Method and system for optimizing blasting design based on machine-rock relationship and multi-parameter inversion

Abstract

The disclosure provides a blasting design optimization method and system based on rock-machine relationship and multi-parameter inversion, relating to the technical field of geotechnical engineering exploitation, comprising: obtaining mining area lithology data and drilling operation parameters in the blasting process, and preprocessing the same to extract lithology characteristic parameters of the lithology data; using specific energy analysis method, establishing the inversion relationship between the lithology characteristic parameters and the drilling operation parameters according to Pearson correlation selection and correlation weight analysis, and obtaining the inverted rock-machine relationship parameters; introducing a drilling operation parameter feedback reinforcement learning RLDF optimization algorithm, taking the highest prediction value accuracy as the objective function, optimizing the rock-machine relationship parameter combination, obtaining the optimal parameter combination, optimizing the blasting scheme, and directly adjusting the subsequent borehole mesh distribution through the optimal parameter combination. The disclosure solves the problems of extensive control and lagging blasting effect evaluation in the traditional blasting construction process.

Description

Technical Field

[0001] This disclosure relates to the field of geotechnical engineering mining technology, specifically to a method and system for optimizing blasting design based on machine-rock relationship and multi-parameter inversion. Background Technology

[0002] The statements in this section are merely background information relating to this disclosure and do not necessarily constitute prior art.

[0003] In the current field of geotechnical engineering and mining, whether it is surface or underground mining, the problem of determining geological and geotechnical parameters is always present. In geotechnical engineering design, construction, and operation, the correct selection, evaluation, and application of geotechnical parameters and their engineering properties, such as compressive strength, cohesion, internal friction angle, compression modulus, and permeability coefficient, obtained from field investigations, laboratory tests, or empirical relationships, are the foundation of engineering design and construction.

[0004] In mining and blasting scenarios, the utilization of rock and soil parameters is not simply a matter of directly using experimental values, but rather a systematic process that mainly includes data acquisition, data processing and analysis, parameter selection and estimation, and specific applications. Existing effective methods for detecting rock mass parameters in blasting processes still have the following limitations: (1) In the parameter acquisition stage, the testing methods have obvious limitations. Geotechnical engineering commonly uses in-situ testing methods such as standard penetration test and static cone penetration test. However, rock engineering relies on indoor rock mechanics tests to obtain parameters due to the high cost of in-situ testing. Indoor tests are easily affected by sampling disturbances and the test environment, resulting in large test errors and making it difficult to truly reflect the actual mechanical properties of in-situ rock masses.

[0005] (2) In the data processing and analysis stage, the technical methods are relatively simple and crude. At present, the project only calculates the mean and extreme values ​​of parameters through simple statistical calculations and relies on manual removal of obvious abnormal data to avoid experimental errors and sampling interference. However, the soil and rock mass has highly heterogeneous and anisotropic characteristics. Conventional processing methods cannot take into account the spatial distribution differences of parameters. There is a lack of professional methods such as geostatistics to systematically evaluate the spatial variability of parameters, making it difficult to achieve accurate deduction from point test data to surface and volume engineering characteristics.

[0006] (3) Technical deficiencies are particularly prominent in parameter selection and engineering application. Engineering projects generally use a single confidence level characteristic value as the design parameter, simply substituting it into the mechanical model to conduct various engineering calculations, without recognizing the essential difference between characteristic values ​​and simple average values. Furthermore, existing application models ignore the discrete characteristics of geotechnical parameters, failing to combine indicators such as standard deviation and coefficient of variation to assess the degree of dispersion and reliability of parameters. Especially when test points are in unfavorable working conditions, the representativeness of a single parameter is insufficient, and human error in value selection is prominent, easily leading to distortions in engineering calculation results for slope stability, foundation settlement, seepage, and blasting optimization, affecting the safety and accuracy of engineering design. Summary of the Invention

[0007] To address the aforementioned issues, this disclosure proposes a blasting design optimization method and system based on machine-rock relationships and multi-parameter inversion. Utilizing the variable relationships between various rock mechanics parameters, combined with the calculation and characterization of drilling rig rock-breaking mechanical parameters, the method correlates mechanical operating parameters with lithological characteristic parameters to obtain the matching relationship between machine and rock. Based on the machine-rock relationship, blasting design optimization is achieved, solving the problems of extensive process control and delayed evaluation of blasting effects in traditional blasting construction. Through block size optimization, ore and rock separation is performed, reducing dilution losses, improving loading and transportation efficiency, and lowering beneficiation costs.

[0008] According to some embodiments, the present disclosure adopts the following technical solutions: Blasting design optimization methods based on machine-rock relationships and multi-parameter inversion include: Acquire lithological data of the mining area and drilling operation parameters during blasting, and preprocess them to extract lithological characteristic parameters from the lithological data; Using the specific energy analysis method, and based on Pearson correlation selection and correlation weight analysis, the inversion relationship between various lithological characteristic parameters and drilling rig operating parameters was established, and the inverted machine-rock relationship parameters were obtained. The drilling operation parameter feedback reinforcement learning (RLDF) optimization algorithm is introduced. With the highest prediction accuracy as the objective function, the combination of machine-rock relationship parameters is optimized through a cascaded machine learning algorithm to obtain the optimal parameter combination and establish a blasting database. Based on the historical blasting designs in the area, the blasting scheme was optimized. The mesh distribution of subsequent boreholes was directly adjusted through the optimal parameter combination. The machine-rock relationship parameters were dynamically optimized based on the quantitative evaluation of the blasting effect, and the data was imported into the blasting database for feedback updates.

[0009] According to some embodiments, the present disclosure adopts the following technical solutions: A blasting design optimization system based on machine-rock relationship and multi-parameter inversion includes: The data acquisition module is used to acquire lithological data of the mining area and drilling operation parameters during the blasting process, and to preprocess the data to extract lithological characteristic parameters. The inversion module is used to establish the inversion relationship between various lithological characteristic parameters and drilling rig operating parameters by using the specific energy analysis method and based on Pearson correlation selection and correlation weight analysis, so as to obtain the inverted machine-rock relationship parameters. The optimization module is used to introduce the drilling operation parameter feedback reinforcement learning RLDF optimization algorithm. With the highest prediction accuracy as the objective function, it optimizes the combination of machine-rock relationship parameters to obtain the optimal parameter combination and establishes a blasting database. The blasting feedback module is used to optimize blasting schemes based on historical blasting designs in the area. It directly adjusts the mesh distribution of subsequent boreholes through the optimal parameter combination, dynamically optimizes the machine-rock relationship parameters based on the quantitative evaluation of blasting effects, and imports the data into the blasting database for feedback updates.

[0010] According to some embodiments, the present disclosure adopts the following technical solutions: A computer program product includes a computer program that, when executed by a processor, implements the aforementioned blasting design optimization method based on machine-rock relationship and multi-parameter inversion.

[0011] According to some embodiments, the present disclosure adopts the following technical solutions: A non-transitory computer-readable storage medium is provided for storing computer instructions, which, when executed by a processor, implement the aforementioned blasting design optimization method based on machine-rock relationship and multi-parameter inversion.

[0012] According to some embodiments, the present disclosure adopts the following technical solutions: An electronic device includes a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the blasting design optimization method based on machine-rock relationship and multi-parameter inversion.

[0013] Compared with the prior art, the beneficial effects of this disclosure are as follows: This disclosed method for optimizing blasting design based on machine-rock relationships and multi-parameter inversion obtains the ore-rock structure and blastability through drilling data acquisition equipment and parameter inversion. A refined large-scale mining model is used to optimize ore-rock blasting parameters in real time, ensuring that rock sections are formed into large blocks and ore sections are generated with reasonable block sizes that meet beneficiation requirements, thus separating ore and rock in the stope and achieving low ore loss and high recovery rate. Simultaneously, the method optimizes the charge quantity and structure in the borehole of the blasting zone to meet the requirements for rock and ore loading and transportation, thereby improving loading and transportation efficiency, reducing waste rock contamination and dilution, and lowering beneficiation costs.

[0014] This disclosure presents a blasting design optimization method based on machine-rock relationships and multi-parameter inversion. It employs integrated sensors based on field conditions to reveal the time-history relationships of drilling pressure, torque, and rotational speed, as well as the sensitivity of drilling parameters to ore and rock characteristics. Addressing the issue of overlapping and redundancy in drilling parameters due to similar physical and mechanical properties among different ores, a method for fully extracting multivariate features of the drilling process is proposed. Intelligent computing and data visualization are used to achieve real-time inversion of ore and rock information.

[0015] This disclosed blasting design optimization method based on machine-rock relationship and multi-parameter inversion integrates various parameter measurement sensors, enabling comprehensive control and monitoring of drilling operation parameters according to actual needs. Due to its refined parameter acquisition and intelligent big data inversion, it achieves real-time identification of rock mass characteristics during drilling, accurately obtaining parameters such as the structure, strength, and blastability of the drilled rock mass, thus implementing precise blasting and efficient mining. Its refined intelligent mining technology reduces blasting disturbance by 30%, achieves a reduction of over 10% in the proportion of large blocks in the blasting area, a 95% ore-rock separation rate, a 97% ore resource recovery rate, significantly reduces explosive consumption by over 15%, saves costs by at least 10%, improves loading and transportation efficiency by 85%, and reduces ore beneficiation costs by 6%. Applying this technology to mining not only improves the safety and accuracy of blasting but also significantly enhances blasting efficiency and reduces labor and material costs.

[0016] The blasting design optimization method disclosed herein, based on machine-rock relationship and multi-parameter inversion, can also be used for tunnel and earthwork foundation excavation. Based on instrument drilling, it can be applied to tunnel and slope protection, as well as geotechnical engineering investigation, design, and related geotechnical, water conservancy, and oil and gas development projects. Attached Figure Description

[0017] The accompanying drawings, which form part of this disclosure, are used to provide a further understanding of this disclosure. The illustrative embodiments of this disclosure and their descriptions are used to explain this disclosure and do not constitute an undue limitation of this disclosure.

[0018] Figure 1 This is a system structure diagram of an embodiment of the present disclosure; Figure 2 This is a schematic diagram showing the installation location and usage of the device according to an embodiment of the present disclosure; Figure 3 This is a schematic diagram of an integrated processor according to an embodiment of the present disclosure; Figure 4 This is a schematic diagram of a blasting design optimization method based on machine-rock relationship and multi-parameter inversion according to an embodiment of this disclosure. Detailed Implementation

[0019] The present disclosure will be further described below with reference to the accompanying drawings and embodiments.

[0020] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of this disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0021] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this disclosure. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms “comprising” and / or “including” are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0022] Example 1 One embodiment of this disclosure provides a blasting design optimization method based on machine-rock relationship and multi-parameter inversion, the method steps of which include: Step 1: Obtain lithological data of the mining area and drilling operation parameters during the blasting process, and preprocess them to extract lithological characteristic parameters from the lithological data; Step 2: Using the specific energy analysis method, and based on Pearson correlation selection and correlation weight analysis, establish the inversion relationship between various lithological characteristic parameters and drilling rig operating parameters to obtain the inverted machine-rock relationship parameters; Step 3: Introduce the drilling operation parameter feedback reinforcement learning (RLDF) optimization algorithm, with the highest prediction accuracy as the objective function, to optimize the combination of machine-rock relationship parameters, obtain the optimal parameter combination, and establish a blasting database; Step 4: Based on the historical blasting designs in the area, optimize the blasting scheme, directly adjust the mesh distribution of subsequent boreholes through the optimal parameter combination, dynamically optimize the machine-rock relationship parameters according to the quantitative evaluation of the blasting effect, and import the data into the blasting database for feedback updates.

[0023] As one embodiment, the blasting design optimization method disclosed herein, based on machine-rock relationship and multi-parameter inversion, integrates the variable relationships between various parameters of rock mechanics, combines the calculation and characterization of drilling rig rock-breaking mechanical parameters, and correlates mechanical operating parameters with lithological characteristic parameters. Through the matching relationship between machine and rock, from identifying rock strata to rock breaking, it utilizes the characteristic parameters fed back from instrument drilling to achieve blasting design optimization. This solves the problems of extensive control and delayed evaluation of blasting effects in traditional blasting construction processes. Ore and rock are separated through block size optimization, reducing dilution losses, improving loading and transportation efficiency, and lowering beneficiation costs. Rock sections form large blocks, and ore sections generate blocks of the size required for beneficiation. Separating ore and rock in the stope reduces ore loss, increases ore recovery rate, improves loading and transportation efficiency, reduces waste rock contamination and dilution, and lowers beneficiation costs. The specific implementation process is as follows: Step 1: Obtain lithological data of the mining area and drilling operation parameters during the blasting process, and preprocess them to extract lithological characteristic parameters from the lithological data; Specifically, the basic components of lithological data are: (1) Composition: mineral and geochemical composition of rocks; (2) Structure: particle size, shape, arrangement, and cementation type of rocks; (3) Genesis: indicative features of the rock formation environment, such as sedimentary structures, magmatic structures, and metamorphic mineral assemblages; (4) Physical properties: physical properties of rocks such as density, porosity, permeability, acoustic velocity, and resistivity; (5) Mechanical properties: rock mechanical parameters such as compressive strength, tensile strength, shear strength, elastic modulus, cohesion, and Poisson's ratio. A database (such as MySQL) is used to record multiple parameters, including rock composition characteristics, structural characteristics, genetic characteristics, physical property characteristics, and mechanical property characteristics.

[0024] Furthermore, in the working mining area, core sampling, geological exploration, and geological information collection will be carried out to establish a basic database. Related experiments will be conducted, and the lithological data obtained from these experiments will be imported into the basic database.

[0025] By simulating and calibrating high-precision test drilling rigs to measure drilling operation parameters (speed, torque, drilling pressure, vibration, etc.), the drilling rig operation parameters are encoded sequentially and matched with the corresponding lithological parameters of the drilled rock to construct an instrument drilling gene library.

[0026] Drilling parameter devices, such as instruments that measure real-time drilling parameters including rangefinders, drilling pressure, drilling speed, torque, rotational speed, and vibration sensors, are installed on drilling rigs.

[0027] Debugging and drilling: Determine the drilling location and debug the drilling rig. Drill as needed and record various parameters during the drilling process, as well as the drilling rig's operating status. Different ores and different drilling equipment have different response relationships. In order to meet the needs of various drilling rigs and ores, the drilling rig operating parameters are further quantified, and time-domain and frequency-domain feature values ​​are extracted by combining statistical methods.

[0028] The characteristic values ​​include mean, maximum, minimum, median, peak, mode, root mean square error (RMSE), mean absolute error (MAE), and amplitude factor. As shown in Table 1, x(n) is the time-domain sequence of the signal, n is a natural number greater than or equal to 1, and N is the number of samples. After statistical analysis of a large amount of experimental data, it was found that the drilling parameters exhibit data overlap and intersection in the time domain, making it difficult to accurately distinguish their characteristics. Therefore, the data was converted to frequency domain analysis.

[0029] Table 1 Calculation of characteristic values ​​of drilling process parameters

[0030] Step 2: Using the specific energy analysis method, and based on Pearson correlation selection and correlation weight analysis, establish the inversion relationship between various lithological characteristic parameters and drilling rig operating parameters to obtain the inverted machine-rock relationship parameters; Specifically, the data collected during on-site drilling operations are compared with the data collected during drilling experiments, and categorized using intelligent algorithms. Different parameters are converted using different key coefficients to determine their corresponding relationships. The basic relationships are as follows: the conversion relationships between the drill pressure, rotation speed, drilling speed, vibration, and torque variables under different rock types in the laboratory and the corresponding data of the roller cone drill are as follows: Lab drill pressure = α * Field drill pressure, Lab rotation speed = β * Field rotation speed, Lab drilling speed = γ * Field drilling speed, Lab torque = δ * Field torque. The first fitting coefficient α, the second fitting coefficient β, the third fitting coefficient γ, and the fourth fitting coefficient δ can be obtained through previous experiments. Among them, the intelligent algorithm adopts different machine learning methods in series for different rock characteristics, including but not limited to SVM, XGBoost, and LightGBM.

[0031] Using the specific energy analysis method, relevant theoretical formula databases are statistically analyzed. Based on Pearson correlation selection and correlation weight analysis, the inversion relationship between various lithological characteristic parameters and drilling rig operation parameters is established. This inversion relationship includes the matching relationship between the drilling rig experimental test calibration and the instrument drilling lithology gene library established by field measurement. The results of the instrument drilling test inversion were compared with the results measured by actual coring, and the optimization was repeated until the accuracy was greater than 90%. Physical formulas were introduced to enhance interpretability and accuracy. The torque work and drilling pressure work per unit volume of rock were calculated using the following formulas:

[0032] In the formula: The mechanical efficiency factor; F This refers to the axial pressure acting on the drill bit; T For drill bit torque; v The drill bit rotation speed is expressed in rpm. ROP This refers to the drilling rate; R Where is the drill bit radius.

[0033] The work done by friction is :

[0034]

[0035] In the formula: The coefficient of friction between the drill bit and the rock at the bottom of the hole; The coefficient of friction between the drill bit and the wellbore rock; The radius of the borehole; Vertical drilling pressure; This refers to the lateral pressure coefficient; For torque.

[0036] according to Range of values Simplified to R / 2; with m set to 0.1, we can obtain the formula: In the formula: To do work vertically, To do work laterally, This is to perform work for reciprocating impact rock breaking. In addition, during drilling, mechanical rigidity often induces drill string vibration, the cutting fluid flows out of the drill string nozzle with a certain resistance, and the sound, light, and heat energy generated during drilling, if these energy dissipations are collectively referred to as… W n The minimum energy required to drill through a unit volume of rock is:

[0037] According to the energy principle, the lateral pressure coefficient is defined as:

[0038] The formula for Poisson's ratio can be obtained as follows: The shear strength of rock can be defined by unconfined shear failure on one side:

[0039] In the formula: F D This is the cutting resistance; θ The drill tooth inclination angle.

[0040]

[0041] In the rotational rock-breaking mode, the rock is mainly subjected to axial forces. and tangential force (Torque) Composition. According to Newton's third law, when cutting teeth penetrate rock, the rock will generate a reaction force. The resultant force of normal pressure The resultant force of friction The coefficient of friction between the cutting teeth and the rock is... When the side tilt angle θ of the cutting tooth unit is 0, take... P v = P h When the side tilt angle of the cutting tooth unit is not 0, it can be known from geometric relationships that... The angle formed by the cutting plane and the cutting plane is , It is a lateral force, and its direction is the same as that of the axial force. They are perpendicular to each other. According to the principle of force equilibrium, the following relationship can be obtained: Drill bit tangential force With axial force The ratio is I:

[0042]

[0043] The above formulas are used to determine the correlation between rock mechanical properties such as uniaxial compressive strength, internal friction angle, Poisson's ratio, cohesion, and shear strength, and drilling operation parameters such as drilling pressure, torque, drilling speed, and rotational speed.

[0044] Step 3: Introduce the drilling operation parameter feedback reinforcement learning (RLDF) optimization algorithm, with the highest prediction accuracy as the objective function. Optimize the combination of machine-rock relationship parameters through a cascaded machine learning algorithm to obtain the optimal parameter combination and establish a blasting database. Specifically, the determined inversion parameters are applied in the blasting area, and instrument drilling tests are conducted in the borehole area. Through the above steps, the matching relationship is determined and the lithological parameters of different boreholes are quickly calculated. A reinforcement learning algorithm (RLDF) based on feedback of drilling parameters is introduced, which combines the advantages of LSTM-XGBoost in LNNs. An ODE solver replaces the traditional recurrent neural network (RNN) computation, and the process is divided into forward and backward propagation parts. It not only learns during training but also adapts and changes "online" based on newly encountered data after training. Finally, tree models with varying drilling parameters are combined into a relatively high-performance model, which can be represented by addition, as shown in the following formula:

[0045] In the formula: This is the model's final predicted value; For the first Sub-model; K To adjust the number of decision trees; For the first One input sample; F For decision tree sets, In order to be in The predicted value of the next iteration; based on continuous gradient boosting, new learning errors from before tree fitting are added during the training process; Optimize the objective function using Taylor expansion with regularization terms:

[0046] In the formula: For the first t The objective function for the next iteration; T This represents the number of leaf nodes in the model. For sample correspondence The first derivative; For the sample The corresponding second derivative; For the first j Output values ​​for each node.

[0047] The objective function is a convex function. This can be solved by setting the derivative to zero and... Find the derivative and calculate the value that minimizes the objective function. The optimal value is obtained, that is: A rigorous greedy algorithm can be used to calculate the gain after each leaf node split, and the structure of each tree is built by selecting the maximum gain. Starting from a single leaf, branches are iteratively added to the tree, and the gradient tree is boosted and sorted. The loss reduction after splitting can be obtained as follows: The hyperparameter set is optimized by combining algorithms to obtain a model that adapts to the training samples, thereby improving the final detection probability.

[0048] Furthermore, based on the inverted lithological parameters and the blasting energy of the explosive, a correlation between blastability and drillability is established.

[0049] The original blasting plans were statistically analyzed, and a blasting database was established. Based on the original preliminary blasting design and the historical blasting designs of the area, the blasting plans were optimized; the mesh spacing, burial depth, charge amount, and delay time were adjusted; furthermore, when the subsequent blasting area is similar to the inversion results of this instrument drilling, the mesh distribution of the subsequent boreholes can be directly adjusted based on the inversion results of the first few boreholes. As a further implementation method, changes in formation information are determined based on variations in drilling parameters, thereby altering the blasting design, including: The blasting design was optimized based on the principle that rocks with high strength are difficult to blast and have denser mesh and larger charge; rocks with more fractured rock and sparser mesh and smaller charge.

[0050] Taking the separation of ore and rock in the blasting zone as an example, the required ore and waste rock areas are identified by the instrument drilling algorithm. By carrying out refined blasting design in different zones, the amount of explosive charge is increased and the mesh spacing is tightened to increase the blasting energy. The delay time is appropriately shortened to enhance the superposition effect of explosive energy in the rock and form stronger stress wave interference, thereby improving the degree of rock fragmentation. For the waste rock area, the amount of explosive charge is reduced and the mesh spacing is widened to appropriately increase the block size to save mining costs.

[0051] Taking steep slope mining as an example, the geological characteristics are identified through instrument drilling algorithms. By extending the blasting delay time of each borehole, the inappropriate stress superposition effect is reduced, thereby reducing more minor damage to the slope rock mass, reducing the possibility of forming potential slip surfaces, and ensuring the long-term stability of the slope.

[0052] The specific quantitative relationship function for adjustment and optimization is generated by a deep learning algorithm based on the database content and is dynamically updated and iterated. After the blasting is completed, the blasting effect is evaluated, and the blasting design parameters are dynamically optimized based on the quantitative evaluation of the blasting effect. The data is then imported into the blasting database for feedback updates.

[0053] Example 2 One embodiment of this disclosure provides a blasting design optimization method based on machine-rock relationship and multi-parameter inversion. Taking open-pit bench blasting design as an example, in a mine bench blasting area, the vertical borehole parameters are a diameter of 310mm and a depth of 15m. The steps are as follows: S1, the integrated processor is installed on the drilling rig for no-load testing of the drilling rig; S2 imports geological data of the mining area from the backend, updates the corresponding instrument drilling data, and automatically establishes a new machine-rock matching relationship; S3, read geological parameters and obtain original stratigraphic conditions: Quaternary is the first layer 2m, carbonaceous slate is the second layer 3m, and magnetite is the fifth layer 10m; match the rock mechanical parameters of these three minerals and rocks through the lithology gene library; S4, based on the stratum characteristic information inverted from the first borehole, designs the interval distance of the second borehole, and so on, optimizing and determining the mesh parameters in real time to complete the blasting design for all single holes in the area; based on the blasting area, completes the mesh layout design, with the actual mesh area being S. Traditional blasting design only includes borehole depth, while this technology includes complete geological and blasting information. Based on lithology, structural planes, single-hole charge amount, and maximum single-section charge amount in the borehole, the borehole charge amount is adjusted by matching the wave impedance and the previous geological database with the traditional explosive consumption. The lithological characteristics of each layer are automatically matched and compared with the data in the lithological gene library, and the parameters such as hole depth, hole spacing, row spacing, and blasting delay design are comprehensively optimized and adjusted.

[0054] The S6 system performs intelligent analysis and design based on geological conditions, matching drillability with explosiveness. By comparing the blasting energy with the emulsion explosives used on site, it adjusts parameters such as charge concentration and depth based on explosive consumption.

[0055] S7 optimizes the blasting delay time based on vibration control requirements, rock hardness, blastability, and rock physical properties, and according to the distance from the borehole to the blasting zone. For example, by optimizing the design according to the principle of shorter delay time for near-blasting empty zones and longer delay time for far-blasting empty zones, other parameters such as blasting delay and backfilling are adjusted to form a fully information-based interconnected blasting design.

[0056] Based on the preliminary plan, the detonation point was selected considering factors such as vibration impact, large block ratio, and cost-effective charge. The detonation was then carried out according to the optimal design scheme calculated by the system, completing the blasting operation. Through on-site blasting effect analysis, blasting parameters were statistically analyzed, and a pre-design for the next section of the blasting was automatically generated. Simultaneously, negative feedback can be provided based on the blasting results to update and update subsequent borehole data and rock strata characteristic data.

[0057] Example 3 One embodiment of this disclosure provides a blasting design optimization system based on machine-rock relationship and multi-parameter inversion, including: The data acquisition module is used to acquire lithological data of the mining area and drilling operation parameters during the blasting process, and to preprocess the data to extract lithological characteristic parameters. The inversion module is used to establish the inversion relationship between various lithological characteristic parameters and drilling rig operating parameters by using the specific energy analysis method and based on Pearson correlation selection and correlation weight analysis, so as to obtain the inverted machine-rock relationship parameters. The optimization module is used to introduce the drilling operation parameter feedback reinforcement learning RLDF optimization algorithm. With the highest prediction accuracy as the objective function, it optimizes the combination of machine-rock relationship parameters to obtain the optimal parameter combination and establishes a blasting database. The blasting feedback module is used to optimize blasting schemes based on historical blasting designs in the area. It directly adjusts the mesh distribution of subsequent boreholes through the optimal parameter combination, dynamically optimizes the machine-rock relationship parameters based on the quantitative evaluation of blasting effects, and imports the data into the blasting database for feedback updates.

[0058] Example 4 One embodiment of this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned blasting design optimization method based on machine-rock relationship and multi-parameter inversion.

[0059] Example 5 One embodiment of this disclosure provides a non-transitory computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, they implement the blasting design optimization method based on machine-rock relationship and multi-parameter inversion.

[0060] Example 6 One embodiment of this disclosure provides an electronic device, including a processor, a memory, and a computer program; wherein the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the blasting design optimization method based on machine-rock relationship and multi-parameter inversion.

[0061] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0062] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0063] While the specific embodiments of this disclosure have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of this disclosure. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of this disclosure are still within the scope of protection of this disclosure.

Claims

1. A blasting design optimization method based on machine-rock relationship and multi-parameter inversion, characterized in that, include: Acquire lithological data of the mining area and drilling operation parameters during blasting, and preprocess them to extract lithological characteristic parameters from the lithological data; Using the specific energy analysis method, and based on Pearson's correlation selection and correlation weight theory, an inversion relationship between various lithological characteristic parameters and drilling rig operating parameters was established, and the inverted machine-rock relationship parameters were obtained. The drilling operation parameter feedback reinforcement learning (RLDF) optimization algorithm is introduced. With the highest prediction accuracy as the objective function, the combination of machine-rock relationship parameters is optimized to obtain the optimal parameter combination and establish a blasting database. Based on the historical blasting designs in the area, the blasting scheme was optimized. The mesh distribution of subsequent boreholes was directly adjusted through the optimal parameter combination. The machine-rock relationship parameters were dynamically optimized based on the quantitative evaluation of the blasting effect, and the data was imported into the blasting database for feedback updates.

2. The blasting design optimization method based on machine-rock relationship and multi-parameter inversion as described in claim 1, characterized in that, The drilling operation parameters include rotational speed, torque, drilling pressure, and vibration, while the lithological data include composition, structure, genesis, physical properties, and mechanical properties.

3. The blasting design optimization method based on machine-rock relationship and multi-parameter inversion as described in claim 1, characterized in that, The drilling operation parameters are quantified, and time-domain and frequency-domain feature values ​​are extracted using statistical methods. These feature values ​​include, but are not limited to, mean, maximum, minimum, median, peak, mode, root mean square error (RMSE), mean absolute error (MAE), and amplitude.

4. The blasting design optimization method based on machine-rock relationship and multi-parameter inversion as described in claim 1, characterized in that, By converting the drilling pressure, rotation speed, drilling speed, vibration, and torque variables under different lithologies with the corresponding data of roller cone drills, the specific energy analysis method is used to statistically analyze the relevant theoretical formula database. Based on Pearson correlation selection and correlation weight analysis, a series machine learning algorithm is used to establish the inversion relationship between various lithological characteristic parameters and various drilling rig operation parameters. This inversion relationship includes the matching relationship between the drilling rig experimental test calibration and the instrument drilling lithology gene library established by field measurement.

5. The blasting design optimization method based on machine-rock relationship and multi-parameter inversion as described in claim 1, characterized in that, By inversion, the correlation between rock mechanical properties such as uniaxial compressive strength, internal friction angle, Poisson's ratio, cohesion, and shear strength and drilling operation parameters such as drilling pressure, torque, drilling speed, and rotational speed is determined. The determined inversion parameters are applied in the blasting area, and instrument drilling tests are conducted in the borehole area. By determining the matching relationship, the lithological parameters of different boreholes are quickly calculated. The instrument drilling parameter feedback reinforcement learning RLDF optimization algorithm is introduced, and the ODE solver is used to replace the traditional recurrent neural network calculation. It is divided into two parts: forward propagation and backward propagation. Finally, the tree models with different drilling parameters are combined into a relatively high-performance model.

6. The blasting design optimization method based on machine-rock relationship and multi-parameter inversion as described in claim 1, characterized in that, Establish a blasting database, optimize blasting schemes based on the original preliminary blasting design and historical blasting designs for the area; adjust mesh spacing, burial depth, charge quantity and delay time; When the subsequent blasting area is similar to the inversion results of this instrument drilling, the mesh distribution of the subsequent boreholes is directly adjusted based on the inversion results of the previous few boreholes.

7. A blasting design optimization system based on machine-rock relationship and multi-parameter inversion, characterized in that, include: The data acquisition module is used to acquire lithological data of the mining area and drilling operation parameters during the blasting process, and to preprocess the data to extract lithological characteristic parameters. The inversion module is used to establish the inversion relationship between various lithological characteristic parameters and drilling rig operating parameters by using the specific energy analysis method and based on Pearson correlation selection and correlation weight analysis, so as to obtain the inverted machine-rock relationship parameters. The optimization module is used to introduce the drilling operation parameter feedback reinforcement learning RLDF optimization algorithm. With the highest prediction accuracy as the objective function, it optimizes the combination of machine-rock relationship parameters to obtain the optimal parameter combination and establishes a blasting database. The blasting feedback module is used to optimize blasting schemes based on historical blasting designs in the area. It directly adjusts the mesh distribution of subsequent boreholes through the optimal parameter combination, dynamically optimizes the machine-rock relationship parameters based on the quantitative evaluation of blasting effects, and imports the data into the blasting database for feedback updates.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the blasting design optimization method based on machine-rock relationship and multi-parameter inversion as described in any one of claims 1-6.

9. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium is used to store computer instructions, which, when executed by a processor, implement the blasting design optimization method based on machine-rock relationship and multi-parameter inversion as described in any one of claims 1-6.

10. An electronic device, characterized in that, include: The device includes a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to perform the blasting design optimization method based on machine-rock relationship and multi-parameter inversion as described in any one of claims 1-6.

Images