Micro-seismic analysis task dynamic assignment method for multiple coal mines

Abstract

The invention discloses a micro-seismic analysis task dynamic assignment method for multiple coal mines. The method is used for solving the problems that traditional micro-seismic analysis tasks are low in distributed processing efficiency and high in delay rate. According to the method, micro-seismic analysis tasks are generated on the basis of micro-seismic events uploaded by mines in real time, and a heterogeneous parallel machine assignment scheduling model with the aim of minimizing the number of delay tasks is established in combination with available time windows and processing capacity of analysts. And generating a scheduling scheme by adopting a scheduling algorithm based on a task sequence, and optimizing the scheduling scheme by adopting a genetic algorithm. And after the task is completed, the system updates an analyst load and a time window. According to the method, the task delay rate is remarkably reduced and the calculation efficiency is improved while the task scheduling reasonability is ensured, and the method has good expansibility and practicability and can be widely applied to scenes such as coal mine micro-seismic monitoring and disaster early warning.

Description

Technical Field

[0001] This invention relates to the field of coal mine safety monitoring and intelligent scheduling technology, specifically to a dynamic assignment method for microseismic analysis tasks in multiple coal mines, belonging to the field of mine disaster prediction and intelligent task scheduling. Background Technology

[0002] With the increasing depth of coal mining, the "three highs" phenomenon—high ground stress, high gas pressure, and high ground temperature—is becoming increasingly prominent, leading to a significant increase in the frequency of mine dynamic disasters such as rockbursts. Microseismic monitoring technology, with its high sensitivity, real-time capability, and non-destructive nature, has become an important technical means for disaster prediction. However, existing microseismic data analysis generally adopts a single-mine, manually monitored, and decentralized processing model, which has many shortcomings. With the widespread application of microseismic monitoring in coal mine rockburst early warning, the demand for monitoring data analysis has increased dramatically, making timely and accurate analysis a critical issue. In actual production, microseismic event analysis faces two major contradictions: first, the varying professional levels of analysts across different coal mines can easily lead to misjudgments or omissions, affecting the reliability and timeliness of early warning results; second, my country currently has over 100 coal mines prone to rockbursts, generating a large number of microseismic events daily, requiring professional analysis within a short timeframe, while the traditional decentralized processing model is inefficient and cannot meet the demands of large-scale, high-timeliness, and high-precision analysis. Summary of the Invention

[0003] To address the problems of fragmented task scheduling, low analysis efficiency, high delay rates, and heavy manual burden in current coal mine microseismic analysis tasks, this invention aims to provide a dynamic assignment method for microseismic analysis tasks across multiple coal mines. This method enables centralized management, intelligent scheduling, and efficient execution of microseismic analysis tasks across mines. It can dynamically allocate microseismic analysis tasks, reduce the number of delayed tasks, and improve the accuracy and timeliness of analysis results, thereby enhancing the overall level of coal mine safety monitoring and disaster early warning.

[0004] This invention provides a method for dynamically assigning microseismic analysis tasks across multiple coal mines, comprising the following steps:

[0005] S1, based on the real-time upload of microseismic events from each mine, generates corresponding microseismic analysis tasks, collects microseismic analysis task data including arrival time and deadline, and adds the microseismic analysis tasks to the current task queue.

[0006] S2, based on the available time window, historical task processing efficiency and current task load data of each analyst, determine the working status of each analyst and update the analyst set and working status;

[0007] S3. If a newly assigned microseismic analysis task is received, a task assignment and scheduling model is established based on the current task queue and the set of analysts, with the goal of minimizing the number of delayed microseismic analysis tasks.

[0008] S4. A task-order-based scheduling algorithm is used to generate multiple scheduling schemes. The fitness value of each scheduling scheme is calculated, and the schemes are sorted from best to worst according to their fitness values. The best individual is retained. A genetic algorithm is used to iteratively optimize the scheduling schemes to obtain the scheduling result.

[0009] S5, determine the optimal target analyst from the scheduling results as the task executor, and send the microseismic analysis task data to the task executor's work terminal;

[0010] S6. If the microseismic analysis task is completed, record the actual completion time of the microseismic analysis task and determine whether the microseismic analysis task has been delayed; update the available time window of the task executor and the current task load data.

[0011] Prioritizing the real-time uploading of microseismic events from each mine, corresponding microseismic analysis tasks are generated, including:

[0012] Microseismic events are generated based on microseismic signals collected by mine microseismic sensors; microseismic analysis task data are dynamically generated and added to the current task queue according to the event type, priority and analysis requirements of the microseismic events.

[0013] Prior to this, the establishment of the task assignment and scheduling model includes:

[0014] The objective function for constructing a task assignment and scheduling model is:

[0015]

[0016]

[0017] In the formula, Microseismic analysis task indicating delay , This indicates that the analysts are performing microseismic analysis tasks. End time; Indicates microseismic analysis task The deadline;

[0018] Step 3: Establish the constraint formulas for the task assignment and scheduling model:

[0019]

[0020]

[0021]

[0022]

[0023]

[0024]

[0025]

[0026] In the formula, As decision variables, For analysts Perform microseismic analysis tasks The start time, For microseismic analysis tasks Arrival time, For analysts The start time of the working time window For analysts The stop time of the working time window Let be the current task queue at time t. Let be the set of analysts at time t.

[0027] Firstly, a task-order-based scheduling algorithm is used to generate multiple scheduling schemes. The fitness value of each scheduling scheme is calculated, and the schemes are sorted from best to worst according to their fitness values. The best individual is retained. A genetic algorithm is then used to iteratively optimize the scheduling schemes to obtain the scheduling results, including:

[0028] A scheduling scheme based on a greedy allocation strategy is adopted. For each microseismic analysis task to be scheduled, all available analysts are traversed, and the earliest available time window for the microseismic analysis task under the current task load data is calculated using dynamic programming. The analyst with the earliest expected completion time of the microseismic analysis task under the current task load is selected for allocation, and the available time window of the analyst is updated synchronously. If all analysts cannot be scheduled, the microseismic analysis task to be scheduled is marked as a delayed task and recorded. A scheduling scheme is generated according to the order of microseismic analysis tasks, and a scheduling result set containing the start time, end time and executor information of the microseismic analysis tasks is output.

[0029] Firstly, a genetic algorithm is used to iteratively optimize the scheduling scheme to obtain the scheduling results, including:

[0030] An initial population is generated based on the set of microseismic analysis tasks and the set of analysts;

[0031] The scheduling order of microseismic analysis tasks is represented by a symbolic arrangement code.

[0032] A fitness function is constructed based on the number of delayed microseismic analysis tasks, and the total completion time is introduced as an auxiliary optimization index.

[0033] A tournament selection process is used for parent generation selection, and an elite retention strategy is used to extract the current best individual.

[0034] Chromosomal recombination is achieved using partial mapping crossover PMX;

[0035] An insertion mutation strategy is adopted, and the mutation probability is adaptively adjusted according to the evolutionary process.

[0036] The scheduling result is obtained by iteratively updating until the maximum number of iterations or the convergence condition is reached.

[0037] Prior to this, upon completion of each microseismic analysis task, an assignment table is generated in real time, containing information on the task executor, start time, end time, and whether the task was extended.

[0038] Preferably, a dynamic assignment system for microseismic analysis tasks in multiple coal mines, implementing the method described above, includes:

[0039] The task generation module is used to generate microseismic analysis task data based on the microseismic events uploaded by each mine.

[0040] The task assignment and scheduling module is used for initial scheduling based on a task order scheduling algorithm, and for dynamic selection of the optimal task executor based on a genetic algorithm.

[0041] The task distribution module is used to distribute microseismic analysis tasks.

[0042] The task recording module is used to update the available time window of the task executors and the current task load data and generate a scheduling report after the microseismic analysis task is completed. The scheduling report includes the task number, task executors, start time, end time, delay status and task status.

[0043] Beneficial effects:

[0044] This invention generates corresponding microseismic analysis tasks by uploading microseismic events from various mines in real time, and collects microseismic analysis task data, including arrival time and deadline time, and adds it to the current task queue; at the same time, it dynamically updates the status of analysts based on the available time window of each analyst, historical task processing efficiency, and current task load.

[0045] This invention achieves centralized management of microseismic data across mines and real-time generation of microseismic analysis tasks through a microseismic analysis task assignment and scheduling platform. It gathers expert resources within the industry, improves the method of microseismic analysis task assignment, enables collaborative analysis between different regions, and provides a real-time and reliable data foundation for subsequent microseismic analysis task scheduling, thereby significantly improving the response speed of microseismic analysis tasks and the overall scheduling flexibility of the system.

[0046] In this invention, when a new microseismic analysis task assignment and scheduling module receives a new microseismic analysis task, it establishes a task assignment and scheduling model with the goal of minimizing the number of delayed microseismic analysis tasks based on the current task queue and the set of analysts; and it uses a greedy scheduling algorithm based on task order to generate a preliminary scheme, and combines it with a genetic algorithm for multiple rounds of iterative optimization to obtain the optimal scheduling result.

[0047] This invention enables intelligent and optimized decision-making in the microseismic analysis task scheduling process, allowing the system to quickly solve for the globally optimal or near-optimal scheduling scheme in complex scenarios involving multiple mines, multiple tasks, and multiple personnel. This significantly reduces the delay rate of microseismic analysis tasks and improves the efficiency of microseismic analysis task allocation and the rationality of scheduling results.

[0048] The microseismic analysis task distribution and recording module in this invention identifies the target analyst in the optimal scheduling result as the task executor and automatically sends microseismic analysis task data to the corresponding work terminal; after the microseismic analysis task is completed, it records the actual completion time and delay of the microseismic analysis task, and updates the available time window and task load data of the analyst in real time, and generates a microseismic analysis task scheduling report.

[0049] This invention establishes a closed-loop management mechanism of task assignment, execution, and feedback, realizing automated and data-driven management of the entire process of microseismic analysis task execution, supporting dynamic adjustment and continuous optimization of the system, thereby further improving overall operating efficiency and system stability.

[0050] The method provided by this invention enables centralized management and intelligent assignment scheduling of microseismic analysis tasks across multiple mines, effectively reducing the delay rate of microseismic analysis tasks and improving the efficiency of task allocation. An adaptive genetic algorithm is used to achieve rapid computation of large-scale microseismic analysis tasks, and the scheduling results exhibit high real-time performance and rationality. This method supports dynamic feedback and fault-tolerant processing, and can be widely applied to coal mine safety monitoring, disaster early warning, and other industrial scenarios requiring efficient task allocation. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0052] Figure 1A flowchart provided for an embodiment of the present invention;

[0053] Figure 2 This is a schematic diagram of a microseismic analysis task assignment and scheduling platform provided in an embodiment of the present invention;

[0054] Figure 3 This is a Gantt chart for the assignment and scheduling of microseismic analysis tasks obtained in an embodiment of the present invention. Detailed Implementation

[0055] 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] Microseismic events are generated based on microseismic signals acquired by mine microseismic sensors. Microseismic analysis task data is dynamically generated and added to the current task queue according to the event type, priority, and analysis requirements of the microseismic events. The event type, priority, and analysis requirements are commonly used parameters in the field of microseismic detection, used to describe the nature, urgency, and depth of analysis of the event. For example, event types may include mine tremors, blasting, and rock mass fracturing; priorities may be determined based on energy level or risk level; and analysis requirements may include waveform analysis and energy analysis.

[0057] The establishment of the task assignment and scheduling model includes:

[0058] After a new microseismic analysis task arrives in the system, the system will dynamically establish a task assignment and scheduling model based on the current task queue and the set of analysts. The system will assign and schedule microseismic analysis tasks that are not yet completed or executed in real time to ensure that the model can reflect the latest microseismic analysis tasks and the status of analysts.

[0059] Among them, the set of microseismic analysis tasks and the set of analysts are dynamically changed over time: when a new microseismic analysis task arrives, it is added to the current task queue in real time, and when an analyst completes a task or updates its status, its available time window and load information are adjusted in real time.

[0060] Step 1: Define the symbols for the parameters and variables used in the task assignment and scheduling model, including the corresponding sets, parameter and variable symbols:

[0061] —Decision variables, if microseismic analysis task Assigned to analysts ,but ,otherwise ;

[0062] —Variables representing the microseismic analysis task Whether the completion date will be extended;

[0063] —Microseismic analysis task, Indicates the total number of tasks;

[0064] —A group of analysts, This indicates the total number of analysts;

[0065] —Analysts Perform microseismic analysis tasks The time required;

[0066] Microseismic analysis task Arrival time;

[0067] Microseismic analysis task The deadline;

[0068] —Analysts perform microseismic analysis tasks The start time;

[0069] —Analysts perform microseismic analysis tasks End time, If microseismic analysis task Analysts implement;

[0070] —Analysts The available working time range, among which , Separate analysis personnel The start and end times of the working time window;

[0071] —The current task queue at time t;

[0072] —The set of analysts at time t;

[0073] Step 2: Construct the objective function of the task assignment and scheduling model, the expression of which is shown in equation (1).

[0074]

[0075] in,

[0076]

[0077] The objective function of equation (1) represents minimizing the number of microseismic analysis tasks that have not been completed by the deadline;

[0078] Step 3: Establish the following constraint formulas

[0079] st

[0080]

[0081]

[0082]

[0083]

[0084]

[0085]

[0086]

[0087] Constraint formula (3): represents each microseismic analysis task Only one analyst is allowed. It must be completed independently, not by multiple analysts working together; that is, the microseismic analysis task cannot be split up and completed collaboratively.

[0088] Constraint formula (4): represents the microseismic analysis task start time Cannot arrive earlier than its arrival time ;

[0089] Constraint formula (5): This means that each analyst can only perform one microseismic analysis task at a time. The current microseismic analysis task must be completed before the next microseismic analysis task can be performed. Multiple microseismic analysis tasks are not allowed to be performed at the same time.

[0090] Constraint formula (6): Analysts can only perform microseismic analysis tasks during the working time;

[0091] Constraint formula (7): Constraints on the values ​​of decision variables;

[0092] Constraint formula (8): Task completion time constraint;

[0093] Constraint formula (9): The task queue and the set of analysts change dynamically over time. When a new microseismic analysis task arrives, it is updated in real time, and the task assignment and scheduling model is solved again.

[0094] The task assignment and scheduling model abstracts analysts as heterogeneous parallel machines, with each analyst having independent processing capacity parameters and available time window constraints.

[0095] Each coal mine reports microseismic event data to the microseismic analysis task assignment and scheduling platform in real time. The platform generates microseismic analysis tasks based on event attributes and extracts information such as arrival and deadline times, updating the current task queue. Each microseismic analysis task includes at least a task number, arrival time, deadline time, and the processing time for each analyst.

[0096] Table 1. Data Table for Microseismic Analysis Task

[0097]

[0098] The microseismic analysis task assignment and scheduling platform synchronously obtains the available time windows of each analyst and determines the real-time working status of the analysts based on the above data. This ultimately forms a set of analysts, with each analyst having an ID number and available time slots.

[0099] Table 2. Analyst Data Sheet

[0100]

[0101] Based on task arrival time, deadline, heterogeneous processing capabilities of analysts, and their available time windows, a task assignment and scheduling model is established with the goal of minimizing the number of delayed tasks.

[0102] Multiple initial scheduling schemes were generated using a task sequence-based scheduling algorithm, each corresponding to a matching sequence between microseismic analysis tasks and analysts. The fitness value of each initial scheduling scheme was calculated, with the number of delayed microseismic analysis tasks as the primary optimization metric, supplemented by the total completion time as an auxiliary metric. The schemes were then sorted from best to worst fitness value, and the individual with the highest fitness was retained. Subsequently, a genetic algorithm was used for iterative optimization, with the following parameter settings:

[0103] Population size: A relatively large population size N=100 is adopted;

[0104] Crossover rate: Set the crossover probability to 0.8;

[0105] Mutation rate: Set the mutation probability to 0.2;

[0106] Termination conditions: Set an early termination mechanism: the fitness value of the best individual in the population has not significantly improved in 100 consecutive generations; set the total genetic process to a maximum of 500 generations;

[0107] The optimal target analyst from the scheduling results is selected as the task executor, and the microseismic analysis task data is sent to their work terminal.

[0108] After the microseismic analysis task is completed, the actual completion time is recorded, and it is determined whether there is a delay. Simultaneously, the available time window and task load data for the task executors are updated. A microseismic analysis task assignment and scheduling table is generated, including the task number, executors, start time, end time, and delay flag, as well as a microseismic analysis task assignment and scheduling Gantt chart, as shown in Table 3.

[0109] Table 3. Algorithm Assignment and Scheduling Results

[0110]

[0111] Table 3 shows the simulation results of the dynamic assignment method for microseismic analysis tasks in multiple coal mines according to the present invention. It shows the allocation of different microseismic analysis tasks among the analysts, the start and end times of the microseismic analysis tasks, and whether delays occurred. Table 4 is a table of microseismic analysis task assignment and scheduling results compiled from the algorithm assignment and scheduling diagram.

[0112] Table 4. Microseismic Analysis Task Assignment and Scheduling

[0113]

[0114] Figure 3 A Gantt chart is used to assign and schedule microseismic analysis tasks. The horizontal axis represents time, and the vertical axis represents the analyst's ID. Different colored bars represent different microseismic analysis tasks. This Gantt chart visually reflects the allocation of microseismic analysis tasks to each analyst and the distribution of task execution time, thereby verifying the rationality and dynamic optimization effect of the microseismic analysis task assignment and scheduling model described in this invention.

[0115] The above embodiments are merely preferred embodiments of the present invention and specific descriptions of the technical principles employed, used to illustrate the implementation of the present invention, and are not intended to limit the scope of protection of the present invention. After reading this specification, those skilled in the art can make various obvious improvements, substitutions, or equivalent adjustments to the step sequence, algorithm strategy, data modeling method, scheduling optimization method, etc., based on the concept of the present invention. All such improvements, adjustments, and equivalent solutions should be considered to fall within the scope of protection of the present invention. Although the present invention has been described in detail above with reference to specific embodiments, the present invention is not limited to the described embodiments. Other implementations may be included without departing from the basic concept and spirit of the present invention, and the scope of protection of the present invention should be determined by the appended claims.

Claims

1. A dynamic assignment method for microseismic analysis tasks in multiple coal mines, characterized in that, Includes the following steps: S1, based on the real-time upload of microseismic events from each mine, generates corresponding microseismic analysis tasks, collects microseismic analysis task data including arrival time and deadline, and adds the microseismic analysis tasks to the current task queue. S2, based on the available time window, historical task processing efficiency and current task load data of each analyst, determine the working status of each analyst and update the analyst set and working status; S3. If a newly assigned microseismic analysis task is received, a task assignment and scheduling model is established based on the current task queue and the set of analysts, with the goal of minimizing the number of delayed microseismic analysis tasks. S4. A task-order-based scheduling algorithm is used to generate multiple scheduling schemes. The fitness value of each scheduling scheme is calculated, and the schemes are sorted from best to worst according to their fitness values. The best individual is retained. A genetic algorithm is used to iteratively optimize the scheduling schemes to obtain the scheduling result. S5, determine the optimal target analyst from the scheduling results as the task executor, and send the microseismic analysis task data to the task executor's work terminal; S6. If the microseismic analysis task is completed, record the actual completion time of the microseismic analysis task and determine whether the microseismic analysis task has been delayed. Update the available time window for task performers and the current task load data.

2. The method for dynamic assignment of microseismic analysis tasks for multiple coal mines according to claim 1, characterized in that, Based on real-time uploads of microseismic events from various mines, corresponding microseismic analysis tasks are generated, including: Microseismic events are generated based on microseismic signals collected by mine microseismic sensors; microseismic analysis task data are dynamically generated and added to the current task queue according to the event type, priority and analysis requirements of the microseismic events.

3. The method for dynamic assignment of microseismic analysis tasks for multiple coal mines as described in claim 1, characterized in that, The establishment of the task assignment and scheduling model includes: The objective function for constructing a task assignment and scheduling model is: ， ， In the formula, Microseismic analysis task indicating delay , This indicates that the analysts are performing microseismic analysis tasks. End time; Indicates microseismic analysis task The deadline; Step 3: Establish the constraint formulas for the task assignment and scheduling model: ， ， ， ， ， ， ， In the formula, As decision variables, For analysts Perform microseismic analysis tasks The start time, For microseismic analysis tasks Arrival time, For analysts The start time of the working time window For analysts The stop time of the working time window Let be the current task queue at time t. Let be the set of analysts at time t.

4. The method for dynamic assignment of microseismic analysis tasks for multiple coal mines according to claim 1, characterized in that, Multiple scheduling schemes are generated using a task-order-based scheduling algorithm. The fitness value of each scheme is calculated, and the schemes are sorted from best to worst fitness value, with the best individual retained. A genetic algorithm is then used to iteratively optimize the scheduling schemes, yielding the scheduling results, including: A scheduling scheme based on a greedy allocation strategy is adopted. For each microseismic analysis task to be scheduled, all available analysts are traversed, and the earliest available time window for the microseismic analysis task under the current task load data is calculated using dynamic programming. The analyst with the earliest expected completion time of the microseismic analysis task under the current task load is selected for allocation, and the available time window of the analyst is updated synchronously. If all analysts cannot be scheduled, the microseismic analysis task to be scheduled is marked as a delayed task and recorded. A scheduling scheme is generated according to the order of microseismic analysis tasks, and a scheduling result set containing the start time, end time and executor information of the microseismic analysis tasks is output.

5. The method for dynamic assignment of microseismic analysis tasks for multiple coal mines according to claim 4, characterized in that, The scheduling scheme is iteratively optimized using a genetic algorithm to obtain the scheduling results, including: An initial population is generated based on the set of microseismic analysis tasks and the set of analysts; The scheduling order of microseismic analysis tasks is represented by a symbolic arrangement code. A fitness function is constructed based on the number of delayed microseismic analysis tasks, and the total completion time is introduced as an auxiliary optimization index. A tournament selection process is used for parent generation selection, and an elite retention strategy is used to extract the current best individual. Chromosomal recombination is achieved using partial mapping crossover PMX; An insertion mutation strategy is adopted, and the mutation probability is adaptively adjusted according to the evolutionary process. The scheduling result is obtained by iteratively updating until the maximum number of iterations or the convergence condition is reached.

6. The method for dynamic assignment of microseismic analysis tasks for multiple coal mines according to claim 1, characterized in that, Upon completion of each microseismic analysis task, an assignment table is generated in real time, containing information on the task executor, start time, end time, and whether the task was delayed.

7. A dynamic assignment system for microseismic analysis tasks in multiple coal mines, implementing the methods described in claims 1 to 6, characterized in that, include: The task generation module is used to generate microseismic analysis task data based on the microseismic events uploaded by each mine. The task assignment and scheduling module is used for initial scheduling based on a task order scheduling algorithm, and for dynamic selection of the optimal task executor based on a genetic algorithm. The task distribution module is used to distribute microseismic analysis tasks. The task recording module is used to update the available time window of the task executors and the current task load data and generate a scheduling report after the microseismic analysis task is completed. The scheduling report includes the task number, task executors, start time, end time, delay status and task status.

Images