Multi-process collaborative decision-making control system for coal mine tunneling operation

Abstract

The invention relates to a coal mine tunneling operation multi-process collaborative decision-making control system, and belongs to the technical field of coal mine intellectualization. Comprising a multi-process spatial constraint model construction module used for constructing a multi-process spatial constraint model; the multi-process collaborative decision-making module is used for importing a tunneling work event set, an adjacency list and an input array at the beginning of a current tunneling period, determining a next executable optimal process according to the input array, and sending a control instruction to execution equipment corresponding to the next executable optimal process; the process sensing module is used for sensing and sending a process execution state signal in real time; and the multi-process collaborative decision-making module is also used for updating the in-process array when the execution of the process is determined to be completed, and deciding a next executable optimal process according to the updated in-process array. The optimal process decision-making method provided by the invention is not limited by a time relation constraint threshold range and an abnormal working condition or a complex working condition, and can dynamically adapt to an underground real-time mining working condition.

Description

Technical Field

[0001] The present invention relates to the technical field of coal mine intelligence, and particularly to a multi-process collaborative decision-making control system for coal mine tunneling operations. Background Art

[0002] The coal mine tunneling operation process is cumbersome, involving numerous operation steps, and the sequence, immediate responsiveness, and accuracy of these steps are all crucial. With the deployment of a large number of intelligent sensors underground and the continuous popularization of computer technology, it has been possible to achieve real-time early warning of the tunneling face environment and online monitoring of the working status of the tunneling equipment group, and individual equipment has been able to achieve automatic control with few or no operators. However, the tunneling operation involves multi-process and collaborative operation among multiple devices. Due to the harsh underground mining environment, unexpected situations may occur during the execution of each process, and the execution time may be significantly delayed.

[0003] Patent CN114967456A discloses a multi-behavior collaborative control decision-making method for a coal mine intelligent tunneling robot. The proposed multi-behavior collaborative control decision-making method for the coal mine intelligent tunneling robot solves for the optimal time sequence that satisfies the constraint relationship by presetting the time relationship constraint threshold range between various tunneling actions. However, the technical solutions in the above patent and traditional automated multi-process collaborative decision-making systems usually only set the time constraints between each process as a fixed range threshold according to experience, without considering the adjustment of the control method in the event of abnormal and complex working conditions, and cannot dynamically adapt to the real-time underground mining working conditions, resulting in poor practical application capabilities. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a multi-process collaborative decision-making control system for coal mine tunneling operations. The technical solution of the present invention is as follows: A multi-process collaborative decision-making control system for coal mine tunneling operations, which includes a multi-process collaborative decision-making module. The multi-process collaborative decision-making module is communicatively connected to a multi-process spatio-temporal constraint model construction module and a process perception module: The multi-process spatio-temporal constraint model construction module is used to construct a multi-process spatio-temporal constraint model according to the actual mining situation of the tunneling face. Among them, the multi-process spatio-temporal constraint model includes a tunneling work event set, an adjacency list, and an in-degree array; The multi-process collaborative decision-making module is used to import the tunneling work event set, the adjacency list, and the in-degree array at the beginning of the current tunneling cycle, and determine the next best executable process according to the in-degree array, and send a control instruction to the execution device corresponding to the next best executable process; The process perception module is used to continuously perceive the process execution status signal during the execution of the control instruction by the execution device, and continuously send the process execution status signal to the multi-process collaborative decision-making module; The multi-process collaborative decision-making module is also used to record the process execution time, update the in-degree array when it is determined that the process execution is completed according to the process execution status signal sent by the process perception module, and decide the next best executable process according to the updated in-degree array until the current tunneling cycle ends.

[0005] Optionally, when constructing the multi-process spatio-temporal constraint model, the multi-process spatio-temporal constraint model construction module is used to: Construct a tunneling process event set for the current tunneling cycle according to the actual mining situation of the tunneling face. The tunneling process event set uses nodes to represent processes and edges to represent the spatio-temporal constraints for the execution of two processes, including multiple process constraint binary tuples, denoted as {u, v}, where u→v means that process u needs to be executed before process v. Determine the adjacency list of all nodes in the tunneling process event set, and determine the in-degree array of all nodes according to the adjacency list of all nodes; among them, the adjacency list is the set of nodes of the next process that can be continued after the current process is executed, and the in-degree array includes the in-degree value of each node; the in-degree value represents the number of processes that still need to be executed if the current process wants to be executed.

[0006] Optionally, when determining the adjacency list of all nodes in the tunneling process event set, the multi-process spatio-temporal constraint model construction module is used to: First, obtain the previous node u and the next node v1 in the first process constraint binary tuple {u, v1} in the tunneling process event set, then create an adjacency list for node u, put node v1 into the adjacency list of u, and continue to traverse the tunneling process event set. If there is a new process constraint binary tuple {u, v2} for node u, then continue to put v2 into the adjacency list of u until all process constraint binary tuples for node u are processed, indicating that the adjacency list of node u is constructed. Then continue to process the remaining process constraint binary tuples in the order of each process constraint binary tuple in the tunneling process event set until the adjacency lists of all nodes in the tunneling process event set are constructed.

[0007] Optionally, when determining the in-degree array of all nodes according to the adjacency list of all nodes, the multi-process spatio-temporal constraint model construction module is used to: First, set the initial value of the in-degree value of all nodes to 0, then traverse the adjacency list of the first node. Whenever a node in the adjacency list of the first node is read, the in-degree value of that node is incremented by 1; then traverse the next adjacency list and perform the same operation until after traversing the adjacency lists of all nodes, the in-degree values of all nodes are obtained, and the in-degree array of all nodes is constructed according to the in-degree values of all nodes.

[0008] Optionally, when determining the next best executable process according to the in-degree array, the multi-process collaborative decision-making module is used to: Traverse the nodes with an in-degree value of 0 in the in-degree array, add the nodes with an in-degree value of 0 to the execution queue, and determine the process corresponding to the nodes with an in-degree value of 0 according to the preset correspondence between nodes and processes, as the next executable optimal process.

[0009] Optionally, the multi-process collaborative decision-making module is used when updating the in-degree array: Obtain the adjacency list of the nodes with an in-degree value of 0 from the in-degree array, update the in-degree value of the nodes with an in-degree value of 0 to -1, and subtract 1 from the in-degree value of each node in the adjacency list of the nodes with an in-degree value of 0 to obtain the updated in-degree array.

[0010] Optionally, the multi-process collaborative decision-making module is used when making a decision on the next executable optimal process according to the updated in-degree array: Judge whether the in-degree values of all nodes in the updated in-degree array are all -1. If so, it is determined that the current tunneling cycle ends. If not, continue to traverse the nodes with an in-degree value of 0 in the updated in-degree array, and use the process corresponding to the nodes with an in-degree value of 0 as the next executable optimal process until it is determined that the current tunneling cycle ends when the in-degree values of all nodes in the updated in-degree array are -1.

[0011] Optionally, the multi-process collaborative decision-making module is also used to put the nodes corresponding to the processes that are sequentially executed into the collaborative control queue, and record the execution time of each process and the total time of the current tunneling cycle.

[0012] Optionally, the multi-process spatio-temporal constraint model construction module is also used to update the tunneling work event set in the multi-process spatio-temporal constraint model according to the collaborative control queue.

[0013] All the above optional technical solutions can be combined arbitrarily, and the present invention does not elaborate on the structures after combination one by one.

[0014] With the above solutions, the beneficial effects of the present invention are as follows: By constructing a multi-process spatio-temporal constraint model through the multi-process spatio-temporal constraint model construction module, it is possible to effectively constrain the execution order of numerous processes in the complex tunneling process, and dynamically update the latest process execution status according to the execution process. Through the multi-process collaborative decision-making module, making collaborative decisions on all processes involved in the entire tunneling process according to the multi-process spatio-temporal constraint model and the perception results of the process perception module, it is possible to automatically solve the next executable optimal process, so that the provided optimal process decision-making method is not restricted by the time relationship constraint threshold range and abnormal or complex working conditions that occur during the execution of each process, can dynamically adapt to the underground real-time mining working conditions, and has good practical application ability.

[0015] The above description is only an overview of the technical solution of the present invention. In order to understand the technical means of the present invention more clearly and be able to implement it according to the content of the specification, the following describes in detail with reference to the preferred embodiments of the present invention and the accompanying drawings. Description of the Drawings

[0016] Figure 1 It is a schematic structural diagram of the multi-process collaborative decision-making control system for coal mine tunneling operations provided by an embodiment of the present invention.

[0017] Figure 2 It is a working flow chart of the multi-process collaborative decision-making control system for coal mine tunneling operations provided by an embodiment of the present invention. Detailed Embodiments

[0018] The following further describes in detail the specific embodiments of the present invention in conjunction with the accompanying drawings and embodiments. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0019] The main task of the multi-process collaborative decision-making control system for coal mine tunneling operations provided by the embodiment of the present invention is to study the dynamic correlation between each process and each device during the tunneling process, analyze the time-space constraints of the processes executed by each device, obtain the optimal process plan with sequentially related actions, and finally obtain the optimal process plan result.

[0020] As Figure 1 shown, the multi-process collaborative decision-making control system for coal mine tunneling operations provided by the embodiment of the present invention includes a multi-process collaborative decision-making module, and the multi-process collaborative decision-making module is communicatively connected to a multi-process time-space constraint model construction module and a process perception module: The multi-process time-space constraint model construction module is used to construct a multi-process time-space constraint model according to the actual mining situation of the tunneling face. Among them, the multi-process time-space constraint model includes a tunneling work event set, an adjacency list, and an in-degree array; The multi-process collaborative decision-making module is used to import the tunneling work event set, the adjacency list, and the in-degree array at the beginning of the current tunneling cycle, and determine the next best executable process according to the in-degree array, and send a control instruction to the execution device corresponding to the next best executable process; The process perception module is used to continuously sense the process execution status signal during the execution of the control instruction by the execution device, and continuously send the process execution status signal to the multi-process collaborative decision-making module; The multi-process collaborative decision-making module is further used to record the process execution time, update the in-degree array when it is determined that the process execution is completed according to the process execution status signal sent by the process perception module, and decide the next best executable process according to the updated in-degree array until the current tunneling cycle ends.

[0021] Among them, the multi-process spatio-temporal constraint model is used to define the execution order between each process, avoiding major safety accidents caused by improper operations. For example, if the roadheader cuts the coal wall and then continues to advance without supporting the roof and two sides, it may lead to an excessive empty roof area, possibly triggering roof fall or rib spalling accidents. The multi-process spatio-temporal constraint model restricts the execution order between each process in the actual underground tunneling process through tunneling safety regulations and manual experience, ensuring the safety of tunneling work.

[0022] Specifically, the multi-process collaborative decision-making module and the process perception module can be connected by wire or wirelessly. The multi-process collaborative decision-making module and the multi-process spatio-temporal constraint model construction module can be integrated on different terminals or located on the same terminal.

[0023] The tunneling process is divided into three categories: tunneling - transportation - support, as shown in Table 1, which shows a corresponding relationship between each process and node in the tunneling cycle.

[0024]

[0025] In a specific embodiment, when constructing the multi-process spatio-temporal constraint model, the multi-process spatio-temporal constraint model construction module is used for: First, construct the tunneling process event set of the current tunneling cycle according to the actual mining situation of the tunneling face. The tunneling process event set uses nodes to represent processes and edges to represent the spatio-temporal constraints for the execution of two processes. The tunneling process event set includes multiple process constraint binary groups, and the process constraint binary group is represented as {u, v}, where u → v means that process u needs to be executed first before executing process v. Then, determine the adjacency list of all nodes in the tunneling process event set, and determine the in-degree array of all nodes according to the adjacency list of all nodes; among them, the adjacency list is the set of nodes of the next process that can be continued after executing the current process, and the in-degree array includes the in-degree value of each node; the in-degree value represents the number of processes that still need to be executed if you want to execute the current process.

[0026] Specifically, the tunneling process event sets of each tunneling cycle are determined according to the spatio-temporal constraint relationships of each process in the tunneling process, and they can be the same or different. For example, after one tunneling cycle, the tunneling process event set of the next tunneling cycle can be adjusted according to the execution situation of the processes in this tunneling cycle. In the embodiments of the present invention, it only needs to be ensured that when executing the current tunneling cycle, the tunneling process event set for the current tunneling cycle has been established according to the actual mining situation of the tunneling face. Among them, the actual mining situation of the tunneling face can include the execution order of each process defined in the tunneling process safety operation regulations, the execution order of each process determined manually according to historical tunneling cycles, and other contents.

[0027] For example, based on the correspondence between the processes and nodes shown in Table 1 and some tunneling cycles that have been executed in history, determine the tunneling process event set for certain tunneling cycles eages It is represented as {{1, 2}, {1, 3}, {2, 4}, {3, 4}, {4, 5}, {5, 6}, {6, 8}, {8, 17}, {8, 18}, {17, 9}, {17, 10}, {18, 9}, {18, 10}, {18, 13}, {13, 14}, {14, 15}, {14, 16}...}. Among them, {1, 2} means that process 1 needs to be executed before process 2.

[0028] In a specific embodiment, when the multi-process spatio-temporal constraint model construction module determines the adjacency list of all nodes in the tunneling process event set, it is used to: first obtain the previous node u and the subsequent node v1 in the first process constraint binary group {u, v1} in the tunneling process event set, then create an adjacency list for node u, put node v1 into the adjacency list of u, continue to traverse the tunneling process event set, if there is a new process constraint binary group {u, v2} about node u in the tunneling process event set, then continue to put v2 into the adjacency list of u until all the process constraint binary groups about node u are processed, indicating that the construction of the adjacency list of node u is completed, and then continue to process the remaining process constraint binary groups in the order of each process constraint binary group in the tunneling process event set until the adjacency lists of all nodes in the tunneling process event set are constructed.

[0029] Taking the above tunneling process event set eages as an example, for node 1, its adjacency list Graph [1] = {2, 3}, which means that after process 1 is executed, process 2 or 3 can be executed. Similarly, Graph [2] = {4}, Graph [3] = {4}, Graph [4] = {5}, Graph [5] = {6}, and so on.

[0030] Specifically, the in-degree value of a certain node represents the number of other processes that need to be executed first when the process corresponding to the current node is executed. When the in-degree value of a certain node is 0, it means that there is no constraint of other processes when executing the process corresponding to this node and it can be executed directly; when the in-degree value is greater than 0, it means that the process corresponding to the current node cannot be executed yet and needs to wait until the processes corresponding to other nodes in the spatio-temporal constraint model are executed before it can start.

[0031] In a specific embodiment, when the multi-process spatio-temporal constraint model construction module determines the in-degree array of all nodes according to the adjacency list of all nodes, it is used to: first, set the initial value of the in-degree value of all nodes to 0, and then traverse the adjacency list of the first node. Whenever a node in the adjacency list of the first node is read, the in-degree value of that node is incremented by 1; then traverse the next adjacency list and perform the same operation (that is, whenever a node in the adjacency list of the next node is read, the in-degree value of that node is incremented by 1), until after traversing the adjacency lists of all nodes, the in-degree values of all nodes are obtained, and the in-degree array of all nodes is constructed according to the in-degree values of all nodes.

[0032] Specifically, each node and its corresponding in-degree value are recorded in the in-degree array.

[0033] Taking the above Graph [1] = {2, 3} as an example, when traversing this adjacency list, nodes 2 and 3 can be read, and the in-degree values of nodes 2 and 3 are incremented by 1 respectively.

[0034] On the basis of the above content, in a specific embodiment, when the multi-process collaborative decision-making module determines the next executable best process according to the in-degree array, it is used to: traverse the nodes in the in-degree array whose in-degree values are 0, add the nodes with in-degree values of 0 to the execution queue, and determine the process corresponding to the nodes with in-degree values of 0 according to the preset correspondence between nodes and processes (Table 1) as the next executable best process.

[0035] It should be noted here that when there are multiple nodes with in-degree values of 0 in the in-degree array, the processes corresponding to multiple nodes can be executed in parallel.

[0036] Furthermore, the execution devices corresponding to each process in the tunneling face may be different. For example, the execution device for "moving forward to the tunneling face" is a roadheader, and the execution device for "retracting the temporary support" is a bolter, etc. It should be noted that at least one sensor and other sensing devices are installed on each execution device. Through the sensing devices, the process execution status signal when the execution device executes the process can be sensed in real time. When the multi-process collaborative decision-making module determines the next executable optimal process, it obtains the execution device corresponding to the next executable optimal process according to the preset correspondence between the process and the execution device, and sends a control instruction to it. After the execution device corresponding to the next executable optimal process receives the control instruction, it executes the next executable optimal process according to the control instruction. In this process, the sensing device installed on the execution device corresponding to the next executable optimal process senses the process execution status signal in real time and sends the process execution status signal to the multi-process collaborative decision-making module in real time. After receiving the process execution status signal, the multi-process collaborative decision-making module judges the process execution status according to the process execution status signal in real time, and when it determines that the process execution is completed, it performs subsequent operations such as updating the in-degree array.

[0037] In a specific embodiment, when updating the in-degree array, the multi-process collaborative decision-making module is used to: obtain the adjacency list of the nodes with an in-degree value of 0 from the in-degree array, update the in-degree value of the nodes with an in-degree value of 0 to -1, and subtract 1 from the in-degree value of each node in the adjacency list of the nodes with an in-degree value of 0 to obtain the updated in-degree array.

[0038] For example, taking the adjacency list Graph [1] = {2, 3} as an example, when updating the in-degree array, the multi-process collaborative decision-making module performs a subtraction operation on the in-degree values of nodes 2 and 3 in the adjacency list of node 1. For example, if before the update, the in-degree values of nodes 2 and 3 in the adjacency list of node 1 are 2 and 1 respectively, then after the update, the in-degree values of nodes 2 and 3 in the adjacency list of node 1 become 1 and 0 respectively.

[0039] After updating the in-degree value of each node in the adjacency list of all nodes, the updated in-degree array is obtained.

[0040] Further, when the multi-process collaborative decision-making module decides the next executable best process according to the updated in-degree array, it is used to: determine whether the in-degree values of all nodes in the updated in-degree array are all -1. If the in-degree values of all nodes in the in-degree array are all -1, it is determined that the current tunneling cycle ends; if the in-degree value of any node in the in-degree array is not -1, continue to traverse the nodes with an in-degree value of 0 in the updated in-degree array, take the process corresponding to the node with an in-degree value of 0 as the next executable best process, and send a control instruction to the execution device corresponding to the next executable best process. The execution device corresponding to the next executable best process executes the control instruction and real-time senses its process execution status signal through the sensing device installed on it during the instruction execution. The multi-process collaborative decision-making module repeats the decision-making multiple times until the in-degree values of all nodes in the updated in-degree array are all -1, and then determines that the current tunneling cycle ends.

[0041] In a specific embodiment, the multi-process collaborative decision-making module is further used to put the nodes corresponding to the processes that are sequentially executed into the collaborative control queue queue ={1, 3, ……}, and record the execution time of each process and the total time of the current tunneling cycle.

[0042] Further, the multi-process spatio-temporal constraint model construction module is further used to update the tunneling work event set in the multi-process spatio-temporal constraint model according to the collaborative control queue.

[0043] Specifically, the nodes in the collaborative control queue can, to a certain extent, represent the execution sequence of each process. Therefore, when the sequence of the nodes in the collaborative control queue shows that the execution sequence of some of the nodes may need to be adjusted, the tunneling work event set in the multi-process spatio-temporal constraint model can be updated according to the collaborative control queue to be used as the tunneling work event set for the subsequent tunneling cycle.

[0044] In summary, when the multi-process collaborative decision-making control system for coal mine tunneling operations provided by the embodiments of the present invention is in operation, it includes the following steps: S1, constructing a multi-process spatio-temporal constraint model, where the multi-process spatio-temporal constraint model includes a tunneling work event set, an adjacency list, and an in-degree array; S2, at the beginning of the current tunneling cycle, the multi-process collaborative decision-making module imports the tunneling work event set, the adjacency list, and the in-degree array, and determines the next best executable process according to the in-degree array, and sends a control instruction to the execution device corresponding to the next best executable process; S3, during the process of the execution device executing the control instruction, the process perception module real-time perceives the process execution status signal and sends the process execution status signal to the multi-process collaborative decision-making module in real-time; S4, when the multi-process collaborative decision-making module determines that the process execution is completed according to the process execution status signal, it records the process execution time, updates the in-degree array, and determines the next best executable process according to the updated in-degree array until the current tunneling cycle ends.

[0045] The multi-process collaborative decision-making control system for coal mine tunneling operations provided by the embodiments of the present invention has the following characteristics: 1. By constructing a multi-process spatio-temporal constraint model, it can effectively constrain the execution order of numerous processes in the complex tunneling process, and dynamically update the latest process execution status (in-degree array) according to the execution process.

[0046] 2. The multi-process collaborative decision-making module can perform collaborative decision-making on all processes involved in the entire tunneling process according to the multi-process spatio-temporal constraint model and the perception results of the process perception module, and automatically solve the next best executable process.

[0047] The above is only the preferred embodiment of the present invention and is not used to limit the present invention. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the technical principle of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. A multi-process collaborative decision-making control system for coal mine tunneling operations, characterized in that, It includes a multi-process collaborative decision-making module, which is communicatively connected to a multi-process spatio-temporal constraint model construction module and a process perception module: The multi-process spatio-temporal constraint model construction module is used to construct a multi-process spatio-temporal constraint model according to the actual mining situation of the tunneling face. Among them, the multi-process spatio-temporal constraint model includes a tunneling work event set, an adjacency list, and an in-degree array; The multi-process collaborative decision-making module is used to import the tunneling work event set, the adjacency list, and the in-degree array at the beginning of the current tunneling cycle, and determine the next best executable process according to the in-degree array, and send a control instruction to the execution device corresponding to the next best executable process; The process perception module is used to continuously perceive the process execution status signal during the process of the execution device executing the control instruction, and continuously send the process execution status signal to the multi-process collaborative decision-making module; The multi-process collaborative decision-making module is also used to record the process execution time, update the in-degree array when it is determined that the process execution is completed according to the process execution status signal sent by the process perception module, and determine the next best executable process according to the updated in-degree array until the current tunneling cycle ends.

2. The multi-process collaborative decision-making control system for coal mine tunneling operations according to claim 1, wherein When constructing the multi-process spatio-temporal constraint model, the multi-process spatio-temporal constraint model construction module is used for: Constructing a tunneling process event set for the current tunneling cycle according to the actual mining situation of the tunneling face. The tunneling process event set uses nodes to represent processes and edges to represent the spatio-temporal constraints for the execution of two processes, including multiple process constraint binary groups, denoted as {u, v}, where u→v means that process u needs to be executed before process v; Determining the adjacency list of all nodes in the tunneling process event set, and determining the in-degree array of all nodes according to the adjacency list of all nodes; among them, the adjacency list is a set of nodes of the next process that can be continued after the current process is executed, and the in-degree array includes the in-degree value of each node; the in-degree value indicates the number of processes that still need to be executed if the current process wants to be executed.

3. The multi-process collaborative decision-making control system for coal mine tunneling operations according to claim 2, wherein When determining the adjacency list of all nodes in the tunneling process event set, the multi-process spatio-temporal constraint model construction module is used for: First, obtain the previous node u and the next node v1 in the first process constraint binary group {u, v1} in the tunneling process event set, then create an adjacency list for node u, put node v1 into the adjacency list of u, and continue to traverse the tunneling process event set. If there is a new process constraint binary group {u, v2} for node u, then continue to put v2 into the adjacency list of u until all process constraint binary groups for node u are processed, indicating that the adjacency list of node u is constructed. Then continue to process the remaining process constraint binary groups in the order of each process constraint binary group in the tunneling process event set until the adjacency lists of all nodes in the tunneling process event set are constructed.

4. The multi-process collaborative decision-making control system for coal mine tunneling operations according to claim 2 or 3, characterized in that, When determining the in-degree array of all nodes according to the adjacency list of all nodes, the multi-process spatio-temporal constraint model construction module is used for: First, set the initial value of the in-degree value of all nodes to 0, then traverse the adjacency list of the first node. Whenever a node in the adjacency list of the first node is read, the in-degree value of that node is incremented by 1; Then traverse the next adjacency list and perform the same operation until all the adjacency lists of all nodes are traversed, obtaining the in-degree values of all nodes, and constructing an in-degree array for all nodes according to the in-degree values of all nodes.

5. The multi-process collaborative decision-making control system for coal mine tunneling operations according to claim 4, characterized in that The multi-process collaborative decision-making module is used to determine the next executable optimal process according to the in-degree array: Traverse the nodes with in-degree value of 0 in the in-degree array, add the nodes with in-degree value of 0 to the execution queue, and determine the process corresponding to the nodes with in-degree value of 0 according to the preset correspondence between nodes and processes as the next executable optimal process.

6. The multi-process collaborative decision-making control system for coal mine tunneling operations according to claim 5, characterized in that The multi-process collaborative decision-making module is used to update the in-degree array: Obtain the adjacency list of the nodes with in-degree value of 0 from the in-degree array, update the in-degree value of the nodes with in-degree value of 0 to -1, and subtract 1 from the in-degree value of each node in the adjacency list of the nodes with in-degree value of 0 to obtain the updated in-degree array.

7. The multi-process collaborative decision-making control system for coal mine tunneling operations according to claim 6, characterized in that, The multi-process collaborative decision-making module is used to determine the next executable optimal process according to the updated in-degree array: Judge whether the in-degree values of all nodes in the updated in-degree array are all -1. If so, it is determined that the current tunneling cycle ends. If not, continue to traverse the nodes with in-degree value of 0 in the updated in-degree array, and use the process corresponding to the nodes with in-degree value of 0 as the next executable optimal process until it is determined that the current tunneling cycle ends when the in-degree values of all nodes in the updated in-degree array are all -1.

8. The multi-process collaborative decision-making control system for coal mine tunneling operations according to claim 1, characterized in that The multi-process collaborative decision-making module is also used to put the nodes corresponding to the processes that are successively executed into the collaborative control queue, and record the execution time of each process and the total time of the current tunneling cycle.

9. The multi-process collaborative decision-making control system for coal mine tunneling operations according to claim 8, wherein, The multi-process spatio-temporal constraint model construction module is also used to update the tunneling work event set in the multi-process spatio-temporal constraint model according to the collaborative control queue.

Images