Operation control method and system for stacker-reclaimer

Abstract

The invention provides a stacker-reclaimer operation control method and system, and relates to the technical field of stacker operation planning, and the method comprises the steps: obtaining first information and second information; performing dynamic partitioning processing according to the first information to obtain a job block model; performing task allocation processing according to the job block model and the second information to obtain a task priority; operation parameter optimization processing is carried out according to the task priority, and operation parameters are obtained by predicting dynamic deformation of materials in the operation process; performing energy efficiency optimization analysis according to the operation parameters, and decomposing the operation process into a plurality of sub-chains to obtain energy efficiency optimization parameters; according to the energy efficiency optimization parameters and the task priority order, work plan making processing is carried out, and a final work scheme is obtained by comprehensively analyzing priority blocks and the optimal energy consumption path. According to the invention, the operation efficiency is improved, the energy consumption is reduced, the service life of equipment is prolonged, and an intelligent and efficient solution is provided for industrial material carrying.

Description

Technical Field

[0001] The present invention relates to the technical field of stacker operation planning, and in particular to a stacker-reclaimer operation control method and system. Background Art

[0002] In modern industrial and mining production, the widespread use of stackers and reclaimers has put forward higher requirements on the efficiency and accuracy of material stacking and reclaiming. At present, stackers and reclaimers mainly rely on traditional mechanical control methods to perform the handling and retrieval of stacked materials through fixed preset operating parameters. However, this method has significant limitations, such as the inability to dynamically adapt to changes in the shape of material accumulation, equipment load fluctuations, and changes in energy consumption requirements. In addition, the traditional method lacks precise zoning processing, which makes it impossible to effectively optimize the operation path and energy consumption of the stacker and reclaimer. Problems such as low efficiency, high energy consumption and severe equipment wear often occur when operating in high-load or high-density blocks. Current solutions mainly focus on improving equipment hardware performance or manual adjustments under manual monitoring, but there is still a lack of intelligent and automated operation control methods, making it difficult to achieve real-time operation optimization.

[0003] Based on the above shortcomings of the prior art, there is an urgent need for a stacker-reclaimer operation control method and system. Summary of the invention

[0004] The purpose of the present invention is to provide a stacker-reclaimer operation control method and system to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0005] In a first aspect, the present application provides a stacker-reclaimer operation control method, comprising:

[0006] Acquire first information and second information, wherein the first information includes three-dimensional point cloud data and spectral imaging data of the deposited materials, and the second information includes real-time status data of the stacker-reclaimer;

[0007] Perform dynamic partitioning processing according to the first information, analyze the density, humidity and height of the material accumulation through an adaptive partitioning algorithm, dynamically adjust the boundaries and characteristic labels of the blocks, and prioritize the blocks based on density and stability to obtain an operation block model;

[0008] Performing task allocation processing according to the operation block model and the second information, dynamically adjusting the priority of the block tasks based on the current load, inclination angle and speed state of the stacker-reclaimer to obtain a task priority order;

[0009] Optimizing the operation parameters according to the task priority, predicting the dynamic deformation of the material during the operation, and using the finite element model to adjust the angle and depth of the stacker and reclaimer in real time to obtain the operation parameters;

[0010] Performing energy efficiency optimization analysis according to the operation parameters, by decomposing the operation process into multiple sub-chains, gradually calculating the energy consumption of each sub-chain at different densities and inclination angles, and achieving load balance and optimal energy consumption through a multi-objective optimization algorithm, and obtaining energy efficiency optimization parameters;

[0011] The operation plan is formulated according to the energy efficiency optimization parameters and the task priority order, and the final operation plan is obtained by comprehensively analyzing the priority blocks and the optimal energy consumption path.

[0012] In a second aspect, the present application also provides a stacker-reclaimer operation control system, comprising:

[0013] An acquisition module, used to acquire first information and second information, wherein the first information includes three-dimensional point cloud data and spectral imaging data of the deposited materials, and the second information includes real-time status data of the stacker-reclaimer;

[0014] A partitioning module, used to perform dynamic partitioning processing according to the first information, analyze the density, humidity and height of the material accumulation through an adaptive partitioning algorithm, dynamically adjust the boundaries and characteristic labels of the blocks, and prioritize the blocks based on density and stability to obtain an operation block model;

[0015] A sorting module, used for performing task allocation processing according to the operation block model and the second information, dynamically adjusting the priority of the block tasks based on the current load, inclination and speed state of the stacker-reclaimer, and obtaining a task priority order;

[0016] An optimization module is used to optimize the operation parameters according to the task priority order, and obtain the operation parameters by predicting the dynamic deformation of the material during the operation and adjusting the angle and depth of the stacker and reclaimer in real time using a finite element model;

[0017] A decomposition module is used to perform energy efficiency optimization analysis according to the operation parameters, by decomposing the operation process into multiple sub-chains, gradually calculating the energy consumption of each sub-chain at different densities and inclinations, and achieving load balance and optimal energy consumption through a multi-objective optimization algorithm to obtain energy efficiency optimization parameters;

[0018] The output module is used to formulate a work plan according to the energy efficiency optimization parameters and the task priority order, and obtain a final work plan by comprehensively analyzing the priority blocks and the optimal energy consumption path.

[0019] The beneficial effects of the present invention are:

[0020] The present invention dynamically adjusts the priority and parameter settings of the operation blocks through multi-dimensional data analysis, and comprehensively considers the optimal allocation of equipment load, energy consumption and operation path to generate a final operation plan, thereby improving operation efficiency, reducing energy consumption, and extending the service life of equipment, providing an intelligent and efficient solution for industrial material handling.

[0021] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 It is a schematic flow chart of a stacker-reclaimer operation control method described in an embodiment of the present invention;

[0024] Figure 2 It is a schematic diagram of the structure of the stacker-reclaimer operation control system described in an embodiment of the present invention.

[0025] Markings in the figure: 1. Acquisition module; 2. Partition module; 21. First partition unit; 22. First labeling unit; 23. First adjustment unit; 24. First sorting unit; 3. Sorting module; 31. First allocation unit; 32. Second adjustment unit; 33. First matching unit; 34. First update unit; 4. Optimization module; 41. First prediction unit; 42. Third adjustment unit; 43. First optimization unit; 44. Second optimization unit; 5. Decomposition module; 51. First decomposition unit; 52. First estimation unit; 53. Third optimization unit; 54. First solution unit; 6. Output module; 61. Second allocation unit; 62. Fourth optimization unit; 63. Third allocation unit; 64. Fifth optimization unit. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0027] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0028] Embodiment 1:

[0029] This embodiment provides a stacker-reclaimer operation control method.

[0030] See also Figure 1 , the figure shows that the method includes steps S100 to S600.

[0031] Step S100, obtaining first information and second information, the first information including three-dimensional point cloud data and spectral imaging data of the deposited materials, and the second information including real-time status data of the stacker-reclaimer;

[0032] It is understandable that the three-dimensional point cloud data in the first information is obtained through laser scanning or depth camera technology, which can completely and meticulously restore the spatial form of the accumulated materials, including data such as the density distribution and stacking height of the materials. The status data of the stacker-reclaimer in the second information includes real-time parameters such as its inclination, current load and operating speed, which can instantly reflect the working condition of the equipment and the external conditions of the material operation. This step provides complete and real-time updated operating environment data for the subsequent steps of intelligent control, realizing data-driven precise control preparation.

[0033] Step S200, performing dynamic partitioning processing according to the first information, analyzing the density, humidity and height of the material accumulation through an adaptive partitioning algorithm, dynamically adjusting the boundaries and characteristic labels of the blocks, and prioritizing the blocks based on density and stability to obtain an operation block model;

[0034] It should be noted that the adaptive partitioning algorithm can dynamically adjust the block boundaries: in areas of high density or high humidity, the algorithm will refine the partitions so that subsequent operations are more in line with the material state; in areas with low density and low humidity, the blocks will be appropriately expanded to improve the overall operation efficiency. At the same time, this step assigns priority labels to each block according to the density and stability within the block, so that when allocating work tasks, blocks with high stability and moderate density can be processed first, and high-density unstable blocks with the risk of collapse can be postponed or avoided. This partitioning process improves the flexibility and adaptability of the partitions, allowing the stacker-reclaimer to adapt to the dynamic changes in the material stacking form and adjust the operation blocks in real time. The prioritized partitioning model ensures the efficient arrangement of the work sequence, avoids potential risks, and enhances the safety and efficiency of material handling.

[0035] Step S300, performing task allocation processing according to the operation block model and the second information, dynamically adjusting the priority of the block tasks based on the current load, inclination and speed state of the stacker-reclaimer, and obtaining the task priority sequence;

[0036] It can be understood that in this step, by analyzing real-time parameters such as the current load, inclination and speed status, the stacker and reclaimer can dynamically adjust the task priority of each block according to the operating environment and its own status. For example, when the equipment load is high, task allocation will give priority to blocks with lower density or more stability to avoid excessive load on the equipment. Wear and energy consumption; while in a low-load state, the processing of high-density or high-priority blocks can be accelerated to optimize time utilization. Inclination data is used to calculate the stability requirements of the operation. When the inclination increases and the stability decreases, more stable blocks will be given priority to avoid the risk of equipment overturning. At the same time, based on the speed data, the stacker and reclaimer can match the priority of the operating block with the travel speed to avoid the impact of frequent acceleration or deceleration on energy efficiency.

[0037] Step S400, optimizing the operation parameters according to the task priority order, predicting the dynamic deformation of the material during the operation, and using the finite element model to adjust the angle and depth of the stacker and reclaimer in real time to obtain the operation parameters;

[0038] It should be noted that based on the task priority, dynamic deformation prediction is performed using the density, humidity and other stacking characteristics of the material. Through deep learning models such as recurrent neural networks (RNN), the possible movement, compression or sliding trends of the stacked materials during the material retrieving process are estimated to generate a dynamic deformation matrix to reflect the potential change trend of the material morphology in real time. Subsequently, the operating angle and depth of the stacker-reclaimer are adjusted in combination with the finite element analysis model (FEA). The finite element model can simulate the material stress and equipment reaction force at different angles and depths based on the data of the deformation matrix, thereby dynamically determining the optimal operating parameters. For high-density, easy-to-slide material piles, the finite element analysis will recommend reducing the operating angle and depth to ensure equipment stability; in stable blocks, it will be optimized to a larger angle and depth to improve efficiency.

[0039] Step S500: Perform energy efficiency optimization analysis according to the operation parameters, decompose the operation process into multiple sub-chains, gradually calculate the energy consumption of each sub-chain at different densities and inclinations, and achieve load balance and optimal energy consumption through a multi-objective optimization algorithm to obtain energy efficiency optimization parameters;

[0040] It can be understood that the entire operation process is first decomposed into multiple sub-chains, each of which corresponds to independent operations such as reclaiming, moving, and dumping performed by the stacker-reclaimer in a specific block. This decomposition method combines the density, inclination and material characteristics of the operation block to ensure that the energy consumption calculation of each sub-chain can reflect the actual load and operation requirements of the current block. When gradually calculating the energy consumption of each sub-chain, the energy consumption model is used to evaluate the impact of factors such as density and inclination on the energy consumption of the operation. By quantifying the energy consumption of each chain under different block conditions, a sub-chain energy consumption matrix is ​​established, and a multi-objective optimization algorithm is used for analysis to find the best balance between equipment load, energy consumption and operation efficiency. During the optimization process, the algorithm comprehensively considers the impact of the energy consumption and load of each chain on the overall performance of the stacker-reclaimer, thereby automatically adjusting the chain execution order and parameter settings to minimize the total energy consumption. This energy efficiency optimization process ensures that the stacker-reclaimer reasonably allocates resources in each subtask and avoids unnecessary high-energy consumption operations under high load conditions.

[0041] Step S600: formulate a work plan based on energy efficiency optimization parameters and task priorities, and obtain a final work plan by comprehensively analyzing priority blocks and optimal energy consumption paths.

[0042] It is understandable that the final operation plan ensures the optimal path, minimum energy consumption and reasonable time for the stacker-reclaimer operation, enabling the equipment to efficiently complete the operation plan and improve overall resource utilization, while reducing energy consumption and equipment load during the operation, extending equipment life, and enhancing the safety and economy of the operation.

[0043] Further, step S200 includes step S210 to step S240.

[0044] Step S210: performing preliminary area division according to the three-dimensional point cloud data in the first information, performing density clustering on the point cloud data by using a density clustering algorithm, identifying areas and material boundaries with similar densities, and obtaining a preliminary partition model;

[0045] It should be noted that in traditional applications, density clustering algorithms (such as DBSCAN) are only used to identify areas with similar density. In stacker-reclaimer operations, the regional density in point cloud data is not only the basis for block division, but also directly affects the load and operation strategy of the equipment. Therefore, more intelligent parameter control and boundary identification are required when applying. Specifically, first of all, in view of the height and density changes of the accumulated materials, the neighborhood distance parameter is specially optimized in the clustering process, so that the algorithm can maintain sensitivity on the accumulation surface with drastic height gradient and density changes, and adapt to the boundary distinction between high-density accumulation areas and surrounding low-density areas. When a high-density block is identified, the algorithm will automatically shrink the neighborhood radius, accurately identify the local dense area, and prevent erroneous division caused by blurred boundaries. In addition, in order to adapt to the natural deformation of the accumulated materials over time and gravity, the clustering algorithm performs dynamic noise filtering adjustments and generates a "density change map" using historical point cloud data. In this way, non-critical information can be filtered out in a timely manner in the dynamic material accumulation scene and the feature boundaries can be retained. Even when the accumulated materials undergo natural settlement or sliding, the partition model can remain stable. Through such processing, the preliminary partition model not only fits the actual contour of the material stacking, but also can adapt to the density and shape changes of the material, providing an accurate basis for the dynamic characteristic labeling and partition adjustment in subsequent steps.

[0046] Step S220: performing block characteristic labeling processing according to the preliminary partition boundary and the spectral imaging data in the first information, extracting the humidity and density characteristics of the material by a spectral analysis method, and obtaining a block characteristic model with humidity and density labels;

[0047] It is understandable that in the stacking and reclaiming operation scenario, the humidity and density of different blocks have a direct impact on the operating efficiency, energy consumption and safety of the equipment, so the characteristic labeling needs to be highly accurate and able to dynamically reflect the material characteristics. Using spectral imaging technology, the humidity and density distribution of the material can be obtained non-contactly by performing spectral analysis on the multi-band data of the reflected light on the material surface. This method breaks through the limitations of traditional data collection and can collect a large amount of material characteristic information from a long distance in real time. In practical applications, the multi-band spectral data is first reduced in dimension by principal component analysis (PCA) to extract characteristic bands representing humidity and density and reduce noise interference. Then, the distribution of density and humidity is further subdivided by combining the absorption and reflection intensity of specific bands with the material characteristics of the stacked materials. Since the humidity and density in the material stacking environment change complexly and dynamically, this spectral analysis method has specially added a real-time adjustment function, so that the system can automatically calibrate the spectral data when the ambient light or the reflection of the material surface changes, ensuring the accuracy of the humidity and density characteristic data. The humidity and density labels generated by the spectral analysis method enable the block characteristic model to more accurately reflect the material characteristics of each block. At the same time, the block characteristic model with humidity and density labels provides the stacker-reclaimer with an accurate description of material accumulation, ensuring that operation control can be adjusted based on real and dynamic material characteristics, greatly improving the safety and adaptability of intelligent operations.

[0048] Step S230: perform boundary adjustment processing according to the block characteristic model, use the density gradient-based adaptive boundary extension algorithm to calculate the density gradient of each block, determine whether the boundary of each block needs to be expanded or contracted, and dynamically adjust the block boundary to obtain a partition model with stability adaptation;

[0049] It is understandable that in the stacking and reclaiming operation environment, the density distribution of different blocks often shows significant gradient differences, which may affect the stability of the operation. Therefore, density gradient calculation and boundary adjustment can help better reflect the actual state of material accumulation and improve the refined management of the operation block. The adaptive boundary expansion algorithm is used to calculate the density gradient according to the density changes inside and outside each block. For example, if the density of the boundary area of ​​a block changes rapidly, it means that the density difference between the block and the surrounding blocks is large, and the boundary of the block is automatically shrunk to avoid including unstable high-density change areas; on the contrary, if the density of the boundary area changes slowly, the boundary can be appropriately expanded to increase the operation range of the block, thereby improving efficiency. This adaptive adjustment process specially designs a dynamic response mechanism for boundary expansion and contraction, which can be updated in real time when the material morphology changes, ensuring that the partition model always meets the stability requirements of the current accumulation. Through this density gradient-based boundary adjustment, the final partition model is more stable and adaptable, which can not only accurately reflect the density characteristics of each block, but also maintain the rationality of the boundary when the material accumulation is deformed.

[0050] Step S240: Prioritize the partition model based on the stability adaptation, analyze the density and humidity characteristics of the blocks through a sorting algorithm based on multi-factor weights, and obtain a hierarchical priority operation block model.

[0051] It should be noted that the density and humidity of different blocks directly affect their operating difficulty, energy consumption requirements and equipment load stability. Therefore, the multi-factor weight sorting algorithm specifically converts key factors such as density and humidity into priority scores to determine the processing order of each block. Specifically, density and humidity are assigned different weight coefficients: high-density blocks will increase the energy consumption and load of the equipment, and are usually located at the bottom of the pile, and their priority is usually low; blocks with higher humidity may have a higher risk of slippage, so when the humidity exceeds the set threshold, their priority will be further reduced. The sorting algorithm automatically calculates the priority score of each block based on these factors, and sorts them in layers according to the operating conditions of the stacker and reclaimer, placing high-priority blocks suitable for rapid processing in the front, and low-priority blocks are processed when they are safe and suitable for load. Through this sorting, the hierarchical priority operation block model formed has significantly improved the operating efficiency and safety of the stacker and reclaimer in terms of technical effects. In actual operation, the stacker-reclaimer can flexibly adjust the order of operations according to the sorting results, give priority to stable and easy-to-access blocks, and postpone or avoid blocks with high risks, thereby effectively balancing energy consumption, safety and efficiency.

[0052] Further, step S300 includes step S310 to step S340.

[0053] Step S310, performing load distribution processing according to the operation block model and the current load data of the stacker-reclaimer in the second information, calculating the task allocation priority of each block by using the real-time load data of the stacker-reclaimer as a weight factor, and obtaining a preliminary task priority sequence;

[0054] It can be understood that in this step, the real-time load data of the stacker and reclaimer is used as a weight factor to assign priority scores to different blocks and calculate the task allocation priority of each block. Specifically, when the equipment load is high, the algorithm will reduce the priority of high-density and high-humidity blocks, because these blocks are more difficult to operate, which may cause the equipment to overload and increase wear and energy consumption; on the contrary, under low-load conditions, the priority of high-density blocks will be appropriately increased to make full use of the equipment's load capacity. By introducing real-time load data into the priority calculation, the load distribution algorithm can adjust the priority weights at different load levels to match the current optimal load capacity of the equipment. This method ensures the reasonable scheduling of high-load blocks and effectively prevents potential risks caused by overload operations.

[0055] Step S320: Perform stability adjustment processing according to the preliminary task priority sequence and the stacker-reclaimer inclination data in the second information, calculate the inclination risk of each task block using the inclination feedback control algorithm, and rearrange the task sequence based on the risk calculation result to obtain an optimized task sequence;

[0056] It should be noted that the inclination data reflects the stable state of the equipment at different working positions, especially when operating in high-density and high-humidity blocks, excessive changes in the inclination may lead to the risk of overturning of the equipment. Therefore, this step combines the inclination feedback control algorithm to perform real-time inclination risk assessment on each task block. Specifically, the inclination feedback control algorithm calculates the inclination stress that the equipment may bear during the operation according to the current value of the equipment inclination and the density characteristics of the block. If the operating inclination of a block exceeds the set safety threshold, the priority of the block will be reduced; for blocks within the allowable inclination range, their task priority will be appropriately increased according to the risk assessment results. Through this risk-based reordering, the operation order of high-risk blocks can be automatically adjusted to postpone them until the equipment load is small and the inclination is stable. This stability adjustment process optimizes the task order, enabling the stacker-reclaimer to intelligently avoid risks in areas with high density, high humidity and complex inclination conditions, and give priority to completing tasks with high safety.

[0057] Step S330, performing speed matching processing according to the optimized task sequence and the stacker-reclaimer speed state in the second information, and obtaining the task sequence by calculating the distance and speed matching degree of the block tasks;

[0058] It can be understood that this step ensures that the equipment can maintain a reasonable speed when performing different tasks by calculating the distance and speed matching degree of each block task, thereby reducing the energy waste caused by frequent acceleration and deceleration. Specifically, the speed matching processing algorithm combines the current speed state of the equipment and the distance between blocks: when the stacker and reclaimer is at a higher speed, the algorithm will give priority to task blocks with shorter distances or lower density, thereby avoiding the increase in energy consumption caused by emergency stops or deceleration, and ensuring the smoothness of the operation process; on the contrary, when the equipment speed is low, it will give priority to matching long-distance or high-priority task blocks to fully utilize the speed improvement efficiency of the equipment. Through this dynamic matching mechanism, the stacker and reclaimer can effectively connect each task block and avoid the waste of resources caused by the mismatch between speed and task. This speed matching processing method optimizes the overall travel efficiency of the stacker and reclaimer, reduces unnecessary energy consumption and equipment wear, and enables the equipment to complete tasks at an appropriate speed on an efficient path.

[0059] Step S340: Perform dynamic priority update processing according to the task sequence, assign different weights to the density of the task block, the real-time load, inclination angle and speed state of the stacker and reclaimer by constructing a multi-factor weight matrix, and comprehensively calculate the dynamic priority of each block to obtain the final task priority sequence.

[0060] It should be noted that the construction of the weight matrix is ​​based on the importance and influence of each factor. For example, high-density blocks usually require greater load capacity. Therefore, when the stacker-reclaimer load is low, the density weight will be appropriately increased to give priority to high-density blocks; and when the equipment inclination angle approaches the stability threshold, the inclination angle weight increases, and low-risk blocks are given priority to avoid overturning. In addition, the weight of the speed state is used to optimize the smoothness of switching between blocks, and prioritizes matching blocks with close distances at high speeds to reduce frequent speed adjustments. Through dynamic priority updates, the final generated task priority order reflects the optimal operating path for real-time working conditions.

[0061] Further, step S400 includes step S410 to step S440.

[0062] Step S410: Deformation prediction processing is performed according to the task priority order, and the density, pressure and stress changes of the materials in each block during the stacker-reclaimer operation are analyzed using a recurrent neural network model based on material density and force analysis, and the morphological change trend of the materials is estimated to obtain a dynamic deformation matrix;

[0063] It should be noted that the material accumulation morphology in the stacking and reclaiming operation environment is complex and easily affected by the operation process, especially in areas with high density or uneven stress, where deformation may bring risks such as slippage and collapse. The application of the recurrent neural network (RNN) model effectively captures the dynamic changes in the material morphology during the operation process and provides real-time prediction of the deformation trend. In practical applications, the RNN model combines the material density of each block and the current stress state of the stacker and reclaimer to generate gradually changing stress distribution data. Through the recursive analysis model (LSTM or GRU of the recurrent neural network), the RNN can gradually learn the deformation law of each block under pressure changes, such as predicting the sinking of the morphology in blocks with higher stacking density and predicting the sliding tendency in blocks with lower density. The dynamic deformation matrix generated by this process not only captures the current morphology, but also provides an estimate of future short-term deformation. This deformation prediction process enables the stacker and reclaimer to grasp the morphological change trend of the material in real time, ensure that the operating parameters of the stacker and reclaimer can adapt to the dynamic changes of the stacking morphology, and effectively improve the safety and operation accuracy during the operation process.

[0064] Specifically, the initial stress distribution of each block is calculated first as the basic condition for the input of the recurrent neural network:

[0065] σ i,j =ρ i ·g·h i,j f(θ);

[0066] Where i represents the number of the large block; j represents the number of the small unit in block i; σ i,j represents the initial stress of block (i, j); ρ i represents the material density of block i; g represents the acceleration of gravity; h i,j represents the height of block (i, j); f(θ) represents the influence factor of the tilt angle.

[0067] Then, based on the initial stress σ i,j , the recurrent neural network (RNN) model then gradually calculates the morphological change trend of each time step. Using the long short-term memory (LSTM) unit, the state update formula of the unit is:

[0068] h t =σ(W h ·[x t ,h t-1 ]+b h );

[0069] Among them, h t represents the morphological change trend of the material at the current time step; σ represents the activation function; W h represents the weight matrix; x trepresents the input feature vector at time step t; h t-1 Indicates the deformation state at the previous moment; b h is a bias term used to adjust the equilibrium state of the model.

[0070] After generating the morphological change trend, the output of the model will be used to predict the future deformation state. The predicted deformation variable is expressed as:

[0071] Δd i,j =W o ·h t +b o ;

[0072] Where, Δd i,j W represents the deformation prediction of block (i, j); o represents the output weight matrix, which is used to map the hidden state to the predicted deformation; b o is the output bias term, which is used to adjust the balance of deformation prediction.

[0073] Finally, the deformation prediction Δd of all blocks is i,j The dynamic deformation matrix D is aggregated and used for subsequent morphological adjustment.

[0074] Step S420, performing angle adjustment processing according to the dynamic deformation matrix and the stacker-reclaimer inclination data in the second information, dynamically adjusting the stacker-reclaimer inclination based on the predicted material deformation trend, and obtaining a real-time inclination adjustment parameter;

[0075] It should be noted that during the stacking and reclaiming process, the deformation trend of the material, such as sinking or sliding, will affect the stability of the equipment, especially when operating in high-density blocks, where a slight change in the inclination angle may cause the equipment to become unbalanced. In this process, the predicted deformation data and the real-time inclination angle are combined to calculate the appropriate inclination adjustment parameters through a fuzzy control algorithm or an adaptive control algorithm. For example, when the deformation matrix shows that the density of the block increases or the material slides to one side, the inclination angle will be automatically lowered to reduce the center of gravity shift of the equipment to avoid the risk of overturning. Conversely, when operating in blocks with reduced density and lower deformation risks, the inclination angle can be appropriately increased to improve the stacking and reclaiming efficiency. This step dynamically adjusts the inclination angle of the stacker and reclaimer so that the equipment can respond to changes in the shape of material accumulation in real time and maintain the stability and safety of the operation.

[0076] Step S430, performing depth optimization processing according to the real-time inclination adjustment parameters, and obtaining depth setting parameters by simulating the optimal stacking depth under the current inclination angle and stacking form;

[0077] It is understandable that the change of the stacking shape and the dynamic adjustment of the inclination angle directly affect the ideal stacking depth, which is related to the material reclaiming efficiency, equipment stability and energy consumption control. To this end, the finite element analysis (FEA) model or simulation algorithm is used to simulate the stress of the stacked materials at the current inclination angle and calculate the optimal stacking depth.

[0078] Step S440: Parameter optimization processing is performed according to the depth setting parameters and the real-time inclination adjustment parameters, and the operation parameters are obtained by load adjustment of the inclination and depth settings.

[0079] The core of this step is to achieve load balance through the dual setting of inclination and depth, ensuring that the equipment can operate efficiently and stably under different material blocks and morphological conditions. This process involves a load optimization algorithm, which generates optimal operating parameters by fine-tuning the current inclination and depth settings to match the real-time load bearing capacity of the equipment. In actual operation, when the stacker-reclaimer detects a high load (such as in a high-density or high-humidity area), the algorithm automatically adjusts the parameters according to the inclination and depth settings, such as reducing the inclination or reducing the stacking depth, thereby reducing the equipment load and preventing damage to the equipment due to overload operation. In low-load blocks, the inclination and depth settings can be appropriately increased to improve operating efficiency and optimize the material reclaiming speed. The load optimization algorithm also monitors the feedback information between the stacking morphology and the equipment load in real time, further refining the inclination and depth settings, so that the equipment can achieve dynamic adaptation of the load while ensuring safety. The final operating parameters not only improve the adaptability and flexibility of the equipment, but also reduce the operating energy consumption and mechanical stress, extend the service life of the equipment, and optimize the energy efficiency and resource utilization of the overall operation process.

[0080] Further, step S500 includes step S510 to step S540.

[0081] Step S510: Decompose the operation chain according to the operation parameters, divide the operation process into multiple sub-chains based on the operation characteristics and material density of each block, where each sub-chain represents the material collection, movement and dumping operations in the corresponding block, and obtain a chain sequence;

[0082] It can be understood that the core of chain decomposition is to decompose the operation process into independent sub-task sequences according to the operation characteristics of each block (such as density, humidity and priority) and operation parameters (such as angle and depth). Each sub-chain represents an independent operation unit of the reclaiming, moving and dumping operations in a specific block, forming a series of logical chains for further energy consumption optimization and path planning. In the decomposition process, the step-by-step operation sequence of each block operation is first determined according to the material density and operation difficulty of each block. For example, for high-density blocks, chain decomposition will set a shorter reclaiming chain to ensure stability and energy consumption control; while in low-density blocks, a longer chain may be formed, containing more moving and dumping tasks, thereby reducing the frequency of equipment switching. In addition, chain decomposition also considers the adaptability of inclination and depth parameters to ensure that the operation of each chain meets the current equipment parameters and material characteristics. Breaking down the complex overall operation process into multiple controllable sub-chains helps the stacker-reclaimer to efficiently schedule the operation needs of different blocks.

[0083] Step S520: Perform energy consumption estimation processing according to the chain sequence, and obtain a sub-chain energy consumption matrix by calculating the energy consumption of each sub-chain under the density and inclination conditions in its operating block;

[0084] It should be noted that the key to energy consumption estimation is to evaluate the actual energy consumption of the stacker-reclaimer when performing operations such as reclaiming, moving, and dumping, combining the density and inclination conditions of each block. The material density and block inclination in the stacker-reclaim operation have a significant impact on the equipment load and energy consumption, so accurately calculating the energy consumption under different conditions is crucial to optimizing the equipment's operating efficiency.

[0085] In the specific calculation, first of all, the energy demand of the unit operation is evaluated for the density of the block where each sub-chain is located, combined with the material characteristics and the equipment load model. For example, the material extraction operation in the high-density block consumes a lot of energy, and the algorithm will weight its energy consumption. Then, based on the inclination of the block, the algorithm further adjusts the energy consumption calculation to consider the additional energy loss of the equipment during tilted operation. Through weighted processing of multiple factors, an energy consumption model is formed, which calculates the total energy consumption of each sub-chain and records it in the sub-chain energy consumption matrix. This step refines the energy consumption of each sub-chain, and the generated energy consumption matrix can truly reflect the impact of different operating conditions on equipment energy consumption.

[0086] Step S530: Perform load balancing optimization processing according to the sub-chain energy consumption matrix, and rearrange the task order of the sub-chain by adopting a weighted round-robin scheduling algorithm to obtain a load balancing optimization chain;

[0087] It is understandable that when the stacker-reclaimer performs tasks in different blocks, the energy consumption and load vary with the block density, inclination angle and sub-chain operation content. If the task sequence is not arranged properly, it may cause the energy consumption of the equipment to rise sharply or the equipment to wear more when it is operating in the high-load area. The weighted polling scheduling algorithm is used in this step to balance the scheduling order of high-load and low-load sub-chains. Specifically, first, based on the sub-chain energy consumption matrix, the algorithm extracts the specific energy consumption value of each chain and calculates the load factor of each sub-chain under the current operating load. The calculation of the load factor combines the energy consumption of the chain, the current load level of the equipment and the density characteristics of the material block to ensure that the equipment does not continuously allocate high-energy consumption chains when the load is high. This calculation uses the energy consumption distribution equation to identify the high-energy consumption sub-chains in the energy consumption matrix as peak nodes, and then insert low-energy consumption chains between the peak nodes through the interpolation method to achieve a smooth transition of the load. The weighted polling scheduling is only used to preliminarily determine the priority of the chain, and further load balancing processing is achieved through the dynamic programming algorithm. During the derivation process of load balancing, the dynamic programming algorithm will gradually adjust the energy consumption gradient of each subtask in the chain sequence to make the energy consumption change curve stable. By calculating the variance of the energy consumption gradient under different arrangements, the sequence with the smallest variance is selected as the final task arrangement to ensure the uniformity of the load. This load balancing optimization that combines energy consumption variance derivation and dynamic programming greatly smoothes the load curve, allowing the device to operate stably when executing high-load blocks.

[0088] Step S540: perform optimal energy consumption solution processing according to the load balancing optimization chain, dynamically adjust the path and parameter settings by combining the energy consumption, execution order and load fluctuation of each sub-chain, and obtain energy efficiency optimization parameters.

[0089] Specifically, the algorithm first constructs an energy consumption objective function for the energy consumption and load data of each sub-chain in the load balancing optimization chain. This objective function combines the total energy consumption of the sub-chain, the impact of the execution order, and the load changes of the device between task switching to evaluate the energy consumption under different path combinations and parameter settings. Through the multi-objective optimization algorithm, the device continuously iterates and optimizes during the execution path adjustment process, distributes the high-energy consumption sub-chains between the low-energy consumption sub-chains to prevent excessive concentration of energy consumption. In addition, in order to control the load fluctuation of the device, the algorithm introduces a load change constraint in the calculation, and sets the load change rate as a dynamically updated optimization parameter. This constraint simulates the load gradient changes of the device under different path combinations, and selects the path combination with small load changes and optimal energy consumption. Finally, after multiple iterations, the balance point between load and energy consumption is found, and the corresponding operation path and parameter settings are output to form energy efficiency optimization parameters.

[0090] Further, step S600 includes step S610 to step S640.

[0091] Step S610: Perform weight allocation processing according to the energy efficiency optimization parameters, and construct a multi-bit operation weight matrix based on the density, distance, energy consumption priority and equipment load response of each block;

[0092] It should be noted that this step first takes the density of each block as the key weight factor. Blocks with higher density require larger equipment loads and are therefore assigned higher weights. Then, the algorithm evaluates the energy consumption of movement and operation based on the distance between the stacker and each block, and appropriately reduces the weight of blocks that are farther away to reduce unnecessary long-distance energy consumption. Next, combined with the energy consumption priority of each block, high-energy consumption blocks are marked as priority in the weight matrix to optimize the overall energy efficiency. In addition, the equipment load response reflects the adaptability of the stacker and reclaimer to the operation of each block under different load conditions. For example, when the equipment is under high load, low-density, low-energy consumption blocks will be selected first to reduce the total load pressure of the equipment. By classifying the above factors into a multi-bit weight matrix, the weight allocation process effectively achieves the unification of multi-dimensional factors and assigns a comprehensive weight value to each block.

[0093] Step S620: Optimize the path according to the operation weight matrix, use the ant colony algorithm to search the path of the multi-dimensional operation weight matrix, simulate the accumulation and attenuation of pheromones, gradually discover and strengthen the path sequence with low energy consumption and high priority to obtain the optimal operation path sequence;

[0094] It should be noted that the ant colony algorithm simulates the behavior of ants looking for food and uses the accumulation and attenuation mechanism of pheromones to make the stacker-reclaimer gradually converge to the operating path with the best energy efficiency. It is suitable for path optimization problems under multi-dimensional conditions.

[0095] Specifically, when the algorithm is initialized, multiple virtual ants are "released" on each block node in the job weight matrix, and each ant explores different block combinations by randomly selecting the next path. As each ant traverses the path in the weight matrix, the path with high weight and low energy consumption will "deposit" more pheromones on its path, indicating that the path has a higher priority; while the path with low weight or high energy consumption will gradually reduce the deposition of pheromones. After each iteration, the pheromone will decay over time, so that the low-priority path will be gradually excluded. Through multiple rounds of iterations, the ant colony gradually strengthens the tendency to choose the optimal path, and the path with low energy consumption and high priority will obtain a greater weight in the process of pheromone accumulation. The optimal operation path sequence finally formed is the best path selection for the stacker-reclaimer under various operating conditions. This sequence takes into account multiple factors such as the density, distance, and equipment load of each block to ensure that the operation path can balance energy consumption and operation priority.

[0096] Step S630: Perform time allocation processing according to the optimal operation path sequence and task priority, and use Bellman dynamic programming algorithm to dynamically program the operation time and resources of each block in the path to obtain a time resource allocation model;

[0097] It is understandable that due to the differences in operating requirements and equipment resource consumption in different blocks, it is necessary to ensure the maximization of operating efficiency and resource utilization through detailed time planning and resource allocation. In this application, the Bellman dynamic programming algorithm can recursively decompose the decision problem and decompose the path into multiple continuous decision stages, thereby achieving optimal control of the time and resource allocation of the overall path. Specifically, the Bellman dynamic programming algorithm backtracks from the final block, gradually calculates the optimal operating time for each block, and adjusts the allocation of resources according to the current status of the equipment resources. Through dynamic recursion, resources and time are iterated multiple times at each stage so that each step can obtain the optimal time allocation that meets the resource constraints. Through the optimized operating time and resource allocation, the operating time of each block of the stacker and reclaimer is matched with the equipment resource consumption, ensuring smooth and efficient operation.

[0098] Step S640: Perform job scheduling optimization processing according to the time resource allocation model, and automatically match the optimal job start time, duration and required equipment parameters of each block to obtain the final job plan while satisfying the job block priority, energy consumption limit and equipment load constraints.

[0099] It should be noted that this step comprehensively considers multiple constraints and dynamic environmental factors to ensure that the stacker-reclaimer can complete all tasks with high efficiency and low energy consumption. First, the scheduling optimization process assigns an earlier operation start time to blocks with high priority based on the priority order to ensure that key blocks are completed first to maintain the overall smoothness and efficiency of the operation. Then, the algorithm adjusts the operation duration of each block through energy consumption restrictions and load constraints, especially in high-energy consumption blocks, and appropriately shortens the operation time to prevent equipment from overloading, reducing energy consumption and extending equipment life. According to the characteristics of each block, the scheduling algorithm also dynamically matches the optimal equipment parameters (such as angle, depth and speed) according to the resource allocation model to ensure operation safety and effective use of resources. The final operation plan provides clear operating instructions for the stacker-reclaimer, enabling it to maintain stable and efficient operation in a complex operating environment, significantly improving the efficiency and economic benefits of the overall operation process.

[0100] Further, step S620 includes step S621 to step S624.

[0101] Step S621, performing initial path generation processing according to the job weight matrix, and obtaining an initial path set by constructing an initial pheromone distribution matrix to adapt to the block priority and energy consumption differences;

[0102] It should be noted that this step performs initial path generation processing based on the job weight matrix. By analyzing the priority and energy consumption of each block in the weight matrix, a pheromone distribution matrix is ​​constructed. The initial distribution of pheromones reflects the differences in priority and energy consumption among different blocks. The initial value of pheromones is higher in blocks with low energy consumption and high priority to guide virtual ants to prioritize exploring more energy-efficient paths. In this step, the pheromone concentration is adjusted according to the block characteristics in the stacking and reclaiming scenario through the distribution adaptation algorithm, giving priority to areas with higher density and lower energy consumption. The obtained initial path set provides a path basis for subsequent path searches.

[0103] Step S622: performing path exploration processing according to the initial path set, obtaining a candidate path set through random path search and local update of pheromone by ants in the ant colony algorithm;

[0104] It should be noted that individual ants start from different block nodes and explore the path set by randomly selecting the next node, while guiding the path selection through the weight difference with the adjacent blocks. Each ant decides the next move by comprehensive calculation of distance, priority and energy consumption data. After the local update of the path search, the pheromone is slightly accumulated or attenuated on each path to initially highlight the path trend with high priority and low energy consumption.

[0105] Step S623, performing path optimization processing according to the candidate path set, strengthening the low-energy consumption path through the pheromone global update algorithm, and obtaining a strengthened path set;

[0106] It is understandable that this step uses the pheromone global update mechanism of the ant colony algorithm to accumulate and strengthen the pheromones on the path passed, especially to significantly enhance the pheromones of the path segments formed between high-priority and low-energy blocks. Combined with the stacker-reclaimer scenario, the accumulation of pheromones also takes into account the stability of the stacking form, and appropriately enhances the scheduling of low-inclination and low-density block path segments. This process ensures that ants choose more low-energy and high-priority path segments in subsequent iterations.

[0107] Step S624: perform optimal path screening processing according to the enhanced path set, select the lowest energy consumption path sequence through the convergence calculation of the ant colony algorithm, and obtain the optimal operation path sequence.

[0108] It should be noted that through multiple iterative calculations, the ant colony algorithm gradually converges to the path sequence with the lowest energy consumption. The ants select the path with the lowest energy consumption and the highest pheromone concentration in the enhanced path set, and constantly correct the path selection. Combined with the energy consumption data and priority requirements in the stacker-reclaimer scenario, the path segment combination with the highest pheromone concentration is finally selected.

[0109] Embodiment 2:

[0110] like Figure 2 As shown, this embodiment provides a stacker-reclaimer operation control system, including:

[0111] An acquisition module 1 is used to acquire first information and second information, the first information includes three-dimensional point cloud data and spectral imaging data of the deposited materials, and the second information includes real-time status data of the stacker-reclaimer;

[0112] Partitioning module 2 is used to perform dynamic partitioning processing according to the first information, analyze the density, humidity and height of the material accumulation through an adaptive partitioning algorithm, dynamically adjust the boundaries and characteristic labels of the blocks, and prioritize the blocks based on density and stability to obtain an operation block model;

[0113] The sorting module 3 is used to perform task allocation processing according to the operation block model and the second information, and dynamically adjust the priority of the block tasks based on the current load, inclination and speed state of the stacker-reclaimer to obtain the task priority order;

[0114] Optimization module 4 is used to optimize the operation parameters according to the task priority order, and obtain the operation parameters by predicting the dynamic deformation of the material during the operation and adjusting the angle and depth of the stacker and reclaimer in real time using the finite element model;

[0115] Decomposition module 5 is used to perform energy efficiency optimization analysis according to the operation parameters. By decomposing the operation process into multiple sub-chains, the energy consumption of each sub-chain at different densities and inclinations is gradually calculated, and load balance and energy consumption optimization are achieved through a multi-objective optimization algorithm to obtain energy efficiency optimization parameters;

[0116] The output module 6 is used to formulate the operation plan according to the energy efficiency optimization parameters and the task priority, and obtain the final operation plan by comprehensively analyzing the priority blocks and the optimal energy consumption path.

[0117] In a specific implementation disclosed in the present application, the partition module 2 includes:

[0118] A first partitioning unit 21 is used to perform preliminary area partitioning according to the three-dimensional point cloud data in the first information, and to perform density clustering on the point cloud data by using a density clustering algorithm to identify areas and material boundaries with similar densities, thereby obtaining a preliminary partitioning model;

[0119] A first labeling unit 22 is used to perform block characteristic labeling processing according to the preliminary partition boundary and the spectral imaging data in the first information, extract the moisture and density characteristics of the material through a spectral analysis method, and obtain a block characteristic model with moisture and density labels;

[0120] The first adjustment unit 23 is used to perform boundary adjustment processing according to the block characteristic model, calculate the density gradient of each block using an adaptive boundary expansion algorithm based on density gradient, determine whether the boundary of each block needs to be expanded or contracted, and dynamically adjust the boundary of the block to obtain a partition model with stability adaptation;

[0121] The first sorting unit 24 is used to perform priority sorting according to the stability-adaptive partition model, analyze the density and humidity characteristics of the blocks through a sorting algorithm based on multi-factor weights, and obtain a hierarchical priority operation block model.

[0122] In a specific implementation disclosed in the present application, the sorting module 3 includes:

[0123] The first allocation unit 31 is used to perform load allocation processing according to the current load data of the stacker-reclaimer in the operation block model and the second information, and calculate the task allocation priority of each block by using the real-time load data of the stacker-reclaimer as a weight factor to obtain a preliminary task priority sequence;

[0124] The second adjustment unit 32 is used to perform stability adjustment processing according to the preliminary task priority sequence and the stacker-reclaimer inclination data in the second information, calculate the inclination risk of each task block by using the inclination feedback control algorithm, and rearrange the task sequence based on the risk calculation result to obtain an optimized task sequence;

[0125] The first matching unit 33 is used to perform speed matching processing according to the optimized task sequence and the speed state of the stacker-reclaimer in the second information, and obtain the task sequence by calculating the distance and speed matching degree of the block task;

[0126] The first updating unit 34 is used to perform dynamic priority update processing according to the task sequence, and allocates different weights to the density of the task block, the real-time load, inclination angle and speed state of the stacker and reclaimer by constructing a multi-factor weight matrix, and comprehensively calculates the dynamic priority of each block to obtain the final task priority sequence.

[0127] In a specific implementation disclosed in the present application, the optimization module 4 includes:

[0128] The first prediction unit 41 is used to perform deformation prediction processing according to the task priority order, use a recurrent neural network model based on material density and force analysis to analyze the density, pressure and stress changes of each block of materials during the stacker-reclaimer operation, and estimate the morphological change trend of the materials to obtain a dynamic deformation matrix;

[0129] The third adjustment unit 42 is used to perform angle adjustment processing according to the dynamic deformation matrix and the stacker-reclaimer inclination data in the second information, dynamically adjust the stacker-reclaimer inclination based on the predicted material deformation trend, and obtain a real-time inclination adjustment parameter;

[0130] The first optimization unit 43 is used to perform depth optimization processing according to the real-time inclination adjustment parameter, and obtain the depth setting parameter by simulating the optimal stacking depth under the current inclination and stacking form;

[0131] The second optimization unit 44 is used to perform parameter optimization processing according to the depth setting parameters and the real-time inclination adjustment parameters, and obtain the operation parameters by load adjustment of the inclination and depth settings.

[0132] In a specific embodiment disclosed in the present application, the decomposition module 5 includes:

[0133] The first decomposition unit 51 is used to perform operation chain decomposition processing according to the operation parameters, and divide the operation process into multiple sub-chains based on the operation characteristics and material density of each block, wherein each sub-chain represents the material collection, movement and dumping operations in the corresponding block, and obtain a chain sequence;

[0134] The first estimation unit 52 is used to perform energy consumption estimation processing according to the chain sequence, and obtain a sub-chain energy consumption matrix by calculating the energy consumption of each sub-chain under the density and inclination conditions in its operation block;

[0135] The third optimization unit 53 is used to perform load balancing optimization processing according to the sub-chain energy consumption matrix, and to obtain a load balancing optimization chain by rearranging the task order of the sub-chains using a weighted polling scheduling algorithm;

[0136] The first solving unit 54 is used to perform optimal energy consumption solving processing according to the load balancing optimization chain, and dynamically adjust the path and parameter settings by combining the energy consumption, execution order and load fluctuation of each sub-chain to obtain energy efficiency optimization parameters.

[0137] In a specific embodiment disclosed in the present application, the decomposition module 5 includes:

[0138] The second allocation unit 61 is used to perform weight allocation processing according to the energy efficiency optimization parameter, and construct a multi-bit operation weight matrix based on the density, distance, energy consumption priority and equipment load response of each block;

[0139] The fourth optimization unit 62 is used to perform path optimization processing according to the operation weight matrix, use the ant colony algorithm to search the path of the multi-dimensional operation weight matrix, simulate the accumulation and attenuation of pheromones, and gradually discover and strengthen the path sequence with low energy consumption and high priority to obtain the optimal operation path sequence;

[0140] The third allocation unit 63 is used to perform time allocation processing according to the optimal operation path sequence and task priority, and use the Bellman dynamic programming algorithm to dynamically program the operation time and resources of each block in the path to obtain a time resource allocation model;

[0141] The fifth optimization unit 64 is used to perform job scheduling optimization processing according to the time resource allocation model, and automatically match the optimal job start time, duration and required equipment parameters of each block to obtain the final job plan while satisfying the job block priority, energy consumption limit and equipment load constraint conditions.

[0142] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0143] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0144] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A stacker-reclaimer operation control method, characterized in that: include: Acquire first information and second information, wherein the first information includes three-dimensional point cloud data and spectral imaging data of the deposited materials, and the second information includes real-time status data of the stacker-reclaimer; Perform dynamic partitioning processing according to the first information, analyze the density, humidity and height of the material accumulation through an adaptive partitioning algorithm, dynamically adjust the boundaries and characteristic labels of the blocks, and prioritize the blocks based on density and stability to obtain an operation block model; Performing task allocation processing according to the operation block model and the second information, dynamically adjusting the priority of the block tasks based on the current load, inclination angle and speed state of the stacker-reclaimer to obtain a task priority order; Optimizing the operation parameters according to the task priority, predicting the dynamic deformation of the material during the operation, and using the finite element model to adjust the angle and depth of the stacker and reclaimer in real time to obtain the operation parameters; Performing energy efficiency optimization analysis according to the operation parameters, by decomposing the operation process into multiple sub-chains, gradually calculating the energy consumption of each sub-chain at different densities and inclination angles, and achieving load balance and optimal energy consumption through a multi-objective optimization algorithm, and obtaining energy efficiency optimization parameters; The operation plan is formulated according to the energy efficiency optimization parameters and the task priority order, and the final operation plan is obtained by comprehensively analyzing the priority blocks and the optimal energy consumption path.

2. The stacker-reclaimer operation control method according to claim 1, characterized in that ,According to the first information, dynamic partition processing is performed, the density, humidity and height of the material accumulation are analyzed through an adaptive partitioning algorithm, the boundaries and characteristic labels of the blocks are dynamically adjusted, and the blocks are prioritized based on density and stability to obtain an operation block model, including: Performing preliminary area division according to the three-dimensional point cloud data in the first information, performing density clustering on the point cloud data by using a density clustering algorithm, identifying areas and material boundaries with similar density, and obtaining a preliminary partition model; Performing block characteristic labeling processing according to the preliminary partition boundary and the spectral imaging data in the first information, extracting the moisture and density characteristics of the material through a spectral analysis method, and obtaining a block characteristic model with moisture and density labels; Perform boundary adjustment processing according to the block characteristic model, use a density gradient-based adaptive boundary expansion algorithm to calculate the density gradient of each block, determine whether the boundary of each block needs to be expanded or contracted, and dynamically adjust the block boundary to obtain a partition model with stability adaptation; Priority sorting is performed according to the stability-adaptive zoning model, and the density and humidity characteristics of the blocks are analyzed by a sorting algorithm based on multi-factor weights to obtain a hierarchical priority operation block model.

3. The stacker-reclaimer operation control method according to claim 1, characterized in that , according to the operation block model and the second information, task allocation processing is performed, and based on the current load, inclination and speed state of the stacker and reclaimer, the priority of the block task is dynamically adjusted to obtain the task priority sequence, including: Perform load distribution processing according to the operation block model and the current load data of the stacker-reclaimer in the second information, calculate the task allocation priority of each block by using the real-time load data of the stacker-reclaimer as a weight factor, and obtain a preliminary task priority sequence; Performing stability adjustment processing according to the preliminary task priority sequence and the stacker-reclaimer inclination data in the second information, calculating the inclination risk of each task block using an inclination feedback control algorithm, and rearranging the task sequence based on the risk calculation result to obtain an optimized task sequence; Performing speed matching processing according to the optimized task sequence and the stacker-reclaimer speed state in the second information, and obtaining the task sequence by calculating the distance and speed matching degree of the block tasks; Dynamic priority update processing is performed according to the task sequence. Different weights are assigned to the density of the task blocks, the real-time load, inclination angle and speed state of the stacker-reclaimer by constructing a multi-factor weight matrix. The dynamic priority of each block is comprehensively calculated to obtain the final task priority sequence.

4. The stacker-reclaimer operation control method according to claim 1, characterized in that , according to the task priority, the operation parameters are optimized, and the dynamic deformation of the material during the operation is predicted, and the angle and depth of the stacker and reclaimer are adjusted in real time using the finite element model to obtain the operation parameters, including: Deformation prediction processing is performed according to the task priority order, and a recurrent neural network model based on material density and force analysis is used to analyze the density, pressure and stress changes of materials in each block during the stacker-reclaimer operation process, and the morphological change trend of the materials is estimated to obtain a dynamic deformation matrix; Performing angle adjustment processing according to the dynamic deformation matrix and the stacker-reclaimer inclination data in the second information, dynamically adjusting the stacker-reclaimer inclination based on the predicted material deformation trend, and obtaining a real-time inclination adjustment parameter; Performing depth optimization processing according to the real-time inclination adjustment parameters, and obtaining depth setting parameters by simulating the optimal stacking depth under the current inclination angle and stacking form; Parameter optimization processing is performed according to the depth setting parameter and the real-time inclination adjustment parameter, and operation parameters are obtained by load adjustment of the inclination and depth settings.

5. The stacker-reclaimer operation control method according to claim 1, characterized in that ,According to the operation parameters, an energy efficiency optimization analysis is performed, by decomposing the operation process into multiple sub-chains, gradually calculating the energy consumption of each sub-chain at different densities and inclinations, and achieving load balance and optimal energy consumption through a multi-objective optimization algorithm, and obtaining energy efficiency optimization parameters, including: Decomposing the operation chain according to the operation parameters, dividing the operation process into multiple sub-chains based on the operation characteristics and material density of each block, wherein each sub-chain represents the material taking, moving and dumping operations in the corresponding block, and obtaining a chain sequence; Performing energy consumption estimation processing according to the chain sequence, and obtaining a sub-chain energy consumption matrix by calculating the energy consumption of each sub-chain under density and inclination conditions in its operating block; Performing load balancing optimization processing according to the sub-chain energy consumption matrix, and rearranging the task order of the sub-chain by adopting a weighted polling scheduling algorithm to obtain a load balancing optimization chain; The optimal energy consumption solution is performed according to the load balancing optimization chain, and the path and parameter settings are dynamically adjusted by combining the energy consumption, execution order and load fluctuation of each sub-chain to obtain energy efficiency optimization parameters.

6. A stacker-reclaimer operation control system, characterized in that: include: An acquisition module, used to acquire first information and second information, wherein the first information includes three-dimensional point cloud data and spectral imaging data of the deposited materials, and the second information includes real-time status data of the stacker-reclaimer; A partitioning module, used to perform dynamic partitioning processing according to the first information, analyze the density, humidity and height of the material accumulation through an adaptive partitioning algorithm, dynamically adjust the boundaries and characteristic labels of the blocks, and prioritize the blocks based on density and stability to obtain an operation block model; A sorting module, used for performing task allocation processing according to the operation block model and the second information, dynamically adjusting the priority of the block tasks based on the current load, inclination and speed state of the stacker-reclaimer, and obtaining a task priority order; An optimization module is used to optimize the operation parameters according to the task priority order, and obtain the operation parameters by predicting the dynamic deformation of the material during the operation and adjusting the angle and depth of the stacker and reclaimer in real time using a finite element model; A decomposition module is used to perform energy efficiency optimization analysis according to the operation parameters, by decomposing the operation process into multiple sub-chains, gradually calculating the energy consumption of each sub-chain at different densities and inclinations, and achieving load balance and optimal energy consumption through a multi-objective optimization algorithm to obtain energy efficiency optimization parameters; The output module is used to formulate a work plan according to the energy efficiency optimization parameters and the task priority order, and obtain a final work plan by comprehensively analyzing the priority blocks and the optimal energy consumption path.

7. The stacker-reclaimer operation control system according to claim 6, characterized in that: The partition module comprises: A first partitioning unit is used to perform preliminary area partitioning according to the three-dimensional point cloud data in the first information, and to perform density clustering on the point cloud data by using a density clustering algorithm to identify areas and material boundaries with similar densities, so as to obtain a preliminary partitioning model; A first labeling unit is used to perform block characteristic labeling processing according to the preliminary partition boundary and the spectral imaging data in the first information, extract the humidity and density characteristics of the material through a spectral analysis method, and obtain a block characteristic model with humidity and density labels; A first adjustment unit is used to perform boundary adjustment processing according to the block characteristic model, calculate the density gradient of each block using a density gradient-based adaptive boundary expansion algorithm, determine whether the boundary of each block needs to be expanded or contracted, and dynamically adjust the block boundary to obtain a stability-adaptive partition model; The first sorting unit is used to perform priority sorting according to the stability-adaptive partition model, analyze the density and humidity characteristics of the blocks through a sorting algorithm based on multi-factor weights, and obtain a hierarchical priority operation block model.

8. The stacker-reclaimer operation control system according to claim 6, characterized in that: The sorting module comprises: A first allocation unit is used to perform load allocation processing according to the operation block model and the current load data of the stacker-reclaimer in the second information, and calculate the task allocation priority of each block by using the real-time load data of the stacker-reclaimer as a weight factor to obtain a preliminary task priority sequence; a second adjustment unit, configured to perform stability adjustment processing according to the preliminary task priority sequence and the stacker-reclaimer inclination data in the second information, calculate the inclination risk of each task block by using an inclination feedback control algorithm, and rearrange the task sequence based on the risk calculation result to obtain an optimized task sequence; A first matching unit, configured to perform speed matching processing according to the optimized task sequence and the speed state of the stacker-reclaimer in the second information, and obtain a task sequence by calculating the distance and speed matching degree of the block tasks; The first updating unit is used to perform dynamic priority update processing according to the task sequence, and assign different weights to the density of the task block, the real-time load, inclination angle and speed state of the stacker and reclaimer by constructing a multi-factor weight matrix, and comprehensively calculate the dynamic priority of each block to obtain the final task priority sequence.

9. The stacker-reclaimer operation control system according to claim 6, characterized in that: The optimization module includes: The first prediction unit is used to perform deformation prediction processing according to the task priority order, use a recurrent neural network model based on material density and force analysis to analyze the density, pressure and stress changes of each block of materials during the stacker-reclaimer operation, and estimate the morphological change trend of the materials to obtain a dynamic deformation matrix; a third adjustment unit, configured to perform angle adjustment processing according to the dynamic deformation matrix and the stacker-reclaimer inclination data in the second information, dynamically adjust the stacker-reclaimer inclination based on the predicted material deformation trend, and obtain a real-time inclination adjustment parameter; A first optimization unit is used to perform depth optimization processing according to the real-time inclination adjustment parameter, and obtain a depth setting parameter by simulating an optimal stacking depth under a current inclination and stacking form; The second optimization unit is used to perform parameter optimization processing according to the depth setting parameter and the real-time inclination adjustment parameter, and obtain the operation parameter by load adjustment of the inclination and depth settings.

10. The stacker-reclaimer operation control system according to claim 6, characterized in that: The decomposition module comprises: A first decomposition unit is used to perform operation chain decomposition processing according to the operation parameters, and divide the operation process into multiple sub-chains based on the operation characteristics and material density of each block, wherein each sub-chain represents the material collection, movement and dumping operations in the corresponding block, and obtain a chain sequence; A first estimation unit is used to perform energy consumption estimation processing according to the chain sequence, and obtain a sub-chain energy consumption matrix by calculating the energy consumption of each sub-chain under density and inclination conditions in its operation block; A third optimization unit is used to perform load balancing optimization processing according to the sub-chain energy consumption matrix, and to obtain a load balancing optimization chain by rearranging the task order of the sub-chains by adopting a weighted polling scheduling algorithm; The first solving unit is used to perform optimal energy consumption solution processing according to the load balancing optimization chain, and dynamically adjust the path and parameter settings by combining the energy consumption, execution order and load fluctuation of each sub-chain to obtain energy efficiency optimization parameters.

Images