Dynamic load optimal distribution method and system of coal conveying system

Abstract

The invention provides a dynamic load optimal distribution method and system of a coal conveying system, and belongs to the technical field of coal crushing control. The method comprises the following steps: monitoring a coal hardness generation time sequence in real time through high-frequency sampling; constructing a nonlinear mapping relation between the coal hardness and the main shaft rotating speed of the crushing equipment based on a support vector regression algorithm; dynamically calculating the rotating speed adjustment value and the updating frequency of the single equipment according to the hardness change amplitude and the speed; aggregating the current rotating speed data of multiple devices, and generating cascade crushing configuration parameters and a mechanical impact strength distribution scheme by applying a particle swarm optimization algorithm; a Kalman filtering algorithm is adopted to optimize the cooperative control parameters so as to eliminate response delay, and a final rotating speed adjusting instruction is generated; and the running state of the equipment is dynamically adjusted through real-time feedback control. The problems of high crushing energy consumption and response lag caused by dynamic change of coal quality are solved, and balance optimization of efficiency and energy consumption is achieved.

Description

Technical Field

[0001] This application relates to the field of coal mining technology, and in particular to a dynamic load optimization allocation method and system for a coal conveying system. Background Technology

[0002] In modern energy industry, the crushing process in coal conveying systems is crucial to energy efficiency and production stability. As the core link in coal processing, the operating efficiency of crushing equipment directly affects the energy consumption and production capacity of the entire coal conveying system. With the diversification of coal resources and the dynamic changes in coal hardness, higher technical requirements are placed on the system, necessitating the achievement of efficient crushing and energy-saving goals through dynamic load optimization.

[0003] Chinese Patent, Publication No. CN103953339A, Publication Date: July 30, 2014, discloses a coal mining machine and a coal seam mining method for lump coal. The coal mining machine includes a machine body and a cutting section installed on the machine body. The number of spiral blades n on the cutting section drum is greater than or equal to 5° to 30°, and the spiral angle is 5° to 30°. D and P are the width and pitch of the spiral blades, respectively. The number m of cutting teeth m on each spiral blade is determined by the hardness coefficient f of the coal seam being mined: when the hardness coefficient f of the coal seam being mined is 2.5 to 3.5, m = 7 to 10 teeth; when the hardness coefficient f of the coal seam being mined is greater than 3.5, m = 9 to 17 teeth. The mining method includes the following steps: 1. Setting mining process parameters: setting the drum rotation speed, traction speed, cutting thickness, drum rotation direction, and cutting depth; 2. Coal seam mining, using a unidirectional coal cutting method.

[0004] The shortcomings of the above-mentioned technical solutions are: reliance on fixed parameters or experience-based adjustments makes it difficult to adapt to real-time fluctuations in coal hardness, and inefficient or overloaded operation of multiple devices. When faced with rapid changes in coal hardness, the lack of a precise dynamic adjustment mechanism often limits its effectiveness. Especially when coal quality rapidly changes from soft to hard, the system struggles to respond quickly, leading to uneven crushing or a surge in energy consumption. Furthermore, insufficient coordination between crushing devices, with each adjusting its speed independently, often results in poor overall crushing performance, making it difficult to match mechanical impact force with coal characteristics. The core challenge lies in establishing a dynamic mapping relationship between coal hardness and crushing equipment speed. Continuous changes in coal hardness require the system to acquire accurate hardness parameters in real time and adjust the spindle speed accordingly. However, this process requires not only high-precision hardness detection but also ensuring that the speed adjustment response matches the rate of hardness change. If there is a delay in hardness detection or an inappropriate speed adjustment step size, such as when switching from low-hardness to high-hardness coal in a short time, the system may experience excessively large crushed particles or excessive equipment load due to the lag in speed adjustment. Furthermore, this dynamic adjustment also needs to consider the rotational coordination of multiple crushing devices to avoid uneven crushing or equipment overload caused by excessively large or small speed differences. Summary of the Invention

[0005] To address the shortcomings of existing technologies, the purpose of this application is to provide a dynamic load optimization allocation method and system for a coal conveying system, which establishes a dynamic mapping relationship between coal hardness and crushing equipment rotation speed to achieve matching between mechanical impact force and coal characteristics.

[0006] To achieve the above objectives, this application adopts the following technical solution: This application provides a dynamic load optimization allocation method for a coal conveying system, the method comprising the following steps: S101, real-time coal hardness is obtained by using a high-frequency sampling method to continuously monitor the dynamic changes in coal hardness and obtain a coal hardness time series. S102, Based on the coal hardness time series, a nonlinear mapping relationship between coal hardness and the main shaft speed of the crushing equipment is constructed using the support vector regression algorithm; S103: Obtain the hardness change range based on the coal hardness time series. If the hardness change range exceeds the preset threshold, calculate the main shaft speed adjustment step size based on the nonlinear mapping relationship to obtain the main shaft speed adjustment value of a single crushing equipment. S104. Calculate the rate of change of hardness based on the coal hardness time series. If the rate of change of hardness is higher than the preset threshold, adjust the rotation speed adjustment frequency based on the coal hardness time series and determine the rotation speed update time interval. S105: Obtain the current spindle speed from multiple crushing devices, combine it with the spindle speed adjustment value of a single crushing device, and use the particle swarm optimization algorithm to calculate the difference in spindle speed among multiple crushing devices to obtain the cascade crushing configuration parameters; S106, Based on the configuration parameters of the cascade crushing, adjust the spindle speed of each crushing device, generate a mechanical impact force distribution scheme, and determine the control parameters for the coordinated process of the spindle speed of each crushing device; S107: Obtain the response delay value of real-time coal hardness, and use the Kalman filter algorithm to optimize the control parameters of the main shaft speed coordination process of each crushing device to obtain the final speed adjustment command; S108, based on the final speed adjustment command, update the main shaft speed of multiple crushing equipment according to the speed update time interval, and generate a dynamic load optimization distribution scheme; S109, for the dynamic load optimization allocation scheme, adopts a real-time feedback control method to adjust the operating status of each crushing equipment, and obtains operating parameters that balance crushing efficiency and energy consumption.

[0007] As a preferred technical solution, step S101 further includes: preprocessing the initial coal hardness time series by using a sliding window method to calculate the local mean and variance to obtain a smoothed coal hardness time series; if outliers exist in the smoothed coal hardness time series, the outliers are corrected using a Kalman filter algorithm to generate a corrected coal hardness time series; based on the corrected coal hardness time series, the frequency components of hardness changes are extracted using a fast Fourier transform algorithm to determine the trend of change; if the frequency components of the trend of change exceed a preset threshold, future hardness changes are predicted using an autoregressive model to generate a predicted coal hardness time series; based on the predicted coal hardness time series, the periodic characteristics of hardness changes are calculated to obtain a periodic pattern of coal hardness; and based on the periodic pattern of coal hardness, a feature vector of dynamic changes in coal hardness is generated to determine the final coal hardness time series.

[0008] As a preferred technical solution, in step S102, the step of constructing a nonlinear mapping relationship between coal hardness and the main shaft speed of the crushing equipment using a support vector regression algorithm based on the coal hardness time series includes: preprocessing the coal hardness time series, including checking for missing values ​​and filling in the missing points using linear interpolation, and standardizing the coal hardness time series; constructing a nonlinear mapping relationship between coal hardness and the main shaft speed of the crushing equipment using a support vector regression algorithm, wherein the support vector regression algorithm selects a radial basis function kernel and sets kernel parameters and regularization parameters; optimizing hyperparameters through grid search, training the model of the nonlinear mapping relationship, and determining the optimal kernel parameters and regularization parameters.

[0009] As a preferred technical solution, step S102 further includes: predicting the model of the nonlinear mapping relationship and calculating the prediction error of the model of the nonlinear mapping relationship; if the prediction error of the model of the nonlinear mapping relationship is less than a preset threshold, then extracting the mapping relationship between the spindle speed and coal hardness from the model of the nonlinear mapping relationship and determining the speed adjustment parameter; calculating the target spindle speed value based on the speed adjustment parameter and combined with the hardness change sequence collected in real time, and obtaining the speed adjustment command; adjusting the spindle speed of the crushing equipment through the speed adjustment command and obtaining the adjusted coal hardness time series; if the deviation between the adjusted coal hardness time series and the target hardness range is less than a preset threshold, then determining that the speed adjustment parameter is valid and outputting the final speed adjustment parameter.

[0010] As a preferred technical solution, in step S105, the step of obtaining the current spindle speed from multiple crushing devices, combining it with the spindle speed adjustment value of a single crushing device, and using a particle swarm optimization algorithm to calculate the difference in spindle speed among multiple crushing devices to obtain the cascade crushing configuration parameters includes: collecting the spindle speed value of each crushing device and storing it as a time series dataset of spindle speed values ​​to obtain a real-time speed dataset; calculating the average spindle speed of each crushing device based on the real-time speed dataset, combining it with a preset speed adjustment value to generate the adjusted speed value of each crushing device, obtaining an adjusted speed set; and using the adjusted speed set to calculate the difference in spindle speed among multiple crushing devices. The difference in spindle speed between the main shafts is calculated. If the difference exceeds a preset threshold, it is marked as an abnormal difference, resulting in a set of speed difference values. This set is then input into a particle swarm optimization algorithm, with the optimization iteration count set to calculate the optimal parameters for the cascade crushing configuration, yielding preliminary configuration parameters. Based on these preliminary parameters and the operating status of the crushing equipment, if the operating status is abnormal, the configuration parameters are corrected to obtain optimized configuration parameters. The optimized configuration parameters are then used to calculate the crushing efficiency, resulting in an efficiency evaluation value. If the efficiency evaluation value is lower than a preset threshold, the optimization iteration count is adjusted, and the particle swarm optimization algorithm is re-executed to obtain the final cascade crushing configuration parameters.

[0011] As a preferred technical solution, step S106, which involves adjusting the spindle speed of each crushing device according to the cascade crushing configuration parameters, generating a mechanical impact force distribution scheme, and determining the control parameters for the coordinated process of the spindle speeds of each crushing device, includes: determining the initial spindle speed value of each crushing device by analyzing the process flow data based on the cascade crushing configuration parameters; analyzing the relationship between the speed and the mechanical impact force using a linear regression algorithm based on the initial spindle speed value to obtain the speed influence coefficient; adjusting the spindle speed value to generate an optimized speed distribution scheme if the speed influence coefficient exceeds a preset threshold; calculating the mechanical impact force of each crushing device using the optimized speed distribution scheme to determine the impact force distribution result; generating the control parameters for the coordinated process of the spindle speeds of each crushing device using a particle swarm optimization algorithm based on the impact force distribution result; outputting the final control parameters for the coordinated process of the spindle speeds of each crushing device if the control parameters for the coordinated process of the spindle speeds of each crushing device meet the process flow constraints, and determining the equipment operating status; and obtaining real-time process data based on the equipment operating status to determine whether the speed control accuracy meets the requirements and updating the control parameters for the coordinated process of the spindle speeds of each crushing device.

[0012] As a preferred technical solution, step S107, which involves obtaining the response delay value of real-time coal hardness and optimizing the control parameters of the coordinated process of the main shaft speeds of each crushing device using a Kalman filter algorithm to obtain the final speed adjustment command, includes: acquiring coal hardness through a real-time data acquisition module at a preset sampling frequency to obtain real-time coal hardness; if the real-time coal hardness exceeds a preset threshold, calculating the response delay value of coal hardness through timestamp analysis to determine the delay time sequence; smoothing the delay time sequence using a Kalman filter algorithm to generate a smoothed delay time sequence; adjusting the speed adjustment parameters according to the smoothed delay time sequence to obtain an optimized speed adjustment parameter set; calculating the deviation between the main shaft speed and the current main shaft speed in the optimized speed adjustment parameter set; if the deviation exceeds a preset threshold, calculating the speed adjustment amount based on the deviation value to generate a preliminary adjustment command; verifying the preliminary adjustment command through the real-time data acquisition module and updating the adjustment command using a feedback loop mechanism to obtain the final speed adjustment command; and updating the control parameters of the coordinated process of the main shaft speeds of each crushing device according to the final speed adjustment command to generate a real-time control signal.

[0013] As a preferred technical solution, in step S108, the step of updating the spindle speeds of multiple crushing devices based on the final speed adjustment command and the speed update time interval to generate a dynamic load optimization allocation scheme includes: obtaining the spindle speed from the crushing devices; if the spindle speed is lower than a preset threshold, adjusting the spindle speed through real-time control signals to obtain the updated spindle speed; using a linear regression algorithm to analyze the relationship between the updated spindle speed and load allocation to determine the optimization target; calculating the load allocation ratio of each crushing device according to the optimization target to obtain a dynamic load allocation scheme; collecting the operating parameters of the crushing devices to determine whether the dynamic load allocation scheme meets the preset conditions; if the load allocation scheme does not meet the preset conditions, using a genetic algorithm to adjust the allocation ratio to obtain a dynamic load optimization allocation scheme.

[0014] As a preferred technical solution, in step S109, the step of adjusting the operating status of each crushing device using a real-time feedback control method to obtain operating parameters that balance crushing efficiency and energy consumption for the dynamic load optimization allocation scheme includes: collecting crushing device operating parameters and determining the dynamic load of the crushing device; if the dynamic load exceeds a preset threshold, adjusting the crushing device operating parameters through a feedback control algorithm to obtain an optimized device status; calculating the crushing efficiency value based on the optimized device status and determining whether the crushing efficiency value meets a preset standard; if the crushing efficiency value is lower than the preset standard, predicting the energy consumption change trend through a linear regression model to obtain energy consumption adjustment parameters; updating the device status based on the energy consumption adjustment parameters and determining a new load allocation scheme; collecting the updated crushing device operating parameters and determining whether the crushing efficiency value meets a preset standard; if the crushing efficiency value meets the preset standard, determining whether the crushing device has reached energy consumption balance based on the energy consumption change trend; if the crushing device has not reached energy consumption balance, repeating the steps of adjusting the crushing device operating parameters and collecting the crushing device operating parameters until the crushing device reaches energy consumption balance, and obtaining the final operating parameters that balance crushing efficiency and energy consumption.

[0015] This application also provides a dynamic load optimization allocation system for a coal conveying system. The system includes: a dynamic monitoring and data processing module, which collects coal hardness data in real time and generates a coal hardness time series; a built-in threshold judgment unit, which determines whether the hardness change amplitude or hardness change rate exceeds a preset threshold; a speed mapping and calculation module, which constructs a nonlinear mapping relationship between coal hardness and the main shaft speed of the crushing equipment based on the coal hardness time series using a support vector regression algorithm; the speed mapping and calculation module calculates the adjustment value of the main shaft speed of a single piece of equipment based on the hardness change amplitude and determines the speed update time interval based on the hardness change rate; and a collaborative optimization and configuration generation module, which aggregates... The system combines the current spindle speed data of multiple crushing devices and applies a particle swarm optimization algorithm to calculate the spindle speed difference between the devices. The collaborative optimization and configuration generation module generates tiered crushing configuration parameters and formulates a mechanical impact force distribution scheme accordingly. The instruction optimization and delay compensation module acquires the response delay value of real-time coal hardness and optimizes the collaborative control parameters using a Kalman filter algorithm. This module generates the final speed adjustment instruction, eliminating the impact of system response lag. The execution control and feedback module dynamically adjusts the spindle speed of each crushing device based on the final speed adjustment instruction and update time interval. This module continuously monitors the equipment operating status through a real-time feedback control unit, optimizing operating parameters that balance crushing efficiency and energy consumption.

[0016] Compared with the prior art, the beneficial effects of this application are as follows: This application presents a dynamic load optimization and allocation method for a coal conveying system, achieving energy conservation, efficiency improvement, and stable operation through multi-dimensional technology integration. The method involves real-time sensing of coal hardness changes, employing high-frequency sampling technology to continuously monitor coal hardness and generate time series data. Based on this, a nonlinear mapping relationship between coal hardness and crushing equipment rotation speed is constructed. When the detected hardness change amplitude or rate exceeds a threshold, the system dynamically adjusts the speed adjustment step size and update frequency of a single piece of equipment to ensure that equipment response is synchronized with coal quality fluctuations. In the multi-machine collaborative stage, the system calculates the spindle speed difference among multiple crushing devices based on a particle swarm optimization algorithm, generating tiered crushing configuration parameters and formulating a mechanical impact force distribution scheme accordingly. This achieves balanced load distribution among multiple devices, avoiding local overload or idling. To address the system response delay issue, a Kalman filter algorithm is introduced to optimize control commands, eliminating lag effects and improving the robustness of command execution. Finally, the system dynamically adjusts the equipment operating status through speed update intervals and continuously calibrates parameters using a real-time feedback mechanism, reducing energy consumption while ensuring crushing efficiency. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the steps of a dynamic load optimization allocation method for a coal conveying system according to this application. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present application, the technical solutions in specific embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0019] This application provides a dynamic load optimization allocation method for a coal conveying system, the method comprising the following steps: S101, real-time coal hardness is obtained by using a high-frequency sampling method to continuously monitor the dynamic changes in coal hardness and obtain a coal hardness time series. S102, Based on the coal hardness time series, a nonlinear mapping relationship between coal hardness and the main shaft speed of the crushing equipment is constructed using the support vector regression algorithm; S103: Obtain the hardness change range based on the coal hardness time series. If the hardness change range exceeds the preset threshold, calculate the main shaft speed adjustment step size based on the nonlinear mapping relationship to obtain the main shaft speed adjustment value of a single crushing equipment. S104. Calculate the rate of change of hardness based on the coal hardness time series. If the rate of change of hardness is higher than the preset threshold, adjust the rotation speed adjustment frequency based on the coal hardness time series and determine the rotation speed update time interval. S105: Obtain the current spindle speed from multiple crushing devices, combine it with the spindle speed adjustment value of a single crushing device, and use the particle swarm optimization algorithm to calculate the difference in spindle speed among multiple crushing devices to obtain the cascade crushing configuration parameters; S106, Based on the configuration parameters of the cascade crushing, adjust the spindle speed of each crushing device, generate a mechanical impact force distribution scheme, and determine the control parameters for the coordinated process of the spindle speed of each crushing device; S107: Obtain the response delay value of real-time coal hardness, and use the Kalman filter algorithm to optimize the control parameters of the main shaft speed coordination process of each crushing device to obtain the final speed adjustment command; S108, based on the final speed adjustment command, update the main shaft speed of multiple crushing equipment according to the speed update time interval, and generate a dynamic load optimization distribution scheme; S109, for the dynamic load optimization allocation scheme, adopts a real-time feedback control method to adjust the operating status of each crushing equipment, and obtains operating parameters that balance crushing efficiency and energy consumption.

[0020] This application presents a dynamic load optimization and allocation method for a coal conveying system, achieving energy conservation, efficiency improvement, and stable operation through multi-dimensional technology integration. The method involves real-time sensing of coal hardness changes, employing high-frequency sampling technology to continuously monitor coal hardness and generate time series data. Based on this, a nonlinear mapping relationship between coal hardness and crushing equipment rotation speed is constructed. When the detected hardness change amplitude or rate exceeds a threshold, the system dynamically adjusts the speed adjustment step size and update frequency of a single piece of equipment to ensure that equipment response is synchronized with coal quality fluctuations. In the multi-machine collaborative stage, the system calculates the spindle speed difference among multiple crushing devices based on a particle swarm optimization algorithm, generating tiered crushing configuration parameters and formulating a mechanical impact force distribution scheme accordingly. This achieves balanced load distribution among multiple devices, avoiding local overload or idling. To address the system response delay issue, a Kalman filter algorithm is introduced to optimize control commands, eliminating lag effects and improving the robustness of command execution. Finally, the system dynamically adjusts the equipment operating status through speed update intervals and continuously calibrates parameters using a real-time feedback mechanism, reducing energy consumption while ensuring crushing efficiency.

[0021] Specifically, real-time coal hardness is acquired using a coal hardness sensor. For example, the MPX5700 coal hardness sensor has a range of 0-700 kPa and an accuracy of ±0.5%. In this application, the coal hardness sensor is installed near the coal mining machine drum, and the sampling frequency is set to 100 Hz to capture instantaneous changes in coal hardness. The coal hardness sensor transmits data to an industrial control computer via an RS-485 interface. The data is recorded with a timestamp (accurate to milliseconds, such as 2025-08-05 02:50:00.123) to ensure the time-series accuracy of subsequent analysis. The coal hardness time-series data is stored in a database (such as MySQL), generating 100 data points per second. The data format is {timestamp, hardness value (unit kPa)}, for example, {2025-08-05 02:50:00.123, 450.2}.

[0022] Furthermore, step S101 also includes: The initial coal hardness time series is preprocessed, and a sliding window method is used to calculate the local mean and variance to obtain a smoothed coal hardness time series. For example, the sliding window size is 1 second, the step size is 0.1 seconds, the mean is 450 kPa to reflect the hardness level, and the standard deviation is ±10 kPa to assess the fluctuation of coal hardness.

[0023] If outliers are found in the smoothed coal hardness time series, a Kalman filter algorithm is used to correct them, generating a corrected coal hardness time series. For example, when the standard deviation exceeds a threshold (e.g., 20 kPa), an anomaly alarm is triggered, indicating a sudden change in coal seam hardness, which may be related to geological structural changes. To ensure logical consistency, outlier data is automatically correlated with the operating parameters of the coal mining machine (e.g., rotational speed of 200 rpm) to analyze whether the hardness change is caused by equipment vibration. The Kalman filter algorithm corrects outliers, reducing noise impact (e.g., reducing high-frequency noise amplitude from ±5 kPa to ±1 kPa) and improving data reliability.

[0024] Based on the corrected coal hardness time series, a fast Fourier transform algorithm is used to extract the frequency components of hardness changes and determine the trend. If the frequency components of the trend exceed a preset threshold, an autoregressive model is used to predict future hardness changes, generating a predicted coal hardness time series.

[0025] Based on the predicted coal hardness time series, the periodic characteristics of hardness changes are calculated to obtain the periodic pattern of coal hardness. Specifically, the Fast Fourier Transform (FFT) algorithm is used to perform frequency domain analysis on the collected coal hardness time series, extracting the dominant frequency component (such as a peak frequency of 10Hz in the range of 0-50Hz) to determine the periodic characteristics of coal hardness changes.

[0026] By using the periodic pattern of coal hardness, a feature vector of dynamic changes in coal hardness is generated, and the final coal hardness time series is determined.

[0027] Furthermore, in step S102, based on the coal hardness time series, the support vector regression algorithm is used to construct a nonlinear mapping relationship between coal hardness and the main shaft speed of the crushing equipment, including: Preprocessing of the coal hardness time series includes checking for missing values ​​and filling in missing points using linear interpolation, as well as standardizing the coal hardness time series. For example, 100 sets of hardness values ​​(unit: HB, Brinell hardness) and spindle speeds (unit: r / min) were collected, with hardness values ​​ranging from 50 to 150 HB and spindle speeds ranging from 500 to 2000 r / min. In this application, the pandas library of Python is used to read the coal hardness time series data, check for missing values, and fill in missing points using linear interpolation. For example, if a hardness value at a certain point is NaN (Not a Number, indicating an undefined or unrepresentable value), then 75 is obtained by interpolation based on the hardness values ​​of 70 and 80 before and after it. In this application, the StandardScaler function of sklearn is used to standardize the coal hardness time series, scaling the hardness and speed values ​​to a mean of 0 and a standard deviation of 1 to eliminate the influence of dimensions.

[0028] A nonlinear mapping relationship between coal hardness and the spindle speed of the crushing equipment is constructed using the Support Vector Regression (SVR) algorithm. The SVR algorithm selects a radial basis function (RBF) kernel and sets the kernel parameters and regularization parameters. In this application, the kernel parameter γ = 0.1 and the regularization parameter C = 100 are set.

[0029] The hyperparameters are optimized using grid search to train a model of nonlinear mapping relationships and determine the optimal kernel and regularization parameters. In this application, the search range is C=[10,50,100,200], and γ=[0.01,0.1,1]. The optimal parameter combination is found using sklearn's GridSearchCV with 5-fold cross-validation. For example, when C=100 and γ=0.1, the mean squared error (MSE) of the nonlinear mapping relationship model is minimized to 2.5.

[0030] Furthermore, step S102 also includes: The model of the nonlinear mapping relationship is used for prediction, and the prediction error of the model is calculated. If the prediction error of the nonlinear mapping relationship model is less than a preset threshold, the mapping relationship between the spindle speed and coal hardness is extracted from the model to determine the speed adjustment parameters. For example, after training the nonlinear mapping relationship model, with an input coal hardness of 120, the predicted spindle speed is 1450 r / min, and the model prediction error R² is 0.92, indicating a good fit. Analyzing the prediction results of the nonlinear mapping relationship model, the coal hardness variation range is set to [50, 150] with a step size of 10, and the corresponding speed is calculated. When the coal hardness increases from 50 to 150, the spindle speed decreases from 1800 to 1000, showing a nonlinear negative correlation.

[0031] Based on the speed adjustment parameters and the real-time acquired hardness change sequence, the target spindle speed value is calculated, resulting in a speed adjustment command. This command adjusts the spindle speed of the crushing equipment, obtaining the adjusted coal hardness time series. If the deviation between the adjusted coal hardness time series and the target hardness range is less than a preset threshold, the speed adjustment parameters are deemed valid, and the final speed adjustment parameters are output. For example, in the final speed adjustment parameters, a coal hardness of 100 corresponds to a spindle speed of 1500±50 r / min, stored as a CSV file for subsequent use by the crushing equipment control system.

[0032] For example, in step S103, the current coal hardness is 7.5, the previous cycle coal hardness was 6.8, and the preset threshold is 0.5. The coal hardness change is calculated as |7.5 - 6.8| = 0.7, which exceeds the preset threshold of 0.5, triggering the spindle speed adjustment step. The speed adjustment step size is calculated using a nonlinear mapping model; for example, a quadratic function mapping is used. Where a = 10, b = 5, c = 2.

[0033] Substituting a hardness change of 0.7, the speed adjustment step size is: 10 * (0.7)^2 + 5 * 0.7 + 2 = 10 * 0.49 + 3.5 + 2 = 4.9 + 3.5 + 2 = 10.4 rpm. Considering the current spindle speed of the crushing equipment is 1500 rpm and the maximum allowable spindle speed is 1800 rpm, the adjusted spindle speed is 1500 + 10.4 = 1510.4 rpm, which is still within the safe range.

[0034] For example, in step S104, the preset threshold for the hardness change rate is 0.5 HB / s. The hardness sequence is [100, 101, 102, 103.5, 105] HB, with a time interval of 1 second. Therefore, the hardness change rate = (105-100) / 4 = 1.25 HB / s, which is higher than the preset threshold of 0.5 HB / s, triggering the speed adjustment step. The speed adjustment frequency is adjusted according to the hardness change rate using a linear mapping algorithm: the relationship between the speed adjustment frequency f (in Hz) and the hardness change rate v (in HB / s) is: ; Substituting v=1.25, we get f=2×1.25+1=3.5 Hz, which means the speed is adjusted 3.5 times per second.

[0035] To determine the rotational speed update interval, the system takes the reciprocal of the adjustment frequency, calculating the update interval t = 1 / f = 1 / 3.5 ≈ 0.286 seconds. If the hardness change rate is too high (e.g., 1.25 HB / s), it indicates that the material is hardening rapidly, requiring more frequent rotational speed adjustments to avoid overloading the equipment; conversely, if the hardness change rate is below the preset threshold (e.g., 0.3 HB / s), the default frequency of 1 Hz is maintained with an interval of 1 second. Historical data analysis verifies that when the hardness change rate is between 0.5 and 2 HB / s, a 3.5 Hz frequency can control the processing error within ±0.1 mm, meeting the accuracy requirements. All calculations are automatically executed by the PLC controller, and sensor data is transmitted via the Modbus protocol to ensure real-time performance and reliability.

[0036] Furthermore, in step S105, the current spindle speed is obtained from multiple crushing devices, and combined with the spindle speed adjustment value of a single crushing device, the difference in spindle speed among the multiple crushing devices is calculated using a particle swarm optimization algorithm to obtain the cascade crushing configuration parameters, including: The spindle speed values ​​of each crusher are collected and stored as a time-series dataset to obtain a real-time speed dataset. Based on the real-time speed dataset, the average spindle speed of each crusher is calculated. Combined with a preset speed adjustment value, the adjusted speed value of each crusher is generated, resulting in a set of adjusted speeds. In this application, the spindle speed values ​​of each crusher are collected through an industrial Internet of Things (IoT) system, and the speed register is read from the PLC using the Modbus protocol. Assume there are three crushers with current spindle speeds of 1200 rpm, 1250 rpm, and 1180 rpm, respectively. The spindle speed of crusher 1 needs to be increased by 50 rpm, the spindle speed of crusher 2 needs to be decreased by 30 rpm, and the spindle speed of crusher 3 remains unchanged.

[0037] Using an adjusted set of rotational speeds, the spindle speed difference between multiple crushing devices is calculated. If the spindle speed difference exceeds a preset threshold, it is marked as an abnormal difference, resulting in a set of speed difference values. This set of speed difference values ​​is then input into a particle swarm optimization algorithm (PSO) with a set of optimization iterations to calculate the optimal parameters for the cascade crushing configuration, yielding preliminary configuration parameters. Based on these preliminary parameters and the operating status of the crushing devices, if the operating status is abnormal, the configuration parameters are corrected to obtain optimized configuration parameters. The crushing efficiency is then calculated using these optimized parameters to obtain an efficiency evaluation value. If the efficiency evaluation value is lower than a preset threshold, the number of optimization iterations is adjusted, and the PSO algorithm is re-executed to obtain the final cascade crushing configuration parameters.

[0038] Specifically, a particle swarm optimization (PSO) algorithm is used to calculate the spindle speed differences between multiple machines to optimize the cascade crushing configuration parameters. For example, PSO initializes 20 particles, each representing a set of spindle speed adjustment values, with the particle position defined by three-dimensional coordinates (x, y, z). The objective function is the sum of squares of the total speed differences, expressed as: ;in Adjust the rotation speed of each piece of equipment. The target speed is 1300 rpm.

[0039] The PSO iteration is performed 100 times, with particle velocity restricted to a range of 0.01 to 0.1, a convergence rate of 0.9, a mutation frequency of 0.05 Hz, and a computation time step of 0.01 seconds. Each iteration updates the particle position, evaluates the objective function value, and optimizes the adjustment values ​​to minimize F. Finally, the PSO outputs the following adjustment values: 1240 rpm for the main shaft speed of crusher 1, 1220 rpm for crusher 2, and 1180 rpm for crusher 3.

[0040] Furthermore, in step S106, based on the cascade crushing configuration parameters, the spindle speed of each crushing device is adjusted to generate a mechanical impact force distribution scheme, and the control parameters for the coordinated process of the spindle speeds of each crushing device are determined, including: Based on the cascade crushing configuration parameters, the initial spindle speed of each crushing device is determined by analyzing the process flow data. Based on the initial spindle speed, a linear regression algorithm is used to analyze the relationship between speed and mechanical impact force, obtaining the speed influence coefficient. If the speed influence coefficient exceeds a preset threshold, the spindle speed is adjusted to generate an optimized speed distribution scheme. For example, the spindle speed range for a jaw crusher is 200-350 rpm, for a cone crusher it is 400-600 rpm, and for an impact crusher it is 500-800 rpm, taking into account material hardness (Mohs hardness 5.5) and feed particle size (maximum 300 mm). Based on these parameters, the influence of the spindle speed of each device on the impact force is calculated using the formula... Where F is the impact force (in kN), k is the equipment coefficient (k = 0.02 for jaw crusher, k = 0.015 for cone crusher, and k = 0.01 for impact crusher), n is the main shaft speed (rpm), and m is the material mass (kg). In a jaw crusher, assuming m = 100 kg and initial n = 300 rpm, calculate F = 0.02 × 300² × 100 = 180 kN. If the target impact force is 200 kN, adjust the main shaft speed n = sqrt(200 / (0.02 × 100)) = 316.23 rpm, rounded to 316 rpm. Similarly, for the cone crusher, the target is F=150 kN, m=80 kg, and the main shaft speed is n=sqrt(150 / (0.015×80))=353.55 rpm, which is adjusted to 354 rpm; for the impact crusher, the target is F=100 kN, m=60 kg, and the main shaft speed is n=sqrt(100 / (0.01×60))=408.25 rpm, which is adjusted to 408 rpm.

[0041] The optimized speed distribution scheme is used to calculate the mechanical impact force of each crusher and determine the impact force distribution result. Specifically, a linear programming algorithm is used to optimize and ensure the lowest total energy consumption, generating the impact force distribution result. For example, the constraints are set as follows: total impact force ΣF = 450 kN, energy consumption formula E = 0.5 × n² × t (t is the running time in hours). Taking t = 1 hour as an example, the optimized result is: jaw crusher F = 200 kN, cone crusher F = 150 kN, impact crusher F = 100 kN, and total energy consumption E = 0.5 × (316² + 354² + 408²) × 1 = 145250 J.

[0042] Based on the impact force distribution results, a particle swarm optimization algorithm is used to generate control parameters for the coordinated rotational speed process of each crusher's main shaft. If the control parameters for the coordinated rotational speed process of each crusher's main shaft meet the process constraints, the final control parameters for the coordinated rotational speed process of each crusher's main shaft are output to determine the equipment operating status. Real-time process data is obtained through the equipment operating status to determine whether the speed control accuracy meets the requirements, and the control parameters for the coordinated rotational speed process of each crusher's main shaft are updated accordingly. Specifically, the coordinated process control parameters are implemented using a PID algorithm. For example, the proportional coefficient Kp = 0.8, the integral time Ti = 0.5 s, and the derivative time Td = 0.1 s are set to ensure that the main shaft speed fluctuation is less than ±5 rpm. Analysis shows that after speed adjustment, the impact force distribution meets the material crushing requirements, and energy consumption is reduced by approximately 10%. Speed ​​and energy consumption data are collected through a real-time monitoring system to verify the feasibility of the scheme. The adjusted parameters can be automatically sent to the equipment controller via the PLC system to ensure information-based coordinated control.

[0043] Furthermore, in step S107, the response delay value of real-time coal hardness is obtained, and the control parameters of the coordinated process of the main shaft speed of each crushing device are optimized using a Kalman filter algorithm to obtain the final speed adjustment command, including: The real-time coal hardness is obtained by acquiring coal hardness data at a preset sampling frequency using a real-time data acquisition module. For example, the time series of real-time coal hardness is [50.2, 50.5, 49.8, 50.1, 50.3] HB. If the real-time coal hardness exceeds a preset threshold, the response delay value of the coal hardness is calculated through timestamp analysis to determine the delay time series. Specifically, the response delay value is calculated by analyzing the arrival time of data packets using timestamp analysis. For example, the time from when a data packet is sent by the sensor to when it is received by the processing unit is 8.2 ms, which meets the real-time requirement.

[0044] A Kalman filter algorithm is used to smooth the delayed time series, generating a smoothed delayed time series. For example, the initial spindle speed is 1500 rpm, the target coal hardness is 50 HB, and the control parameters include proportional gain Kp = 0.5 and integral gain Ki = 0.02. The Kalman filter passes through: Equations of state: ; Observation equation: ; The optimal rotational speed is estimated, where A=1, B=0.1, H=1, and the covariances of process noise w(k) and measurement noise v(k) are Q=0.01 and R=0.05, respectively. After filtering, a smoothed delay time series is obtained. For example, the smoothed delay time series is [1498, 1501, 1500, 1499, 1500] rpm, which reduces the impact of noise and improves control accuracy.

[0045] Based on the smoothed delay time series, the speed regulation parameters are adjusted to obtain an optimized speed regulation parameter set. The deviation between the main shaft speed and the current main shaft speed in the optimized speed regulation parameter set is calculated. If the deviation exceeds a preset threshold, the speed regulation amount is calculated based on the deviation, generating a preliminary regulation command. The preliminary regulation command is verified through a real-time data acquisition module, and a feedback loop mechanism is used to update the regulation command, resulting in the final speed regulation command. Based on the final speed regulation command, the control parameters for the coordinated main shaft speed process of each crushing device are updated, generating a real-time control signal. For example, based on the filtered main shaft speed and the deviation value (50HB-50.3HB=-0.3HB), the regulation command is calculated using a PID algorithm. ; Where e(t) represents the hardness deviation. The calculated speed adjustment is -2 rpm, and the commanded speed is 1498 rpm. This command is sent to the motor controller via the Modbus protocol to complete the closed-loop regulation.

[0046] Furthermore, in step S108, based on the final speed adjustment command, the main shaft speeds of multiple crushing devices are updated according to the speed update time interval to generate a dynamic load optimization allocation scheme, including: The spindle speed is obtained from the crushing equipment. If the spindle speed is lower than a preset threshold, it is adjusted via real-time control signals to obtain an updated spindle speed. A linear regression algorithm is used to analyze the relationship between the updated spindle speed and load distribution to determine the optimization objective. Based on the optimization objective, the load distribution ratio of each crushing unit is calculated to obtain a dynamic load distribution scheme. The operating parameters of the crushing equipment are collected to determine whether the dynamic load distribution scheme meets preset conditions. If the load distribution scheme does not meet the preset conditions, a genetic algorithm is used to adjust the distribution ratio to obtain an optimized dynamic load distribution scheme.

[0047] For example, the current spindle speed of crusher 1 is 1200 rpm, the current spindle speed of crusher 2 is 1100 rpm, and the current spindle speed of crusher 3 is 1300 rpm. The system receives an instruction to optimize the allocation of the total dynamic load, aiming to balance the load of the three crushers and minimize total energy consumption. Based on this, a genetic algorithm is used for speed optimization allocation. The initial population is set to 100 speed combinations, each combination containing the speed values ​​of the three devices, limited to a range of 1000 to 1500 rpm. The fitness function is defined as: ; in For the load of each crushing machine, Where E is the average load and E is the total energy consumption. and As weight, The value is 0.6. The value is set to 0.4. After the first iteration, the algorithm selects the optimal solution: the main shaft speed of crusher 1 is adjusted to 1250 rpm, the main shaft speed of crusher 2 is adjusted to 1220 rpm, and the main shaft speed of crusher 3 is adjusted to 1230 rpm. At this time, the load deviation... The total energy consumption E decreased from 4500 joules / second to 4200 joules / second as the initial power was reduced from 150 kilowatts to 30 kilowatts.

[0048] Furthermore, in step S109, for the dynamic load optimization allocation scheme, a real-time feedback control method is used to adjust the operating status of each crushing device, and the operating parameters that balance crushing efficiency and energy consumption are obtained, including: The operating parameters of the crushing equipment are collected to determine its dynamic load. If the dynamic load exceeds a preset threshold, the operating parameters are adjusted through a feedback control algorithm to obtain an optimized equipment state. For example, the operating parameters of the crushing equipment are: spindle speed of 1800 rpm, feed rate of 50 tons / hour, and energy consumption of 200 kWh. These operating parameters are transmitted to the central control system via the Industrial Internet of Things (IIoT). A time-series-based sliding window algorithm (window size of 30 seconds) is used to analyze the dynamic load and calculate the load change rate. For example, the current load change rate is 5% per minute. In this application, a PID control algorithm (proportional coefficient Kp=0.5, integral coefficient Ki=0.1, derivative coefficient Kd=0.05) is used to dynamically adjust the operating parameters of the crushing equipment. For example, when the energy consumption exceeds the set threshold of 220 kWh, the spindle speed is reduced to 1750 rpm to reduce energy consumption.

[0049] Based on the optimized equipment status, the crushing efficiency value is calculated, and it is determined whether the crushing efficiency value meets the preset standard. If the crushing efficiency value is lower than the preset standard, the energy consumption change trend is predicted using a linear regression model to obtain energy consumption adjustment parameters. Based on the energy consumption adjustment parameters, the equipment status is updated, and a new load distribution scheme is determined. The updated crushing equipment operating parameters are collected, and it is determined whether the crushing efficiency value meets the preset standard. If the crushing efficiency value meets the preset standard, it is determined whether the crushing equipment has reached energy consumption balance based on the energy consumption change trend. If the crushing equipment has not reached energy consumption balance, the steps of adjusting the crushing equipment operating parameters and collecting the crushing equipment operating parameters are repeated until the crushing equipment reaches energy consumption balance, obtaining the final crushing efficiency and energy consumption balanced operating parameters.

[0050] For example, the preset crushing efficiency standard is 95%. Based on real-time feedback data, a trade-off index between crushing efficiency and energy consumption is calculated, defined as the crushing efficiency / energy consumption ratio (currently 95 / 200 = 0.475). A genetic algorithm is used to optimize the parameter combination, setting the population size to 50 and iterating 20 times to obtain the optimal spindle speed of 1760 rpm and the feed rate adjusted to 48 tons / hour. At this point, energy consumption drops to 195 kWh, while the crushing efficiency remains at 94.8%. If a change in feed particle size is detected (e.g., average particle size increases from 10 mm to 12 mm), the vibrating screen frequency is automatically adjusted (from 30 Hz to 32 Hz) to ensure feed uniformity. Through historical data analysis, the load trend for the next 10 minutes is predicted, and the operating parameters of the crushing equipment are pre-adjusted to avoid energy consumption peaks.

[0051] This application also provides a dynamic load optimization allocation system for a coal conveying system, which includes: a dynamic monitoring and data processing module, a speed mapping and calculation module, a collaborative optimization and configuration generation module, an instruction optimization and delay compensation module, and an execution control and feedback module.

[0052] The dynamic monitoring and data processing module collects coal hardness data in real time and generates a coal hardness time series. This module also includes a built-in threshold judgment unit, which determines whether the magnitude or rate of hardness change exceeds a preset threshold.

[0053] The speed mapping and calculation module uses a support vector regression algorithm based on the coal hardness time series to construct a nonlinear mapping relationship between coal hardness and the spindle speed of the crushing equipment. The module calculates the adjustment value of the spindle speed for a single piece of equipment based on the hardness change amplitude and determines the speed update interval by combining this with the hardness change rate.

[0054] The collaborative optimization and configuration generation module aggregates the current spindle speed data of multiple crushing devices and applies a particle swarm optimization algorithm to calculate the spindle speed difference between the devices. This module then generates cascade crushing configuration parameters and formulates a mechanical impact force distribution scheme accordingly.

[0055] The instruction optimization and delay compensation module obtains the response delay value of real-time coal hardness and uses a Kalman filter algorithm to optimize the cooperative control parameters. The module then generates the final speed regulation command, eliminating the effects of system response lag.

[0056] The execution control and feedback module dynamically adjusts the spindle speed of each crusher based on the final speed adjustment command and update time interval. The real-time feedback control unit continuously monitors the equipment's operating status, optimizing operating parameters that balance crushing efficiency and energy consumption.

[0057] It should be noted that the terms "first," "second," and similar terms used in this application specification and claims do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Similarly, "a" or "one," and similar terms do not indicate a quantity limitation, but rather indicate the presence of at least one. "A plurality" or "several" indicates at least two. Unless otherwise stated, terms such as "front," "back," "left," "right," "lower," and / or "upper" are for illustrative purposes only and are not limited to a location or spatial orientation. Terms such as "comprising" or "including" indicate that the elements or objects preceding "comprising" encompass the elements or objects listed following "comprising" or "including" and their equivalents, and do not exclude other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect.

[0058] The singular forms “a,” “the,” and “the” used in this application specification and appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0059] It should be understood that those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A dynamic load optimization allocation method for a coal conveying system, characterized in that, The method includes the following steps: S101, real-time coal hardness is obtained by using a high-frequency sampling method to continuously monitor the dynamic changes in coal hardness and obtain a coal hardness time series. S102, Based on the coal hardness time series, a nonlinear mapping relationship between coal hardness and the main shaft speed of the crushing equipment is constructed using the support vector regression algorithm; S103: Obtain the hardness change range based on the coal hardness time series. If the hardness change range exceeds the preset threshold, calculate the main shaft speed adjustment step size based on the nonlinear mapping relationship to obtain the main shaft speed adjustment value of a single crushing equipment. S104. Calculate the rate of change of hardness based on the coal hardness time series. If the rate of change of hardness is higher than the preset threshold, adjust the rotation speed adjustment frequency based on the coal hardness time series and determine the rotation speed update time interval. S105: Obtain the current spindle speed from multiple crushing devices, combine it with the spindle speed adjustment value of a single crushing device, and use the particle swarm optimization algorithm to calculate the difference in spindle speed among multiple crushing devices to obtain the cascade crushing configuration parameters; S106, Based on the configuration parameters of the cascade crushing, adjust the spindle speed of each crushing device, generate a mechanical impact force distribution scheme, and determine the control parameters for the coordinated process of the spindle speed of each crushing device; S107: Obtain the response delay value of real-time coal hardness, and use the Kalman filter algorithm to optimize the control parameters of the main shaft speed coordination process of each crushing device to obtain the final speed adjustment command; S108, based on the final speed adjustment command, update the main shaft speed of multiple crushing equipment according to the speed update time interval, and generate a dynamic load optimization distribution scheme; S109, for the dynamic load optimization allocation scheme, adopts a real-time feedback control method to adjust the operating status of each crushing equipment, and obtains operating parameters that balance crushing efficiency and energy consumption.

2. The energy distribution optimization method for parking batteries according to claim 1, characterized in that, Step S101 further includes: preprocessing the initial coal hardness time series by using a sliding window method to calculate the local mean and variance to obtain a smoothed coal hardness time series; if outliers exist in the smoothed coal hardness time series, the outliers are corrected using a Kalman filter algorithm to generate a corrected coal hardness time series; based on the corrected coal hardness time series, the frequency components of hardness changes are extracted using a fast Fourier transform algorithm to determine the trend of change; if the frequency components of the trend of change exceed a preset threshold, future hardness changes are predicted using an autoregressive model to generate a predicted coal hardness time series; based on the predicted coal hardness time series, the periodicity characteristics of hardness changes are calculated to obtain a periodic pattern of coal hardness; and based on the periodic pattern of coal hardness, a feature vector of dynamic changes in coal hardness is generated to determine the final coal hardness time series.

3. The dynamic load optimization allocation method for a coal conveying system according to claim 1, characterized in that, In step S102, the step of constructing a nonlinear mapping relationship between coal hardness and the main shaft speed of the crushing equipment using a support vector regression algorithm based on the coal hardness time series includes: preprocessing the coal hardness time series, including checking for missing values ​​and filling in the missing points using linear interpolation, and standardizing the coal hardness time series; constructing a nonlinear mapping relationship between coal hardness and the main shaft speed of the crushing equipment using a support vector regression algorithm, wherein the support vector regression algorithm selects a radial basis function kernel and sets kernel parameters and regularization parameters; optimizing hyperparameters through grid search, training the model of the nonlinear mapping relationship, and determining the optimal kernel parameters and regularization parameters.

4. The dynamic load optimization allocation method for a coal conveying system according to claim 1 or 3, characterized in that, Step S102 further includes: predicting the model of the nonlinear mapping relationship and calculating the prediction error of the model of the nonlinear mapping relationship; if the prediction error of the model of the nonlinear mapping relationship is less than a preset threshold, then extracting the mapping relationship between the spindle speed and coal hardness from the model of the nonlinear mapping relationship and determining the speed adjustment parameters; based on the speed adjustment parameters and combined with the hardness change sequence collected in real time, calculating the target spindle speed value and obtaining the speed adjustment command; adjusting the spindle speed of the crushing equipment through the speed adjustment command and obtaining the adjusted coal hardness time series; if the deviation between the adjusted coal hardness time series and the target hardness range is less than a preset threshold, then determining that the speed adjustment parameters are valid and outputting the final speed adjustment parameters.

5. The dynamic load optimization allocation method for a coal conveying system according to claim 1, characterized in that, In step S105, the step of obtaining the current spindle speed from multiple crushing devices, combining it with the spindle speed adjustment value of a single crushing device, and using a particle swarm optimization algorithm to calculate the difference in spindle speed among multiple crushing devices to obtain the cascade crushing configuration parameters includes: collecting the spindle speed value of each crushing device and storing it as a time series dataset of spindle speed values ​​to obtain a real-time speed dataset; calculating the average spindle speed of each crushing device based on the real-time speed dataset, combining it with a preset speed adjustment value to generate the adjusted speed value of each crushing device to obtain an adjusted speed set; and using the adjusted speed set to calculate the spindle speed among multiple crushing devices. If the difference in spindle speed exceeds a preset threshold, it is marked as an abnormal difference, resulting in a set of speed difference values. This set is then input into the particle swarm optimization algorithm, the number of optimization iterations is set, and the optimal parameters for the cascade crushing configuration are calculated to obtain preliminary configuration parameters. Based on these preliminary configuration parameters and the operating status of the crushing equipment, if the operating status is abnormal, the configuration parameters are corrected to obtain optimized configuration parameters. Using the optimized configuration parameters, the crushing efficiency is calculated to obtain an efficiency evaluation value. If the efficiency evaluation value is lower than a preset threshold, the number of optimization iterations is adjusted, and the particle swarm optimization algorithm is re-executed to obtain the final cascade crushing configuration parameters.

6. The dynamic load optimization allocation method for a coal conveying system according to claim 5, characterized in that, In step S106, adjusting the spindle speed of each crusher according to the cascade crushing configuration parameters, generating a mechanical impact force distribution scheme, and determining the control parameters for the coordinated process of the spindle speeds of each crusher include: determining the initial spindle speed value of each crusher by analyzing the process flow data based on the cascade crushing configuration parameters; analyzing the relationship between the speed and the mechanical impact force using a linear regression algorithm based on the initial spindle speed value to obtain the speed influence coefficient; if the speed influence coefficient exceeds a preset threshold, adjusting the spindle speed value to generate an optimized speed distribution scheme; calculating the mechanical impact force of each crusher using the optimized speed distribution scheme to determine the impact force distribution result; generating the control parameters for the coordinated process of the spindle speeds of each crusher using a particle swarm optimization algorithm based on the impact force distribution result; outputting the final control parameters for the coordinated process of the spindle speeds of each crusher if the control parameters for the coordinated process of the spindle speeds of each crusher meet the process flow constraints, and determining the equipment operating status; obtaining real-time process data based on the equipment operating status, judging whether the speed control accuracy meets the requirements, and updating the control parameters for the coordinated process of the spindle speeds of each crusher.

7. The dynamic load optimization allocation method for a coal conveying system according to claim 6, characterized in that, In step S107, the step of obtaining the response delay value of real-time coal hardness and optimizing the control parameters of the coordinated process of the main shaft speed of each crushing device using the Kalman filter algorithm to obtain the final speed adjustment command includes: acquiring coal hardness through a real-time data acquisition module at a preset sampling frequency to obtain real-time coal hardness; if the real-time coal hardness exceeds a preset threshold, calculating the response delay value of coal hardness through timestamp analysis to determine the delay time sequence; smoothing the delay time sequence using the Kalman filter algorithm to generate a smoothed delay time sequence; adjusting the speed adjustment parameters according to the smoothed delay time sequence to obtain an optimized speed adjustment parameter set; calculating the deviation value between the main shaft speed and the current main shaft speed in the optimized speed adjustment parameter set; if the deviation value exceeds a preset threshold, calculating the speed adjustment amount based on the deviation value to generate a preliminary adjustment command; verifying the preliminary adjustment command through the real-time data acquisition module and updating the adjustment command using a feedback loop mechanism to obtain the final speed adjustment command; updating the control parameters of the coordinated process of the main shaft speed of each crushing device according to the final speed adjustment command to generate a real-time control signal.

8. The dynamic load optimization allocation method for a coal conveying system according to claim 1, characterized in that, In step S108, the step of updating the spindle speeds of multiple crushing devices based on the final speed adjustment command and the speed update time interval to generate a dynamic load optimization allocation scheme includes: obtaining the spindle speed from the crushing devices; if the spindle speed is lower than a preset threshold, adjusting the spindle speed through real-time control signals to obtain the updated spindle speed; using a linear regression algorithm to analyze the relationship between the updated spindle speed and load allocation to determine the optimization target; calculating the load allocation ratio of each crushing device according to the optimization target to obtain a dynamic load allocation scheme; collecting the operating parameters of the crushing devices to determine whether the dynamic load allocation scheme meets the preset conditions; if the load allocation scheme does not meet the preset conditions, using a genetic algorithm to adjust the allocation ratio to obtain a dynamic load optimization allocation scheme.

9. The dynamic load optimization allocation method for a coal conveying system according to claim 8, characterized in that, In step S109, the step of adjusting the operating status of each crushing device using a real-time feedback control method to obtain operating parameters that balance crushing efficiency and energy consumption for the dynamic load optimization allocation scheme includes: collecting crushing device operating parameters and determining the dynamic load of the crushing device; if the dynamic load exceeds a preset threshold, adjusting the crushing device operating parameters through a feedback control algorithm to obtain an optimized device status; calculating the crushing efficiency value based on the optimized device status and determining whether the crushing efficiency value meets a preset standard; if the crushing efficiency value is lower than the preset standard, predicting the energy consumption change trend through a linear regression model to obtain energy consumption adjustment parameters; updating the device status based on the energy consumption adjustment parameters and determining a new load allocation scheme; collecting the updated crushing device operating parameters and determining whether the crushing efficiency value meets a preset standard; if the crushing efficiency value meets the preset standard, determining whether the crushing device has reached energy consumption balance based on the energy consumption change trend; if the crushing device has not reached energy consumption balance, repeating the steps of adjusting the crushing device operating parameters and collecting the crushing device operating parameters until the crushing device reaches energy consumption balance, and obtaining the final operating parameters that balance crushing efficiency and energy consumption.

10. A dynamic load optimization and allocation system for a coal conveying system, characterized in that, The system includes: The dynamic monitoring and data processing module collects coal hardness data in real time and generates a coal hardness time series. The built-in dynamic monitoring and data processing module threshold judgment unit is used to determine whether the hardness change amplitude or hardness change rate exceeds a preset threshold. The rotational speed mapping and calculation module is based on the coal hardness time series and uses the support vector regression algorithm to construct a nonlinear mapping relationship between coal hardness and the main shaft rotational speed of the crushing equipment. The rotational speed mapping and calculation module calculates the adjustment value of the main shaft rotational speed of a single piece of equipment according to the hardness change range and determines the rotational speed update time interval in combination with the hardness change rate. The collaborative optimization and configuration generation module aggregates the current spindle speed data of multiple crushing devices, applies the particle swarm optimization algorithm to calculate the spindle speed difference between multiple devices, generates cascade crushing configuration parameters, and formulates a mechanical impact force distribution scheme accordingly. The instruction optimization and delay compensation module obtains the response delay value of real-time coal hardness, optimizes the cooperative control parameters using a Kalman filter algorithm, and generates the final speed adjustment instruction to eliminate the influence of system response lag. The execution control and feedback module dynamically adjusts the spindle speed of each crushing device according to the final speed adjustment command and update time interval. The execution control and feedback module continuously monitors the operating status of the equipment through the real-time feedback control unit and optimizes the operating parameters that balance crushing efficiency and energy consumption.

Images