Intelligent self-adaptive tensioning system and method for belt conveyor under mine

Abstract

The invention provides an intelligent self-adaptive tensioning system and method for a belt conveyor under a mine. The system comprises a belt assembly, a tension detection unit, an intelligent control unit and an execution mechanism which form a closed-loop control system. The tension detection unit monitors the belt tension in real time and outputs a signal; the intelligent control unit receives the processing signal, calculates an adjustment amount according to a self-adaptive control algorithm and generates an instruction; and the execution mechanism receives the instruction to adjust the belt tension. A fuzzy PID (Proportion Integration Differentiation) control algorithm is adopted, a tension prediction model is included, and a tension adjusting assembly can be accurately adjusted. The method comprises the steps of tension detection, data transmission, preprocessing, working condition recognition and target setting, tension prediction, control quantity calculation, instruction generation and execution, closed-loop feedback, safety monitoring and the like. Real-time accurate automatic adjustment is achieved, frequent manual intervention is not needed, complex working conditions can be dealt with, the belt problem is avoided, the production efficiency is improved, the service life of equipment is prolonged, and the operation performance is optimized.

Description

Technical Field

[0001] This invention relates to the field of belt conveyor auxiliary equipment technology, specifically an intelligent adaptive tensioning system and method for underground belt conveyors. Background Technology

[0002] In industrial production fields such as mining, underground belt conveyors are key equipment for material transport, and their operating status directly affects the efficiency and stability of the entire production process. The belt tensioning system is one of the core components that ensures the normal operation of the belt conveyor. Reasonable belt tension can ensure that sufficient friction is generated between the belt and the drive roller, preventing belt slippage and ensuring efficient material transport.

[0003] Currently, the tensioning systems of underground conveyor belts in mines generally rely on manual periodic inspection and adjustment. Workers need to check the belt tension at predetermined intervals and manually adjust the tensioning device based on experience to maintain the belt tension within a suitable range. However, this method has many drawbacks. On the one hand, manual inspection and adjustment not only consume a large amount of manpower and resources but also have low efficiency, making it difficult to meet the high-efficiency requirements of modern mine production. On the other hand, the underground working environment is complex and variable, with frequent load fluctuations, and the belt gradually wears down during use. These factors all cause changes in belt tension. Manual periodic inspection and adjustment cannot respond to these changes in working conditions in a timely and accurate manner. When the load suddenly increases or the belt wears severely, the belt tension may not be adjusted to the appropriate state in time, leading to problems such as belt slippage and insufficient tension. In severe cases, it can even cause belt damage, affecting production efficiency, increasing equipment maintenance costs, and shortening equipment lifespan.

[0004] Although some automated tensioning devices have emerged in existing technologies, most of these devices still have certain limitations. While some automated tensioning devices can achieve automatic adjustment to a certain extent, they still require manual intervention and parameter setting, and cannot fully adapt to the actual working conditions underground. Faced with complex and changing working environments, these devices struggle to adjust belt tension in real time and accurately, and cannot effectively solve problems such as belt slippage and unstable tension, thus failing to meet the demands of modern mining production for intelligent and efficient equipment. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the above-mentioned technical defects and provide an intelligent adaptive tensioning system and method for underground conveyor belts.

[0006] To address the aforementioned technical problems, this invention provides an intelligent adaptive tensioning system and method for underground conveyor belts. This system effectively improves the automation level of conveyor belts, reduces manual maintenance, and increases production efficiency and equipment lifespan, thus solving a pressing technical problem in the field of underground material conveying.

[0007] To solve the above-mentioned technical problems, the present invention provides an intelligent adaptive tensioning system for underground conveyor belts, comprising:

[0008] The belt assembly includes a drive roller, a driven roller, a drive motor, and a belt. The drive roller is connected to the output shaft of the drive motor via a coupling, and the belt is wound around the drive roller and the driven roller to form a closed loop structure.

[0009] The tension detection unit is installed on the tension side of the belt to monitor the tension changes of the belt in real time and convert the monitored tension signal into an electrical signal for output.

[0010] The intelligent control unit is communicatively connected to the tension detection unit. It receives and processes tension signals from the tension detection unit via an RS-485 communication module. Its microprocessor calculates the adjustment amount of belt tension according to a preset adaptive control algorithm and generates corresponding control commands.

[0011] An actuator, communicatively connected to the intelligent control unit, is used to receive control commands sent by the intelligent control unit and adjust the belt tension through a mechanical structure to keep the belt tension within a set range; it includes a motor, a reducer, and a tension adjustment assembly, wherein the motor is connected to the reducer, and the reducer drives the tension adjustment assembly to adjust the belt tension;

[0012] The tension detection unit, intelligent control unit, and actuator form a closed-loop control system to achieve adaptive adjustment of belt tension.

[0013] Preferably, the tension detection unit includes:

[0014] Tension detection roller, installed below the belt, has several resistance strain gauge tension sensors arranged circumferentially that contact the bottom of the belt.

[0015] A signal conditioning circuit board, electrically connected to the strain gauge tension sensor, receives the raw analog voltage signal output by the sensor and performs collaborative processing. It integrates the following:

[0016] The bridge excitation module provides a stable operating voltage for the sensor.

[0017] The signal amplification module amplifies the weak voltage signal output by the sensor.

[0018] The low-pass filter module filters out high-frequency interference noise in the signal;

[0019] The temperature compensation module receives measurements from the built-in temperature sensor and compensates for the drift of the tension signal based on the ambient temperature. The compensation formula is as follows:

[0020]

[0021] in, This is the actual tension value after temperature compensation; F t The compensation value is the tension value; α is the temperature coefficient; T is the current ambient temperature; T0 is the reference temperature during calibration;

[0022] The data acquisition terminal has its input end directly connected to the output end of the signal conditioning circuit board to receive the conditioned and compensated analog voltage signal; the data acquisition terminal includes a high-precision analog-to-digital converter for converting the conditioned analog voltage signal into a digital tension signal;

[0023] The communication module is connected to the data acquisition terminal and transmits the digital tension signal and associated temperature data to the intelligent control unit.

[0024] The power management module provides power to the resistance strain gauge tension sensor, signal conditioning circuit board, and data acquisition terminal.

[0025] Preferably, the intelligent control unit performs smoothing filtering on the received raw tension data, using a first-order moving average algorithm, the formula of which is:

[0026]

[0027] in, F represents the smoothed tension value at time k, i.e., the tension data after moving average processing; t (k) is the original tension value at the current time k, which is the real-time data directly measured by the sensor; λ is the smoothing factor, which is between 0 and 1.

[0028] Preferably, the adaptive control algorithm of the intelligent control unit is a fuzzy PID control algorithm, and its control output, i.e., the tension adjustment distance Δd, is calculated using the following formula:

[0029]

[0030] in, The tension error at time k; K represents the target tension value. p K i and K d For PID control parameters; K p Ki and K d The value is adjusted in real time by the fuzzy inference module based on the tension error e and its rate of change Δe.

[0031] Preferably, the intelligent control unit further includes a time-series-based tension prediction model, used to predict the tension trend in future periods based on historical and current tension data, and to perform preventative adjustments based on the prediction results. The time-series-based tension prediction model is a Long Short-Term Memory (LSTM) neural network model. This model uses historical time-series tension data and corresponding operating parameters as input, and outputs a predicted tension value T^t+1 for future periods, expressed by the formula:

[0032]

[0033] Where θ are model parameters, and the function f LSTM This represents a trained LSTM network.

[0034] Preferably, the tension adjustment assembly includes a speed reducer base, an adjustment seat on the speed reducer base, an adjustment port on the adjustment seat, a lead screw rotatably mounted vertically inside the adjustment port, the speed reducer and the drive motor are both mounted inside the speed reducer base and the output shaft of the drive motor is connected to the bottom of the lead screw, a lifting seat is threaded on the lead screw and slides against the inner wall of the adjustment port, and a tension adjustment roller pressing against the inner side of the belt is rotatably mounted on the lifting seat.

[0035] Preferably, the actuator includes a position feedback sensor for detecting the actual displacement L of the tension adjusting roller. actual The intelligent control unit converts the target displacement ΔL into the target rotation angle θ of the drive motor. target The formula is:

[0036]

[0037] Where P is the lead of the leadscrew; Its k is the stiffness coefficient of the tensioning system, ΔT = T target -T current , where T is the difference between the target tension and the current tension. current This refers to real-time tension data obtained from the tension detection unit;

[0038] The system compares the actual displacement L in real time. actual The system continuously adjusts the displacement ΔL relative to the target displacement when the deviation exceeds the preset tolerance range. If the target is not reached within the preset time, the actuator is controlled to stop and an alarm is triggered.

[0039] This application also provides an intelligent adaptive tensioning method for underground conveyor belts in mines, which specifically includes the following steps:

[0040] S1. Tension Detection: A strain gauge tension sensor detects real-time changes in belt tension, converting them into an electrical signal. After signal conditioning and temperature compensation, the signal is converted into a digital tension signal F by an ADC. t ;

[0041] S2. Data transmission: Pack the digital tension signal and ambient temperature data and transmit them to the intelligent control unit through the communication interface;

[0042] S3. Data Preprocessing: The intelligent control unit processes the raw tension data F... t (k) Perform moving average filtering to obtain the smoothed tension value.

[0043] S4. Operating Condition Identification and Target Setting: Based on real-time acquired belt speed, conveying load, and ambient temperature and humidity parameters, the current operating condition is identified; according to the identification result, the preset optimal tension setting range for the corresponding operating condition is applied. And calculate the target tension value

[0044] S5. Tension Prediction: Input historical and current smoothed tension values ​​and operating parameters into a pre-trained LSTM prediction model, and output the future short-term tension prediction value T^t+1.

[0045] S6. Control quantity calculation:

[0046] Calculate tension error A fuzzy PID control algorithm is used to calculate the target displacement Δd(k) of the tension adjustment mechanism; based on the system stiffness parameter k, the tension adjustment requirement ΔT is converted into the target displacement ΔL = ΔT / k;

[0047] S7. Command Generation and Execution: Convert the target displacement ΔL into the target rotation angle θ of the drive motor. target The system generates control commands containing direction and time / angle and sends them to the actuator; the actuator drives the servo motor to drive the transmission motor, which in turn drives the lead screw through the reducer to move the tension adjustment roller up and down.

[0048] S8. Closed-loop feedback and safety monitoring: Feedback of actual displacement L via position sensor. actual Meanwhile, the actual tension T is continuously monitored. current The adjustment stops when the actual value reaches the target value; if the target value is not reached within the time limit or the tension is abnormal, the drive stops and an alarm is triggered.

[0049] Preferably, in step S7, the servo motor begins to adjust its position according to the control signal, using a built-in encoder for precise position control.

[0050] The output torque T of the servo motor motorThe output torque T is obtained by amplification using a speed reducer. output The formula is as follows:

[0051] T output =T motor ×i

[0052] Where i is the reduction ratio of the reducer, the rotary motion output by the reducer drives the lead screw to rotate, which in turn drives the lifting seat to move linearly, thereby adjusting the tension of the belt.

[0053] The seat height adjustment is achieved by using a position feedback sensor to detect the rotation angle θ. feedback calculate:

[0054]

[0055] The adjustment process is complete when the actual displacement of the lifting seat matches the target displacement ΔL.

[0056] Its control unit continuously reads the encoder feedback and tension sensor data from the servo motor, and the actual tension T is fed back. current And target tension T target The system is compared in real time. If the target tension is reached, the system will enter steady-state mode; otherwise, it will continue to adjust until |T| is reached. current -T target t∣<ε, where ε is the set tolerance range.

[0057] In summary, compared with existing technologies, the advantages of this application lie in constructing a highly adaptive and intelligent control system for underground conveyor belt tensioning. Compared to traditional methods relying on periodic manual inspection and adjustment, this application achieves real-time, precise automatic adjustment without frequent manual intervention, greatly improving work efficiency. It can quickly respond to complex working conditions such as fluctuations in underground load and belt wear, effectively avoiding problems such as belt slippage, insufficient tension, and belt damage caused by untimely or inaccurate manual adjustments, significantly improving production efficiency. Simultaneously, through intelligent adaptive adjustment, it ensures the belt is always at a suitable tension, reducing equipment losses due to abnormal tension, extending equipment lifespan, and optimizing the overall operating performance of the underground conveyor belt. This better meets the needs of complex and changing working environments, providing a strong guarantee for the efficient and stable operation of underground production. Attached Figure Description

[0058] Figure 1 This is a schematic diagram of the structure of an intelligent adaptive tensioning system for a mine conveyor belt according to this application;

[0059] Figure 2 This is a schematic diagram of another perspective of the intelligent adaptive tensioning system for a mine conveyor belt according to this application;

[0060] Figure 3 This is a control flow diagram of the tension detection unit in this application;

[0061] Figure 4 This is a control flow diagram of the intelligent control unit of this application;

[0062] Figure 5 This is a control flow diagram of the implementing agency of this application.

[0063] As shown in the figure: 1. Driven roller; 2. Driven roller; 3. Drive motor; 4. Belt; 5. Tension detection roller; 6. Reducer base; 7. Adjusting seat; 8. Lead screw; 9. Lifting seat; 10. Tension adjusting roller. Detailed Implementation

[0064] The present invention will now be described in further detail with reference to the accompanying drawings.

[0065] The specific embodiments of the present invention will be further described below with reference to the accompanying drawings. Identical components are indicated by the same reference numerals.

[0066] It should be noted that the terms “front,” “back,” “left,” “right,” “up,” and “down” used in the following description refer to the directions shown in the attached diagram, while the terms “inside” and “outside” refer to the directions toward or away from the geometric center of a specific component, respectively.

[0067] To make the content of this invention easier to understand, the technical solutions in the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings.

[0068] The technical problem to be solved by the present invention is to overcome the above-mentioned technical defects and provide an intelligent adaptive tensioning system and method for underground conveyor belts.

[0069] Reference Appendix Figure 1 - Appendix Figure 5 To solve the above-mentioned technical problems, the present invention provides an intelligent adaptive tensioning system for underground conveyor belts, comprising:

[0070] The belt assembly includes a drive roller 1, a driven roller 2, a drive motor 3, and a belt 4. The drive roller 1 is connected to the output shaft of the drive motor 3 via a coupling. The belt 4 is wound around the drive roller 1 and the driven roller 2 to form a closed loop structure.

[0071] The tension detection unit is installed on the tension side of belt 4 to monitor the tension change of belt 4 in real time and convert the monitored tension signal into an electrical signal for output.

[0072] The intelligent control unit is connected to the tension detection unit. It receives and processes tension signals from the tension detection unit through an RS-485 communication module. Its microprocessor calculates the adjustment amount of belt tension according to a preset adaptive control algorithm and generates corresponding control commands.

[0073] The actuator is connected to the intelligent control unit and is used to receive control commands sent by the intelligent control unit. It adjusts the tension of belt 4 through a mechanical structure to keep the belt tension within a set range. It includes a motor, a reducer, and a tension adjustment assembly. The motor is connected to the reducer and drives the tension adjustment assembly to adjust the belt tension.

[0074] The tension detection unit, intelligent control unit, and actuator form a closed-loop control system to achieve adaptive adjustment of belt tension.

[0075] To achieve accurate monitoring of belt tension in underground conveyor belts, the tension detection unit designed in this invention comprises several key components. First, the tension detection roller 5 is cleverly installed below the belt 4, and several resistance strain gauge tension sensors are evenly arranged around its circumference, which are in close contact with the bottom of the belt 4. These sensors are BM Z6FC3 / 500kg shear beam sensors with a range of 0–500kg, capable of accurately sensing changes in belt tension and converting them into electrical signals.

[0076] Next, the signal conditioning circuit board is electrically connected to the strain gauge tension sensor, undertaking the crucial task of collaboratively processing the sensor's raw analog voltage signal output. Specifically, the bridge excitation module provides a stable operating voltage to the sensor, ensuring its normal operation even in complex environments; the signal amplification module amplifies the weak voltage signal output by the sensor for subsequent processing; the low-pass filter module effectively filters out high-frequency interference noise in the signal, improving signal quality; and the temperature compensation module receives measurements from the built-in temperature sensor and performs drift compensation on the tension signal based on the ambient temperature, using the following formula:

[0077]

[0078] in, This is the actual tension value after temperature compensation; F t The compensation value is the tension value; α is the temperature coefficient; T is the current ambient temperature; T0 is the reference temperature during calibration;

[0079] The input terminal of the data acquisition terminal is directly connected to the output terminal of the signal conditioning circuit board, receiving the conditioned and compensated analog voltage signal. The data acquisition terminal has a built-in high-precision analog-to-digital converter, which can quickly and accurately convert the conditioned analog voltage signal into a digital tension signal, providing a reliable basis for subsequent data processing.

[0080] The communication module connects to the data acquisition terminal and transmits the digital tension signal and associated temperature data to the intelligent control unit via the RS-485 communication protocol, ensuring the stability and real-time performance of data transmission.

[0081] The power management module provides a stable power supply to the resistance strain gauge tension sensor, signal conditioning circuit board, and data acquisition terminal, ensuring the normal operation of the entire tension detection unit. Through the coordinated work of these components, the tension detection unit can monitor belt tension changes in real time and accurately, and transmit the monitoring data to the intelligent control unit, providing an important basis for subsequent tension adjustment.

[0082] The intelligent control unit, as the core component of this invention, undertakes the crucial tasks of processing and analyzing the received raw tension data and generating control commands. First, the intelligent control unit performs smoothing filtering on the received raw tension data using a first-order moving average algorithm, the formula of which is:

[0083]

[0084] in, F represents the smoothed tension value at time k, i.e., the tension data after moving average processing; t (k) represents the original tension value at the current time k, i.e., the real-time data directly measured by the sensor; λ is the smoothing factor, between 0 and 1. This algorithm effectively eliminates sensor noise and improves control reliability. In practical applications, the system sets the smoothing factor λ to 0.2 to reasonably control the weighting of the current tension value and the previous smoothed value in the calculation. A larger λ value means that the original tension value at the current time has a larger weight in the smoothing process, and vice versa, it indicates that the previous smoothed value has a greater influence.

[0085] After receiving the tension data, the intelligent control unit first smooths the data, then performs anomaly detection and data analysis. To eliminate sensor noise and improve control reliability, the system applies a first-order moving average algorithm to the raw tension data, controlling the weighting of the current tension value and the previous smoothed value in the calculation. A larger λ value means that the current raw tension value has a larger weight in the smoothing process, and vice versa; here, it is set to 0.2.

[0086] The system determines whether the current tension is within the set reasonable tension range based on the preset tension model in the storage module. min ,F max ]Inside:

[0087] like The tension is deemed insufficient.

[0088] like The tension is deemed too high.

[0089] If it is within the range, no adjustment is needed.

[0090] Tension intervals are stored as tabular data based on different belt models and operating conditions.

[0091] When an abnormal tension is detected, the microprocessor will calculate the required adjustment amount:

[0092]

[0093] in:

[0094] And call the lookup table model to calculate the required running time of the motor:

[0095]

[0096] Where L is the belt length; K is the device tension stiffness constant (N / mm); and η is the mechanism adjustment efficiency (obtained from experimental calibration, here it is 0.85).

[0097] The system sends the following control commands to the actuator via the ESP32 module.

[0098] <DIR:+1> ,<TIME:3.2> , <checksum:0xad>

[0099] DIR: +1 indicates tension;

[0100] TIME:3.2 indicates that the motor running time is 3.2 seconds;

[0101] CHECKSUM is a data verification value that ensures secure command transmission.

[0102] Because belt conveyor systems operate under different conditions in underground mining environments, the required belt tension varies. This invention develops corresponding tension adjustment strategies for different operating conditions. The main factors influencing these strategies are shown in the table below:

[0103]

[0104] For each working condition, the system establishes a recommended tension range [F] based on experimental data. min i ,F max i ],as follows:

[0105] Operating conditions Optimal tension range (unit: N) W1 450–600 W2 600–850 W3 800–1100 W4 Dynamic adjustment (taking temperature / humidity into account)

[0106] The system obtains the following parameters as input through sensors:

[0107] Vb: Belt speed (obtained by a speed encoder)

[0108] Lc: Current conveying load (measured by belt scale)

[0109] Te: ambient temperature, Hr: relative humidity

[0110] Conditional rule matching method is used to identify working conditions:

[0111] if (L_c < 30% && V_b < 0.8) → Working condition = W1

[0112] elseif(L_c<=80%&&V_b<=1.2)→Working Condition=W2

[0113] elseif(L_c>80%||Length>X m)→Working Condition=W3

[0114] elseif(T_e>45℃||H_r>85%)→Working Condition = W4

[0115] After identifying the operating conditions, the system loads the corresponding tension range from EEPROM or Flash.

[0116] In one embodiment, the adaptive control algorithm of the intelligent control unit is a fuzzy PID control algorithm, and the formula for calculating its control output, i.e., the tension adjustment distance Δd, is as follows:

[0117]

[0118] in, The tension error at time k; K represents the target tension value. p K i and K d For PID control parameters; K p K i and K d The value is adjusted in real time by the fuzzy inference module based on the tension error e and its rate of change Δe.

[0119] In one embodiment, the intelligent control unit further includes a time-series-based tension prediction model for predicting future tension trends based on historical and current tension data, and for making preventative adjustments based on the prediction results. The time-series-based tension prediction model is a Long Short-Term Memory (LSTM) neural network model. This model uses historical time-series tension data and corresponding operating parameters as input, and outputs a predicted tension value T^t+1 for the future period, expressed by the formula:

[0120]

[0121] Where θ are model parameters, and the function f LSTM This represents a trained LSTM network. Using this model, the system can predict future tension trends based on historical and current tension data, and make preventative adjustments in advance based on the predictions. For example, if it is predicted that the belt tension may be too high or too low in the future, the system can adjust the actuators in advance to keep the belt tension within the set range, avoiding problems such as belt slippage and breakage caused by abnormal tension, thus improving the reliability and safety of the belt conveyor system.

[0122] As a crucial component of the actuator, the tension adjustment assembly's mechanical structure directly impacts the belt tension adjustment effect. The tension adjustment assembly designed in this invention includes a reducer base 6, an adjustment seat 7 on the reducer base 6, an adjustment port on the adjustment seat 7, and a lead screw 8 vertically rotatable within the adjustment port. The reducer and drive motor are both housed within the reducer base 6, with the output shaft of the drive motor connected to the bottom of the lead screw 8. A lifting seat 9, threaded onto the lead screw 8 and slidingly engaging with the inner wall of the adjustment port, is rotatably mounted on the lifting seat 9, pressing against the inner side of the belt 4 with a tension adjustment roller 10.

[0123] When the actuator receives the control command from the intelligent control unit, the drive motor starts running, driving the lead screw 8 to rotate via the reducer. Since the lifting seat 9 is threadedly engaged with the lead screw 8 and slides against the inner wall of the adjustment port, the rotation of the lead screw 8 causes the lifting seat 9 to move linearly, thereby pushing the tension adjusting roller 10 up and down to adjust the tension of the belt 4. This mechanical structure design is simple and reliable, enabling precise adjustment of belt tension.

[0124] To ensure that the actuator can accurately and reliably adjust the belt tension, the actuator includes a position feedback sensor to detect the actual displacement L of the tension adjusting roller. actual The intelligent control unit converts the target displacement ΔL into the target rotation angle θ of the drive motor. target The formula is:

[0125]

[0126] Where P is the lead of the leadscrew; Its k is the stiffness coefficient of the tensioning system, ΔT = T target -T current , where T is the difference between the target tension and the current tension. current This refers to real-time tension data obtained from the tension detection unit;

[0127] The system compares the actual displacement with the target displacement in real time. When the deviation exceeds the preset tolerance range, it continuously adjusts. If the target is not reached within the preset time, the actuator is stopped and an alarm is triggered. Through this closed-loop control method, the system can monitor and adjust the position of the tension regulating roller in real time, ensuring that the belt tension is always kept within the set range, thus improving the system's control accuracy and stability.

[0128] This application also provides an intelligent adaptive tensioning method for underground conveyor belts in mines, which specifically includes the following steps:

[0129] S1. Tension Detection: A strain gauge tension sensor detects real-time changes in belt tension, converting them into an electrical signal. After signal conditioning and temperature compensation, the signal is converted into a digital tension signal F by an ADC. t ;

[0130] S2. Data transmission: Pack the digital tension signal and ambient temperature data and transmit them to the intelligent control unit through the communication interface;

[0131] S3. Data Preprocessing: The intelligent control unit processes the raw tension data F... t (k) Perform moving average filtering to obtain the smoothed tension value.

[0132] S4. Operating Condition Identification and Target Setting: Based on real-time acquired belt speed, conveying load, and ambient temperature and humidity parameters, the current operating condition is identified; according to the identification result, the preset optimal tension setting range for the corresponding operating condition is applied. And calculate the target tension value

[0133] S5. Tension Prediction: Input historical and current smoothed tension values ​​and operating parameters into a pre-trained LSTM prediction model, and output the future short-term tension prediction value T^t+1.

[0134] S6. Control quantity calculation:

[0135] Calculate tension error A fuzzy PID control algorithm is used to calculate the target displacement Δd(k) of the tension adjustment mechanism; based on the system stiffness parameter k, the tension adjustment requirement ΔT is converted into the target displacement ΔL = ΔT / k;

[0136] S7. Command Generation and Execution: Convert the target displacement ΔL into the target rotation angle θ of the drive motor. target The system generates control commands containing direction and time / angle and sends them to the actuator; the actuator drives the servo motor to drive the transmission motor, which in turn drives the lead screw 8 through the reducer, thus pushing the tension adjusting roller 10 to move up and down.

[0137] S8. Closed-loop feedback and safety monitoring: Feedback of actual displacement L via position sensor. actual Meanwhile, the actual tension T is continuously monitored. current The adjustment stops when the actual value reaches the target value; if the target value is not reached within the time limit or the tension is abnormal, the drive stops and an alarm is triggered.

[0138] In step S7, the servo motor begins to adjust its position according to the control signal, using a built-in encoder for precise position control, and the output torque T of the servo motor... motor The output torque T is obtained by amplification using a speed reducer. output The formula is as follows:

[0139] T output =T motor ×i

[0140] Where i is the reduction ratio of the reducer, the rotary motion output by the reducer drives the lead screw to rotate, which in turn drives the lifting seat 9 to move linearly, thereby adjusting the tension of the belt 4.

[0141] The displacement of the lifting seat 9 is determined by the rotation angle θ fed back by the position feedback sensor. feedback calculate:

[0142]

[0143] The adjustment process is complete when the actual displacement of the lifting seat 9 matches the target displacement ΔL.

[0144] Its control unit continuously reads the encoder feedback and tension sensor data from the servo motor, and the actual tension T is fed back. current And target tension T target The system is compared in real time. If the target tension is reached, the system will enter steady-state mode; otherwise, it will continue to adjust until |T| is reached. current -T target t | < ε, where ε is the set tolerance range. Through this precise position adjustment and displacement calculation, the system can ensure that the belt tension is always kept within the set range, improving the stability and reliability of the belt conveyor system.

[0145] The present invention and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present invention; the actual structure is not limited thereto. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the invention, such designs should fall within the protection scope of the present invention.

Claims

1. An intelligent adaptive tensioning system for underground conveyor belts in mines, characterized in that, include: The belt assembly includes a drive roller (1), a driven roller (2), a drive motor (3) and a belt (4). The drive roller (1) is connected to the output shaft of the drive motor (3) via a coupling. The belt (4) is wound around the drive roller (1) and the driven roller (2) to form a closed loop structure. The tension detection unit is installed on the tension side of the belt (4) to monitor the tension change of the belt (4) in real time and convert the monitored tension signal into an electrical signal for output. The intelligent control unit is communicatively connected to the tension detection unit. It receives and processes tension signals from the tension detection unit via an RS-485 communication module. Its microprocessor calculates the adjustment amount of belt tension according to a preset adaptive control algorithm and generates corresponding control commands. The actuator is communicatively connected to the intelligent control unit and is used to receive control commands sent by the intelligent control unit and adjust the tension of the belt (4) through a mechanical structure to keep the belt tension within a set range; it includes a motor, a reducer and a tension adjustment assembly, wherein the motor is connected to the reducer and the reducer drives the tension adjustment assembly to adjust the belt tension; The tension detection unit, intelligent control unit, and actuator form a closed-loop control system to achieve adaptive adjustment of belt tension.

2. The intelligent adaptive tensioning system for a mine conveyor belt according to claim 1, characterized in that, The tension detection unit includes: Tension detection roller (5) is installed below belt (4), and several resistance strain gauge tension sensors that contact the bottom of belt (4) are arranged around it. A signal conditioning circuit board, electrically connected to the strain gauge tension sensor, receives the raw analog voltage signal output by the sensor and performs collaborative processing. It integrates the following: The bridge excitation module provides a stable operating voltage for the sensor. The signal amplification module amplifies the weak voltage signal output by the sensor. The low-pass filter module filters out high-frequency interference noise in the signal; The temperature compensation module receives measurements from the built-in temperature sensor and compensates for the drift of the tension signal based on the ambient temperature. The compensation formula is as follows: in, This is the actual tension value after temperature compensation; F t The compensation value is the tension value; α is the temperature coefficient; T is the current ambient temperature; T0 is the reference temperature during calibration; The data acquisition terminal has its input end directly connected to the output end of the signal conditioning circuit board to receive the conditioned and compensated analog voltage signal; the data acquisition terminal includes a high-precision analog-to-digital converter for converting the conditioned analog voltage signal into a digital tension signal; The communication module is connected to the data acquisition terminal and transmits the digital tension signal and associated temperature data to the intelligent control unit. The power management module provides power to the resistance strain gauge tension sensor, signal conditioning circuit board, and data acquisition terminal.

3. The intelligent adaptive tensioning system for a mine conveyor belt according to claim 2, characterized in that, The intelligent control unit performs smoothing filtering on the received raw tension data, using a first-order moving average algorithm, the formula of which is: in, F represents the smoothed tension value at time k, i.e., the tension data after moving average processing; t (k) is the original tension value at the current time k, which is the real-time data directly measured by the sensor; λ is the smoothing factor, which is between 0 and 1.

4. The intelligent adaptive tensioning system for a mine conveyor belt according to claim 2, characterized in that, The adaptive control algorithm of the intelligent control unit is a fuzzy PID control algorithm, and its control output, i.e., the tension adjustment distance Δd, is calculated using the following formula: in, The tension error at time k; K represents the target tension value. p K i and K d For PID control parameters; K p K i and K d The value is adjusted in real time by the fuzzy inference module based on the tension error e and its rate of change Δe.

5. The intelligent adaptive tensioning system for a mine conveyor belt according to claim 1, characterized in that, The intelligent control unit also includes a time-series-based tension prediction model, used to predict future tension trends based on historical and current tension data, and to perform preventative adjustments based on the prediction results. The time-series-based tension prediction model is a Long Short-Term Memory (LSTM) neural network model. This model uses historical time-series tension data and corresponding operating parameters as input, and outputs a predicted tension value T^t+1 for the future period, expressed by the formula: Where θ are model parameters, and the function f LSTM This represents a trained LSTM network.

6. The intelligent adaptive tensioning system for a mine conveyor belt according to claim 1, characterized in that, The tension adjustment assembly includes a speed reducer base (6), an adjustment seat (7) on the speed reducer base (6), an adjustment port on the adjustment seat (7), a lead screw (8) that rotates vertically inside the adjustment port, the speed reducer and the transmission motor are both located inside the speed reducer base (6) and the output shaft of the transmission motor is connected to the bottom of the lead screw (8), a lifting seat (9) that slides with the inner wall of the adjustment port is threaded on the lead screw (8), and a tension adjustment roller (10) that presses against the inner side of the belt (4) is rotatably mounted on the lifting seat (9).

7. The intelligent adaptive tensioning system for underground conveyor belts according to claim 6, characterized in that, The actuator includes a position feedback sensor for detecting the actual displacement L of the tension adjusting roller. actual The intelligent control unit converts the target displacement ΔL into the target rotation angle θ of the drive motor. target The formula is: Where P is the lead of the leadscrew; Its k is the stiffness coefficient of the tensioning system, ΔT = T target -T current , where T is the difference between the target tension and the current tension. current This refers to real-time tension data obtained from the tension detection unit; The system compares the actual displacement L in real time. actual The system continuously adjusts the displacement ΔL relative to the target displacement when the deviation exceeds the preset tolerance range. If the target is not reached within the preset time, the actuator is controlled to stop and an alarm is triggered.

8. A smart adaptive tensioning method for underground conveyor belts in mines, characterized in that, Specifically, the following steps are included: S1. Tension Detection: A strain gauge tension sensor detects real-time changes in belt tension, converting them into an electrical signal. After signal conditioning and temperature compensation, the signal is converted into a digital tension signal F by an ADC. t ; S2. Data transmission: Pack the digital tension signal and ambient temperature data and transmit them to the intelligent control unit through the communication interface; S3. Data Preprocessing: The intelligent control unit processes the raw tension data F... t (k) Perform moving average filtering to obtain the smoothed tension value. S4. Operating condition identification and target setting: Based on the real-time acquired belt (4) speed, conveying load, and ambient temperature and humidity parameters, identify the current operating condition; Based on the identification results, the preset optimal tension setting range for the corresponding working condition is applied. And calculate the target tension value S5. Tension Prediction: Input historical and current smoothed tension values ​​and operating parameters into a pre-trained LSTM prediction model, and output the future short-term tension prediction value T^t+1. S6. Control quantity calculation: Calculate tension error A fuzzy PID control algorithm is used to calculate the target displacement Δd(k) of the tension adjustment mechanism; based on the system stiffness parameter k, the tension adjustment requirement ΔT is converted into the target displacement ΔL = ΔT / k; S7. Command Generation and Execution: Convert the target displacement ΔL into the target rotation angle θ of the drive motor. target The system generates control commands containing direction and time / angle and sends them to the actuator; the actuator drives the servo motor to drive the transmission motor, which in turn drives the lead screw (8) through the reducer to move the tension adjustment roller (10) up and down. S8. Closed-loop feedback and safety monitoring: Feedback of actual displacement L via position sensor. actual Meanwhile, the actual tension T is continuously monitored. current The adjustment stops when the actual value reaches the target value; if the target value is not reached within the time limit or the tension is abnormal, the drive stops and an alarm is triggered.

9. The intelligent adaptive tensioning method for a mine conveyor belt according to claim 8, characterized in that, In step S7, the servo motor begins to adjust its position according to the control signal, using a built-in encoder for precise position control. The output torque T of the servo motor motor The output torque T is obtained by amplification using a speed reducer. output The formula is as follows: T output =T motor ×i Where i is the reduction ratio of the reducer, and then the rotational motion output by the reducer drives the lead screw to rotate, which drives the lifting seat (9) to move linearly, thereby adjusting the tension of the belt (4). The displacement of the lifting seat (9) is determined by the rotation angle θ fed back by the position feedback sensor. feedback calculate: The adjustment process is complete when the actual displacement of the lifting seat (9) matches the target displacement ΔL. Its control unit continuously reads the encoder feedback and tension sensor data from the servo motor, and the actual tension T is fed back. current And target tension T target The system is compared in real time. If the target tension is reached, the system will enter steady-state mode; otherwise, it will continue to adjust until |T| is reached. current -T target t∣<ε, where ε is the set tolerance range.

Images