A bucket ship unloader taking head torque prediction and overload intelligent control method

Abstract

This invention relates to the field of intelligent control technology, specifically a method for predicting the torque and overload control of the feed head of a bucket chain unloader. The method includes: acquiring operating parameters of the bucket chain unloader at a set frequency and performing data preprocessing; constructing a feed head rotation torque prediction model and calculating the feed head rotation torque based on the operating parameters; constructing a lifting torque prediction model based on the load characteristics of the lifting mechanism and calculating the lifting torque; normalizing the feed head rotation torque and lifting torque and verifying the rationality of the normalization; assessing the overload risk index based on the overload risk indicator and determining the overload risk level; and formulating a graded control strategy based on the overload risk level to achieve intelligent control when an overload occurs.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and in particular to a method for predicting the torque and overload intelligent control of the feed head of a chain bucket unloader. Background Technology

[0002] Chain bucket unloaders are core equipment for bulk cargo unloading operations in ports, boasting advantages such as high unloading efficiency and adaptability to a wide range of materials. In actual operation, the chain bucket unloader's material handling head rotation mechanism and lifting chain bucket mechanism are in direct contact with the material. Its torque load is affected by various factors, including material characteristics, operating parameters, and equipment posture, making it prone to overload conditions.

[0003] When overload occurs, failure to take timely control measures can lead to equipment failures such as chain damage, motor overcurrent, and deformation of the material handling head structure. This not only affects operational efficiency but may also cause safety accidents. In existing technologies, overload control of chain bucket unloaders often employs a feedback control method based on real-time torque detection. This involves using sensors to detect the current torque, and triggering a stop or deceleration command when the torque exceeds the rated threshold. However, this method has significant drawbacks: firstly, sensor detection has a certain lag; by the time overload is detected, the equipment has already been under overload for some time, significantly increasing the risk of failure; secondly, real-time torque only reflects the current load state and cannot predict future load changes in the short term, making it difficult to provide early warning for sudden overloads, resulting in insufficient timeliness and effectiveness of control response.

[0004] Furthermore, existing technologies lack quantitative assessment methods for overload risk, often using a single torque threshold as the judgment standard without comprehensively considering the synergistic effects of multiple factors such as material depth, flow rate, and speed change rate on overload. This results in low accuracy in overload judgment and a tendency for false alarms or missed alarms.

[0005] Therefore, there is an urgent need to develop an intelligent control technology for chain bucket unloaders that can predict overload risks in advance, conduct comprehensive quantitative assessments of multiple factors, and respond promptly, in order to address the shortcomings of existing technologies. Summary of the Invention

[0006] To address the aforementioned technical problems, this invention provides a method for predicting the torque and intelligently controlling overload of the feed head of a chain bucket unloader. This invention primarily overcomes the limitations of traditional control methods, such as lag and single-parameter limitations, by constructing a dual torque prediction model and an overload risk index, thereby achieving early prediction and tiered control of overload risks.

[0007] The technical means employed in this invention are as follows:

[0008] A method for predicting the torque of the feed unloader's reclaiming head and intelligently controlling overload includes: collecting operating parameters of the feed unloader at a set frequency and performing data preprocessing; constructing a predictive model for the rotational torque of the feed unloader's reclaiming head and calculating the rotational torque of the feed unloader's reclaiming head based on the operating parameters; constructing a predictive model for the lifting torque based on the load characteristics of the lifting mechanism and calculating the lifting torque; normalizing the rotational torque of the feed unloader's reclaiming head and the lifting torque and verifying the rationality of the normalization; assessing the overload risk index based on the overload risk indicator and determining the overload risk level; and formulating a graded control strategy based on the overload risk level to achieve intelligent control when an overload occurs.

[0009] Furthermore, the operating parameters include material handling depth parameters, speed parameters, flow rate parameters, torque parameters, and attitude parameters; the material handling depth parameters This indicates the extension / retraction length of the material handling head, and the speed parameters include: cross-cutting speed. , tangential velocity slope and parallel velocity The flow parameters include real-time flow. The torque parameters include: the rotation torque of the material handling head. Increase torque Historical material handling head rotation torque and historical torque increase The attitude parameters include: boom rotation angle. boom pitch angle and material handling head angle The raw data is filtered using a moving average filtering algorithm to eliminate sensor noise interference. An abnormal threshold is set for parameters, and outliers are automatically removed and replaced with valid values ​​from the previous time step to ensure the continuity and reliability of the input data.

[0010] Furthermore, the construction of the prediction model for the rotating torque of the material receiving head specifically includes: the core variables affecting the rotating torque of the material receiving head include: the extension length of the material receiving head. Absolute value of transverse cutting speed , square of transverse velocity Real-time traffic The product of flow rate and absolute value of tangential velocity slope Absolute value of boom slewing angle Current rotational torque Historical rotational torque And the correlation function between boom posture and head angle. The boom posture and the head angle correlation function are used to characterize the additional resistance under different postures; The following expression is used to construct the prediction model for the rotating torque of the material handling head, employing a combination of linear and nonlinear methods:

[0011] in, For the parameters to be calibrated, For the future Predicted rotational torque at time t.

[0012] Furthermore, the construction of the torque prediction model specifically includes: variables affecting the torque include: real-time flow rate. The product of flow rate and material depth Current boost torque Current rotational torque absolute value of parallel velocity Historical torque increase Correlation function of frame rotation attitude The product of the flow rate and the material picking depth is used to characterize the synergistic effect of material weight and lifting path. Establish a lifting torque prediction model based on the load characteristics of the lifting mechanism:

[0013] in, For the parameters to be calibrated, For the future Predicting the moment to increase torque.

[0014] Furthermore, the normalization process specifically includes: eliminating the dimensional differences between the current torque and the predicted torque through normalization. ,

[0015] ,

[0016] in, , These are the normalized values ​​of the current and predicted rotational torques, respectively. , These are the normalized values ​​of the current and predicted boost torques, respectively, both ranging from [0, +∞). , , and A value greater than 1 indicates that the torque exceeds the rated load; If the normalized value is abnormal, trace back to the parameter acquisition stage to check if the sensor is faulty or if the parameter preprocessing is incorrect; if the normalized value is always greater than 0.5 within a set period of time, prompt the operator to optimize the operating parameters and improve the unloading efficiency.

[0017] Furthermore, the overload risk indicators include: a velocity change rate indicator and a flow load indicator, wherein the velocity change rate indicator is the ratio of the absolute value of the tangential velocity slope to the reference acceleration. ,in The slope of the average cross-sectional velocity under normal operating conditions reflects the drastic degree of load change; the flow load index is the ratio of real-time flow rate to reference flow rate. ,in The rated flow rate of the equipment represents the degree of deviation of the current material load from the rated operating conditions. The overload risk index is constructed using a linear weighted summation method. The expression is as follows:

[0018] An overload risk threshold of 1.0 is set to determine the overload risk level, which is then categorized into no risk, low risk, medium risk, and high risk based on an index value. The range of no risk is... This indicates that the equipment load is within a safe range; the low-risk range is... This indicates that the load is close to the rated value and requires slight adjustment; the range of moderate risk is... This indicates that the load exceeds the rated value and requires significant adjustment; the high-risk range is... This indicates a severe overload, requiring immediate intervention.

[0019] Furthermore, the graded control strategy includes: when the overload risk level is no risk, maintaining the current operating parameters; if efficiency needs to be improved, fine-tuning the parameters according to the flow maximization logic; when the overload risk level is low risk, issuing a deceleration command to reduce the cross-cutting speed by 10%~20% and the parallel speed by 15%~25%, monitoring torque changes in real time; if the overload risk index falls back to the no-risk range, restoring the original speed parameters; when the overload risk level is medium risk, issuing a combination of retraction and deceleration commands to raise the material head telescopic mechanism by 0.2m~0.5m, reduce the cross-cutting speed by 20%~30%, reduce the parallel speed by 30%~40%, and trigger an audible and visual warning to remind operators to pay attention to the material condition; when the overload risk level is high risk, issuing an emergency stop command to stop the cross-cutting drive motor, the lifting drive motor, and the material head telescopic mechanism, triggering a high-level alarm, locking the equipment's operating permissions, requiring operators to troubleshoot the fault and manually unlock and restart.

[0020] Compared with the prior art, the present invention has the following advantages: The present invention provides a method for torque prediction and intelligent overload control of the feed head of a chain bucket unloader. Through dual torque prediction and multi-factor overload assessment, it anticipates overload risks in advance, effectively decoupling sensor lag issues and significantly reducing equipment failure risks. This method can be seamlessly integrated with existing systems without large-scale modifications. Hierarchical control provides a precise balance between safety and efficiency, resulting in low engineering application costs and high operational efficiency. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of the intelligent control method for torque prediction and overload control of the feed head of the chain bucket unloader in this invention. Detailed Implementation

[0023] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the present invention or its application or use. 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.

[0025] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0026] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of the invention. It should also be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale. Techniques, methods, and devices known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters in the following figures denote similar items; therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0027] like Figure 1 As shown, this invention provides a method for predicting the torque and intelligently controlling overload of the feed head of a chain bucket unloader, comprising: collecting the operating parameters of the chain bucket unloader based on a set frequency and performing data preprocessing; in a preferred embodiment of this invention, the operating parameters include feed depth parameters, speed parameters, flow rate parameters, torque parameters, and attitude parameters; the feed depth parameter... This indicates the extension / retraction length of the feed head; speed parameters include: cross-cutting speed. , tangential velocity slope and parallel velocity Traffic parameters include real-time traffic. Torque parameters include: rotational torque of the feed head. Increase torque Historical material handling head rotation torque and historical torque increase Attitude parameters include: boom rotation angle boom pitch angle and material handling head angle The parameter sampling frequency is no less than 10Hz to ensure that the data reflects the dynamic operating status of the equipment in real time. Historical torque parameters. , Stored through data cache units The (prediction time interval) ranges from 0.1s to 1s and can be adaptively adjusted according to the device's response speed (such as motor start-stop delay and sensor lag time).

[0028] The raw data is filtered using a moving average filtering algorithm to eliminate sensor noise interference. An abnormal threshold is set for parameters, and outliers are automatically removed and replaced with valid values ​​from the previous time step to ensure the continuity and reliability of the input data.

[0029] A model for predicting the rotational torque of the material receiving head is constructed, and the rotational torque of the material receiving head is calculated based on operating parameters. In a preferred embodiment of this invention, the core variables affecting the rotational torque of the material receiving head include: the extension length of the material receiving head. Absolute value of transverse cutting speed , square of transverse velocity Real-time traffic The product of flow rate and absolute value of tangential velocity slope Absolute value of boom slewing angle Current rotational torque Historical rotational torque And the correlation function between boom posture and head angle. The boom posture and the head angle correlation function are used to characterize the additional resistance under different postures; A combined linear and nonlinear approach is used to construct a prediction model for the rotating torque of the material handling head, balancing physical interpretability and fitting accuracy. The expression is as follows:

[0030] in, For the parameters to be calibrated, For the future Predicted rotational torque at time t.

[0031] Historical operating data of the chain bucket unloader was collected, including input variables and actual rotational torque sample pairs under different material conditions and operating parameters. These were divided into training and validation sets in an 8:2 ratio. Linear regression or XGBoost machine learning algorithms were used, with the mean square error (MSE) between predicted and actual torques as the objective function, and parameters were optimized using gradient descent. The pre-processed real-time and historical parameters were then substituted into the calibrated model to calculate future... Predicted rotational torque at time This information is then output to the subsequent overload risk assessment step.

[0032] A lifting torque prediction model is constructed based on the load characteristics of the lifting mechanism to calculate the lifting torque. Specifically, in a preferred embodiment of this invention, the variables affecting the lifting torque include: real-time flow rate. The product of flow rate and material depth Current boost torque Current rotational torque absolute value of parallel velocity Historical torque increase Correlation function of frame rotation attitude The product of flow rate and material handling depth is used to characterize the synergistic effect of material weight and lifting path. Establish a lifting torque prediction model based on the load characteristics of the lifting mechanism:

[0033] in, For the parameters to be calibrated, For the future Predicting the moment to increase torque.

[0034] The predicted lifting torque is calculated by substituting the preprocessed parameters into the calibrated lifting torque model. , and the output Together, they serve as core inputs for overload risk assessment.

[0035] The rotational torque and lifting torque of the material receiving head are normalized, and the rationality of the normalization is verified. In a preferred embodiment of the invention, the dimensional difference between the current torque and the predicted torque is eliminated through normalization. ,

[0036] ,

[0037] in, , These are the normalized values ​​of the current and predicted rotational torques, respectively. , These are the normalized values ​​of the current and predicted boost torques, respectively, both ranging from [0, +∞). , , and A value greater than 1 indicates that the torque exceeds the rated load; If the normalized value is abnormal, trace back to the parameter acquisition stage to check if the sensor is faulty or if the parameter preprocessing is incorrect; if the normalized value is always greater than 0.5 within a set period of time, prompt the operator to optimize the operating parameters and improve the unloading efficiency.

[0038] The overload risk index is assessed based on overload risk indicators to determine the overload risk level. In a preferred embodiment of this invention, the overload risk indicators include: a velocity change rate indicator and a flow load indicator. The velocity change rate indicator is the ratio of the absolute value of the tangential velocity slope to the reference acceleration. ,in The average tangential velocity slope under normal operating conditions reflects the drastic degree of load change; the flow load index is the ratio of real-time flow rate to reference flow rate. ,in The rated flow rate of the equipment represents the degree of deviation of the current material load from the rated operating conditions. The overload risk index is constructed using a linear weighted summation method. The expression is as follows:

[0039] By combining historical overload case data fitting with engineering experience, the weights of each parameter are determined. This ensures that the core parameter (predicted torque) has a higher weight.

[0040] An overload risk threshold of 1.0 is set to determine the overload risk level, which is then categorized into no risk, low risk, medium risk, and high risk based on the index value. The range for no risk is... This indicates that the equipment load is within a safe range; the low-risk range is... This indicates that the load is close to the rated value and requires slight adjustment; the range of medium risk is... This indicates that the load exceeds the rated value and requires significant adjustment; the high-risk range is... This indicates a severe overload, requiring immediate intervention.

[0041] A graded control strategy is developed based on the overload risk level to achieve intelligent control when an overload occurs. In specific implementation, as a preferred embodiment of the present invention, the graded control strategy includes: when the overload risk level is no risk, maintaining the current operating parameters; if efficiency needs to be improved, fine-tuning the parameters according to the flow maximization logic; when the overload risk level is low risk, issuing a deceleration command to reduce the cross-cutting speed by 10%~20% and the parallel speed by 15%~25%, monitoring torque changes in real time; if the overload risk index falls back to the no-risk range, restoring the original speed parameters; when the overload risk level is medium risk, issuing a combination of retraction and deceleration commands to raise the material head telescopic mechanism by 0.2m~0.5m, reduce the cross-cutting speed by 20%~30%, reduce the parallel speed by 30%~40%, and trigger an audible and visual warning to remind operators to pay attention to the material condition; when the overload risk level is high risk, issuing an emergency stop command to stop the operation of the cross-cutting drive motor, the lifting drive motor, and the material head telescopic mechanism, triggering a high-level alarm, locking the equipment operating permissions, requiring operators to troubleshoot the fault and manually unlock and restart.

[0042] The intelligent control module in the chain bucket unloader converts control commands into signals that the actuators can recognize (such as frequency adjustment signals from the frequency converter and switching signals from the hydraulic valve group), driving the lateral cutting, lifting, and telescopic mechanisms to move; and collects the action feedback signals of the actuators in real time (such as motor speed and displacement of the telescopic mechanism) to verify whether the commands have been executed properly.

[0043] If the overload risk index does not change as expected after the command is executed, the adjustment range will be further increased. The manual control mode is retained. When operators discover abnormal operating conditions (such as sensor failure or abnormal material accumulation), they can switch to manual mode via the HMI (Human Machine Interface) to override the automatic control command. In manual mode, operators can directly set parameters such as cutting speed and material handling depth. The equipment operates according to the manual parameters, while the system continuously monitors torque and overload index. If a high risk is detected, an emergency shutdown will be triggered to ensure safety.

[0044] Example This embodiment uses a 3600t / h chain bucket unloader at a port in Zhanjiang as an example to explain in detail the implementation process and effects of the present invention. This equipment is mainly used for unloading bulk cargo such as coal and iron ore.

[0045] S1. Determine the core parameters of the model and the data acquisition rules. S11, Basic Parameter Calibration Rated torque of the feed head rotation Increase the rated torque of the system Prediction time interval Reference acceleration Reference flow Overload risk index weight: , , , , , .

[0046] S12, Data Acquisition Parameters Sampling frequency: The sampling frequency for all operating parameters is set to 10Hz; Key parameter acquisition range: extension / retraction length of the material handling head. Cross-cutting speed Real-time traffic .

[0047] S2. Model Parameter Training and Calibration By collecting 1200 hours of historical operating data of the ship unloader, the parameters of the dual torque model were trained using the XGBoost algorithm.

[0048] S21, Rotational Torque Prediction Model Parameters

[0049] , , , , , , , , , Attitude correlation function: hour, ;when hour, .

[0050] S22, Parameters of the Torque Prediction Model

[0051] , , , (dimensionless) (dimensionless) (dimensionless) , Boom association function: hour, ;when hour, .

[0052] S3. Field Application and Effect Verification S31, Test Conditions Material type: iron ore (density 4.8 t / m³); the working vessel's hold is an irregularly shaped hold (bulwark inclination angle 10°); set operating parameters: material extraction depth. Initial cross-cutting velocity Target traffic .

[0053] S32. Key Data and Results Torque prediction accuracy: The prediction error of rotational torque is 4.2%, and the prediction error of boosting torque is 5.1%, both of which meet the requirements of engineering applications; Overload response: When a sudden change in material flow causes the predicted torque to rise to 118% of the rated value, the system makes an advance prediction and issues a deceleration command to avoid continuous overload; Application effect: After 100 hours of trial operation, there were no equipment jams or motor overload faults, the false alarm rate was 3.8%, and the efficiency of unloading operations was improved by 12% compared with traditional control.

[0054] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and 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 or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting torque and intelligently controlling overload of the feed head of a chain bucket unloader, characterized in that, include: The operating parameters of the chain bucket unloader are collected based on a set frequency, and the data is preprocessed. Construct a model for predicting the rotational torque of the material receiving head, and calculate the rotational torque of the material receiving head based on the operating parameters; A lifting torque prediction model is constructed based on the load characteristics of the lifting mechanism, and the lifting torque is calculated. The rotational torque and lifting torque of the material receiving head are normalized, and the rationality of the normalization process is verified. The overload risk index is assessed based on overload risk indicators to determine the overload risk level. A graded control strategy is formulated based on the overload risk level to achieve intelligent control when an overload occurs.

2. The method for predicting torque and intelligent overload control of the feed head of a chain bucket unloader according to claim 1, characterized in that, The operating parameters include material handling depth parameters, speed parameters, flow rate parameters, torque parameters, and attitude parameters; the material handling depth parameters This indicates the extension / retraction length of the material handling head, and the speed parameters include: cross-cutting speed. , tangential velocity slope and parallel velocity The flow parameters include real-time flow. The torque parameters include: the rotation torque of the material handling head. Increase torque Historical material handling head rotation torque and historical torque increase The attitude parameters include: boom rotation angle. boom pitch angle and material handling head angle ; The raw data is filtered using a moving average filtering algorithm to eliminate sensor noise interference. An abnormal threshold is set for parameters, and outliers are automatically removed and replaced with valid values ​​from the previous time step to ensure the continuity and reliability of the input data.

3. The method for predicting torque and intelligent overload control of the feed head of a chain bucket unloader according to claim 1, characterized in that, The construction of the rotational torque prediction model for the material taking head specifically includes: The key variables affecting the rotational torque of the feed head include: the feed head extension / retraction length. Absolute value of transverse cutting speed , square of transverse velocity Real-time traffic The product of flow rate and absolute value of tangential velocity slope Absolute value of boom slewing angle Current rotational torque Historical rotational torque And the correlation function between boom posture and head angle. The boom posture and the head angle correlation function are used to characterize the additional resistance under different postures; The following expression is used to construct the prediction model for the rotating torque of the material handling head, employing a combination of linear and nonlinear methods: in, For the parameters to be calibrated, For the future Predicted rotational torque at time t.

4. The method for predicting torque and intelligent overload control of the feed head of a chain bucket unloader according to claim 1, characterized in that, The construction of the torque prediction model specifically includes: Variables affecting the boost torque include: real-time flow rate The product of flow rate and material depth Current boost torque Current rotational torque absolute value of parallel velocity Historical torque increase Correlation function of frame rotation attitude The product of the flow rate and the material picking depth is used to characterize the synergistic effect of material weight and lifting path. Establish a lifting torque prediction model based on the load characteristics of the lifting mechanism: in, For the parameters to be calibrated, For the future Predicting the moment to increase torque.

5. The method for predicting torque and intelligent overload control of the feed head of a chain bucket unloader according to claim 3 or 4, characterized in that, The normalization process specifically includes: The dimensional difference between the current torque and the predicted torque is eliminated through normalization: ， ， in, , These are the normalized values ​​of the current and predicted rotational torques, respectively. , These are the normalized values ​​of the current and predicted boost torques, respectively, both ranging from [0, +∞). , , and A value greater than 1 indicates that the torque exceeds the rated load; If the normalized value is abnormal, trace back to the parameter acquisition stage to check if the sensor is faulty or if the parameter preprocessing is incorrect; if the normalized value is always greater than 0.5 within a set period of time, prompt the operator to optimize the operating parameters and improve the unloading efficiency.

6. The method for predicting torque and intelligent overload control of the feed head of a chain bucket unloader according to claim 1, characterized in that, The overload risk indicators include: a velocity change rate indicator and a flow load indicator. The velocity change rate indicator is the ratio of the absolute value of the tangential velocity slope to the reference acceleration. ,in The slope of the average cross-sectional velocity under normal operating conditions reflects the drastic degree of load change; the flow load index is the ratio of real-time flow rate to reference flow rate. ,in The rated flow rate of the equipment represents the degree of deviation of the current material load from the rated operating conditions. The overload risk index is constructed using a linear weighted summation method. The expression is as follows: An overload risk threshold of 1.0 is set to determine the overload risk level, which is then categorized into no risk, low risk, medium risk, and high risk based on an index value. The range of no risk is... This indicates that the equipment load is within a safe range; the low-risk range is... This indicates that the load is close to the rated value and requires slight adjustment; the range of moderate risk is... This indicates that the load exceeds the rated value and requires significant adjustment; the high-risk range is... This indicates a severe overload, requiring immediate intervention.

7. The method for predicting torque and intelligent overload control of the feed head of a chain bucket unloader according to claim 6, characterized in that, The hierarchical control strategy includes: When the overload risk level is no risk, maintain the current operating parameters. If efficiency needs to be improved, fine-tune the parameters according to the flow maximization logic. When the overload risk level is low risk, issue a deceleration command to reduce the cross-cutting speed by 10%~20% and the parallel speed by 15%~25%, monitor torque changes in real time, and restore the original speed parameters if the overload risk index falls back to the no-risk range. When the overload risk level is medium risk, issue a combination of retraction and deceleration commands to raise the material head telescopic mechanism by 0.2m~0.5m, reduce the cross-cutting speed by 20%~30%, reduce the parallel speed by 30%~40%, and trigger an audible and visual alarm to remind operators to pay attention to the material condition. When the overload risk level is high risk, issue an emergency stop command to stop the cross-cutting drive motor, the lifting drive motor, and the material head telescopic mechanism, trigger a high-level alarm, lock the equipment's operating permissions, and require operators to troubleshoot the fault and manually unlock and restart.

Images