Coal mine underground operation measurement mode and drilling parameter adjustment method and device, medium and product

Abstract

The invention discloses a coal mine underground operation measurement mode and drilling parameter adjustment method and device, a medium and a product, and relates to the field of coal mine underground operation, and the method comprises the steps: collecting information data of a coal rock mass in a drilling process; the information data comprises physical and mechanical parameters and stress states; the information data is preprocessed; and based on the preprocessed information data, determining the optimal measurement mode and the optimal drilling parameters in the drilling process by adopting the trained reinforcement learning model, and completing the adjustment of the measurement mode and the drilling parameters. Working parameters can be dynamically adjusted according to real-time data, potential risks are prevented, and powerful technical support is provided for underground coal mine operation.

Description

Technical Field

[0001] The present application relates to the field of underground coal mine operations, and in particular to a method, device, medium and product for measuring a coal mine underground operation mode and adjusting drilling parameters. Background Art

[0002] The underground working environment of coal mines is complex, and the physical and mechanical parameters and stress state of coal and rock masses have a direct impact on mine safety. Traditional sensor modules can usually only measure certain parameters in a single dimension, lacking the integration of multiple sensors, resulting in insufficient comprehensiveness and accuracy of data. Secondly, data acquisition and processing units often cannot process and analyze large amounts of measurement data in real time, resulting in low data processing efficiency and inability to provide timely feedback. Furthermore, conventional technologies lack dynamic adaptive adjustment and intelligent prediction functions, and are unable to adjust measurement modes and drilling parameters according to real-time changing environments, resulting in insufficient system adaptability and safety. Summary of the invention

[0003] The purpose of this application is to provide a mine operation measurement mode and drilling parameter adjustment method, device, medium and product, which can improve the safety of underground coal mine operations.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a mine operation measurement mode and a drilling parameter adjustment method, including:

[0006] Collecting information data of coal and rock mass during drilling; the information data includes physical and mechanical parameters and stress state;

[0007] Preprocessing the information data;

[0008] Based on the preprocessed information data, the trained reinforcement learning model is used to determine the optimal measurement mode and optimal drilling parameters during the drilling process, and the adjustment of the measurement mode and drilling parameters is completed.

[0009] In a second aspect, the present application provides a mine operation measurement mode and a drilling parameter adjustment device, comprising:

[0010] The sensor module is used to collect information data of the coal and rock mass during drilling; the information data includes physical and mechanical parameters and stress state;

[0011] A data preprocessing unit, connected to the sensor module, for preprocessing the information data;

[0012] The adjustment module is connected to the data processing unit and is used to determine the optimal measurement mode and optimal drilling parameters in the drilling process based on the preprocessed information data using the trained reinforcement learning model to complete the adjustment of the measurement mode and drilling parameters.

[0013] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned underground mine operation measurement mode and drilling parameter adjustment method.

[0014] In a fourth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned underground mine operation measurement mode and drilling parameter adjustment method.

[0015] According to the specific embodiments provided in this application, this application has the following technical effects:

[0016] This application provides a method, device, medium and product for measuring mode and adjusting drilling parameters for underground mine operations, which realizes intelligent adjustment of measurement mode and drilling parameters through reinforcement learning and big data analysis. In the complex underground environment, it can dynamically adjust working parameters according to real-time data to prevent potential risks, provide strong technical support for underground coal mine operations, significantly improve the efficiency and safety of coal mine production, and reduce the accident rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A schematic flow chart of an underground mine operation measurement mode and a drilling parameter adjustment method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0021] In an exemplary embodiment, Figure 1 As shown, a method for measuring a mine operation mode and adjusting drilling parameters is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to a server as an example for explanation, and includes the following steps S1 to S3. Among them:

[0022] S1: Collect information data of coal and rock mass during drilling; the information data includes physical and mechanical parameters and stress state.

[0023] Physical parameters include pressure, tensile strength, vibration, sound wave velocity, strain change, etc. of coal rock mass.

[0024] S2: Preprocessing the information data.

[0025] Specifically, the checksum is used to verify the integrity of the information data. If the received data is found to be incomplete, the sensor is requested to resend the data. After receiving the information data, a timestamp record is required. After completing the timestamp record, a digital filter is used to filter the information data to remove high-frequency noise and environmental interference.

[0026] S3: Based on the preprocessed information data, the trained reinforcement learning model is used to determine the optimal measurement mode and optimal drilling parameters during the drilling process, and the adjustment of the measurement mode and drilling parameters is completed.

[0027] Specifically, based on the preprocessed information data, a trained reinforcement learning model is used to determine the optimal drilling action; and the measurement mode and drilling parameters corresponding to the optimal drilling action are determined as the optimal measurement mode and the optimal drilling parameters.

[0028] The reinforcement learning model includes a policy network and a value network. The training process of the reinforcement learning model includes:

[0029] (1) Obtain information data of coal and rock mass at time t.

[0030] In the coal rock mass measurement environment, the state S at time t is collected t , which contains relevant characteristic data such as the physical and mechanical parameters and stress state of the coal rock mass.

[0031] (2) Based on the information data at time t, the action probability distribution output by the strategy network is adopted, and the ε-greedy strategy is used to determine the optimal drilling action at time t.

[0032] According to the action probability distribution output by the policy network, the ε-greedy strategy is used to select actions, randomly select actions with probability ∈ (exploration), and select the optimal action A output by the policy network with probability 1-∈ t .

[0033] (3) The measurement mode and drilling parameters are adjusted according to the optimal drilling action at time t, and the reward value corresponding to the optimal drilling action at time t and the information data at time t+1 are obtained from the coal rock environment.

[0034] In state S t Next, execute the selected action A t , adjust the measurement mode and drilling parameters to adapt to the current coal rock environment, and obtain feedback information from the environment after execution, including the reward value R corresponding to the optimal drilling action at time t t and the state S at time t+1 t+1 , where the reward value R t Calculated based on measurement accuracy, drilling efficiency and safety indicators, used to evaluate action A t The advantages and disadvantages of the model can provide a reference for subsequent model updates.

[0035] (4) Adjust the parameters of the value network according to the information data at time t, the optimal drilling action at time t, the reward value corresponding to the optimal drilling action at time t, and the information data at time t+1, and copy the adjusted value network parameters to the strategy network to complete the training of the strategy network and the value network.

[0036] The experience gained (S t , A t , R t , S t+1 ) is stored in the experience replay pool D. The replay pool is a fixed-size storage device used to record the operation data of the model in different states. Each time storage is performed, the earliest record is replaced when the replay pool is full.

[0037] Randomly sample small batches of data (Si, Ai, Ri, Si+1) from the replay pool to update the parameters of the value network; calculate the target value Where γ is the discount factor, Q(S i+1 ,a′;θ - ) is the maximum expected value of the next state output by the value network; by minimizing the mean square error loss function Adjust the parameters θ of the value network.

[0038] The advantage function A(S) is calculated through the value network t ,A t )=Q(S t ,A t )-V(S t ), where V(St ) represents the state value; calculate the policy gradient Based on this gradient, the parameters of the policy network are adjusted to update.

[0039] Every fixed number of steps, copy the current value network parameters θ to the policy network parameters θ - In order to maintain the stability of the value network during the training process and ensure the progressive optimization effect of the model parameters.

[0040] In another exemplary embodiment of the present application, in order to prevent potential risks, based on the preprocessed information data, a trained long short-term memory network is used to predict potential danger areas and issue early warnings.

[0041] Specifically, the method includes: predicting the stress state at the next moment based on the preprocessed information data using a trained long short-term memory network; determining the stress state change rate based on the stress state at the next moment; and determining a potential danger zone according to the stress state change rate.

[0042] A large amount of historical data on coal and rock masses is collected, including physical and mechanical parameters and stress states. The acquired data are cleaned to remove outliers and noise. Finally, all data are normalized to the same dimensional range.

[0043] The processed data set is divided into training set, validation set and test set. The training set is used to optimize the parameters of the long short-term memory network, the validation set is used to monitor the performance of the long short-term memory network on non-training data to avoid overfitting, and the test set is used to finally evaluate the performance of the long short-term memory network.

[0044] Set the shape of the input layer to (time_steps,n features ), where time_steps is the number of time steps used for prediction, n features is the number of features. Then, a single-layer LSTM is set with 64 neurons to ensure that the model has sufficient expressive power when processing the complex time dependency of coal rock data. Next, the output layer is set to 1 neuron and the activation function is linear activation, which is used to predict a single physical quantity of the coal rock. Subsequently, the weights of the LSTM layer and the output layer are assigned and the bias term of the forget gate in the LSTM layer is initialized to 1. Next, the mean square error is selected as the loss function to reduce the prediction error. The Adam optimizer with a learning rate of 0.001 is used for parameter optimization, and the mean square error is used as the expression of the loss function. The mean square error represents the average square difference between the predicted value and the true value, which is used to measure the prediction accuracy of the model.

[0045] The training set is input into the model, forward propagation is performed to calculate the predicted value, and the weights and biases are adjusted to gradually reduce the loss function value. During the training process, the validation set error is monitored in real time to avoid overfitting. If the validation error increases and the training error continues to decrease, a Dropout layer with a ratio of 0.2 is added.

[0046] After each round of training, the validation set is input into the model, and the performance of the model on unseen data is evaluated by calculating the validation error. The hyperparameters such as learning rate and training cycle are adjusted according to the validation error. After the training and validation effects of the model meet the expectations, the test set is used for the final evaluation to verify the generalization ability and stability of the model. After the test is completed, the weights and parameter structure of the trained LSTM model are saved for use in practical applications.

[0047] The application process is as follows:

[0048] The sensor module collects the physical and mechanical parameters and stress state of the coal and rock mass in real time, and inputs the pre-processed real-time data into the trained LSTM model. The LSTM model predicts the stress state of the coal and rock mass based on the learned time dependency, outputs the predicted value, and then uses the formula Calculate the rate of change ΔH t Through the change rate analysis, the change trend of coal and rock mass status can be identified, whether there is a risk of abnormal increase or decrease, and potential danger areas can be determined. Early warning information is generated and sent to operators.

[0049] Through the deep learning ability of the LSTM layer, it is possible to adaptively learn complex patterns and relationships in time series data, improving the accuracy and stability of predictions; this design is particularly suitable for processing time series data such as physical and mechanical parameters and stress states of coal rock masses, and can accurately predict the stress state and potential dangerous areas of coal rock masses, combine historical data with real-time data, evaluate the changing trend and potential risks of the current stress state, generate early warning information and operational recommendations, and improve the safety and efficiency of coal mine production. In this way, this application not only demonstrates advanced technical solutions, but also highlights its great potential and wide applicability in practical applications, providing important technical support and guarantee for the intelligent and safe development of the coal mining industry.

[0050] Based on the same inventive concept, the embodiment of the present application also provides a device for implementing the above-mentioned underground mine operation measurement mode and drilling parameter adjustment method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the underground mine operation measurement mode and drilling parameter adjustment device provided below can refer to the above-mentioned limitations on the underground mine operation measurement mode and drilling parameter adjustment method, and will not be repeated here.

[0051] In an exemplary embodiment, a mine operation measurement mode and drilling parameter adjustment device is provided, comprising:

[0052] The sensor module is used to collect information data of the coal and rock mass during the drilling process; the information data includes physical and mechanical parameters and stress state.

[0053] In a specific embodiment, a sensor group is used to measure physical parameters such as pressure, tensile strength, vibration, acoustic wave velocity, strain change, and stress state of the coal and rock mass.

[0054] The sensor group includes pressure sensors, stretch sensors, vibration sensors, sound velocity sensors and fiber Bragg grating sensors, strain gauges, magnetic resonance imaging sensors and triaxial stress sensors.

[0055] A data preprocessing unit is connected to the sensor module and is used to preprocess the information data.

[0056] The data preprocessing unit has multi-channel receiving capability and can simultaneously receive data from different sensors with each channel corresponding to one sensor type, thereby improving the efficiency and accuracy of data reception.

[0057] The adjustment module is connected to the data processing unit and is used to determine the optimal measurement mode and optimal drilling parameters in the drilling process based on the preprocessed information data using the trained reinforcement learning model to complete the adjustment of the measurement mode and drilling parameters.

[0058] The underground mine operation measurement mode and drilling parameter adjustment device provided by the present application also include:

[0059] The communication module is used to receive the data sent by the data preprocessing unit and send the data to the ground monitoring center, realizing real-time data transmission and remote monitoring, ensuring the real-time and interactivity of the system. The communication module transmits the obtained data to the ground station via WiFi or 5G signals.

[0060] The underground mine operation measurement mode and drilling parameter adjustment device provided by the present application also include:

[0061] The power module supports the device to work continuously for a long time underground, enhances the stability and durability of the system, and ensures that the equipment can continue to operate in harsh environments.

[0062] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0063] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0064] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0065] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0066] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0067] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0068] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application; at the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A mine operation measurement mode and drilling parameter adjustment method, characterized in that: include: Collecting information data of coal and rock mass during drilling; the information data includes physical and mechanical parameters and stress state; Preprocessing the information data; Based on the preprocessed information data, the trained reinforcement learning model is used to determine the optimal measurement mode and optimal drilling parameters during the drilling process, and the adjustment of the measurement mode and drilling parameters is completed.

2. The underground mine operation measurement mode and drilling parameter adjustment method according to claim 1, characterized in that: Preprocessing the information data specifically includes: Using a check code to verify the data integrity of the information data, and recording the information data with a timestamp; After completing the timestamp recording, a digital filter is used to filter the noise of the information data and unify the data format.

3. The underground mine operation measurement mode and drilling parameter adjustment method according to claim 1, characterized in that: Based on the preprocessed information data, the trained reinforcement learning model is used to determine the optimal measurement mode and optimal drilling parameters during the drilling process, including: Based on the preprocessed information data, the trained reinforcement learning model is used to determine the optimal drilling action; The measurement mode and drilling parameters corresponding to the optimal drilling action are determined as the optimal measurement mode and the optimal drilling parameters.

4. The underground mine operation measurement mode and drilling parameter adjustment method according to claim 1, characterized in that: The reinforcement learning model includes a strategy network and a value network; Among them, the training process of the reinforcement learning model includes: Obtain information data of coal and rock mass at time t; Based on the information data at time t, the action probability distribution output by the strategy network is adopted, and the ε-greedy strategy is adopted to determine the optimal drilling action at time t; Adjust the measurement mode and drilling parameters according to the optimal drilling action at time t, and obtain the reward value corresponding to the optimal drilling action at time t and the information data at time t+1 from the coal rock environment; The parameters of the value network are adjusted according to the information data at time t, the optimal drilling action at time t, the reward value corresponding to the optimal drilling action at time t, and the information data at time t+1, and the adjusted value network parameters are copied to the strategy network to complete the training of the strategy network and the value network.

5. The underground mine operation measurement mode and drilling parameter adjustment method according to claim 1, characterized in that: Also includes: Based on the preprocessed information data, the trained long short-term memory network is used to predict potential danger areas and issue early warnings.

6. The underground mine operation measurement mode and drilling parameter adjustment method according to claim 5, characterized in that: Based on the preprocessed information data, the trained long short-term memory network is used to predict potential danger areas, including: Based on the preprocessed information data, the trained long short-term memory network is used to predict the stress state at the next moment; determining a rate of change of the stress state based on the stress state at the next moment; A potential danger zone is determined according to the stress state change rate.

7. A device for measuring the operation mode and adjusting the drilling parameters in a mine, characterized in that: include: The sensor module is used to collect information data of the coal and rock mass during drilling; the information data includes physical and mechanical parameters and stress state; A data preprocessing unit, connected to the sensor module, for preprocessing the information data; The adjustment module is connected to the data processing unit and is used to determine the optimal measurement mode and optimal drilling parameters in the drilling process based on the preprocessed information data using the trained reinforcement learning model to complete the adjustment of the measurement mode and drilling parameters.

8. The underground mine operation measurement mode and drilling parameter adjustment device according to claim 7, characterized in that: Also includes: The prediction module is connected to the data processing unit and is used to predict potential danger areas based on the preprocessed information data and use the trained long short-term memory network to issue an early warning.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the underground mine operation measurement mode and drilling parameter adjustment method described in any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the underground mine operation measurement mode and drilling parameter adjustment method described in any one of claims 1 to 6 are implemented.

Images