Belt feeder coal feeder cooperative control method and system

Abstract

The application relates to the technical field of coal mine transportation, and discloses a belt conveyor coal feeder cooperative control method and system, wherein the belt conveyor coal feeder cooperative control method comprises the following steps: acquiring a coal flow image on a belt conveyor belt and a belt conveying speed; determining a coal flow cross-sectional area on the belt conveyor belt according to the coal flow image, and determining an instantaneous transportation capacity according to the coal flow cross-sectional area and the belt conveying speed; predicting a coal flow trend according to the instantaneous transportation capacity to obtain a predicted coal flow; and performing speed control on the belt conveyor and adjusting a discharging speed of the coal feeder according to the predicted coal flow. The application realizes cooperative control of the belt conveyor and the coal feeder based on the predicted coal flow in view of the operation differentiation of the belt conveyor and the coal feeder, not only makes the speed regulation process of the belt conveyor more accurate and reliable, but also realizes millisecond-level synchronization between dynamic adjustment of the coal feeder and change of the belt coal flow, improves timeliness and accuracy of system regulation and control, and the speed regulation effect is remarkable, and operation is more stable.

Description

Technical Field

[0001] This application relates to the field of coal mine transportation technology, and in particular to a method and system for coordinated control of belt conveyor feeders. Background Technology

[0002] In the coal mining industry, speed control of belt conveyors and coal feeders has significant economic, safety, and environmental implications. Among these, dynamically adjusting the belt conveyor speed based on coal demand to avoid idling or light-load operation and reduce energy waste is currently a widely accepted solution.

[0003] In related technologies, most speed control of belt conveyors is based on instantaneous coal flow rate. However, in actual production, the coal flow rate at the outlet has inherent fluctuation characteristics. These fluctuations are mainly manifested in: (1) periodic fluctuations caused by uneven coal seam thickness; (2) intermittent fluctuations during the coal mining machine cutting process; and (3) disturbance fluctuations during the coordinated operation of the transportation system. If instantaneous coal flow rate is directly used as the basis for speed control, the drive motor of the belt conveyor will frequently start and stop, which will not only accelerate equipment wear but also cause energy waste.

[0004] In addition, belt speed control systems have inherent lag characteristics, mainly manifested in: (1) detection delay, which takes about 0.5-1.5 seconds from the time the coal flow passes through the sensor to the completion of signal processing; (2) mechanical response delay, which takes 2-3 seconds from the time the frequency converter receives the command to the time the belt speed stabilizes; and (3) feeder adjustment delay, which takes 3-5 seconds from the time the command is issued to the time the coal output is adjusted. With the superposition of these multi-level delays, if the coal output increases rapidly, it is very easy to cause the belt to be crushed due to untimely adjustment. Therefore, the response delay of the belt speed control system often leads to control failure and poses certain safety hazards. Summary of the Invention

[0005] Therefore, the purpose of this application is to provide a method and system for coordinated control of belt conveyor and coal feeder. Addressing the operational differences between the belt conveyor and coal feeder, this method achieves coordinated control of the belt conveyor and coal feeder based on predicted coal flow, effectively solving technical problems such as sensitivity to coal flow fluctuations and response delays in related technologies. This not only makes the speed regulation process of the belt conveyor more precise and reliable, but also enables millisecond-level synchronization between the dynamic adjustment of the coal feeder and changes in the belt coal flow, significantly improving the timeliness and accuracy of system regulation, resulting in significant speed regulation effects and more stable system operation.

[0006] To achieve the above objectives, the main technical solutions adopted in this application include:

[0007] In a first aspect, embodiments of this application provide a method for coordinated control of a belt conveyor and a coal feeder. The method includes: acquiring an image of coal flow on the belt conveyor and the belt conveyor speed; determining the cross-sectional area of ​​the coal flow on the belt conveyor based on the coal flow image, and determining the instantaneous transport volume based on the cross-sectional area of ​​the coal flow and the belt conveyor speed; predicting the coal flow trend based on the instantaneous transport volume to obtain a predicted coal flow rate; and adjusting the speed of the belt conveyor and the discharge speed of the coal feeder based on the predicted coal flow rate.

[0008] The belt conveyor and coal feeder coordinated control method provided in this application can determine the cross-sectional area of ​​the coal flow on the belt conveyor based on the coal flow image, and determine the instantaneous transport volume based on the cross-sectional area of ​​the coal flow and the belt conveying speed. Then, based on the coal flow trend prediction model of time series analysis, the coal flow trend is predicted to obtain the predicted coal flow rate. Finally, the belt conveyor speed is adjusted and the coal feeder discharge speed is adjusted based on the predicted coal flow rate, realizing coordinated control of the belt conveyor and coal feeder. This not only makes the belt conveyor speed adjustment process more accurate and reliable, but also enables the dynamic adjustment of the coal feeder and the belt coal flow rate to be synchronized at the millisecond level, significantly improving the timeliness and accuracy of system regulation, resulting in significant speed regulation effect and more stable system operation.

[0009] Optionally, in some embodiments of this application, determining the instantaneous transport volume based on the cross-sectional area of ​​the coal flow and the belt conveyor speed includes: determining the instantaneous coal flow volume value based on the cross-sectional area of ​​the coal flow and the belt conveyor speed; and determining the instantaneous transport volume based on the instantaneous coal flow volume value and the belt conveyor speed.

[0010] Furthermore, in some embodiments of this application, determining the instantaneous transport volume based on the instantaneous coal flow volume value and the belt conveyor speed includes: determining the instantaneous coal flow volume values ​​of n coal flow segments on the belt conveyor, where n is an integer greater than 1; obtaining the maximum coal flow volume value among the n instantaneous coal flow volume values, and determining the instantaneous transport volume based on the maximum coal flow volume value, the length of the n coal flow segments, and the belt conveyor speed.

[0011] Optionally, in some embodiments of this application, predicting the coal flow trend based on the instantaneous transport volume includes: inputting the instantaneous transport volume into a pre-trained LSTM neural network model for rolling prediction to obtain coal flow rates for multiple future time periods, and judging the coal flow trend based on the coal flow rates for the multiple future time periods.

[0012] Optionally, in some embodiments of this application, speed control of the belt conveyor based on the predicted coal flow includes: determining the rated hourly capacity and maximum design speed of the belt conveyor; determining the required speed of the belt conveyor based on the predicted coal flow, the rated hourly capacity, and the maximum design speed of the belt conveyor, and determining the required frequency of the belt conveyor based on the required speed of the belt conveyor; and performing speed control of the belt conveyor based on the required frequency of the belt conveyor, the current frequency of the belt conveyor, and a dead zone frequency threshold.

[0013] Optionally, in some embodiments of this application, speed control of the belt conveyor is performed based on the required frequency of the belt conveyor, the current frequency of the belt conveyor, and the adjustment dead zone frequency threshold, including: accelerating the belt conveyor when the required frequency of the belt conveyor is greater than the sum of the current frequency of the belt conveyor and the adjustment dead zone frequency threshold; and decelerating the belt conveyor when the required frequency of the belt conveyor is less than the difference between the current frequency of the belt conveyor and the adjustment dead zone frequency threshold, if the duration is greater than a first preset time and the historical speed trend derivative of the belt conveyor is less than a preset threshold.

[0014] Optionally, in some embodiments of this application, when it is determined that the belt conveyor needs to be decelerated, the method further includes: locking the speed of the belt conveyor for a second preset time.

[0015] Optionally, in some embodiments of this application, adjusting the discharge speed of the coal feeder based on the predicted coal flow rate includes: determining the coal output of the coal feeder based on the predicted coal flow rate; if the coal output of the coal feeder is greater than or equal to a preset coal output threshold, then reducing the discharge speed of the coal feeder; if the coal output of the coal feeder is less than the preset coal output threshold, then increasing the discharge speed of the coal feeder.

[0016] Optionally, in some embodiments of this application, during the process of speed control of the belt conveyor based on the predicted coal flow rate, the method further includes: detecting the material level in the coal bunker to obtain material level information; inputting the material level information and the predicted coal flow rate into a time series prediction model to predict the material level trend change, thereby obtaining coal bunker material level prediction information, so as to adjust the discharge speed of the coal feeder based on the coal bunker material level prediction information.

[0017] Optionally, in some embodiments of this application, during the process of speed control of the belt conveyor based on the predicted coal flow rate, the method further includes: responding to an energy-saving operation command and controlling the coal feeder to discharge material based on a pulsed full-load operation strategy.

[0018] Secondly, embodiments of this application also provide a belt conveyor and coal feeder coordinated control system, including: an image acquisition module for acquiring images of coal flow on the belt conveyor; a speed detection module for detecting the belt conveyor speed; and a control module for determining the cross-sectional area of ​​the coal flow on the belt conveyor based on the coal flow image, determining the instantaneous transport volume based on the cross-sectional area of ​​the coal flow and the belt conveyor speed, predicting the coal flow trend based on the instantaneous transport volume to obtain a predicted coal flow rate, and adjusting the speed of the belt conveyor and the discharge speed of the coal feeder based on the predicted coal flow rate.

[0019] According to the belt conveyor and coal feeder coordinated control system of this application embodiment, the coal flow image on the belt conveyor is acquired by the image acquisition module and the belt conveying speed is detected by the speed detection module. This allows the cross-sectional area of ​​the coal flow on the belt conveyor to be determined based on the coal flow image, and the instantaneous transport volume is determined based on the cross-sectional area of ​​the coal flow and the belt conveying speed. Then, the coal flow trend is predicted based on a coal flow trend prediction model using time series analysis to obtain the predicted coal flow rate. Finally, the belt conveyor speed is adjusted and the coal feeder discharge speed is adjusted based on the predicted coal flow rate, achieving coordinated control of the belt conveyor and coal feeder. This not only makes the belt conveyor speed adjustment process more precise and reliable, but also enables millisecond-level synchronization between the dynamic adjustment of the coal feeder and the changes in belt coal flow rate, significantly improving the timeliness and accuracy of system control, resulting in significant speed adjustment effect and more stable system operation. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating a belt conveyor and coal feeder coordinated control method according to an embodiment of this application;

[0022] Figure 2 This is a system topology diagram of a belt conveyor and coal feeder coordinated control system provided in one embodiment of this application;

[0023] Figure 3 A schematic diagram of a process for speed control of a belt conveyor based on predicted coal flow rate, provided as an embodiment of this application;

[0024] Figure 4 A flowchart illustrating a specific embodiment of the belt conveyor and coal feeder coordinated control method provided in this application;

[0025] Figure 5 A schematic diagram illustrating the process of controlling the discharge speed of a coal feeder using multiple speed control modes, provided as an embodiment of this application;

[0026] Figure 6 This is a block diagram of a belt conveyor and coal feeder coordinated control system provided in one embodiment of this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] In related technologies, most speed control of belt conveyors is based on instantaneous coal flow rate. However, in actual operation, due to the inherent fluctuation characteristics of coal flow rate at the coal outlet and the inherent lag characteristics of belt speed control system, frequent equipment start-ups and shutdowns and system response delays often occur, which can lead to control failure and adversely affect production and equipment.

[0029] Therefore, the belt conveyor and coal feeder coordinated control method and system provided in this application, taking into account the operational differences between the belt conveyor and the coal feeder, achieves coordinated control of the belt conveyor and the coal feeder based on predicted coal flow. This effectively solves the technical problems existing in related technologies, such as sensitivity to coal flow fluctuations and response delays. It not only makes the speed regulation process of the belt conveyor more precise and reliable, but also enables the dynamic adjustment of the coal feeder to be synchronized with the changes in the coal flow of the belt at the millisecond level, significantly improving the timeliness and accuracy of system regulation, resulting in significant speed regulation effect and more stable system operation.

[0030] The following description, with reference to the accompanying drawings, details the belt conveyor and coal feeder coordinated control method and system provided in the embodiments of this application.

[0031] refer to Figure 1 The diagram shown is a flowchart illustrating a belt conveyor feeder coordinated control method according to an embodiment of this application. Figure 1 As shown, the coordinated control method for the belt conveyor feeder includes the following steps:

[0032] S1, acquire the coal flow image and belt conveyor speed on the belt conveyor.

[0033] Specifically, such as Figure 2 As shown, a depth camera can be installed in the coal-feeding direction of the belt conveyor to capture images of the coal flow in that direction. A speed sensor can also be installed on the belt conveyor to detect the conveying speed.

[0034] S2, determine the cross-sectional area of ​​the coal flow on the belt conveyor based on the coal flow image, and determine the instantaneous transport volume based on the cross-sectional area of ​​the coal flow and the belt conveyor speed.

[0035] Optionally, in some embodiments of this application, an image recognition algorithm can be used to detect and recognize the coal flow image, identify the cross-sectional profile of the coal flow on the conveyor belt, and calculate the cross-sectional area A between the cross-sectional profile and the conveyor belt plane as the cross-sectional area of ​​the coal flow on the belt conveyor.

[0036] Furthermore, the instantaneous transport volume is determined based on the cross-sectional area of ​​the coal flow and the belt conveyor speed, including: determining the instantaneous coal flow volume based on the cross-sectional area of ​​the coal flow and the belt conveyor speed; and determining the instantaneous transport volume based on the instantaneous coal flow volume and the belt conveyor speed.

[0037] Specifically, in one example of this application, the instantaneous coal flow volume can be calculated according to the following formula:

[0038] Qv = A × v;

[0039] Where Qv is the instantaneous coal flow volume (m³) 3 / s), A is the cross-sectional area of ​​the coal flow (m²) 2 ), where v is the belt conveyor speed (m / s).

[0040] Optionally, in some embodiments of this application, determining the instantaneous transport volume based on the instantaneous coal flow volume value and the belt conveyor speed includes: determining the instantaneous coal flow volume values ​​of n coal flow segments on the belt conveyor, where n is an integer greater than 1; obtaining the maximum coal flow volume value among the n instantaneous coal flow volume values, and determining the instantaneous transport volume based on the maximum coal flow volume value, the length of the n coal flow segments, and the belt conveyor speed.

[0041] In other words, in the embodiments of this application, based on the coal flow image captured by the depth camera and the belt conveyor speed detected by the speed sensor, the instantaneous coal flow volume of multiple coal flow segments on the belt conveyor can be calculated. Then, the maximum value is selected from the instantaneous coal flow volume of multiple coal flow segments, and the maximum value is divided by the segment length and then multiplied by the belt conveyor speed to obtain the instantaneous transport volume. Specifically, the instantaneous transport volume is calculated according to the following formula:

[0042] Q = Max(V[1..n]) / L×v;

[0043] Where Q is the instantaneous transport volume, V[1..n] represents the instantaneous coal flow volume of the nth segment before the coal drop point on the front of the belt conveyor, L is the segment length, and v is the belt conveying speed. The number of coal flow segments n and the segment length L can be calibrated according to the actual situation. For example, they can be customized according to the needs of the mine and issued by the host computer software.

[0044] This application calculates the instantaneous coal flow volume using coal flow images and belt conveyor speed, and calculates the instantaneous transport volume on the belt conveyor by the maximum value among a series of continuous instantaneous coal flow volume values. The calculation method is not only simple and reliable, but also fully considers the dynamic fluctuations of coal flow on the belt, which facilitates accurate prediction of subsequent coal flow trends.

[0045] S3 predicts the coal flow trend based on the instantaneous transport volume to obtain the predicted coal flow rate.

[0046] Optionally, in some embodiments of this application, predicting the coal flow trend based on the instantaneous transport volume includes: inputting the instantaneous transport volume into a pre-trained LSTM neural network model for rolling prediction to obtain the coal flow rate for multiple future time periods, and judging the coal flow trend based on the coal flow rate for multiple future time periods.

[0047] In other words, based on real-time calculation of instantaneous transport volume, a pre-trained LSTM neural network model is used for multi-step rolling prediction to accurately predict the coal quantity changes in the next few minutes. This enables advanced speed control of the belt conveyor, improves the speed regulation effect, and makes the system run more smoothly.

[0048] Specifically, a sliding window process is applied to the instantaneous transport volume representing coal flow changes, calculated from real-time acquired coal flow images and belt conveyor speeds. This constructs a three-dimensional tensor with temporal characteristics, and the three-dimensional tensor data is scaled to the same numerical range used during LSTM neural network model training for standardization. Missing value imputation and outlier smoothing are also performed to preprocess the model input data and ensure its quality. Then, a pre-trained LSTM neural network model is used for rolling prediction. For example, the predicted coal flow rate for the next 1 minute (t+1) is generated first, and this predicted value is used as the new input to recursively predict the coal flow rate for the next 2 minutes (t+2) and 3 minutes (t+3). Each prediction considers the temporal characteristics of 60 historical time steps (1 minute), thus predicting the coal flow rate for the next 1-3 minutes and achieving effective prediction of coal flow trends.

[0049] S4 controls the speed of the belt conveyor and adjusts the discharge speed of the coal feeder based on the predicted coal flow rate.

[0050] Optionally, in some embodiments of this application, such as Figure 3As shown, speed control of the belt conveyor based on predicted coal flow includes:

[0051] S10 determines the rated hourly capacity of the belt conveyor and the maximum design speed of the belt.

[0052] The rated hourly capacity and the maximum design speed of the belt conveyor can be calibrated according to the design of the belt conveyor.

[0053] S20 determines the required speed of the belt conveyor based on the predicted coal flow rate, rated hourly capacity, and maximum design speed of the belt, and determines the required frequency of the belt conveyor based on the required speed of the belt conveyor.

[0054] Specifically, in one example of this application, the required speed of the belt conveyor can be calculated using the following formula:

[0055] v_req=(Q_pre / Q_rated)%×v_max;

[0056] Where v_req is the required speed of the belt conveyor, Q_rated is the rated hourly capacity, v_max is the maximum design speed of the belt, and Q_pre is the predicted coal flow rate.

[0057] Furthermore, the required frequency corresponding to the required speed of the belt conveyor can be determined using the formula n = 120f(1-s) / P. Where n = motor speed (r / min), f = power supply frequency (Hz), s = slip, and P = number of motor pole pairs.

[0058] S30 performs speed control on the belt conveyor based on the required frequency, the current frequency of the belt conveyor, and the dead zone frequency threshold.

[0059] By setting the dead zone frequency threshold Δf, the adjustment will not be triggered if the coal quantity fluctuation is within ±Δf%, thus preventing the belt from frequently accelerating and decelerating due to slight fluctuations in the coal quantity and avoiding damage to the belt's service life.

[0060] Specifically, this application can determine the adjustment dead zone based on the Raida criterion, that is, the adjustment dead zone is set as follows:

[0061] Dead zone upper limit = μ + 3σ;

[0062] Lower limit of dead zone = μ - 3σ;

[0063] Where μ is the arithmetic mean of the historical data and σ is the standard deviation.

[0064] At the same time, it can automatically adjust the dead zone range based on historical data of different working conditions of the belt conveyor, thereby adaptively adjusting the dead zone frequency threshold Δf based on historical data, effectively improving the accuracy of belt conveyor speed regulation.

[0065] In the embodiments of this application, the Raida criterion is used to perform statistical analysis on historical data. By calculating the arithmetic mean μ and standard deviation σ of the process parameters, the adjustment dead zone is set to the range of μ±3σ. This can fully take into account the normal fluctuation range of the belt conveyor process parameters, avoid subjective settings, effectively avoid frequent adjustments caused by small fluctuations, and ensure that the system responds promptly to significant deviations.

[0066] Therefore, the belt conveyor and coal feeder coordinated control method of this application embodiment can determine the cross-sectional area of ​​the coal flow on the belt conveyor based on the coal flow image, and determine the instantaneous transport volume based on the cross-sectional area of ​​the coal flow and the belt conveying speed. Then, it predicts the coal flow trend based on the coal flow trend prediction model of time series analysis to obtain the predicted coal flow rate. Finally, it adjusts the speed of the belt conveyor and the discharge speed of the coal feeder based on the predicted coal flow rate, thereby realizing the coordinated control of the belt conveyor and the coal feeder. This not only makes the speed adjustment process of the belt conveyor more accurate and reliable, but also enables the dynamic adjustment of the coal feeder to be synchronized with the changes in the coal flow rate of the belt at the millisecond level, significantly improving the timeliness and accuracy of system regulation, resulting in significant speed adjustment effect and more stable system operation.

[0067] Optionally, in one embodiment of this application, reference is made to... Figure 2 and Figure 4 As shown, the process of the above-mentioned belt conveyor coal feeder collaborative control method mainly includes four parts: data acquisition, coal flow prediction, speed regulation decision layer and execution side.

[0068] In the data acquisition section, coal flow images can be captured by a depth camera and the belt conveyor speed can be detected by a speed sensor to acquire coal flow data. Then, the instantaneous transport volume can be calculated based on the coal flow images and belt conveyor speed. In particular, for the coal flow image acquisition on the output side of the coal feeder, a single depth camera can be shared with the belt conveyor for shooting, which not only saves costs but also enables speed coordination between the belt conveyor and the coal feeder based on the coal flow data.

[0069] In the coal flow prediction section, the calculated instantaneous transport volume is sent to the edge server for coal flow trend prediction. Specifically, the instantaneous transport volume, which represents the coal flow change data, is input into a pre-trained LSTM neural network model for rolling prediction, which can obtain the predicted coal flow for the next 1-3 minutes.

[0070] In the speed control decision-making layer, for belt conveyors, the required speed of the belt conveyor can be calculated based on the predicted coal flow rate, and then a speed control judgment is made to determine whether the belt conveyor currently meets the conditions for acceleration or deceleration.

[0071] Further, in some embodiments of the present application, speed control of the belt conveyor is performed according to the required frequency of the belt conveyor, the current frequency of the belt conveyor, and the adjustable dead zone frequency threshold, including: accelerating the belt conveyor when the required frequency of the belt conveyor is greater than the sum of the current frequency of the belt conveyor and the adjustable dead zone frequency threshold; and decelerating the belt conveyor when the required frequency of the belt conveyor is less than the difference between the current frequency of the belt conveyor and the adjustable dead zone frequency threshold, if the duration is greater than the first preset time and the derivative of the historical speed trend of the belt conveyor is less than the preset threshold.

[0072] Specifically, as Figure 4 shown, when f_req > f_curr + Δf, it is determined that the belt conveyor meets the acceleration condition, and immediately upshifts to the required frequency gear; when f_req < f_curr - Δf, and the continuous low-load time t > 60s, the derivative of the historical speed trend dv / dt < -0.1m / s 2 , it is determined that the belt conveyor meets the deceleration condition, and a downshift operation is performed. Where f_req is the required frequency of the belt conveyor, f_curr is the current frequency of the belt conveyor, and Δf is the adjustable dead zone frequency threshold. Whether it is upshifting or downshifting, an output frequency command is sent, and the command is packaged and transmitted to the Siemens S7-1500 PLC via industrial Ethernet (Profinet protocol). The sampling period ≤ 200ms to control the frequency converter and achieve speed control of the belt conveyor.

[0073] Moreover, in an embodiment of the present application, when it is determined that the belt conveyor needs deceleration adjustment, the above belt conveyor coal feeder coordinated control method further includes: locking the speed of the belt conveyor and lasting for the second preset time.

[0074] That is to say, after performing a downshift operation on the belt conveyor, a 60-second speed adjustment lock-up period is activated, thus avoiding frequent switching.

[0075] In the embodiments of the present application, when adjusting the speed of the belt conveyor, by introducing an intelligent adjustable dead zone mechanism and a dynamic speed adjustment lock-up period strategy, the common frequent disturbance problem in the traditional speed adjustment process is effectively suppressed. Specifically, it is manifested as follows: 1) The setting of the adjustable dead zone enables the system to filter out small fluctuations and avoid unnecessary speed adjustment actions; 2) The lock-up period mechanism ensures that the system has sufficient stable time after each speed adjustment to prevent continuous and frequent adjustment. This dual guarantee mechanism not only significantly reduces the speed adjustment frequency but also significantly improves the smoothness of the system operation, making the speed adjustment process of the belt conveyor more accurate and reliable. The actual operation data shows that the system disturbance can be reduced by more than 60%, and the equipment service life is expected to be extended by 30%.

[0076] As Figure 4 shown, for the coal feeder, the PID algorithm is used to adjust the discharging speed of the coal feeder according to the predicted coal flow rate.

[0077] Furthermore, in some embodiments of this application, adjusting the discharge speed of the coal feeder based on the predicted coal flow rate includes: determining the coal output of the coal feeder based on the predicted coal flow rate; if the coal output of the coal feeder is greater than or equal to a preset coal output threshold, then reducing the discharge speed of the coal feeder; if the coal output of the coal feeder is less than the preset coal output threshold, then increasing the discharge speed of the coal feeder.

[0078] In the embodiments of this application, based on the predicted coal flow rate, the system can adopt a closed-loop control strategy, dynamically adjusting the discharge speed of the coal feeder through a PID algorithm, thereby ensuring that the belt conveyor always maintains its rated operating state. When insufficient coal output is detected, the system automatically increases the discharge speed; when excessive coal output is detected, the system automatically decreases the discharge speed, achieving precise feeding control and ensuring optimal belt conveying efficiency.

[0079] Optionally, in some embodiments of this application, during the process of speed control of the belt conveyor based on the predicted coal flow, the above-mentioned belt conveyor-feeder coordinated control method further includes: detecting the material level in the coal bunker to obtain material level information; inputting the material level information and the predicted coal flow into a time series prediction model to predict the material level trend change, and obtaining coal bunker material level prediction information, so as to adjust the discharge speed of the feeder based on the coal bunker material level prediction information.

[0080] Specifically, such as Figure 2 As shown, multi-level material level sensors can be installed in the coal bunker to detect the material level in the bunker and upload the detected material level information to the coal feeder PLC control system. Combined with the predicted coal flow rate, the discharge speed of the coal feeder is adjusted.

[0081] When adjusting and controlling the discharge speed of the coal feeder, the impact of system delay on production stability needs to be carefully considered. For example, in the scenario of extremely low coal bunker levels (<10%), if the control command is triggered solely based on the current level, there is an inherent delay between the command issuance and the actual action of the actuator. This could result in the coal bunker being completely emptied before the command is executed, causing the coal feeder to stop due to material shortage and severely impacting the operating efficiency and safety performance of the entire coal conveying system.

[0082] Therefore, this application proposes an intelligent prediction algorithm based on time-series forecasting to predict the coal bunker level when adjusting and controlling the discharge speed of the coal feeder. Specifically, an ARIMA (Autoregressive Integral Moving Average) time series forecasting model is adopted, and a prediction model is established by analyzing historical material level change data in real time. This allows for accurate prediction of material level change trends up to 100ms in advance, thereby triggering control strategies in advance based on the prediction results and effectively offsetting the negative impact of equipment response delay.

[0083] Furthermore, taking the extreme low coal level (<10%) condition as an example, traditional control strategies rely on real-time level feedback signals to trigger control commands. However, due to the combined effects of command transmission delay, mechanical lag of the actuator (200–500ms), and sensor sampling period, the system often fails to respond in time before the critical state. This control lag may cause the coal bunker to be completely emptied before the adjustment command takes effect, leading to feeder shutdown, chain failures in the coal conveying system, and even threatening the safe operation of the entire production line. In contrast, this application uses the ARIMA time series forecasting model to effectively predict changes in coal level trends based on level information and predicted coal flow, offsetting system delays through advanced prediction. For the material level detection data input to the model, data filtering methods such as Kalman filtering can be used for preprocessing to filter sensor noise while retaining the high-frequency components of the effective signal. Then, a time synchronization protocol is used to align the data stream to ensure the temporal consistency of multi-source data and avoid prediction errors caused by microsecond-level timestamp deviations between different sensors. After data alignment, feature fusion and extraction are performed to obtain basic temporal features, first-order difference (rate of change) features, and second-order difference features (acceleration). The basic temporal feature L(t) represents the original material level signal and reflects the absolute change. The first-order difference (rate of change) feature ΔL(t) = L(t) - L(t-1) represents the instantaneous rate of change of material level and is used to detect abnormal fluctuations (such as sudden material interruption). The second-order difference feature (acceleration) L(t) = ΔL(t) - ΔL(t-1) reflects the trend of the rate of change and predicts whether the material level will accelerate its decline (such as at the end of the coal bunker emptying process). Simultaneously, the range (Max-Min) and standard deviation over the past N periods (e.g., 5 minutes) are statistically analyzed to quantify the intensity of material level fluctuations and extract periodic features (e.g., FFT spectrum analysis). Finally, combined with the feeder speed, the feeder's discharge speed is effectively controlled.

[0084] Furthermore, in the process of predicting material level change trends based on the ARIMA time series prediction model, the model itself is also adaptively adjusted online. For example, a sliding window mechanism is used to achieve adaptive adjustment of the model. That is, the window size can be dynamically adjusted based on the Akaike information criterion to balance the model's ability to capture short-term mutations and long-term trends. And each time the sliding window moves, only the gradient changes corresponding to the newly included data and the removed data are locally updated to avoid the computational overhead of full retraining and reduce the amount of computation.

[0085] In this embodiment, when adjusting the discharge speed of the coal feeder based on the predicted coal bunker level, if the predicted coal bunker level is in the high range (e.g., greater than 80%), the discharge speed of the coal feeder is increased to the highest speed to quickly consume the stored coal; if the predicted coal bunker level is in the medium range (e.g., 30%-80%), the coal feeder is switched to the economic speed setting to maintain stable coal supply; if the predicted coal bunker level is in the low range (e.g., 10%-30%), the coal feeder is controlled to reduce its speed to the maintenance setting; if the predicted coal bunker level is in the extreme low range (e.g., less than 10%), the coal feeder is controlled to automatically stop for protection, and the coal feeder is automatically restarted when the coal bunker level is detected to return to the high level (e.g., 85%).

[0086] Furthermore, when intelligently adjusting the feeder's discharge speed based on the coal bunker's level, a set delay of approximately one minute is incorporated to prevent frequent speed adjustments due to level fluctuations. When a change in the coal level triggers a speed adjustment condition, the system starts a timer. Speed ​​adjustment is only executed after the specified duration is met. For example, when the feed rate decreases from a medium to a low level, less coal is discharged, potentially causing the coal bunker level to quickly return to the medium level. The time taken to reach the medium level is compared to the previous time; if it does not exceed one minute, the system continues to operate at a low speed to avoid frequent speed adjustments.

[0087] The belt conveyor and coal feeder coordinated control method of this application adopts differentiated prediction strategies based on the operating characteristics of the two key pieces of equipment. For the belt conveyor, accuracy and long-term prediction are prioritized; therefore, an LSTM neural network model is used for rolling prediction, which can predict coal flow over long periods and adapt to changes in coal flow under different operating conditions by automatically learning historical data features. For the coal feeder, timely and accurate control of the discharge speed is required; therefore, an optimized ARIMA time series prediction model is used, which has low computational complexity and can complete a single prediction within 100ms.

[0088] Therefore, this application constructs a multimodal coal flow prediction system by integrating an LSTM neural network model and an ARIMA time series prediction model. Based on historical data and real-time operating conditions, it can accurately predict the coal flow trend over a certain period, achieving a prediction accuracy of 98.2%. Furthermore, based on the coal flow prediction results, an advanced speed regulation mechanism is established, enabling the system to make feeder speed regulation decisions within 80ms before flow anomalies occur, completely solving the lag problem inherent in traditional feedback control. Actual operating data shows that this application reduces the speed regulation response time by 92%, achieving millisecond-level synchronization between the dynamic adjustment of the feeder and changes in belt coal flow, significantly improving the timeliness and accuracy of system control.

[0089] Optionally, in some embodiments of this application, during the process of speed control of the belt conveyor based on the predicted coal flow, the above-mentioned belt conveyor feeder coordinated control method further includes: responding to the energy-saving operation command and controlling the feeder to discharge material based on the pulse-type full-load operation strategy.

[0090] When the coal feeder is controlled by a pulse-type full-load operation strategy, under the condition that the system allows, the maximum output operation mode is given priority to quickly empty the coal bunker, and an intelligent shutdown protection mechanism is set up. After the conveying task is completed, it immediately enters the standby state. At the same time, an adaptive interval protection algorithm is introduced to dynamically calculate the minimum operating interval based on the actual filling rate of the coal bunker. The benchmark value can be the time required for the coal bunker to be 70% filled. For example, if it takes 50 minutes to fill, a 35-minute interval is set to effectively avoid frequent start-ups and shutdowns of the equipment.

[0091] Specifically, the belt conveyor feeder coordinated control method of this application embodiment, when controlling the belt conveyor based on multi-source sensing, can employ various speed control modes to control the feeder's discharge speed, such as... Figure 5 As shown, the speed control modes of the coal feeder include belt conveyor efficiency optimization control mode, coal bunker material level intelligent classification control mode, and energy-saving operation control mode.

[0092] Furthermore, the process of controlling the discharge speed of the coal feeder using the belt conveyor efficiency optimization control mode includes:

[0093] S501, enter belt conveyor efficiency optimization control.

[0094] S502, obtain the predicted coal flow rate output by the LSTM neural network model.

[0095] S503, Based on the predicted coal flow rate, a PID algorithm is used to determine the coal output. If the coal output is insufficient, step S504 is executed; if the coal output is excessive, step S505 is executed.

[0096] S504 increases the discharge speed of the coal feeder.

[0097] S505 reduces the discharge speed of the coal feeder.

[0098] S506, maintain the rated operating time of the coal feeder.

[0099] Based on the predicted coal flow rate, the system can adopt a closed-loop control strategy and dynamically adjust the discharge speed of the coal feeder through a PID algorithm, thereby ensuring that the belt always maintains the rated operating state and ensuring the optimal belt conveying efficiency.

[0100] like Figure 5 As shown, the process of controlling the discharge speed of the coal feeder using the intelligent graded control mode for coal bunker material level includes:

[0101] S511, enters intelligent graded control of coal bunker material level.

[0102] S512 acquires the material level information detected by the sensor and the predicted coal flow rate output by the LSTM neural network model.

[0103] S513 uses the ARIMA time series forecasting model to predict changes in material level trends.

[0104] S514 outputs predicted coal bunker level information.

[0105] S515, determine the material level range based on the predicted material level information of the coal bunker.

[0106] S516 If it is determined that the predicted coal level in the coal bunker is at the lowest possible level (e.g., less than 10%), the coal feeder will be stopped immediately to achieve automatic shutdown protection.

[0107] S517 If it is determined that the predicted coal level in the coal bunker is in the high level range (e.g., greater than 80%), the discharge speed of the coal feeder is increased to the highest speed to quickly consume the stored coal.

[0108] S518 If it is determined that the predicted coal level in the coal bunker is in the medium level range (e.g., 30%-80%), the coal feeder is switched to the economic speed setting, i.e., medium speed operation, to maintain stable coal supply.

[0109] S519 If it is determined that the predicted coal level in the coal bunker is in the low level range (e.g., 10%-30%), the coal feeder speed is reduced to the maintenance operating level, i.e., low speed operation.

[0110] In this embodiment, the ARIMA time series prediction model is used to effectively predict changes in material level trends based on material level information and predicted coal flow. By using advanced prediction to offset system delays, the system can complete the feeder discharge speed adjustment decision within 80ms before the occurrence of flow anomalies, thus completely solving the lag problem of traditional feedback control.

[0111] like Figure 5 As shown, the process of controlling the discharge speed of the coal feeder using the energy-saving operation control mode includes:

[0112] S521, enter energy-saving operation control.

[0113] S522, under system-permitted conditions, controls the coal feeder to operate at maximum output to quickly empty the coal bunker.

[0114] S523, Determine if the coal bunker is empty. If yes, proceed to step S524; otherwise, return to step S522.

[0115] S524, the coal feeder enters standby mode.

[0116] The S525 introduces an adaptive interval protection algorithm, setting the next start interval to 0.7T, which allows for the time required to fill the coal bunker to 70%.

[0117] When controlling the coal feeder to operate in an energy-saving manner, an intelligent standby protection mechanism is set up so that it immediately enters standby mode after completing the conveying task. At the same time, the minimum operating interval is dynamically calculated based on the actual filling rate of the coal bunker. For example, if the bunker is filled in 50 minutes, a 35-minute interval is set to effectively avoid frequent start-ups and shutdowns of the equipment.

[0118] This application employs a multi-control mode operation strategy for coal feeders, allowing for flexible switching between multiple modes to address the varying characteristics of coal seam storage conditions, mining processes, and transportation systems in different mining areas. For coordinated control of belt conveyors and coal feeders, an optimized control strategy can be designed, with belt conveyor speed adjustment and coal feeder speed adjustment occurring simultaneously to ensure maximum belt efficiency. For coal feeders with bin level monitoring, an intelligent graded speed adjustment strategy based on predicted coal flow and current material level is designed, using advanced prediction to offset system delays. For coal feeders lacking gears, an energy-saving operation mode can be adopted, emptying the coal bin at full speed. These three modes complement each other, adapting to different working conditions and offering a wide range of applications.

[0119] In summary, the belt conveyor and coal feeder coordinated control method of this application addresses the differences between the belt conveyor and the coal feeder through coordinated control, effectively solving technical problems such as sensitivity to coal quantity fluctuations and response delays in traditional control methods. Specifically, in terms of belt conveyor speed control, an intelligent dead-zone adjustment mechanism is introduced. An optimal dead-zone range is determined through a dynamic threshold algorithm. When coal quantity fluctuations are within the dead-zone threshold, the current speed is maintained, significantly reducing frequent speed adjustments caused by minor coal quantity fluctuations. Furthermore, a coal quantity trend prediction model based on time series analysis is employed to accurately predict coal quantity changes over a future period, achieving proactive speed control. For coal feeder speed regulation, three different speed control modes are provided for flexible selection, and each mode considers delay issues. Therefore, this application constructs a high-precision coal flow status monitoring network based on a multi-source data fusion mechanism, achieving real-time performance and reliability of the belt conveyor and coal feeder coordinated control.

[0120] Furthermore, embodiments of this application also provide a belt conveyor-feeder coordinated control system, such as... Figure 6 As shown, the belt conveyor feeder collaborative control system includes: an image acquisition module 601, a speed detection module 602, and a control module 603.

[0121] The image acquisition module 601 is used to acquire images of the coal flow on the conveyor belt, for example, by using a depth camera to capture images of the coal flow on the conveyor belt. The speed detection module 602 is used to detect the conveyor belt speed, for example, by setting a speed sensor on the conveyor belt to detect and acquire the conveyor belt speed. The control module 603 is used to determine the cross-sectional area of ​​the coal flow on the conveyor belt based on the coal flow image, determine the instantaneous transport volume based on the cross-sectional area of ​​the coal flow and the conveyor belt speed, predict the coal flow trend based on the instantaneous transport volume to obtain the predicted coal flow rate, and adjust the speed of the conveyor belt and the discharge speed of the coal feeder based on the predicted coal flow rate.

[0122] Furthermore, in this embodiment, the control module 603 can be presented in the form of a functional unit. Here, a functional unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0123] The processor can be a central processing unit, a network processor, or a combination thereof. The processor may further include hardware chips. These hardware chips can be application-specific integrated circuits (ASICs), programmable logic devices (PLDs), or combinations thereof. The programmable logic devices can be complex programmable logic devices (CLPs), field-programmable gate arrays (FPGAs), general-purpose array logic (GDAs), or any combination thereof.

[0124] The memory stores instructions executable by at least one processor to cause the at least one processor to perform the cooperative control method shown in the above embodiments.

[0125] The memory may include a stored program area and a stored data area, wherein the stored program area may store the operating system and application programs required for at least one function; the stored data area may store data created based on the use of the computer device, etc. Furthermore, the memory may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory may optionally include memory remotely located relative to the processor, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0126] The memory may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory may also include a combination of the above types of memory.

[0127] It is understood that the further functional descriptions of the above modules are the same as those of the corresponding embodiments of the above methods, and will not be repeated here.

[0128] According to the belt conveyor and coal feeder coordinated control system of this application embodiment, the coal flow image on the belt conveyor is acquired by the image acquisition module and the belt conveying speed is detected by the speed detection module. This allows the cross-sectional area of ​​the coal flow on the belt conveyor to be determined based on the coal flow image, and the instantaneous transport volume is determined based on the cross-sectional area of ​​the coal flow and the belt conveying speed. Then, the coal flow trend is predicted based on a coal flow trend prediction model using time series analysis to obtain the predicted coal flow rate. Finally, the belt conveyor speed is adjusted and the coal feeder discharge speed is adjusted based on the predicted coal flow rate, achieving coordinated control of the belt conveyor and coal feeder. This not only makes the belt conveyor speed adjustment process more precise and reliable, but also enables millisecond-level synchronization between the dynamic adjustment of the coal feeder and the changes in belt coal flow rate, significantly improving the timeliness and accuracy of system control, resulting in significant speed adjustment effect and more stable system operation.

[0129] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0130] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0131] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0132] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0133] It should also be noted that 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 a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0134] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0135] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

[0136] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for coordinated control of a belt conveyor and coal feeder, characterized in that, The method includes: Acquire images of the coal flow and belt conveyor speed on the belt conveyor; The cross-sectional area of ​​the coal flow on the belt conveyor is determined based on the coal flow image, and the instantaneous transport volume is determined based on the cross-sectional area of ​​the coal flow and the belt conveyor speed. The instantaneous transport volume is determined based on the cross-sectional area of ​​the coal flow and the belt conveyor speed, including: The instantaneous coal flow volume value is determined based on the cross-sectional area of ​​the coal flow and the belt conveyor speed; Determine the instantaneous coal flow volume values ​​of n coal flow segments on the belt conveyor, where n is an integer greater than 1; Obtain the maximum coal flow volume value among n instantaneous coal flow volume values, and determine the instantaneous transport volume based on the maximum coal flow volume value, the lengths of the n coal flow segments, and the belt conveyor speed. The instantaneous transport volume is calculated using the following formula: Q = Max(V[1..n]) / L × v; Where Q is the instantaneous transport volume, V[1..n] represents the instantaneous coal flow volume of the nth segment before the coal drop point on the front of the belt conveyor, L is the segment length, and v is the belt conveying speed; The coal flow trend is predicted based on the instantaneous transport volume to obtain the predicted coal flow rate; wherein, the prediction of the coal flow trend based on the instantaneous transport volume includes: inputting the instantaneous transport volume into a pre-trained LSTM neural network model for rolling prediction to obtain the coal flow rate for multiple future time periods, and judging the coal flow trend based on the coal flow rate for multiple future time periods. The belt conveyor is speed-controlled and the feeder discharge speed is adjusted based on the predicted coal flow rate.

2. The belt conveyor feeder coordinated control method according to claim 1, characterized in that, Speed ​​control of the belt conveyor based on the predicted coal flow includes: Determine the rated hourly capacity and maximum design speed of the belt conveyor; The required speed of the belt conveyor is determined based on the predicted coal flow rate, the rated hourly capacity, and the maximum design speed of the belt conveyor, and the required frequency of the belt conveyor is determined based on the required speed of the belt conveyor. The belt conveyor is speed controlled based on its required frequency, current frequency, and dead zone frequency threshold.

3. The belt conveyor feeder coordinated control method according to claim 2, characterized in that, Speed ​​control of the belt conveyor is performed based on the required frequency, the current frequency, and the dead-zone frequency threshold, including: If the required frequency of the belt conveyor is greater than the sum of the current frequency of the belt conveyor and the adjustment dead zone frequency threshold, the belt conveyor is accelerated. If the required frequency of the belt conveyor is less than the difference between the current frequency of the belt conveyor and the adjustment dead zone frequency threshold, and if the duration is greater than a first preset time and the historical speed trend derivative of the belt conveyor is less than a preset threshold, then the belt conveyor is decelerated.

4. The belt conveyor feeder coordinated control method according to claim 3, characterized in that, If it is determined that the belt conveyor needs to be slowed down, the method further includes: The speed of the belt conveyor is locked and maintained for a second preset time.

5. The belt conveyor feeder coordinated control method according to claim 1, characterized in that, Adjusting the discharge speed of the coal feeder based on the predicted coal flow rate includes: The coal output of the coal feeder is determined based on the predicted coal flow rate. If the coal output of the coal feeder is greater than or equal to a preset coal output threshold, then the output speed of the coal feeder shall be reduced. If the coal output of the coal feeder is less than the preset coal output threshold, the output speed of the coal feeder shall be increased.

6. The belt conveyor feeder coordinated control method according to claim 1, characterized in that, In the process of speed control of the belt conveyor based on the predicted coal flow rate, the method further includes: The material level in the coal bunker is detected to obtain material level information; The material level information and the predicted coal flow rate are input into a time series prediction model to predict the material level trend changes, thereby obtaining coal bunker material level prediction information, so as to adjust the discharge speed of the coal feeder according to the coal bunker material level prediction information.

7. The belt conveyor feeder coordinated control method according to claim 1, characterized in that, In the process of speed control of the belt conveyor based on the predicted coal flow rate, the method further includes: In response to the energy-saving operation command, the coal feeder is controlled to discharge material based on the pulse-type full-load operation strategy.

8. A belt conveyor coal feeder coordinated control system, characterized in that, include: The image acquisition module is used to acquire images of the coal flow on the belt conveyor. The speed detection module is used to detect the belt conveyor speed; The control module is used to determine the cross-sectional area of ​​the coal flow on the belt conveyor based on the coal flow image, and to determine the instantaneous coal flow volume value based on the cross-sectional area of ​​the coal flow and the belt conveying speed, and to determine the instantaneous coal flow volume values ​​of n coal flow segments on the belt conveyor, where n is an integer greater than 1; The control module is further configured to obtain the maximum coal flow volume value among n instantaneous coal flow volume values, and determine the instantaneous transport volume based on the maximum coal flow volume value, the lengths of the n coal flow segments, and the belt conveyor speed. The instantaneous transport volume is calculated according to the following formula: Q = Max(V[1..n]) / L × v; Where Q is the instantaneous transport volume, V[1..n] represents the instantaneous coal flow volume of the nth segment before the coal drop point on the front of the belt conveyor, L is the segment length, and v is the belt conveying speed; The control module is also used to input the instantaneous transport volume into a pre-trained LSTM neural network model for rolling prediction, obtain the coal flow rate for multiple future time periods, judge the coal flow trend based on the coal flow rate for multiple future time periods, obtain the predicted coal flow rate, and adjust the speed of the belt conveyor and the discharge speed of the coal feeder based on the predicted coal flow rate.

Images