Blasting scheme automatic optimization system device

Abstract

The invention discloses an automatic blasting scheme optimization system device, and particularly relates to the technical field of intelligent blasting analysis and processing, which comprises a parameter acquisition module, a data processing module, an optimization algorithm module, a simulation verification module, a dynamic control module, a communication module, a safety protection module and a man-machine interaction module, a visual interface is provided for parameter input, scheme adjustment and three-dimensional dynamic display of simulation results, and multi-terminal synchronous operation and remote cooperative control are supported; according to the invention, multi-source sensor groups such as a vibration sensor and a geological radar are integrated, wavelet transform and Kalman filtering algorithms are combined, dynamic acquisition and space-time alignment of parameters such as an internal structure and water content of a rock mass are realized, and a three-dimensional geological model constructed by a data fusion unit can update a rock mass damage state in a blasting process in real time, so that the blasting accuracy is improved. The method has the advantages that the limitation of a traditional static model is broken through, the precision of explosive load calculation is remarkably improved, and dynamic adaptation of complex geological conditions is supported.

Description

Technical Field

[0001] The present invention relates to the technical field of blasting intelligent analysis and processing, and more particularly to a blasting scheme automatic optimization system device. Background Art

[0002] The automatic blasting plan optimization system breaks the limitations of traditional manual design. Through intelligent algorithms and big data analysis, it processes multiple sources of information, including geological conditions, engineering requirements, and safety regulations, in real time to dynamically generate and optimize blasting plans. It can rapidly simulate blasting effects under different parameter combinations, accurately select the optimal solution, significantly improve the efficiency and scientific nature of design, effectively reduce the errors and risks caused by reliance on human experience, ensure safe and efficient blasting operations, save costs, and shorten construction schedules, and is a key tool for promoting intelligent upgrades in the blasting engineering field.

[0003] The existing technology has the following problems:

[0004] 1. Insufficient data acquisition and fusion capabilities: Existing blasting plan designs often rely on single sensors or manual survey data, making it difficult to obtain key parameters such as internal rock fractures, water content, and hidden structures in real time. Traditional methods cannot effectively integrate multi-source heterogeneous data, resulting in low geological model accuracy. Data updates lag behind dynamic changes in the blasting environment, directly affecting the reliability of parameter design.

[0005] 2. Inefficient multi-objective collaborative optimization: Traditional optimization algorithms, such as empirical formulas or single heuristic algorithms, struggle to simultaneously meet the multi-objective constraints of safety, cost, and efficiency. Existing systems often use fixed weight allocation strategies, are unable to dynamically adjust blasting parameter priorities, and lack automated compliance verification for national standards and environmental regulations.

[0006] 3. Insufficient simulation verification accuracy and real-time performance: Existing blasting effect predictions rely on simplified mechanical models or two-dimensional simulations, ignoring the nonlinear failure behavior of rock masses under high strain rates, such as dynamic crack propagation and blast pile morphology evolution. Traditional finite element methods are time-consuming to calculate, cannot support real-time parameter iterative optimization, and lack closed-loop feedback with on-site monitoring data.

[0007] 4. Weak safety protection and emergency response mechanisms: Existing systems mostly use a passive protection mode based on threshold alarms, lacking multi-level early warning and proactive intervention capabilities. This makes it difficult to quickly terminate blasting sequences or initiate emergency measures under abnormal conditions. Furthermore, historical data storage is susceptible to tampering or loss, hindering accident tracing.

[0008] Therefore, in order to solve the above problems, an automatic optimization system for blasting scheme is proposed. Summary of the Invention

[0009] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a blasting plan automatic optimization system device to solve the problems raised in the above-mentioned background technology.

[0010] To achieve the above objectives, the present invention provides the following technical solutions: a blasting plan automatic optimization system device, comprising the following modules:

[0011] Parameter acquisition module, used to obtain rock parameters, environmental data and historical blasting records in the blasting area in real time, and dynamically collect rock fracture distribution, water content and geological structure characteristics through a multi-source sensor group;

[0012] The data processing module is connected to the parameter acquisition module to filter noise, extract features and standardize the collected data, and reduce the data dimension through principal component analysis (PCA) to generate a structured feature matrix;

[0013] The optimization algorithm module uses a machine learning model to dynamically generate multiple sets of blasting parameter combinations based on preset blasting targets (including blasting range, vibration threshold, and economic cost). It also uses a dynamic programming algorithm to achieve collaborative optimization of charge quantity, hole spacing, and detonation sequence.

[0014] The simulation verification module uses finite element analysis and 3D modeling technology to simulate the blasting effect of the generated parameter combination, accelerates the stress wave propagation simulation through parallel computing clusters, and outputs a quantitative score of safety and efficiency;

[0015] The dynamic control module automatically selects the optimal parameter combination based on the simulation results, adjusts the initiator trigger timing in real time through the fuzzy PID controller, and generates executable blasting control instructions;

[0016] The communication module supports wireless data interaction with external blasting equipment and sensor networks, using LoRa and 5G dual-link redundant communication to achieve low-latency transmission of command issuance and real-time monitoring data;

[0017] The safety protection module integrates an anomaly detection algorithm, which triggers the emergency termination program when the monitoring data exceeds the preset threshold and links the on-site sound and light alarm device;

[0018] The human-computer interaction module provides a visual interface for parameter input, scheme adjustment and three-dimensional dynamic display of simulation results, and supports multi-terminal synchronous operation and remote collaborative control.

[0019] Preferably, the parameter acquisition module includes: a multi-source sensor group, which includes a vibration sensor, an acoustic sensor, a high-definition camera and a geological radar, wherein the geological radar uses high-frequency electromagnetic waves to detect hidden faults inside the rock mass; a data fusion unit, which uses wavelet transform and Kalman filter algorithm to align and fuse multi-sensor data in time and space, construct a three-dimensional geological model and mark potential danger areas.

[0020] Preferably, the optimization algorithm module adopts a hybrid optimization strategy, including: genetic algorithm for global parameter space search, avoiding local optimality through adaptive crossover probability and mutation probability, particle swarm algorithm for rapid convergence of local optimal solution, combined with gradient descent method to optimize charge distribution density; constraint condition library, built-in vibration speed limit rules of national standard GB6722-2014 blasting safety regulations, and integration of dynamic constraints on dust diffusion range of regional environmental protection regulations.

[0021] Preferably, the simulation verification module includes: a rock destruction model, which establishes a dynamic damage constitutive relationship of the rock based on the Hoek-Brown criterion and introduces the JHC model to simulate the rock crushing behavior under high strain rate; an effect prediction unit, which calculates the blasting stress wave propagation path and the range of the crushing zone through the LS-DYNA solver, and uses the SPH method to simulate the blast pile morphology.

[0022] Preferably, the dynamic control module has: a parameter self-correction function, which can dynamically adjust the delayed detonation sequence according to the deviation between the real-time monitored blasting vibration data and the simulated predicted value, and optimize the next round of blasting parameters using a feedback control loop; a multi-objective optimization weight configuration interface, which allows users to customize the priority weights of safety, cost, and efficiency, and output a non-inferior solution set for manual decision-making through Pareto frontier analysis.

[0023] Preferably, the communication module adopts: an anti-interference protocol, which ensures the integrity of data transmission through frequency hopping spread spectrum technology in a blasting electromagnetic interference environment, and uses forward error correction coding to repair lost packet data; an edge computing node, which is deployed at the blasting site to achieve millisecond-level command response, and a built-in lightweight inference engine to perform real-time pre-processing of sensor data.

[0024] Preferably, the safety protection module includes: a multi-level early warning mechanism, which activates the first-level warning when the vibration speed is monitored to be ≥80% of the preset value, and adjusts the charge amount synchronously; when it is ≥95%, the detonation sequence is forcibly interrupted and the backup pressure relief channel is activated; a black box recording unit, which completely stores the data of the entire blasting process for accident tracing analysis, and uses AES-256 encryption technology to prevent data tampering.

[0025] Preferably, the human-computer interaction module provides: an augmented reality (AR) interface, which displays the three-dimensional perspective effect of the charge structure through a head-mounted device, and supports gesture interaction to adjust the hole network parameters; an intelligent recommendation function, which automatically pushes the historical optimal solution as the initial optimization benchmark based on a library of similar engineering cases, and combines a collaborative filtering algorithm to match successful cases with similar geological conditions.

[0026] Technical effects and advantages of the present invention:

[0027] 1. Multi-source data fusion and real-time modeling:

[0028] This method integrates a multi-source sensor system, including vibration sensors and geological radar, and combines wavelet transforms with Kalman filtering algorithms to dynamically collect and spatially align parameters such as rock mass internal structure and moisture content. The three-dimensional geological model constructed by the data fusion unit can update the rock mass damage status in real time during the blasting process. This method overcomes the limitations of traditional static models, significantly improves the accuracy of charge calculations, and supports dynamic adaptation to complex geological conditions.

[0029] 2. Multi-objective optimization driven by hybrid algorithms:

[0030] This method utilizes a hybrid optimization strategy combining genetic and particle swarm optimization algorithms, combined with dynamic programming, to achieve global-local coordinated optimization of blasting range, vibration control, and economic costs. The constraint library includes an automated verification mechanism for national standards and environmental regulations, and users can flexibly adjust target priorities through a weight configuration interface. This approach offers advantages such as a more than threefold increase in optimization efficiency and a 15%-25% reduction in explosives consumption under the same safety standards, while ensuring compliance with the proposed solution.

[0031] 3. High-precision simulation and edge computing acceleration:

[0032] This method constructs a dynamic damage constitutive relationship for rock masses based on the Hoek-Brown criterion and the JHC model, introduces the SPH method to simulate the morphology of the explosive pile, and uses the LS-DYNA solver to achieve high-fidelity simulation of stress wave propagation. Combined with the parallel computing capabilities of edge computing nodes, this method reduces simulation time from hours to minutes, supports real-time feedback control, and synchronizes parameter adjustments with changes in field conditions.

[0033] 4. Active security protection and trusted data storage:

[0034] This invention incorporates a multi-level early warning mechanism that automatically triggers parameter correction (Level 1 warning) or emergency termination (Level 2 warning) when vibration exceeds limits, and also activates pressure relief channels to mitigate risk. The black box unit utilizes AES-256 encryption and blockchain technology for tamper-proof data storage. This advantage reduces accident response time from seconds to milliseconds, ensures military-grade traceability of blasting data, and improves accident analysis efficiency by over 90%. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 Schematic diagram of the workflow of the present invention. DETAILED DESCRIPTION

[0036] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0037] As attached Figure 1 As shown, a blasting plan automatic optimization system device is disclosed, including the following modules:

[0038] Parameter acquisition module, used to obtain rock parameters, environmental data and historical blasting records in the blasting area in real time, and dynamically collect rock fracture distribution, water content and geological structure characteristics through a multi-source sensor group;

[0039] The data processing module is connected to the parameter acquisition module to filter noise, extract features and standardize the collected data, and reduce the data dimension through principal component analysis (PCA) to generate a structured feature matrix;

[0040] The optimization algorithm module uses a machine learning model to dynamically generate multiple sets of blasting parameter combinations based on preset blasting targets (including blasting range, vibration threshold, and economic cost). It also uses a dynamic programming algorithm to achieve collaborative optimization of charge quantity, hole spacing, and detonation sequence.

[0041] The simulation verification module uses finite element analysis and 3D modeling technology to simulate the blasting effect of the generated parameter combination, accelerates the stress wave propagation simulation through parallel computing clusters, and outputs a quantitative score of safety and efficiency;

[0042] The dynamic control module automatically selects the optimal parameter combination based on the simulation results, adjusts the initiator trigger timing in real time through the fuzzy PID controller, and generates executable blasting control instructions;

[0043] The communication module supports wireless data interaction with external blasting equipment and sensor networks, using LoRa and 5G dual-link redundant communication to achieve low-latency transmission of command issuance and real-time monitoring data;

[0044] The safety protection module integrates an anomaly detection algorithm, which triggers the emergency termination program when the monitoring data exceeds the preset threshold and links the on-site sound and light alarm device;

[0045] The human-computer interaction module provides a visual interface for parameter input, solution adjustment, and three-dimensional dynamic display of simulation results. It supports multi-terminal synchronous operation and remote collaborative control. The parameter acquisition module acquires geological and environmental data in real time. After noise reduction and standardization by the data processing module, the data is input into the optimization algorithm module to generate multiple parameter combinations. The simulation verification module performs parallel calculations to select the optimal solution. The dynamic control module issues instructions to the blasting equipment. The communication module ensures real-time data transmission. The safety protection module and the human-computer interaction module provide emergency response and operation interfaces, respectively. Each module is seamlessly connected through a unified data bus, forming an integrated "perception-decision-execution" architecture, realizing fully automated closed-loop control of blasting solution design, simulation, and execution, breaking through the traditional reliance on manual experience.

[0046] As a preferred embodiment, the parameter acquisition module includes: a multi-source sensor group, which includes a vibration sensor, an acoustic sensor, a high-definition camera and a geological radar, wherein the geological radar uses high-frequency electromagnetic waves to detect hidden faults inside the rock mass; a data fusion unit, which uses wavelet transform and Kalman filter algorithm to perform spatiotemporal alignment and fusion of multi-sensor data, construct a three-dimensional geological model and mark potential dangerous areas. Furthermore, vibration sensors are deployed in the blasting area with a spacing of 20m, geological radar (1GHz high-frequency detection) and drone aerial survey to collect data such as crack distribution and elastic modulus; the data fusion unit uses wavelet transform to eliminate clock deviation and Kalman filter to perform spatiotemporal alignment to generate a 0.1m resolution three-dimensional geological model, and mark the fault position and joint density, providing a dynamically updated geological data basis for the optimization algorithm, improving the accuracy and real-time performance of rock parameter detection, and solving the problem of missed detection of hidden structures.

[0047] As a preferred embodiment, the optimization algorithm module adopts a hybrid optimization strategy, including: a genetic algorithm for global parameter space search, avoiding local optimality through adaptive crossover probability and mutation probability, a particle swarm algorithm for rapid convergence of local optimal solutions, and combining the gradient descent method to optimize the charge distribution density; a constraint library, with built-in vibration speed limit rules of the national standard GB6722-2014 blasting safety regulations, and integrated dynamic constraints on dust diffusion range of regional environmental protection regulations. Furthermore, the genetic algorithm globally searches 200 groups of hole network parameter combinations with an adaptive crossover probability (0.6-0.8), and the particle swarm algorithm is combined with the gradient descent method to locally optimize the charge density; the constraint library automatically verifies the national standard vibration limit (≤2.5cm / s) and the environmental dust diffusion range, the user sets the priority through the weight interface, the dynamic programming algorithm generates a 15ms micro-difference detonation sequence, and finally outputs 10 groups of non-inferior solutions for decision-making, realizing multi-objective collaborative optimization and a global optimal solution that takes into account safety, cost and efficiency.

[0048] As a preferred embodiment, the simulation verification module includes: a rock destruction model, which establishes a dynamic damage constitutive relationship of the rock based on the Hoek-Brown criterion, and introduces the JHC model to simulate the rock crushing behavior under high strain rate; an effect prediction unit, which calculates the blasting stress wave propagation path and the crushing zone range through the LS-DYNA solver, and uses the SPH method to simulate the blast pile morphology. Furthermore, the rock damage constitutive relationship is established based on the Hoek-Brown criterion, and the JHC model simulates the high strain rate crushing behavior; the LS-DYNA solver calculates the stress wave propagation path, and the SPH method tracks the particle movement of the blast pile morphology; the simulation is accelerated by the edge computing node cluster, and the single calculation time is compressed from 8 hours to 22 minutes, and the predicted values ​​of the broken fragment size and vibration velocity are output, breaking through the traditional simulation accuracy limitations and realizing millimeter-level prediction of the blasting effect.

[0049] As a preferred embodiment, the dynamic control module has: a parameter self-correction function, which can dynamically adjust the delayed detonation sequence according to the deviation between the real-time monitored blasting vibration data and the simulated predicted value, and optimize the next round of blasting parameters using a feedback control loop; a multi-objective optimization weight configuration interface, which allows users to customize the priority weights of safety, cost, and efficiency, and output a non-inferior solution set for manual decision-making through Pareto front analysis. Furthermore, after detonation, the vibration sensor transmits data back in real time (sampling rate 1kHz). When the third segment vibration reaches 2.1cm / s, the fuzzy PID controller calculates the prediction deviation (Δ=0.2cm / s) and dynamically adjusts the subsequent detonator delay time to 18ms; the multi-objective weight interface allows on-site engineers to manually adjust the safety priority through the AR interface. The system generates a correction plan based on Pareto front analysis to ensure that the vibration throughout the process does not exceed the threshold, realize adaptive adjustment of the blasting process, and suppress the risk of vibration superposition.

[0050] As a preferred embodiment, the communication module adopts: an anti-interference protocol, which ensures the integrity of data transmission through frequency hopping spread spectrum technology in the blasting electromagnetic interference environment, and adopts forward error correction coding to repair lost packet data; an edge computing node is deployed at the blasting site to achieve millisecond-level command response, and a built-in lightweight inference engine pre-processes the sensor data in real time. Furthermore, LoRa-5G dual-link redundant transmission is adopted, and frequency hopping spread spectrum technology is used to achieve 1600 times / second frequency switching in the 2.4GHz frequency band, and forward error correction coding is used to repair 10% packet loss rate data; the edge computing node deploys a lightweight inference engine to pre-process the sensor data in real time, so that the delay in issuing the charge calibration instruction is ≤15ms, which meets the requirements of high-precision detonation timing control and ensures millisecond-level response of instructions in complex electromagnetic environments.

[0051] As a preferred embodiment, the safety protection module includes: a multi-level early warning mechanism, when the vibration speed is monitored to be ≥80% of the preset value, the first-level early warning is activated and the charge is adjusted synchronously; when it is ≥95%, the detonation sequence is forcibly interrupted and the backup pressure relief channel is started; a black box recording unit, which completely stores the data of the entire blasting process for accident tracing analysis, and adopts AES-256 encryption technology to prevent data tampering. Furthermore, the first-level early warning, vibration ≥2.0cm / s, triggers a dynamic reduction of the charge by 5%, and the second-level early warning forces the interruption of the detonation sequence and opens the pressure relief channel; the black box unit stores the entire process data with AES-256 encryption, and the hash value is synchronized to the blockchain node to ensure that the data cannot be tampered with. The accident tracing time is shortened from 48 hours to 2 hours, and potential risks are actively intervened to achieve zero tolerance for accidents.

[0052] As a preferred embodiment, the human-computer interaction module provides: an augmented reality (AR) interface, which displays a three-dimensional perspective effect of the charge structure through a head-mounted device, and supports gesture interaction to adjust the hole network parameters; an intelligent recommendation function, which automatically pushes the historical optimal solution as the initial optimization benchmark based on a similar engineering case library, and combines the collaborative filtering algorithm to match successful cases with similar geological conditions. Furthermore, the AR headset overlays and displays a three-dimensional perspective model of the charge structure, and gesture recognition supports dragging in the air to adjust the hole spacing; the case library matches similar geological conditions based on the collaborative filtering algorithm, and pushes the historical optimal solution as the initial parameter. After the engineer confirms it, the system automatically loads it into the optimization algorithm. The scheme design time is reduced from 6 hours to 40 minutes, lowering the operation threshold and improving the scheme design efficiency.

[0053] Example 1: Implementation process of the blasting plan automatic optimization system

[0054] Scenario description: An open-pit mine needs to carry out bench blasting operations. The goal is to achieve rock fragmentation ≤30cm while ensuring the vibration velocity ≤2.5cm / s (national standard GB6722-2014) and reducing the explosive consumption to 0.35kg / m 3 The rock mass is granite with well-developed joints and hidden faults.

[0055] Implementation process:

[0056] 1. Parameter collection and modeling stage

[0057] By deploying vibration sensors, geological radars, acoustic sensors, and drone aerial survey equipment, we collect real-time data on rock crack distribution, elastic modulus, and three-dimensional surface models in the blasting area. We use wavelet transform to eliminate sensor clock bias, and combine the Kalman filter algorithm to align and fuse multi-source data in time and space, building a 0.1m resolution system. 3A high-precision three-dimensional geological model is created, and the rock mass RQD value, joint density and hidden fault location are marked to provide dynamically updated geological basic data for subsequent optimization.

[0058] 2. Parameter optimization and simulation stage

[0059] Based on safety, economy and efficiency goals, input vibration threshold (≤2.5cm / s), explosive consumption (≤0.35kg / m 3 ) and fragment size (≤30cm) constraints, a genetic algorithm was used for global search to generate 200 groups of initial parameter combinations, and then 10 groups of candidate solutions were screened out through particle swarm optimization. The dynamic programming was combined to optimize the micro-difference detonation sequence. The optimal solution was imported into the LS-DYNA simulation platform, and the JHC model and SPH method were used to simulate the blast pile morphology and stress wave propagation. The fragment size (28.7cm), vibration speed (2.3cm / s) and explosive consumption (0.33kg / m) were verified by GPU parallel computing. 3 )’s compliance.

[0060] 3. Dynamic control and execution phase

[0061] The network parameters (hole spacing 4.2m, row spacing 3.8m) were transmitted to the intelligent drilling machine via 5G-LoRa dual-link communication. The explosive charge (56.4kg ± 0.5kg per hole) and the electronic detonator delay time (15ms interval) were calibrated. Vibration data was monitored in real time during the detonation process. When the vibration velocity of the third segment reached 2.1cm / s, a fuzzy PID controller dynamically adjusted the delay of subsequent segments to 18ms to suppress the vibration superposition effect and ensure that the vibration velocity remained below the threshold throughout the entire process.

[0062] 4. Safety protection and post-processing stage

[0063] A multi-level early warning mechanism is triggered: When the instantaneous vibration value in the fifth segment reaches 2.4 cm / s (96% of the preset threshold), the system automatically reduces the charge in the undetonated hole by 5% and activates the pressure relief channel. After the blast is completed, the black box unit uses AES-256 encryption to store the entire process data and upload it to the blockchain platform.

[0064] This example verifies the reliability and advancement of the system under complex geological conditions, and meets the technical upgrade requirements of intelligent blasting in mines.

[0065] Finally, a few points should be explained: First, in the description of this application, it should be noted that, unless otherwise specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense, and may refer to mechanical or electrical connections, internal communication between two components, or direct connection. "Up," "down," "left," and "right" are only used to indicate relative positional relationships. When the absolute positions of the objects being described change, the relative positional relationships may also change.

[0066] Secondly: The drawings of the embodiments disclosed in the present invention only involve structures related to the embodiments disclosed in the present invention. Other structures may refer to conventional designs. The same embodiment and different embodiments of the present invention may be combined with each other without conflict.

[0067] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A blasting plan automatic optimization system device, characterized in that: Includes the following modules: Parameter acquisition module, used to obtain rock parameters, environmental data and historical blasting records in the blasting area in real time, and dynamically collect rock fracture distribution, water content and geological structure characteristics through a multi-source sensor group; The data processing module is connected to the parameter acquisition module to perform noise filtering, feature extraction and standardization on the collected data, and reduce the data dimension through principal component analysis (PCA) to generate a structured feature matrix; The optimization algorithm module uses a machine learning model to dynamically generate multiple sets of blasting parameter combinations based on preset blasting targets (including blasting range, vibration threshold, and economic cost). It also uses a dynamic programming algorithm to achieve collaborative optimization of charge quantity, hole spacing, and detonation sequence. The simulation verification module uses finite element analysis and 3D modeling technology to simulate the blasting effect of the generated parameter combination, accelerates the stress wave propagation simulation through parallel computing clusters, and outputs a quantitative score of safety and efficiency; The dynamic control module automatically selects the optimal parameter combination based on the simulation results, adjusts the initiator trigger timing in real time through the fuzzy PID controller, and generates executable blasting control instructions; The communication module supports wireless data interaction with external blasting equipment and sensor networks, using LoRa and 5G dual-link redundant communication to achieve low-latency transmission of command issuance and real-time monitoring data; The safety protection module integrates an anomaly detection algorithm, which triggers the emergency termination program when the monitoring data exceeds the preset threshold and links the on-site sound and light alarm device; The human-computer interaction module provides a visual interface for parameter input, scheme adjustment and three-dimensional dynamic display of simulation results, and supports multi-terminal synchronous operation and remote collaborative control.

2. The blasting plan automatic optimization system according to claim 1, characterized in that: The parameter acquisition module includes: a multi-source sensor group, which includes a vibration sensor, an acoustic sensor, a high-definition camera and a geological radar, wherein the geological radar uses high-frequency electromagnetic waves to detect hidden faults inside the rock mass; a data fusion unit, which uses wavelet transform and Kalman filter algorithm to align and fuse multi-sensor data in time and space, construct a three-dimensional geological model and mark potential danger areas.

3. The blasting plan automatic optimization system according to claim 1, characterized in that: The optimization algorithm module adopts a hybrid optimization strategy, including: a genetic algorithm for global parameter space search, avoiding local optimality through adaptive crossover probability and mutation probability, a particle swarm algorithm for rapid convergence of local optimal solutions, combined with a gradient descent method to optimize charge distribution density; a constraint condition library with a built-in vibration velocity limit rule of the national standard GB6722-2014 Blasting Safety Regulations, and integrated dynamic constraints on dust diffusion range based on regional environmental protection regulations.

4. The blasting plan automatic optimization system according to claim 1, characterized in that: The simulation verification module includes: a rock failure model, which establishes a dynamic damage constitutive relationship for rock mass based on the Hoek-Brown criterion and introduces the JHC model to simulate rock crushing behavior under high strain rates; an effect prediction unit, which calculates the blasting stress wave propagation path and the range of the crushing zone through the LS-DYNA solver, and uses the SPH method to simulate the blast pile morphology.

5. The blasting plan automatic optimization system according to claim 1, characterized in that: The dynamic control module has the following features: parameter self-correction function, which can dynamically adjust the delayed detonation sequence based on the deviation between the real-time monitored blasting vibration data and the simulated predicted value, and optimize the next round of blasting parameters using a feedback control loop; a multi-objective optimization weight configuration interface, which allows users to customize the priority weights of safety, cost, and efficiency, and output a non-inferior solution set for manual decision-making through Pareto frontier analysis.

6. The blasting plan automatic optimization system according to claim 1, characterized in that: The communication module adopts: anti-interference protocol, frequency hopping spread spectrum technology to ensure data transmission integrity in the explosive electromagnetic interference environment, and forward error correction coding to repair lost data; Edge computing nodes are deployed at the blasting site to achieve millisecond-level command response, and the built-in lightweight inference engine performs real-time pre-processing of sensor data.

7. The blasting plan automatic optimization system according to claim 1, characterized in that: The safety protection module includes: a multi-level early warning mechanism. When the monitored vibration speed is ≥80% of the preset value, the first level warning is activated and the charge amount is adjusted synchronously; when it is ≥95%, the detonation sequence is forcibly interrupted and the backup pressure relief channel is activated; a black box recording unit completely stores the data of the entire blasting process for accident tracing and analysis, and uses AES-256 encryption technology to prevent data tampering.

8. The blasting plan automatic optimization system according to claim 1, characterized in that: The human-computer interaction module provides: an augmented reality (AR) interface that displays a three-dimensional perspective effect of the charge structure through a head-mounted device, and supports gesture interaction to adjust the hole network parameters; an intelligent recommendation function that automatically pushes the historical optimal solution as the initial optimization benchmark based on a library of similar engineering cases, and combines a collaborative filtering algorithm to match successful cases with similar geological conditions.

Images