A dynamic cooperative control method and system for a multi-stage belt conveyor system of an underground mine

Abstract

The application provides a dynamic cooperative control method and system for a multi-stage belt conveyor system of an underground mine, and relates to the technical field of distributed control, and comprises the following steps: obtaining material monitoring information at a material loading point; using superimposed interference between transmission delay of the material in a transmission process and a material flow fluctuation component to optimize an initial material flow transmission model, so as to obtain a target material flow transmission model; based on the target material flow transmission model, obtaining prediction information of spatial distribution change of the material flow, and using an NSGA-III algorithm to solve the material monitoring information and the prediction information, so as to generate a Pareto optimal solution set covering multiple working conditions, with minimization of total energy consumption of the system and minimization of end output flow fluctuation as optimization objectives; using a state transition model to calculate expected performance indexes of the Pareto optimal solution set under a current prediction working condition, and determining a belt speed control parameter corresponding to the maximum expected performance index as an optimal control strategy of a current control period.

Description

Technical Field

[0001] This invention relates to the field of distributed control technology, and in particular to a dynamic collaborative control method and system for a multi-stage belt conveyor system in an underground mine. Background Technology

[0002] Multi-stage belt conveyor systems are widely used for ore transportation in underground mines. Taking a typical underground mine as an example, after ore is transported from the stope via the mining area conveyor, it passes through multiple stages of equipment, including panel conveyors, stage haulage roadway conveyors, and main shaft conveyors, before finally reaching the surface. These conveyors are connected in a "many-to-one" manner, forming a tree-like convergence structure, which is more common in large underground mines such as potash mines. Due to mining process requirements, the belt conveyors at the stope end typically operate in an intermittent start-stop mode to match the "mining-loading-transporting-unloading" mining process, resulting in pulsed fluctuations in the material flow output to the subsequent panel conveyors. The independent operation of multiple stope conveyors, with their independent start-stop times, operating durations, and conveying distances, causes the originally discrete material flows with different phase characteristics to converge at the same panel conveyor node at different times and connection points during transmission. The resulting new phase difference due to the spatiotemporal differences creates an asynchronous superposition effect, significantly amplifying the fluctuation amplitude. After the "asynchronous superposition effect" of this type of structure amplifies the fluctuation amplitude, the final result in the belt conveyor at the end exhibiting drastic fluctuations in material output, as well as high system energy consumption and drastic fluctuations in equipment power.

[0003] Existing control methods mainly revolve around three technical paths: constant speed operation, reactive local speed regulation, and traditional model predictive control. Constant speed control is simple but lacks system optimization capabilities, resulting in unstable ore production, high system energy consumption, and drastic fluctuations in equipment power. Reactive local speed regulation achieves some energy savings for individual equipment by sensing and adjusting the load of each machine, but lacks overall system coordination. Traditional model predictive control, while possessing rolling optimization capabilities, struggles to balance global optimization and real-time response when faced with conflicting objectives such as energy consumption, stability, and output. Summary of the Invention

[0004] In view of this, the present invention proposes a dynamic collaborative control method and system for a multi-stage belt conveyor system in underground mines.

[0005] The technical solution of this invention is implemented as follows: The first aspect of this invention provides a dynamic collaborative control method for a multi-stage belt conveyor system in underground mines, comprising: Acquire material monitoring information at the material loading point; the material monitoring information includes instantaneous throughput, belt speed data, and time data. An initial material flow transmission model is established based on traveling wave theory. The initial material flow transmission model is then optimized by utilizing the superposition interference between the transmission delay of the material during the transmission process and the material flow fluctuation components of multiple upstream branch conveyors, thereby obtaining the target material flow transmission model. The material monitoring information is input into the target material flow transmission model to obtain the predicted information of material flow rate changes with spatial distribution. With the optimization objectives of minimizing total system energy consumption and minimizing terminal output flow fluctuation, the NSGA-Ⅲ algorithm is used to solve the material monitoring information and the predicted information to generate a Pareto optimal solution set covering multiple operating conditions. The predicted information includes material flow rate distribution, total load change and power fluctuation trend. The expected performance index of each solution in the Pareto optimal solution set under the current predicted operating condition is calculated using the state transition model, and the belt speed control parameter corresponding to the largest expected performance index is determined as the optimal control strategy for the current control cycle.

[0006] Based on the above technical solutions, preferably, the establishment of the initial material flow transport model based on traveling wave theory includes: Using the material loading point as the wave source, the real-time belt speed of the conveyor belt as the wave speed, and the instantaneous flow rate of the material at various locations on the conveyor belt as the amplitude, an initial material flow transmission model characterizing the time-sequential transmission of the material along the conveyor belt is established by combining traveling wave theory.

[0007] Based on the above technical solutions, preferably, the optimization of the initial material flow transmission model by utilizing the superposition interference between the transmission delay of the material during the transmission process and the material flow fluctuation components of multiple upstream branch conveyors to obtain the target material flow transmission model includes: Based on the location information of the upstream branch conveyor connecting to the downstream main conveyor and the belt speed information of each conveyor, the transmission delay experienced by the material on each upstream branch conveyor to reach the same position on the downstream main conveyor is determined. Based on the convergence time and location between the peaks and / or troughs of the material flow of multiple upstream branch conveyors, the superposition interference between the corresponding fluctuation components is determined. The transmission delay and the superposition interference are used to optimize the relationship between the material flow rate and the spatial distribution, so as to obtain the target material flow transmission model.

[0008] Based on the above technical solutions, preferably, the optimization objective is to minimize the total system energy consumption and the fluctuation of the terminal output flow rate. The NSGA-III algorithm is used to solve for the material monitoring information and the prediction information to generate a Pareto optimal solution set covering multiple operating conditions, including: A buffer chamber is introduced between the upstream branch conveyor and the downstream main conveyor; Based on the ore discharge rate of the buffer silo, the first belt speed of the upstream branch conveyor, and the second belt speed of the downstream main conveyor, and with the optimization objectives of minimizing the total energy consumption of the system and minimizing the fluctuation of the terminal output flow, the NSGA-Ⅲ algorithm is used to solve the material monitoring information and the prediction information to generate a Pareto optimal solution set covering multiple operating conditions.

[0009] Based on the above technical solutions, preferably, the optimization objective is to minimize the total system energy consumption and the fluctuation of the terminal output flow rate. The NSGA-III algorithm is used to solve for the material monitoring information and the prediction information to generate a Pareto optimal solution set covering multiple operating conditions, including: Initialize the node population; each individual in the node population corresponds to a set of decision variables for all branch convergence links, and each branch convergence link includes two or more belt conveyors or buffer bin groups. Based on fast non-dominated sorting and reference point mechanism, the diversity of solution set in high-dimensional target space is maintained, and the node population is evolved iteratively through selection, crossover and mutation operations until a preset number of iterations is reached, and at least one uniformly distributed Pareto optimal solution set is output.

[0010] Based on the above technical solutions, preferably, the step of calculating the expected performance index of each solution in the Pareto optimal solution set under the current predicted operating condition using a state transition model, and determining the belt speed control parameter corresponding to the largest expected performance index as the optimal control strategy for the current control cycle, includes: Extract the belt speed control parameters corresponding to each solution from the Pareto optimal solution set; Input the belt speed control parameters and predicted operating conditions of each group into the state transition model, simulate the state evolution process, and calculate the expected performance index corresponding to each solution. The belt speed control parameter corresponding to the expected performance index with the largest value is determined as the optimal control strategy for the current control cycle.

[0011] Based on the above technical solutions, preferably, after determining the belt speed control parameters corresponding to the optimal solution with the highest expected performance index as the optimal control strategy for the current control cycle, the method further includes: Real-time material information is obtained based on sensing and detection equipment deployed downstream of the material loading point; The difference between the real-time material information and the predicted information is determined as the error basis, and the initial value of the predicted information or the Pareto optimal solution set for the next period is adjusted using the error basis.

[0012] Furthermore, a second aspect of the present invention provides a dynamic collaborative control system for a multi-stage belt conveyor system in an underground mine, comprising: an information acquisition module, a model optimization module, a solution set generation module, and a strategy determination module; wherein, The information acquisition module is configured to acquire material monitoring information at the material loading point; the material monitoring information includes instantaneous throughput, belt speed data, and time data. The model optimization module is configured to establish an initial material flow transmission model based on traveling wave theory, and optimize the initial material flow transmission model by utilizing the transmission delay of the material during the transmission process and the superposition interference between the material flow fluctuation components of multiple upstream branch conveyors, so as to obtain the target material flow transmission model. The solution set generation module is configured to input the material monitoring information into the target material flow transmission model, obtain the predicted information of material flow rate changes with spatial distribution, and use the NSGA-Ⅲ algorithm to solve the material monitoring information and the predicted information with the optimization objectives of minimizing the total system energy consumption and minimizing the fluctuation of the terminal output flow rate, to generate a Pareto optimal solution set covering multiple operating conditions; the predicted information includes material flow rate distribution, changes in total transport volume, and power fluctuation trends; The strategy determination module is configured to use a state transition model to calculate the expected performance index of each solution in the Pareto optimal solution set under the current predicted operating condition, and determine the belt speed control parameter corresponding to the largest expected performance index as the optimal control strategy for the current control cycle.

[0013] More preferably, a third aspect of the present invention provides an electronic device, including a processor and a memory; the memory stores a computer program, wherein the computer program, when executed by the processor, implements the dynamic collaborative control method for a multi-stage belt conveyor system in an underground mine as described in the first aspect.

[0014] More preferably, a fourth aspect of the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the dynamic collaborative control method for a multi-stage belt conveyor system in an underground mine as described in the first aspect.

[0015] The dynamic collaborative control method and system for a multi-stage belt conveyor system in underground mines, as proposed in this invention, have the following advantages over existing technologies: 1. By accurately capturing real-time material flow, belt speed, and timing monitoring data, the system builds and optimizes a material flow transmission model based on traveling wave theory. It fully considers material transmission delay and the interference characteristics of multi-branch flow superposition, completely reconstructing the spatial distribution variation of materials along the entire conveying link, and achieving global coordinated control of multi-branch conveyors. Employing the NSGA-Ⅲ multi-objective optimization algorithm, the system solves for the core objectives of minimizing system energy consumption and reducing end-point flow fluctuations, generating Pareto optimal solution sets suitable for various operating conditions. It comprehensively balances multiple mutually constraining indicators such as energy consumption, conveying stability, and material output. Furthermore, it combines state transition models to deduce the actual operating performance of each optimal solution, selecting the optimal belt speed control parameters for the current period. This approach retains the advantages of model predictive control and rolling optimization while also considering global optimal decision-making and real-time on-site response requirements, significantly reducing material flow fluctuations, stabilizing material output efficiency, and ensuring stable and long-term operation of the conveying equipment while achieving system energy saving and consumption reduction.

[0016] 2. By setting up a buffer silo between the upstream branch conveyor and the downstream main conveyor, the system receives materials from multiple upstream branches, buffering instantaneous flow surges. This effectively mitigates disturbances caused by uneven material flow and sudden changes in flow rate from the branch conveyors, preventing system imbalances caused by adjustments to local parameters. This ensures continuous and stable operation of the conveying system while reducing overall energy consumption. Furthermore, by incorporating the buffer silo discharge rate and the belt speeds of different upstream and downstream conveyors into the optimization variables, the control dimensions become more comprehensive, breaking the limitations of single speed regulation and enabling flexible adaptation to the conveying ratio requirements of different material conditions.

[0017] 3. Using the deviation between real-time detection information and prediction information as a correction benchmark, the degree of prediction deviation is intuitively determined, the deviation between model prediction and actual site conditions is accurately located, and the initial prediction value is iteratively corrected and the Pareto optimal solution set is adjusted based on error feedback. This effectively reduces prediction deviation, improves the accuracy of material flow prediction, avoids the problem of fixed solution set and prediction value deviating from actual working conditions, and ensures that control decisions are in line with actual site operation. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a dynamic collaborative control method for a multi-stage belt conveyor system in an underground mine, provided by an embodiment of the present invention; Figure 2 This is a schematic diagram of a conveying scenario using a belt conveyor provided in an embodiment of this application; Figure 3 A schematic diagram of the output waveforms of four upstream conveyors provided in an embodiment of this application; Figure 4 A schematic diagram of the synthesized spatial distribution waveform provided in the embodiments of this application; Figure 5 This is a schematic diagram of the spatial distribution of material flow rate provided in an embodiment of this application; Figure 6 This is a schematic diagram of the connection and convergence of belt conveyors provided in an embodiment of this application; Figure 7 This is a schematic diagram of the comparison curve of the terminal output flow rate under the constant speed strategy provided in the embodiments of this application; Figure 8 This is a schematic diagram of the end-output flow rate comparison curve under the bufferless variable speed strategy provided in the embodiments of this application; Figure 9 This application provides a schematic diagram of the comparison curves of the terminal output flow rate under the variable speed strategy with a buffer chamber. Figure 10 A schematic diagram illustrating the principle of NSGA-Ⅲ and MPC feedback interaction provided for embodiments of this application; Figure 11 This is a schematic diagram of the structure of a dynamic collaborative control system for a multi-stage belt conveyor system in an underground mine, provided by an embodiment of the present invention. Figure 12 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0021] In some embodiments, such as Figure 1 As shown, Figure 1 This is a flowchart illustrating a dynamic collaborative control method for a multi-stage belt conveyor system in an underground mine, provided by an embodiment of the present invention. The dynamic collaborative control method for a multi-stage belt conveyor system in an underground mine, provided by the present invention, includes: S110, acquire material monitoring information at the material loading point; the material monitoring information includes instantaneous flow rate, belt speed data and time data.

[0022] S120. An initial material flow transmission model is established based on traveling wave theory. The initial material flow transmission model is then optimized by utilizing the transmission delay of the material during the transmission process and the superposition interference between the material flow fluctuation components of multiple upstream branch conveyors, thus obtaining the target material flow transmission model.

[0023] S130: Input the material monitoring information into the target material flow transmission model to obtain the predicted information of material flow rate changes with spatial distribution. With the optimization objectives of minimizing the total energy consumption of the system and minimizing the fluctuation of the terminal output flow rate, the NSGA-Ⅲ algorithm is used to solve the material monitoring information and the predicted information to generate a Pareto optimal solution set covering multiple operating conditions. The predicted information includes the material flow rate distribution, the change of the total transport volume, and the power fluctuation trend.

[0024] S140: Calculate the expected performance index of each solution in the Pareto optimal solution set under the current predicted operating condition using the state transition model, and determine the belt speed control parameter corresponding to the largest expected performance index as the optimal control strategy for the current control cycle.

[0025] In this embodiment, using a flow sensor, a speed measuring device, and a time-series acquisition module, three types of basic data can be collected in real time at the initial material loading position: instantaneous material flow rate, real-time conveyor speed, and corresponding timestamps, serving as material monitoring information. The material conveying process on the belt is equated to wave propagation, establishing an initial material flow transmission model. Considering the fixed time difference between upstream and downstream material transport, this lag directly affects flow matching and control timing. Furthermore, the material inflow from multiple upstream branches couples and disturbs each other; fluctuations from a single branch can propagate to the entire link. Therefore, the material transport time delay effect and the interference characteristics of multiple upstream branch flow fluctuations are introduced to optimize the initial material flow transmission model, resulting in the target material flow transmission model.

[0026] This embodiment incorporates the principle of multi-objective optimization. Considering that minimizing energy consumption and maintaining stable flow are conflicting objectives with no single globally optimal solution, and given that the NSGA-III algorithm possesses excellent multi-objective parallel optimization capabilities, it can solve multiple sets of equilibrium compromise solutions within constraints. Therefore, the NSGA-III algorithm is used to solve for material monitoring and prediction information, generating a Pareto optimal solution set covering multiple operating conditions. All solutions in this set cannot improve one objective without compromising the other, covering all operating conditions such as high and low loads and varying flow rates, providing ample candidate solutions for subsequent decision-making.

[0027] By calling the state transition model, the operation process of each control scheme in the Pareto solution set under the predicted operating condition is simulated. The expected comprehensive performance index of each scheme is quantitatively calculated, and the solution with the highest index value is selected. Its corresponding belt speed control parameters are used as the final execution strategy for this control cycle.

[0028] In some embodiments, an initial material flow transport model is established based on traveling wave theory, including: Using the material loading point as the wave source, the real-time belt speed of the conveyor belt as the wave speed, and the instantaneous flow rate of the material at various locations on the conveyor belt as the amplitude, an initial material flow transmission model characterizing the time-sequential transmission of the material along the conveyor belt is established by combining traveling wave theory.

[0029] In this embodiment, the material transport process on the belt conveyor is abstracted as a one-dimensional traveling wave, with the wave source being the material loading point, the wave velocity being the real-time belt speed, and the amplitude being the instantaneous flow rate of the material at various positions on the conveyor. The initial material flow transport model can be represented as: ; in, Let x be the material flow rate at time t and location x. The instantaneous throughput of the monitoring point. For belt speed.

[0030] In some embodiments, the initial material flow transport model is optimized by utilizing the superposition interference between the transport delay of the material during the transport process and the material flow fluctuation components of multiple upstream branch conveyors to obtain the target material flow transport model, including: Based on the location information of the upstream branch conveyor connecting to the downstream main conveyor and the belt speed information of each conveyor, the transmission delay experienced by the material on each upstream branch conveyor to reach the same position on the downstream main conveyor is determined. Based on the convergence time and location between the peaks and / or troughs of the material flow of multiple upstream branch conveyors, the superposition interference between the corresponding fluctuation components is determined. By optimizing the relationship between material flow rate and spatial distribution using transmission delay and superposition interference, a target material flow transmission model is obtained.

[0031] In this embodiment, taking a multi-level "many-to-one" tree-like convergence structure as an example, the downstream main conveyor simultaneously receives material input from multiple upstream branch conveyors. Because the upstream branch equipment connects to the downstream main equipment at different locations and their respective belt speeds are independent, each material stream experiences different transmission time delays when reaching the same downstream location. Therefore, the material flow rate at any location on the downstream main conveyor is the delayed superposition of the historical output flow rates of all upstream branch conveyors. That is, the initial material flow transmission model of the k-th and j-th belt conveyors in the system evolves as follows: ; in, For the set of upstream devices connected to the k-th level, For transmission time delay, This is an indicator function representing the traffic contribution of the segment following this store, where i is the device number.

[0032] In one example, see Figure 2 , Figure 2 This is a schematic diagram of a belt conveyor conveying scenario provided in an embodiment of this application. Taking ore transportation in various large underground mines such as potash mines as an example, after the ore is mined from the working face, it is distributed to multiple parallel working face belt conveyors. From the working face to the main output, the ore flow undergoes multiple merging processes, and the flow fluctuations of multiple branches are transmitted and amplified step by step, significantly affecting the stability at the end. At the same time, there is a significant transmission delay due to the relay of multiple belt segments.

[0033] The output traffic (time-domain waveform) of each upstream device is converted into a spatially distributed waveform on the downstream device through its respective transmission delay, and then linearly superimposed. See here for more information. Figure 3 and Figure 4 ; Figure 3 A schematic diagram of the output waveforms of four upstream conveyors provided in an embodiment of this application; Figure 4 This is a schematic diagram of the synthesized spatial distribution waveform provided in an embodiment of this application. A1-1, A1-2, A2-1, and A2-2 are the numbers of the four upstream conveyors, respectively. The relationship between material flow rate and spatial distribution can be found in [reference needed]. Figure 5 .

[0034] The output flow of each upstream device is decomposed into an average component. With fluctuation components The average component determines the total capacity, while the fluctuation component characterizes the instantaneous amplitude of change. At the convergence node, due to the differences in transmission delays among the upstream branches, the phases of each fluctuation component are randomly distributed. When multiple wave crests arrive simultaneously due to their close phases, constructive interference occurs, and the fluctuation is amplified; when a wave crest meets a wave trough, destructive interference occurs, and the fluctuation is suppressed. To describe this effect, a fluctuation amplification factor is defined. : ; Wherein, the numerator is the variance of the downstream synthesis flow rate at position x, and the denominator is the sum of the variances of the output flow rates of each upstream branch. Asynchronous superposition indicates that the overall effect is constructive, and fluctuations are amplified; it also indicates that fluctuations are suppressed.

[0035] In an alternative embodiment, please refer to Figure 6 , Figure 6This is a schematic diagram of the belt conveyor connection and convergence provided in the embodiments of this application. Considering that the complexity of the underground mine transportation system is mainly reflected in its "tree-like convergence" topology, at key nodes such as "mining area-panel" or "panel-stage", there is a common "multiple-to-one" structure in which multiple upstream equipment / branches converge into a single downstream equipment / main line. In such a "multiple-to-one" belt conveyor connection structure, taking the combined structure of 4 upstream (A1 / A2 / A3 / A4) and 1 downstream (B1) belt conveyor as an example, the ore load at any point on the downstream main line equipment (B1) is the result of the ore flow output by all upstream branch equipment (A1 / A2 / A3 / A4) at different historical moments, after different time delays, and finally the combined effect at that point.

[0036] Connect the upstream device to its access point on the downstream device B1. Considered as downstream equipment at point A separate wave source. Upstream equipment. The output of the ore flow follows the single-machine traveling wave equation, while the real-time total ore flow rate at any point x in the downstream device B1 is... The linear superposition of contributions from all upstream devices connected to it is given by the general formula: ; In the formula, Characterizing upstream equipment The output flow rate of the ore stream at the end, i.e., the intensity of the wave source, , Characterizing ore in B1 equipment from upstream equipment Access point The time taken to transport goods to point x, in seconds, is determined by the belt speed history of B1. .

[0037] in, Characterizing indicator functions, when A value of 1 indicates the upstream device is active, while a value of 0 indicates it is active. It contributes to the ore flow rate in the corresponding section of downstream equipment B1.

[0038] The physical essence of this synthesis equation is to transform the outputs of upstream devices into internal wave sources on downstream devices through spatiotemporal coordinate transformation, revealing how multiple independent wave sources collectively shape the load distribution of downstream devices. It should be noted that the above synthesis model for "multiple-to-one" nodes can be further extended to the entire multi-stage belt conveyor tree-like convergence system. For any node device in the system, its load can be formed by the superposition of the contributions of all its upstream devices. Therefore, a general traveling wave equation for the system is defined.

[0039] In some embodiments, with the optimization objectives of minimizing total system energy consumption and minimizing terminal output flow fluctuations, the NSGA-III algorithm is used to solve for material monitoring and prediction information, generating a Pareto optimal solution set covering multiple operating conditions, including: A buffer chamber is introduced between the upstream branch conveyor and the downstream main conveyor; Based on the ore discharge rate of the buffer bin, the first belt speed of the upstream branch conveyor, and the second belt speed of the downstream main conveyor, and with the optimization objectives of minimizing the total energy consumption of the system and minimizing the fluctuation of the terminal output flow, the NSGA-Ⅲ algorithm is used to solve the material monitoring information and prediction information to generate a Pareto optimal solution set covering multiple working conditions.

[0040] In this embodiment, for a system without a buffer bin, the decision variable is the real-time belt speed of each stage of the belt conveyor, forming a belt speed vector. The belt speed of each conveyor meets the requirements. .

[0041] For systems that add buffers at key convergence nodes, the decision variables are expanded into a joint vector. For the ore discharge rate of each buffer bin, satisfy .

[0042] The dynamic model of the buffer can be represented as: ; in, Real-time storage capacity in the warehouse For feed flow rate, The decision variables for the multi-objective optimization problem are extended to a joint vector of belt speed and ore discharge rate. The constraints also include buffer storage capacity constraints and ore discharge rate constraints.

[0043] With the introduction of buffer silos, the material flow relationship of the system undergoes a fundamental change: the material output from the upstream branch conveyor no longer directly enters the downstream main conveyor, but instead first enters the corresponding buffer silo. The material source for the downstream main conveyor is the ore discharge output from each buffer silo.

[0044] At this point, the original traveling wave equation for the downstream ore flow convergence, i.e., the target material flow transmission model, changes after the integration of the buffer silo: ; The convergence node receives ore input from upstream sources from uncontrollable historical outputs. This has been transformed into a historical ore discharge rate that can be controlled by the buffer. At this point, the control variable is expanded to be the joint vector of the ore discharge rate from the buffer bin and the belt speed of the belt conveyor. This increases the system's optimization freedom. By actively adjusting the ore discharge rate, large fluctuations in intermittent upstream input can be "shaped" within a buffer zone and then released downstream at a stable rate, thereby cutting off the direct transmission path of fluctuations and fundamentally suppressing asynchronous superposition effects. Please refer to [link / reference here]. Figure 7 , Figure 8 and Figure 9 , Figure 7 This is a schematic diagram showing the comparison curves of the terminal output flow rate under the constant speed strategy provided in the embodiments of this application. Figure 8 This is a schematic diagram showing the comparison curves of the terminal output flow rate under the bufferless variable speed strategy provided in the embodiments of this application. Figure 9 This is a schematic diagram of the comparison curves of the terminal output flow rate under the variable speed strategy with buffer bins provided in the embodiments of this application.

[0045] The primary optimization objective is to minimize the total system energy consumption. ; in, Let be the instantaneous power of the i-th belt conveyor.

[0046] The second optimization objective is to minimize the fluctuation of the terminal output flow rate. coefficient of variation express: ; Simultaneously set production output constraints: ; Belt speed constraint: ; Power constraints: ; in, The standard deviation of the terminal output flow rate. This represents the average value of the terminal output flow rate. and These are the minimum belt speed and the maximum belt speed, respectively. This is the rated power.

[0047] In some embodiments, with the optimization objectives of minimizing total system energy consumption and minimizing terminal output flow fluctuations, the NSGA-III algorithm is used to solve for material monitoring and prediction information, generating a Pareto optimal solution set covering multiple operating conditions, including: Initialize the node population; each individual in the node population corresponds to a set of decision variables for all branch convergence links. Each branch convergence link includes two or more belt conveyors or buffer bin groups. Based on fast non-dominated sorting and reference point mechanism, the diversity of solution set in high-dimensional target space is maintained, and the node population is evolved iteratively through selection, crossover and mutation operations until the preset number of iterations is reached, and at least one uniformly distributed Pareto optimal solution set is output.

[0048] In this embodiment, considering the relatively long time window for material transfer from the input end to the output end, NSGA-Ⅲ can utilize this window to search for globally optimal operating conditions in advance, generating a set of evenly distributed Pareto optimal solutions as a forward-looking reference library for the lower-level MPC, providing a set of candidate optimal strategies with a global perspective for real-time control. Specifically, the upper-level NSGA-Ⅲ, as an offline global optimization layer, uses real-time monitoring data from the stope input end (i.e., material loading point) and a traveling wave model to make forward-looking predictions of the material flow distribution of each level of conveyor over a future period, with the optimization objectives of minimizing total system energy consumption and minimizing the fluctuation of the output flow at the end, generating a Pareto optimal solution set covering multiple operating conditions offline. The lower-level MPC, as an online rolling control layer, predicts the system state in the short future time domain based on the current system state (real-time operating conditions of each level of conveyor, buffer bin position, etc.) and the traveling wave model within each control cycle; it selects the control strategy that best matches the current predicted operating condition from the Pareto solution set generated by the upper layer, generates control commands, and issues them for execution. The upper and lower layers exchange information through Pareto solution sets. The upper layer provides the lower layer with a library of candidate optimal solutions under the global perspective, while the lower layer provides the upper layer with actual operational feedback, which is used to predict initial value corrections and trigger solution set updates.

[0049] In an alternative embodiment, please refer to Figure 10 , Figure 10This is a schematic diagram illustrating the principle of NSGA-Ⅲ and MPC feedback interaction provided in this application embodiment. Input monitoring data (inlet / outlet of the belt conveyor in the mining area) serves as the input for NSGA-Ⅲ offline optimization, driving the traveling wave model to perform forward-looking predictions. This fully utilizes the inherent time window (several minutes to tens of minutes) of material transfer from the input to the end, achieving pre-optimization before disturbances occur. Subsequent monitoring data (each level of conveyor, buffer silo) serves as the feedback basis for MPC online control. Within each control cycle, MPC predicts future states based on the current real-time operating conditions and corrects the initial prediction value for the next cycle based on the deviation between the actual output and the predicted value. Upstream and downstream monitoring data achieve precise spatiotemporal correlation through the system topology model: the output of the upstream equipment at a certain historical moment becomes the input of the downstream equipment at the current moment after transmission delay. Therefore, the historical cycle data of the upstream equipment is the feedforward basis for the current control decision of the downstream equipment; the current cycle data of the downstream equipment is the feedback calibration source for the future control strategy of the upstream equipment. This characteristic determines that NSGA-Ⅲ is suitable for handling forward-looking optimization over long time spans, corresponding to input data, while MPC is suitable for handling rolling matching and closed-loop correction in short time domains, corresponding to subsequent stage data.

[0050] In some embodiments, the expected performance index of each solution in the Pareto optimal solution set under the current predicted operating condition is calculated using a state transition model, and the belt speed control parameter corresponding to the largest expected performance index is determined as the optimal control strategy for the current control cycle, including: Extract the belt speed control parameters corresponding to each solution from the Pareto optimal solution set; Input each set of belt speed control parameters and predicted operating conditions into the state transition model, simulate the state evolution process, and calculate the expected performance index corresponding to each solution. The belt speed control parameter corresponding to the expected performance index with the largest value is determined as the optimal control strategy for the current control cycle.

[0051] In some embodiments, after determining the belt speed control parameters corresponding to the optimal solution with the highest expected performance index as the optimal control strategy for the current control cycle, the method further includes: Real-time material information is obtained based on sensing and detection equipment deployed downstream of the material loading point; The difference between real-time material information and forecast information is used as the basis for error, and the initial value of forecast information or Pareto optimal solution set for the next period is adjusted based on the error basis.

[0052] In this embodiment, considering the spatiotemporal characteristics of material transport in a multi-stage belt conveyor system, the offline-generated forward-looking reference library must be verified and corrected based on the actual transport status. The spatial transport process of materials is accompanied by real-time factors such as changes in equipment belt speed and silo position fluctuations, resulting in a deviation between the actual material flow status reaching the downstream and the offline prediction. Therefore, a two-layer feedback closed loop is established based on the real-time transport status: short-term feedback MPC rolling correction and long-term feedback NSGA-Ⅲ solution set update.

[0053] The actual operating data collected in each control cycle is compared with the predicted value of the previous cycle to calculate the prediction deviation. This deviation is used to correct the initial prediction value for the next cycle, improving prediction accuracy. A cumulative prediction deviation threshold is set. When the terminal flow fluctuation continues to exceed the allowable range, or the cumulative deviation of output exceeds a preset proportion, it is determined that the current operating condition has significantly deviated from the assumptions of offline optimization. At this time, NSGA-III is triggered to re-solve offline, updating the model parameters based on recently collected operating data, generating a Pareto optimal solution set adapted to the new operating condition, and replacing the original solution set for subsequent online control.

[0054] In one optional embodiment, taking the first mining panel of an underground potash mine as an example, a four-stage belt conveyor structure is adopted: Level 1 consists of four stope conveyors (A1-1, A1-2, A2-1, A2-2), Level 2 consists of one panel conveyor, Level 3 consists of one buffer conveyor (C1), and Level 4 consists of one main hoisting conveyor (D1). The equipment parameters are shown in Table 1.

[0055] Table 1 Belt Conveyor System Configuration Table

[0056] Taking a Level 2 device as an example, its inlet material flow comes from the output of four Level 1 devices. Because each Level 1 device connects to the conveyor belt at different locations (0m, 8m, 250m, and 258m respectively), and their belt speeds are independent and do not interfere with each other, the output material flow arrives at the same location on the conveyor belt after varying time delays. The optimization objectives are to minimize total system energy consumption and minimize fluctuations in the final output flow. The production constraint is set at a daily output of no less than 20,700 tons (corresponding to an annual capacity of 6.8 million tons). The belt speed constraint is 1.0–5.0 m / s, and the power constraint is no more than the rated power of each device.

[0057] The NSGA-III algorithm is employed, with a population size of 100 and 80 iterations. The das-dennis method is used to generate the reference direction, and the objective function has three dimensions (energy consumption, stability, and output). The number of partitions is set to 12. The algorithm outputs a uniformly distributed set of Pareto optimal solutions, with each solution corresponding to a set of belt speed control strategies. In each control cycle (every 300 seconds), the MPC controller predicts the system state for the next 30 minutes based on the current system state and the dynamic model. From the Pareto solution set generated by NSGA-III, the belt speed control strategy that best matches the current predicted operating condition is selected, control commands are generated, and issued to each conveyor actuator.

[0058] The actual operating data (real-time power, terminal flow) is compared with the predicted values ​​to correct the initial prediction value for the next cycle. When the cumulative deviation exceeds the preset threshold (e.g., terminal flow fluctuations are consistently higher than 20%), NSGA-III is triggered to perform offline solving again and update the Pareto solution set.

[0059] In the simulation test of the 3+3 shuttle configuration (i.e., 3 shuttles each in the A1 and A2 panels), under the constraint of a daily output of 20,700 tons, the coefficient of variation of the terminal output flow rate decreased from 26.58% in the constant speed strategy to 14.05%, the proportion of stable operation range increased from 31.48% to 87.06%, and the total energy consumption of the system was reduced by about 44%.

[0060] In an optional embodiment, based on the previous embodiment, a buffer chamber is added at the convergence node between Level 1 and Level 2, and the belt conveyor and the buffer chamber together constitute a branch control unit. The control variable is expanded to a joint vector of belt speed and ore discharge rate. The buffer silo capacity is set at 1000 tons, the minimum storage capacity is 100 tons, the ore discharge rate ranges from 322 to 1287.9 ​​t / h, and the response time constant is set at 60 seconds. The decision variable dimensions for NSGA-Ⅲ are increased accordingly, and new constraints on storage capacity and ore discharge rate are added.

[0061] Under the same feeding conditions, the introduction of the buffer bin further enhances the system's adaptability to feeding fluctuations: with a 3+3 shuttle configuration, the system can meet the production requirements, the proportion of stable operation at the end increases to 91.72%, and the fluctuation amplification factor decreases from 1.28 in Example 1 to 1.03. Under a lower feeding condition (3+2 / 2+3 shuttle configuration), the system can increase production from below capacity (approximately 95%) to above capacity (103%) to meet production requirements; under the lowest feeding condition and a 2+2 shuttle configuration, the system output gap is reduced from 17% when using pure belt speed optimization to less than 5%, with significant improvements in both energy efficiency and stability.

[0062] In some embodiments, please refer to Figure 11 , Figure 11This is a schematic diagram of the structure of a dynamic collaborative control system for a multi-stage belt conveyor system in an underground mine, provided by an embodiment of the present invention. The present invention provides a dynamic collaborative control system 1100 for a multi-stage belt conveyor system in an underground mine, comprising: an information acquisition module 1110, a model optimization module 1120, a solution set generation module 1130, and a strategy determination module 1140; wherein, The information acquisition module 1110 is configured to acquire material monitoring information at the material loading point; the material monitoring information includes instantaneous flow rate, belt speed data and time data. The model optimization module 1120 is configured to establish an initial material flow transmission model based on traveling wave theory, and optimize the initial material flow transmission model by utilizing the transmission delay of the material during the transmission process and the superposition interference between the material flow fluctuation components of multiple upstream branch conveyors, so as to obtain the target material flow transmission model. The solution set generation module 1130 is configured to input material monitoring information into the target material flow transmission model, obtain prediction information of material flow rate changes with spatial distribution, and use the NSGA-Ⅲ algorithm to solve the material monitoring information and prediction information with the optimization objectives of minimizing the total system energy consumption and minimizing the fluctuation of the terminal output flow rate, so as to generate a Pareto optimal solution set covering multiple operating conditions; the prediction information includes material flow rate distribution, total load change and power fluctuation trend; The strategy determination module 1140 is configured to use the state transition model to calculate the expected performance index of each solution in the Pareto optimal solution set under the current predicted operating condition, and determine the belt speed control parameter corresponding to the largest expected performance index as the optimal control strategy for the current control cycle.

[0063] In some embodiments, the model optimization module 1120 is specifically configured as follows: Using the material loading point as the wave source, the real-time belt speed of the conveyor belt as the wave speed, and the instantaneous flow rate of the material at various locations on the conveyor belt as the amplitude, an initial material flow transmission model characterizing the time-sequential transmission of the material along the conveyor belt is established by combining traveling wave theory.

[0064] In some embodiments, the model optimization module 1120 is specifically configured as follows: Based on the location information of the upstream branch conveyor connecting to the downstream main conveyor and the belt speed information of each conveyor, the transmission delay experienced by the material on each upstream branch conveyor to reach the same position on the downstream main conveyor is determined. Based on the convergence time and location between the peaks and / or troughs of the material flow of multiple upstream branch conveyors, the superposition interference between the corresponding fluctuation components is determined. By utilizing transmission delay and superposition interference, the relationship between material flow rate and spatial distribution is optimized to obtain the target material flow transmission model.

[0065] In some embodiments, the solution set generation module 1130 is specifically configured as follows: A buffer chamber is introduced between the upstream branch conveyor and the downstream main conveyor; Based on the ore discharge rate of the buffer bin, the first belt speed of the upstream branch conveyor, and the second belt speed of the downstream main conveyor, and with the optimization objectives of minimizing the total energy consumption of the system and minimizing the fluctuation of the terminal output flow, the NSGA-Ⅲ algorithm is used to solve the material monitoring information and prediction information to generate a Pareto optimal solution set covering multiple working conditions.

[0066] In some embodiments, the solution set generation module 1130 is specifically configured as follows: Initialize the node population; each individual in the node population corresponds to a set of decision variables for all branch convergence links. Each branch convergence link includes two or more belt conveyors or buffer bin groups. Based on fast non-dominated sorting and reference point mechanism, the diversity of solution set in high-dimensional target space is maintained, and the node population is evolved iteratively through selection, crossover and mutation operations until the preset number of iterations is reached, and at least one uniformly distributed Pareto optimal solution set is output.

[0067] In some embodiments, the policy determination module 1140 is specifically configured as follows: Extract the belt speed control parameters corresponding to each solution from the Pareto optimal solution set; Input each set of belt speed control parameters and predicted operating conditions into the state transition model, simulate the state evolution process, and calculate the expected performance index corresponding to each solution. The belt speed control parameter corresponding to the expected performance index with the largest value is determined as the optimal control strategy for the current control cycle.

[0068] In some embodiments, the dynamic collaborative control system for a multi-stage belt conveyor system in an underground mine further includes a feedback adjustment module; the feedback adjustment module is specifically configured as follows: Real-time material information is obtained based on sensing and detection equipment deployed downstream of the material loading point; The difference between real-time material information and forecast information is used as the basis for error, and the initial value of forecast information or Pareto optimal solution set for the next period is adjusted based on the error basis.

[0069] It should be noted that the dynamic collaborative control system for underground mine multi-stage belt conveyor system provided in this application embodiment and the dynamic collaborative control method for underground mine multi-stage belt conveyor system provided in this application embodiment are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned dynamic collaborative control method for underground mine multi-stage belt conveyor system, and the repeated parts will not be described again.

[0070] In some embodiments, please refer to Figure 12 , Figure 12 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 1200 provided in this application includes a processor 1210 and a memory 1220; the memory 1220 stores a computer program, wherein the computer program, when executed by the processor, implements the aforementioned dynamic collaborative control method for a multi-stage belt conveyor system in underground mines.

[0071] Specifically, processor 1210 may include, for example, a general-purpose microprocessor, an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. Processor 1210 may also include onboard memory for caching purposes. Processor 1210 may be a single processing unit or multiple processing units for performing different actions of the method flow according to embodiments of this application.

[0072] The memory 1220 may be any medium capable of containing, storing, transmitting, propagating, or transmitting instructions. For example, the memory 1220 may include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, instruments, or propagation media. Specific examples of the memory 1220 include: magnetic storage devices such as magnetic tape or hard disk drives (HDDs); optical storage devices such as optical discs (CD-ROMs); and may also be random access memory (RAM) or flash memory; and / or wired / wireless communication links.

[0073] This application also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, this program implements the aforementioned dynamic coordinated control method for a multi-stage belt conveyor system in underground mines. This computer-readable medium may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into that device / apparatus / system. The aforementioned computer-readable medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0074] According to embodiments of this application, a computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wired, optical fiber, radio frequency signals, etc., or any suitable combination thereof.

[0075] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this application. In particular, the features described in the various embodiments and / or claims of this application can be combined and / or combined in various ways without departing from the spirit and teachings of this application. All such combinations and / or combinations fall within the scope of this application. Therefore, the scope of this application should not be limited to the above embodiments, but should be defined not only by the appended claims, but also by their equivalents. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should be included within the protection scope of this invention.

Claims

1. A dynamic collaborative control method for a multi-stage belt conveyor system in underground mines, characterized in that, include: Acquire material monitoring information at the material loading point; the material monitoring information includes instantaneous throughput, belt speed data, and time data. An initial material flow transmission model is established based on traveling wave theory. The initial material flow transmission model is then optimized by utilizing the superposition interference between the transmission delay of the material during the transmission process and the material flow fluctuation components of multiple upstream branch conveyors, thereby obtaining the target material flow transmission model. The target material flow transport model changes after integrating the buffer silo as follows: ； in, Let t be the set of upstream devices connected to the k-th level. For transmission time delay, The indicator function represents the flow contribution of the segment after this point, where i is the equipment number, x is the location, and u is the ore discharge rate; The material monitoring information is input into the target material flow transport model to obtain predicted information on the spatial distribution of material flow. With the optimization objectives of minimizing total system energy consumption and minimizing terminal output flow fluctuations, the NSGA-III algorithm is used to solve for the material monitoring information and the predicted information, generating a Pareto optimal solution set covering multiple operating conditions. The predicted information includes material flow distribution, changes in total transport volume, and power fluctuation trends. The optimization objectives of minimizing total system energy consumption and minimizing terminal output flow fluctuations include: The primary optimization objective is to minimize the total system energy consumption. ； in, Let be the instantaneous power of the i-th belt conveyor, and T be the total transmission time; The second optimization objective is to minimize the fluctuation of the terminal output flow rate. coefficient of variation express: ； Simultaneously set production output constraints: ; Belt speed constraint: ; Power constraints: ; in, The standard deviation of the terminal output flow rate. This represents the average value of the terminal output flow rate. and These are the minimum belt speed and the maximum belt speed, respectively. Rated power; The expected performance index of each solution in the Pareto optimal solution set under the current predicted operating condition is calculated using the state transition model, and the belt speed control parameter corresponding to the largest expected performance index is determined as the optimal control strategy for the current control cycle.

2. The dynamic collaborative control method for a multi-stage belt conveyor system in underground mines as described in claim 1, characterized in that, The initial material flow transport model established based on traveling wave theory includes: Using the material loading point as the wave source, the real-time belt speed of the conveyor belt as the wave speed, and the instantaneous flow rate of the material at various locations on the conveyor belt as the amplitude, an initial material flow transmission model characterizing the time-sequential transmission of the material along the conveyor belt is established by combining traveling wave theory.

3. The dynamic collaborative control method for a multi-stage belt conveyor system in underground mines as described in claim 2, characterized in that, The optimization of the initial material flow transmission model by utilizing the superposition interference between the transmission delay of materials during the transmission process and the material flow fluctuation components of multiple upstream branch conveyors yields the target material flow transmission model, including: Based on the location information of the upstream branch conveyor connecting to the downstream main conveyor and the belt speed information of each conveyor, the transmission delay experienced by the material on each upstream branch conveyor to reach the same position on the downstream main conveyor is determined. Based on the convergence time and location between the peaks and / or troughs of the material flow of multiple upstream branch conveyors, the superposition interference between the corresponding fluctuation components is determined. The transmission delay and the superposition interference are used to optimize the relationship between the material flow rate and the spatial distribution, so as to obtain the target material flow transmission model.

4. The dynamic collaborative control method for a multi-stage belt conveyor system in underground mines as described in claim 1, characterized in that, The optimization objectives are to minimize total system energy consumption and minimize terminal output flow fluctuations. The NSGA-III algorithm is used to solve for the material monitoring information and the prediction information, generating a Pareto optimal solution set covering multiple operating conditions, including: A buffer chamber is introduced between the upstream branch conveyor and the downstream main conveyor; Based on the ore discharge rate of the buffer silo, the first belt speed of the upstream branch conveyor, and the second belt speed of the downstream main conveyor, and with the optimization objectives of minimizing the total energy consumption of the system and minimizing the fluctuation of the terminal output flow, the NSGA-Ⅲ algorithm is used to solve the material monitoring information and the prediction information to generate a Pareto optimal solution set covering multiple operating conditions.

5. The dynamic collaborative control method for a multi-stage belt conveyor system in underground mines as described in claim 1, characterized in that, The optimization objectives are to minimize total system energy consumption and minimize terminal output flow fluctuations. The NSGA-III algorithm is used to solve for the material monitoring information and the prediction information, generating a Pareto optimal solution set covering multiple operating conditions, including: Initialize the node population; each individual in the node population corresponds to a set of decision variables for all branch convergence links, and each branch convergence link includes two or more belt conveyors or buffer bin groups. Based on fast non-dominated sorting and reference point mechanism, the diversity of solution set in high-dimensional target space is maintained, and the node population is evolved iteratively through selection, crossover and mutation operations until a preset number of iterations is reached, and at least one uniformly distributed Pareto optimal solution set is output.

6. The dynamic collaborative control method for a multi-stage belt conveyor system in underground mines as described in claim 1, characterized in that, The step of calculating the expected performance index of each solution in the Pareto optimal solution set under the current predicted operating condition using a state transition model, and determining the belt speed control parameter corresponding to the largest expected performance index as the optimal control strategy for the current control cycle includes: Extract the belt speed control parameters corresponding to each solution from the Pareto optimal solution set; Input the belt speed control parameters and predicted operating conditions of each group into the state transition model, simulate the state evolution process, and calculate the expected performance index corresponding to each solution. The belt speed control parameter corresponding to the expected performance index with the largest value is determined as the optimal control strategy for the current control cycle.

7. The dynamic collaborative control method for a multi-stage belt conveyor system in underground mines as described in claim 1, characterized in that, After determining the belt speed control parameters corresponding to the optimal solution with the highest expected performance index as the optimal control strategy for the current control cycle, the method further includes: Real-time material information is obtained based on sensing and detection equipment deployed downstream of the material loading point; The difference between the real-time material information and the predicted information is determined as the error basis, and the initial value of the predicted information or the Pareto optimal solution set for the next period is adjusted using the error basis.

8. A dynamic collaborative control system for a multi-stage belt conveyor system in underground mines, characterized in that, include: The module comprises an information acquisition module, a model optimization module, a solution set generation module, and a policy determination module; among which, The information acquisition module is configured to acquire material monitoring information at the material loading point; the material monitoring information includes instantaneous throughput, belt speed data, and time data. The model optimization module is configured to establish an initial material flow transmission model based on traveling wave theory, and optimize the initial material flow transmission model by utilizing the transmission delay of materials during transmission and the superposition interference between the material flow fluctuation components of multiple upstream branch conveyors, to obtain the target material flow transmission model; the target material flow transmission model is changed after integrating the buffer bin as follows: ;in, Let t be the set of upstream devices connected to the k-th level. For transmission time delay, The indicator function represents the flow contribution of the segment after this point, where i is the equipment number, x is the location, and u is the ore discharge rate; The solution set generation module is configured to input the material monitoring information into the target material flow transmission model, obtain predicted information on the spatial distribution of material flow, and use the NSGA-III algorithm to solve for the material monitoring information and the predicted information with the optimization objectives of minimizing total system energy consumption and minimizing terminal output flow fluctuation, thereby generating a Pareto optimal solution set covering multiple operating conditions. The predicted information includes material flow distribution, changes in total transport volume, and power fluctuation trends. The optimization objectives of minimizing total system energy consumption and minimizing terminal output flow fluctuation include: The primary optimization objective is to minimize the total system energy consumption. ； in, Let be the instantaneous power of the i-th belt conveyor, and T be the total transmission time; The second optimization objective is to minimize the fluctuation of the terminal output flow rate. coefficient of variation express: ； Simultaneously set production output constraints: ; Belt speed constraint: ; Power constraints: ; in, The standard deviation of the terminal output flow rate. This represents the average value of the terminal output flow rate. and These are the minimum belt speed and the maximum belt speed, respectively. Rated power; The strategy determination module is configured to use a state transition model to calculate the expected performance index of each solution in the Pareto optimal solution set under the current predicted operating condition, and determine the belt speed control parameter corresponding to the largest expected performance index as the optimal control strategy for the current control cycle.

9. An electronic device, characterized in that, It includes a processor and a memory; the memory stores a computer program, wherein the computer program, when executed by the processor, implements the dynamic collaborative control method for a multi-stage belt conveyor system in an underground mine as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that, It stores a computer program, wherein when the computer program is executed by a processor, it implements the dynamic collaborative control method for a multi-stage belt conveyor system in an underground mine as described in any one of claims 1 to 7.

Images