraulic motor speed. The axial force, tangential force and rotation angle of the cantilever are further extracted. The load-side resistance torque is calculated based on the relationship between the force and the length of the rotating arm. The drive-side torque, hydraulic-side torque and load-side resistance torque are superimposed to obtain the cantilever rotation torque value.

4. The method for protecting the cantilever rotation torque of a bucket wheel reclaimer based on intelligent monitoring according to claim 1, characterized in that: The specific steps for evaluating the stability of the cantilever swing condition by dividing the sliding window according to the sampling period are as follows: Arrange the cantilever slewing torque values ​​in chronological order to form a continuous torque time series. Divide the data into sliding windows based on the sampling period and calculate the changes in cantilever slewing torque, slewing angular velocity, cantilever vibration offset, and mean slewing support force within each window. The driving disturbance index is obtained by dividing the change in cantilever slewing torque by the sum of the change in slewing angular velocity and the minimum term, and taking the absolute value of the result. The driving disturbance index is obtained by dividing the change in cantilever vibration offset by the sum of the real-time slewing angular velocity and the minimum term, and taking the absolute value of the ratio as the base. The real-time slewing angular acceleration is divided by the maximum slewing angular acceleration within the window, and one is added to the sum, which is used as the exponent. The exponential function value is calculated to obtain the vibration response index. The difference between the real-time cantilever slewing angle and the cantilever slewing angle of the previous sampling period is calculated, and the absolute value is divided by the sum of the difference between the real-time slewing support force and the mean of the slewing support force and the minimum term, and one is added to the ratio to obtain the support disturbance coefficient. The driving disturbance index, the vibration response index, and the support disturbance coefficient are multiplied sequentially to obtain the slewing stability evaluation value.

5. The method for protecting the cantilever rotation torque of a bucket wheel reclaimer based on intelligent monitoring according to claim 4, characterized in that: The specific steps for marking abnormal windows based on the evaluation results are as follows: The system compares the gyrostability assessment value and the gyrostability threshold in real time. When the gyrostability assessment value is less than or equal to the gyrostability threshold, no action is taken. When the gyrostability assessment value is greater than the gyrostability threshold, the current sampling period is marked as an abnormal sampling period. The number of abnormal sampling periods within the window is calculated, and a gyrostability anomaly density curve is constructed based on the sliding window history. The mean gyrostability assessment value within the window is further calculated. If both the number of abnormal sampling periods and the mean gyrostability assessment value exceed the corresponding threshold, an anomaly warning signal is triggered, and the current window is marked as an abnormal window.

6. The method for protecting the cantilever rotation torque of a bucket wheel reclaimer based on intelligent monitoring according to claim 1, characterized in that: The specific steps for extracting the slewing stability assessment value and cantilever slewing moment data within the abnormal window to evaluate the abnormal strength under cantilever slewing conditions are as follows: Extract the slewing stability assessment value and cantilever slewing condition data within the abnormal window, and calculate the mean slewing stability assessment value, standard deviation of slewing stability assessment value, standard deviation of cantilever slewing torque, and mean cantilever slewing torque within the window; The anomaly intensity factor is obtained by adding the square of the mean of the slewing stability assessment value to the standard deviation of the slewing stability assessment value, and then dividing by the sum of the number of abnormal sampling periods and a constant. The vibration influence factor is obtained by adding the constant to the change in cantilever vibration offset and taking the natural logarithm. The structural disturbance factor is obtained by multiplying the change in cantilever slewing torque by the standard deviation of the cantilever slewing torque, dividing by the sum of the mean of the cantilever slewing torque and the minimum term, and then taking the square root of the product. The slewing operation risk assessment value is obtained by adding the anomaly intensity factor to the product of the vibration influence factor and the structural disturbance factor.

7. The method for protecting the cantilever rotation torque of a bucket wheel reclaimer based on intelligent monitoring according to claim 1, characterized in that: The specific steps for determining the operational risk level within the current abnormal window and triggering the graded protection strategy are as follows: By comparing the slewing operation risk assessment value S with the multi-level slewing risk thresholds S1 and S2 in real time, the operational risk level within the current anomaly window is determined and a graded protection strategy is triggered. When S≤S1, it is judged as a level 1 risk, the current rotational angular velocity is maintained, and the sampling frequency is increased; When S1 < S < S2, it is determined as a secondary risk. The rotational angular velocity is dynamically adjusted according to the difference between S and S1. Meanwhile, the motor output power is reduced, and the continuous torque output on the driving side is limited. When S ≥ S2, it is determined as a tertiary risk. The electronic control torque output of the driving device is aborted, and the rotation on the motor side is paused. The hydraulic flow compensation path is synchronously activated. By limiting the hydraulic pressure difference adjustment range and response step, rotational angular velocity limitation and attitude stability control are implemented for the cantilever. And a risk alarm signal is sent to the main control unit.

8. The method for protecting the cantilever rotation torque of a bucket wheel reclaimer based on intelligent monitoring according to claim 1, characterized in that: The specific steps for extracting the cantilever rotation condition data within K sampling periods after the execution of the extraction hierarchical protection strategy and evaluating the recovery trend of the cantilever rotation condition are as follows: Extract the rotational angular velocity and rotational support force within K sampling periods after the execution of the hierarchical protection strategy, calculate the change in rotational angular velocity and the average value of rotational support force within K sampling periods, and recalculate the current rotational operation risk assessment value based on the real-time cantilever rotation condition data. Add one to the absolute value of the change in rotational angular velocity, and then divide it by the sum of the absolute value of the difference between the current rotational support force and the average value of rotational support force within K sampling periods and the minimum term. Take the natural logarithm of the obtained ratio to get the support disturbance adjustment term. Subtract the initial rotational operation risk assessment value from the current rotational operation risk assessment value, and then divide the obtained ratio by the sum of the current rotational operation risk assessment value and the minimum term. Square the obtained ratio to get the risk fluctuation term. Add the support disturbance adjustment term and the risk fluctuation term to get the rotation trend recovery value.

9. The method for protecting the cantilever rotation torque of a bucket wheel reclaimer based on intelligent monitoring according to claim 1, characterized in that: The specific steps for constructing the rotation trend recovery change curve, dynamically adjusting the protection strategy in combination with the recovery trend evaluation result and the curve slope, and realizing the closed-loop control of the cantilever rotation condition are as follows: Calculate the rotation trend recovery value from the first sampling period to the Kth sampling period after the execution of the protection strategy, construct the rotation trend recovery change curve, and use the moving average and differential trend method to extract the curve slope. When the curve slope is positive and the rotation trend recovery value is lower than the recovery threshold and continues to rise, the angular velocity limitation range is mitigated and the hydraulic pressure difference adjustment step is relaxed. When the curve slope is positive and the rotation trend recovery value is lower than the recovery threshold and there is a downward wave band, the current protection strategy is continued. When the curve slope is zero or negative and the rotation trend recovery value is lower than the recovery threshold, the protection strategy level is automatically upgraded. If the current is already in the tertiary protection state, the power supply of the cantilever is cut off, and an audible and visual alarm is triggered. When the difference between the curve slope and zero is less than the recovery slope threshold and the rotation trend recovery value is greater than the recovery threshold, the protection strategy is exited, and the rotation anomaly evaluation and risk monitoring are re-entered to realize the closed-loop monitoring and adaptive control mechanism of the cantilever rotation condition.

10. A bucket wheel reclaimer cantilever rotation torque protection system based on intelligent monitoring, characterized in that: Include: A data acquisition and preprocessing module, a cantilever moment anomaly identification module, a risk assessment and hierarchical control module, and an anomaly recovery adaptive control module. Among them: The data acquisition and preprocessing module is used to periodically collect the cantilever rotation condition data, and obtain the preprocessed cantilever rotation condition data by performing time synchronization, abnormal data elimination, missing data filling, and standard normalization processing. The cantilever torque anomaly identification module is used to calculate the cantilever slewing torque value based on the preprocessed cantilever slewing condition data, divide the sliding window according to the sampling period, evaluate the stability of the cantilever slewing condition, and mark the abnormal window based on the evaluation result. The risk assessment and hierarchical control module is used to extract the slewing stability assessment value and cantilever slewing torque data within the abnormal window, assess the abnormal intensity under the cantilever slewing condition, determine the operational risk level within the current abnormal window, and trigger the hierarchical protection strategy. The abnormal recovery adaptive control module is used to extract cantilever slewing condition data within K sampling periods after the execution of the graded protection strategy, evaluate the recovery trend of the cantilever slewing condition, construct a slewing trend recovery change curve, and dynamically adjust the protection strategy based on the recovery trend evaluation results and the curve slope to achieve closed-loop control of the cantilever slewing condition.

Images