Intelligent mine-used crushing robot control method based on working condition recognition

Abstract

The application discloses an intelligent mine-used crushing robot control method based on working condition identification, relates to the technical field of mine-used equipment automatic control, and comprises the following steps: a wireless communication system is built in advance, remote driving configuration adjustment of a vehicle end is carried out, a working condition identification system and an environment acquisition system are configured; a centralized control center collects data of the working condition identification system and the environment acquisition system in real time, and controls a working task of the vehicle end. Through accurate working condition identification and efficient path planning, the application can quickly find a position of ore and plan an optimal driving path, reduces invalid running time of equipment in a mine, simultaneously, reasonable crushing action decision ensures efficient crushing of different ores, significantly improves overall efficiency of ore crushing operation, and the optimized crushing action frequency and duration and the strategy of adjusting crushing intensity according to hardness of the ore effectively reduce energy consumption and wear of the equipment, prolong the service life of the equipment, and reduce operation cost.

Description

Technical Field

[0001] This invention relates to the field of automated control technology for mining equipment, and more specifically, to a control method for an intelligent mining crushing robot based on working condition recognition. Background Technology

[0002] In mining operations, ore crushing is one of the key processes. Traditional mining crushing equipment usually relies on manual operation, which is not only labor-intensive and inefficient, but also exposes operators to high safety risks in the complex and dangerous underground environment.

[0003] With the continuous development of intelligent technology, although some mining equipment has begun to introduce automated control technology, existing control methods still have many shortcomings in terms of the accuracy of working condition identification, the rationality of task planning, and equipment adaptability, failing to meet the needs of efficient and safe mining. For example, when facing complex and ever-changing underground working conditions, it is difficult to accurately identify ore distribution and obstacle conditions, leading to low equipment operating efficiency and even accidents such as collisions; in terms of crushing action control, the lack of scientific and reasonable strategies results in problems such as excessive energy consumption and severe equipment wear.

[0004] Therefore, there is an urgent need to propose a new intelligent mining crushing robot control method based on working condition recognition to solve the above-mentioned problems in the existing technology.

[0005] No effective solutions have yet been proposed to address the problems in the relevant technologies. Summary of the Invention

[0006] To address the problems in related technologies, this invention proposes a control method for an intelligent mining crushing robot based on working condition recognition, in order to overcome the aforementioned technical problems existing in the existing related technologies.

[0007] The technical solution of this invention is implemented as follows:

[0008] A control method for an intelligent mining crushing robot based on working condition recognition includes the following steps:

[0009] The wireless communication system is set up in advance. Based on the site environment and the scope of the work area, the installation locations of the aggregation switch and wireless AP are preset, and the network latency is within the preset range.

[0010] Adjustments to the vehicle-side remote driving configuration include at least the following: adjustments to the electrical drive-by-wire configuration, adjustments to the hydraulic system configuration, and adjustments to the monitoring suite configuration.

[0011] Configure a working condition identification system and an environmental data acquisition system;

[0012] The central control center collects data from the working condition identification system and the environmental acquisition system in real time, and controls the work tasks at the vehicle end, including at least: remote control to control the remote control seat to synchronously control the vehicle end to complete the work tasks and automatic control according to the working conditions.

[0013] Furthermore, the adjustment of the electrical wire control configuration includes: according to the area delineation, adopting the trunk-to-branch line method to reduce the number of single wire harnesses and ensure stable and reliable electrical signal transmission.

[0014] Furthermore, the adjustment of the hydraulic system configuration includes: adjusting the flow and pressure control parameters of the hydraulic oil to enhance the force and stability control capability of the crushing action, so as to adapt it to the requirements of remote control and automated operation.

[0015] Furthermore, the monitoring kit configuration adjustment includes: adjusting the installation positions of the vehicle sensing unit, vehicle monitoring and communication connection equipment to ensure comprehensive monitoring of vehicle status.

[0016] Furthermore, the working condition recognition system includes: a vehicle-mounted camera installed on the vehicle end and a tunnel camera installed in the underground tunnel; the environmental acquisition system includes: lidar, ultrasonic sensor, hardness sensor, GPS and IMU.

[0017] Furthermore, the automatic control based on operating conditions includes the following steps:

[0018] Based on the work area map, ore distribution, and obstacle information collected by the work condition identification system and the environmental acquisition system, the central control center plans the optimal driving path from the current location to the ore location.

[0019] Dynamic path planning correction is performed. During the operation of the crusher, the sensor collects environmental information in real time. When environmental changes are detected, such as the addition of obstacles or changes in the distribution of ore, the affected area is determined and the shortest path of the node in the area is corrected.

[0020] The crushing action decision is made based on the optimal travel path to determine the best crushing strategy for different ores. By establishing a mapping relationship between hardness and crushing force, the crushing action sequence and the crushing action frequency and duration are determined to achieve efficient crushing of ores.

[0021] Furthermore, the optimal driving route includes the following steps:

[0022] The current position of the crusher is set as the source point s. A set V containing all drivable locations (nodes) and a set E of edges connecting these nodes are constructed, where the weight w(u,v) of each edge represents the distance from node u to node v. Two arrays are created: a distance array d, initially d[s] = 0, and for all other nodes v ∈ V and v ≠ s, d[v] = ∞; and a predecessor node array pre, initially pre[v] = null, indicating that the predecessor node has not yet been determined. A set Q = V of nodes for which the shortest path has not yet been determined is also created.

[0023] To find the node with the minimum distance, select the node u from set Q that has the minimum distance to the source node s, i.e., u = argmin. v∈Q d[v]. Remove node u from set Q;

[0024] Update the distances between adjacent nodes. For all adjacent nodes v of node u, i.e., there exists an edge (u,v)∈E, calculate the distance d from the source node s through node u to node v. new , represented as: d new =d[u]+w(u,v), where, if d new If d[v] < d[v], then update d[v] = d[v] new And set pre[v] = u, indicating that the predecessor node of node v is updated to u;

[0025] The loop continues until all nodes have been processed. The steps of finding the node with the minimum distance and updating the distance of adjacent nodes are repeated until the set Q is empty. At this point, the distance array d stores the shortest distance from the source point s to each node. The shortest path from the source point to the target node, i.e. the ore location, can be obtained by backtracking through the predecessor node array pre.

[0026] Furthermore, the correction of the shortest path to the nodes in the region includes the following steps:

[0027] Let the area of ​​influence of an obstacle be a region with radius r centered at the obstacle's location. For a node v located within this region, the following condition is met: Among them, (x v ,y v Let (x) be the coordinates of node v, and (x) be the coordinates of node v. obs ,y obs Let d[v] be the coordinates of the obstacle; set d[v] to ∞. When dealing with changes in edge weights caused by changes in ore distribution, the original edge weight is denoted as w(u,v), and the changed weight is denoted as w'(u,v). When w(u,v) ≠ w'(u,v), the shortest distance of the affected node is corrected, expressed as:

[0028] d new =d[u]+w'(u,v).

[0029] The beneficial effects of this invention are:

[0030] 1. This invention, through precise working condition identification and efficient path planning, can quickly locate the ore and plan the optimal travel path, reducing the ineffective operating time of the equipment underground. At the same time, reasonable crushing action decisions ensure efficient crushing of different ores, significantly improving the overall efficiency of ore crushing operations. Furthermore, the optimized crushing action frequency and duration, as well as the strategy of adjusting the crushing force according to the hardness of the ore, effectively reduce the energy consumption and wear of the equipment, extend the service life of the equipment, and reduce operating costs.

[0031] 2. This invention liberates operators from the hazardous underground environment by reducing safety risks through remote control and automated control. Furthermore, the comprehensive monitoring system and real-time environmental data acquisition system can promptly detect potential hazards, further ensuring the safety of equipment and personnel. Simultaneously, it can dynamically adjust to the complex and ever-changing underground conditions (such as changes in ore distribution and the appearance of obstacles), exhibiting strong environmental adaptability and ensuring stable and efficient operation of the equipment under various conditions. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments 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.

[0033] Figure 1 This is a flowchart illustrating a control method for an intelligent mining crushing robot based on working condition recognition according to an embodiment of the present invention. Detailed Implementation

[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention are within the scope of protection of the present invention.

[0035] According to an embodiment of the present invention, a control method for an intelligent mining crushing robot based on working condition recognition is provided.

[0036] like Figure 1 As shown, the intelligent mining crushing robot control method based on working condition recognition according to an embodiment of the present invention includes the following steps:

[0037] A wireless communication system was pre-built. In an underground mining area, based on the terrain and equipment distribution, precise measurements and analysis determined the locations for installing aggregation switches and wireless access points (APs) at key points in the tunnels. Equipment from well-known industrial brands was selected, and installation was carried out strictly according to specifications, ensuring the equipment protection level reached IP5. After installation, professional network testing tools were used to debug the network, ultimately achieving a stable network latency of approximately 30ms, meeting the real-time requirements of remote control and data transmission.

[0038] Adjustments to the vehicle's remote driving configuration are required, including at least the following: adjustments to the electrical drive-by-wire configuration, the hydraulic system configuration, and the monitoring suite configuration; specifically;

[0039] Among these adjustments, taking a certain model of mining crushing robot as an example, the electrical control configuration was modified by using the original vehicle's connectors without altering the original wiring harness. Based on the division of work areas, a trunk-to-branch line conversion method was adopted to optimize the originally complex wiring harness, reducing the number of individual harnesses. Testing showed that the electrical signal transmission was stable and reliable, effectively avoiding signal interference and transmission interruptions.

[0040] Among the adjustments made, the hydraulic system configuration was adjusted, and key components of the hydraulic system of the mining crushing robot were optimized. Through multiple experiments and parameter adjustments, the flow and pressure control parameters of the hydraulic oil were precisely set. After the adjustment, the force and stability of the crushing action were significantly improved, and the crushing action could be controlled more precisely during remote control and automated operation.

[0041] The monitoring suite configuration was adjusted by installing vehicle sensing units, vehicle monitoring equipment, and communication connection equipment at appropriate locations on the vehicle body, based on the vehicle structure and operational requirements. For example, vehicle sensing units were installed at key locations at the front and rear of the vehicle to ensure accurate perception of the surrounding environment. The number and installation angle of the onboard equipment were also determined appropriately, such as installing three onboard cameras and adjusting them to different angles to achieve comprehensive 360-degree monitoring of the vehicle's surroundings.

[0042] Configure a working condition identification system and an environmental data acquisition system;

[0043] The operational condition recognition system includes: a high-resolution vehicle-mounted camera installed on the vehicle, with the camera angle adjusted to achieve 360-degree real-time monitoring, achieving a resolution of 1080P. Roadway cameras are installed every 100 meters in the underground tunnels, also ensuring a 1080P resolution. After debugging, the video images can be stably and uninterruptedly transmitted to the central control center, allowing the driver to clearly view the conditions in the underground tunnels.

[0044] This technical solution involves debugging the working condition recognition system to ensure uninterrupted transmission of video images, allowing the driver to clearly view the underground roadway conditions from the central control center.

[0045] The environmental acquisition system includes a lidar installed at a suitable location on the vehicle's roof to comprehensively scan the work area; an ultrasonic sensor installed near the work surface to assist in close-range detection; a hardness sensor installed on the crushing head to detect ore hardness in real time; and GPS and IMU installed at the vehicle's center of gravity to ensure accurate measurement of equipment position and attitude.

[0046] The central control center collects data from the working condition identification system and the environmental acquisition system in real time, and performs work task control on the vehicle side. The work task control on the vehicle side includes at least: remote control and automatic control based on working conditions.

[0047] The process of remote control includes the following steps:

[0048] Remote control system installation and commissioning: At the Inoue control center, a remote control chair, a 27-inch high-resolution curved screen monitor, and a top-tier brand control computer and server were installed. The various control functions of the remote control chair were repeatedly debugged. For example, the lifting and speed control accuracy of the boom, forearm, and hammer were tested to ensure that the control error was within the allowable range; the impact control function of the hydraulic breaker was tested to ensure that the impact force and frequency could be accurately adjusted. Simultaneously, the LED status indicator function was comprehensively tested to ensure that it could accurately display the vehicle's real-time operating status, running status, fault information, and maintenance guidance.

[0049] Controlling operational tasks: Operators can remotely control the vehicle to complete various operational tasks in real time via a remote control seat, such as driving the vehicle through underground roadways and operating the crusher head to crush ore. During actual operation, operators can precisely control the vehicle's movements based on real-time images and status information displayed on the monitor.

[0050] The automatic control based on operating conditions includes the following steps:

[0051] To plan the optimal travel path, assume that at a certain moment, the working condition identification system and environmental acquisition system collect the work area map, ore distribution, and obstacle information. The control center constructs sets V and E with the current position of the crusher as the source point s. Through a program algorithm, following steps such as finding the minimum distance node and updating the distances of adjacent nodes, the optimal travel path from the current position to the ore location is planned. In practical applications, after multiple tests, this path planning algorithm can calculate the optimal path in a short time, effectively improving the operating efficiency of the equipment. Details are as follows:

[0052] The current position of the crusher is set as the source point s. A set V containing all drivable locations (nodes) and a set E of edges connecting these nodes are constructed, where the weight w(u,v) of each edge represents the distance from node u to node v. Two arrays are created: a distance array d, initially d[s] = 0, and for all other nodes v ∈ V and v ≠ s, d[v] = ∞; and a predecessor node array pre, initially pre[v] = null, indicating that the predecessor node has not yet been determined. A set Q = V of nodes for which the shortest path has not yet been determined is also created.

[0053] To find the node with the minimum distance, select the node u from set Q that has the minimum distance to the source node s, i.e., u = argmin. v∈Q d[v]. Remove node u from set Q;

[0054] Update the distances between adjacent nodes. For all adjacent nodes v of node u, i.e., there exists an edge (u,v)∈E, calculate the distance d from the source node s through node u to node v. new , represented as: d new =d[u]+w(u,v), where, if d new If d[v] < d[v], then update d[v] = d[v] new And set pre[v] = u, indicating that the predecessor node of node v is updated to u;

[0055] The loop continues until all nodes have been processed, repeating the steps of finding the node with the minimum distance and updating the distances of adjacent nodes, until the set Q is empty. At this point, the distance array d stores the shortest distance from the source node s to each node. The shortest path from the source node to the target node, i.e., the location of the ore, can be obtained by backtracking through the predecessor node array pre.

[0056] Dynamic path planning and correction are performed during the operation of the crusher. When sensors detect new obstacles, the system determines the obstacle's impact range based on a preset algorithm and corrects the shortest paths to nodes within the affected area. For example, when a large obstacle is detected ahead, the system quickly calculates the affected area and replans the paths within that area to ensure the equipment can safely avoid the obstacle and continue towards the ore location. Details are as follows:

[0057] Let the area of ​​influence of an obstacle be a region with radius r centered at the obstacle's location. For a node v located within this region, the following condition is met: Among them, (x v ,y v Let (x) be the coordinates of node v, and (x) be the coordinates of node v. obs ,y obsLet d[v] be the coordinates of the obstacle; set d[v] to ∞. When dealing with changes in edge weights caused by changes in ore distribution, the original edge weight is denoted as w(u,v), and the changed weight is denoted as w'(u,v). When w(u,v) ≠ w'(u,v), the shortest distance of the affected node is corrected, expressed as:

[0058] d new =d[u]+w'(u,v).

[0059] The crushing action decision is based on the optimal travel path to determine the best crushing strategy for different ores. By establishing a mapping relationship between hardness and crushing force, the sequence of crushing actions and the optimization of crushing action frequency and duration are determined to achieve efficient crushing of the ore. This includes the following steps:

[0060] Data on the crushing effect of ores of different hardness under different crushing forces were collected in advance through experiments. The hardness value H of the ore was obtained using a hardness sensor, and the hardness value was divided into several intervals. A large number of crushing experiments were carried out for each interval, and the minimum crushing force F that could effectively crush the ore was recorded.

[0061] The relationship between the hardness value H and the crushing force F is fitted using a linear regression model, expressed as:

[0062] F = aH + b;

[0063] Here, a and b are coefficients obtained by fitting experimental data using the least squares method.

[0064] The goal of the least squares method is to minimize the sum of squared errors between the predicted and actual values, expressed as:

[0065]

[0066] By taking the partial derivatives of S(a,b) with respect to a and b respectively, and setting the partial derivatives to 0, we can obtain the system of equations for solving a and b, expressed as:

[0067]

[0068] Solving this system of equations yields the values ​​of a and b, thus determining the mapping relationship between hardness and crushing force.

[0069] The method involves determining the order of crushing actions using a Depth-First Search (DFS) algorithm, combined with the spatial distribution information of the ore and the crushing priority. For example, when faced with multiple ores of different sizes, the larger ores are prioritized for crushing based on their size. Starting from the current robot position, the DFS algorithm traverses the graph to determine the next ore to be crushed. Practical testing has shown that this method can effectively arrange the crushing sequence and improve overall crushing efficiency. The steps include:

[0070] Define a stack S to store the nodes to be visited. Initially, push the current node onto the stack. In each step, pop a node v from the stack. If the node is an unvisited ore node, mark it as visited and push its adjacent unvisited nodes onto the stack. Repeat this process until the stack is empty.

[0071] The optimization process involved adjusting the crushing frequency and duration, setting an objective function, measuring power consumption (P) at different frequencies and durations to obtain energy consumption, evaluating equipment wear (W), and determining weighting coefficients. A genetic algorithm was used to optimize the crushing frequency (f) and duration (t), continuously evolving individuals in the population until the optimal solution was found. In practical applications, after optimization, the equipment's energy consumption was reduced by approximately 20%, and equipment wear was effectively controlled. Details are as follows:

[0072] The calibration objective function J(f,t) takes into account crushing efficiency E, energy consumption P, and equipment wear W, and is expressed as:

[0073] J(f,t)=w1E(f,t)-w2P(f,t)-w3W(f,t)

[0074] Among them, w1, w2, and w3 are weighting coefficients used to adjust the relative importance of each factor, E(f,t) is the amount of ore crushed per unit time, P(f,t) is the energy consumption obtained by measuring the power consumption of the equipment at different frequencies and durations, and W(f,t) is the equipment wear.

[0075] During the optimization process, the values ​​of f and t are continuously updated using an optimization algorithm to maximize J(f,t).

[0076] Specifically, in application, genetic algorithms can be used to continuously evolve individuals in the population, i.e., combinations of f and t, through selection, crossover, and mutation operations, until the optimal solution is found.

[0077] In summary, by employing the above-described technical solution of the present invention, the following effects can be achieved:

[0078] 1. This invention, through precise working condition identification and efficient path planning, can quickly locate the ore and plan the optimal travel path, reducing the ineffective operating time of the equipment underground. At the same time, reasonable crushing action decisions ensure efficient crushing of different ores, significantly improving the overall efficiency of ore crushing operations. Furthermore, the optimized crushing action frequency and duration, as well as the strategy of adjusting the crushing force according to the hardness of the ore, effectively reduce the energy consumption and wear of the equipment, extend the service life of the equipment, and reduce operating costs.

[0079] 2. This invention liberates operators from the hazardous underground environment by reducing safety risks through remote control and automated control. Furthermore, the comprehensive monitoring system and real-time environmental data acquisition system can promptly detect potential hazards, further ensuring the safety of equipment and personnel. Simultaneously, it can dynamically adjust to the complex and ever-changing underground conditions (such as changes in ore distribution and the appearance of obstacles), exhibiting strong environmental adaptability and ensuring stable and efficient operation of the equipment under various conditions.

[0080] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Those skilled in the art, upon considering the disclosure in the specification and embodiments, will readily conceive of other embodiments of this disclosure. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0081] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A control method for an intelligent mining crushing robot based on working condition recognition, characterized in that, Includes the following steps: The wireless communication system is set up in advance. Based on the site environment and the scope of the work area, the installation locations of the aggregation switch and wireless AP are preset, and the network latency is within the preset range. Adjustments to the vehicle-side remote driving configuration include at least the following: adjustments to the electrical drive-by-wire configuration, adjustments to the hydraulic system configuration, and adjustments to the monitoring suite configuration. Configure a working condition identification system and an environmental data acquisition system; The central control center collects data from the working condition identification system and the environmental acquisition system in real time, and controls the work tasks at the vehicle end, including at least: remote control that synchronously controls the vehicle end to complete the work tasks by controlling the remote control seat and automatic control according to the working conditions; The automatic control based on operating conditions includes the following steps: Based on the work area map, ore distribution, and obstacle information collected by the work condition identification system and the environmental acquisition system, the central control center plans the optimal driving path from the current location to the ore location. Dynamic path planning correction is performed. During the operation of the intelligent mining crushing robot, the sensors in the environmental acquisition system collect environmental information in real time. When environmental changes are detected, such as the addition of obstacles or changes in ore distribution, the affected area is determined and the shortest path of the node in the area is corrected. By establishing a mapping relationship between hardness and crushing force, determining the sequence of crushing actions, and optimizing the frequency and duration of crushing actions, efficient crushing of ore can be achieved. Determining the order of crushing actions includes: using the depth-first search (DFS) algorithm, combined with the spatial distribution information of the ore and the crushing priority, to plan the order of crushing actions; Optimize the frequency and duration of the crushing action, including: setting the objective function. : ； in, These are weighting coefficients used to adjust the relative importance of each factor. This represents the amount of ore crushed per unit time. Energy consumption was measured by measuring the power consumption of the intelligent mining crushing robot at different frequencies and durations. To address wear and tear on intelligent mining crushing robots, a genetic algorithm is employed to continuously evolve individuals in the population (i.e., combinations of f and t) through selection, crossover, and mutation operations until an optimal solution is found. maximize.

2. The intelligent mining crushing robot control method based on working condition recognition according to claim 1, characterized in that, The adjustment of the electrical wire control configuration includes: according to the area delineation, adopting the trunk line to branch line method to reduce the number of single wire harnesses and ensure stable and reliable electrical signal transmission.

3. The intelligent mining crushing robot control method based on working condition recognition according to claim 2, characterized in that, The adjustment of the hydraulic system configuration includes: adjusting the flow and pressure control parameters of the hydraulic oil to enhance the force and stability control capability of the crushing action, so as to adapt it to the requirements of remote control and automated operation.

4. The intelligent mining crushing robot control method based on working condition recognition according to claim 3, characterized in that, The configuration adjustment of the monitoring kit includes: adjusting the installation positions of the vehicle sensing unit, vehicle monitoring and communication connection equipment to ensure comprehensive monitoring of vehicle status.

5. The intelligent mining crushing robot control method based on working condition recognition according to claim 1, characterized in that, The working condition identification system includes: a vehicle-mounted camera installed on the vehicle end and a tunnel camera installed in the underground tunnel; the environmental acquisition system includes: lidar, ultrasonic sensor, hardness sensor, GPS and IMU.

6. The intelligent mining crushing robot control method based on working condition recognition according to claim 1, characterized in that, The optimal driving route includes the following steps: The current position of the intelligent mining crushing robot is set as the source point s. A set V containing all drivable positions (nodes) and a set E of edges connecting these nodes are constructed, where the weight w(u,v) of each edge represents the distance from node u to node v. Two arrays are created: a distance array d and a distance array d. Initially... For all other nodes and , The predecessor node array `pre`, initially... This indicates that the predecessor node has not yet been determined; and a set of nodes for which the shortest path has not yet been determined is created. ; Find the node with the minimum distance: select the node u from set Q that has the minimum distance to the source node s. Remove node u from set Q; Update the distances between adjacent nodes. For all adjacent nodes v of node u, i.e., if an edge exists... Calculate the distance from the source node s through node u to node v. , is represented as: , among which, if Then update and will This indicates that the predecessor node of node v is updated to u; The loop continues until all nodes have been processed. The steps of finding the node with the minimum distance and updating the distance of adjacent nodes are repeated until the set Q is empty. At this point, the distance array d stores the shortest distance from the source point s to each node. The shortest path from the source point to the target node, i.e. the ore location, can be obtained by backtracking through the predecessor node array pre.

7. The intelligent mining crushing robot control method based on working condition recognition according to claim 6, characterized in that, The correction of the shortest path to the nodes in the region includes the following steps: Let the area of ​​influence of an obstacle be a region with radius r centered at the obstacle's location; for a node v located within this region, the following condition must be met: ,in, Let v be the coordinates of node v. The coordinates of the obstacle; Set as When dealing with changes in edge weights caused by variations in ore distribution, the original edge weights are denoted as w(u,v), and the changed weights are denoted as w'(u,v). When correcting the shortest distance to the affected nodes, it is expressed as: 。

Images