A gas explosion control method, system, electronic device and storage medium

By constructing historical datasets for closed-loop correction and model extrapolation, gas blasting control parameters are dynamically generated, solving the adaptability problem of blasting control under complex working conditions and improving the safety and consistency of blasting operations.

CN123067262APending Publication Date: 2026-11-10BEIJING SINOBANG DIGITAL TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611279130.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-21
Publication Date
2026-11-10

AI Technical Summary

Technical Problem

In gas blasting operations such as mining, tunneling, and geotechnical engineering, existing technologies struggle to adaptively adjust blasting control parameters, resulting in uneven blasting block size, excessive vibration, or low energy utilization, which affects safety and effectiveness.

Method used

By constructing a dataset containing historical performance feedback, closed-loop correction of control parameters is performed. When the current operating conditions do not match the historical operating conditions, model inference is performed based on the correlation between the operating condition differences and parameter changes to dynamically generate target control parameters.

Benefits of technology

It improves the adaptability of gas blasting control parameters, enhances the consistency of blasting effects, the accuracy of parameter control and operational safety, reduces reliance on human experience, and promotes the intelligent development of blasting engineering.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123067262A_ABST
    Figure CN123067262A_ABST
Patent Text Reader

Abstract

This application relates to the technical field of blasting engineering, and more particularly to a gas blasting control method, system, electronic device, and storage medium. The method includes: acquiring historical operating condition characteristics, historical control parameters, and historical effect feedback of a gas blasting scenario; correcting the historical control parameters based on the historical effect feedback to obtain baseline control parameters; acquiring real-time operating condition characteristics and determining their matching degree with historical operating condition characteristics; determining target control parameters based on the matched baseline control parameters in response to the matching degree meeting preset conditions; importing the difference information into a preset data model based on the correlation between changes in operating condition characteristics and changes in control parameters to deduce the target control parameters in response to the matching degree not meeting preset conditions; and generating blasting control commands based on the target control parameters to control the equipment to perform operations. This application achieves adaptive and precise control of gas blasting parameters in complex scenarios.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the technical field of blasting engineering, and in particular to a gas blasting control method, system, electronic device and storage medium. Background Technology

[0002] Currently, in gas blasting operations such as mining, tunneling, and geotechnical engineering, the setting of blasting control parameters typically relies on manual experience or fixed rule tables. However, the geological conditions, environmental parameters, and equipment status at actual blasting sites are complex and variable, making it difficult for fixed rules to cover all scenarios. Manual experience, on the other hand, is highly subjective and lacks a quantitative feedback mechanism for historical blasting results. This leads to difficulties in adaptively adjusting control parameters when facing unfamiliar complex conditions or scenarios that differ from historical conditions. Consequently, problems such as uneven blasting block size, excessive vibration, or low energy utilization occur, seriously affecting the safety and effectiveness of blasting operations. Summary of the Invention

[0003] To address at least one of the aforementioned technical problems, this application provides a gas explosion control method, system, electronic device, and storage medium.

[0004] In a first aspect, this application provides a gas explosion control method, which adopts the following technical solution: Acquire historical operational characteristics, historical control parameters, and historical effect feedback of gas explosion scenarios; Based on the historical performance feedback, the historical control parameters are corrected to obtain the baseline control parameters; Obtain the real-time operating condition characteristics of the gas explosion scenario, and determine the matching degree between the real-time operating condition characteristics and the historical operating condition characteristics; In response to the matching degree meeting the preset conditions, the target control parameters are determined based on the benchmark control parameters corresponding to the historical operating condition features that match the real-time operating condition features. In response to the matching degree not meeting the preset condition, based on the correlation between changes in operating condition characteristics and changes in control parameters, the difference information between the real-time operating condition characteristics and the historical operating condition characteristics is imported into a preset data model for deduction to obtain the target control parameters. Based on the target control parameters, blasting control commands are generated to control the gas blasting equipment to perform blasting operations.

[0005] By adopting the above technical solution, the reliability of the benchmark is improved by constructing a historical dataset containing effect feedback and performing closed-loop correction on the control parameters. At the same time, when the current operating conditions do not perfectly match the historical operating conditions, model inference is performed based on the correlation between the operating condition differences and parameter changes to dynamically generate suitable target control parameters, thereby solving the problem of high-precision adaptive control of gas explosion in complex and unseen scenarios.

[0006] In one possible implementation, the step of correcting the historical control parameters based on the historical effect feedback to obtain baseline control parameters includes: The historical results are compared with the expected blasting target to determine the blasting deviation; The historical control parameters are compensated and corrected based on the blasting deviation to obtain the baseline control parameters.

[0007] In one possible implementation, the historical effect feedback includes at least one of the following: blasting block size distribution index, vibration velocity index, and scattering distance index; the historical control parameters include at least one of the following: charge quantity parameter, pressurization value parameter, and detonation delay parameter. The historical control parameters are compensated and corrected based on the blasting deviation to obtain the baseline control parameters, including: If the blasting block size distribution index deviates from the expected block size distribution in the expected blasting target, the filling quantity parameter is adjusted according to the first preset mapping rule; If the vibration velocity index or the scattering distance index deviates from the expected safety threshold in the expected blasting target, the detonation delay parameter and / or the filling amount parameter shall be adjusted according to the second preset mapping rule. The adjusted filling quantity parameter and / or the detonation delay parameter shall be used as the baseline control parameter.

[0008] In one possible implementation, in response to the matching degree not meeting the preset condition, based on the correlation between changes in operating condition characteristics and changes in control parameters, the difference information between the real-time operating condition characteristics and the historical operating condition characteristics is imported into a preset data model for deduction to obtain the target control parameters, including: Determine the correlation between changes in operating conditions and changes in control parameters; The difference information and the correlation relationship are concatenated to obtain the model input features; The input features of the model are imported into a preset data model for extrapolation and fitting, and the target control parameters are output.

[0009] In one possible implementation, the step of concatenating the difference information with the association to obtain the model input features includes: The difference information is vectorized and encoded to obtain the difference feature vector; The relationships are represented in a structured manner to obtain the association weight matrix; The difference feature vector and the correlation weight matrix are concatenated and dimensionality reduced to obtain the model input features; The model input features are imported into a preset data model for extrapolation and fitting, and the target control parameters are output, including: The model input features are forward-computed using a multilayer perceptron in a pre-defined data model, and the resulting fitted parameter vector is output. Based on the preset parameter parsing rules, the fitted parameter vector is mapped to physical control quantities to obtain the target control parameters, which include the target filling amount, the target pressurization value, and the target detonation delay.

[0010] In one possible implementation, determining the matching degree between the real-time operating condition features and the historical operating condition features includes: Multi-dimensional feature extraction is performed on the real-time operating condition features and the historical operating condition features respectively to obtain real-time feature vectors and historical feature vectors. The multi-dimensional feature extraction covers feature encoding of geological conditions, environmental parameters and equipment status. Determine the weight coefficients corresponding to each dimension, wherein the weight coefficients are determined based on the historical correlation strength between each dimension and the explosion effect; Based on the weighting coefficients, a weighted similarity calculation is performed between the real-time feature vector and the historical feature vector to obtain a weighted similarity index. The matching degree is determined based on the weighted similarity index; In response to the matching degree satisfying a preset condition, including: the matching degree being greater than or equal to a preset threshold; In response to the matching degree not meeting the preset condition, including: the matching degree being less than the preset threshold.

[0011] In one possible implementation, generating blasting control commands based on the target control parameters to control the gas blasting equipment to perform blasting operations includes: Based on the target control parameters, including the target filling amount, target pressurization value, and target detonation delay, a timing control command containing multiple time nodes is generated. The current equipment status parameters and current environmental safety parameters of the gas explosion device are verified to obtain the safety verification results. In response to the safety verification result meeting the preset safety conditions, the timing control command is sent to the gas explosion device; The gas blasting device is controlled to sequentially perform filling, pressurizing and detonation actions at the corresponding time nodes, and action completion status information is collected during the execution interval of adjacent actions. After confirming that the execution conditions of the next action are met based on the action completion status information, the execution of the next action is triggered. The execution parameters of the filling action are determined by the target filling amount, the execution parameters of the pressurization action are determined by the target pressurization value, and the triggering time of the detonation action is determined by the target detonation delay.

[0012] Secondly, this application provides a gas explosion control system, which adopts the following technical solution: A gas explosion control system, comprising: The data acquisition module is used to acquire historical operating condition characteristics, historical control parameters, and historical effect feedback of the gas explosion scenario, and to acquire the real-time operating condition characteristics of the gas explosion scenario. The parameter correction module is used to correct the historical control parameters based on the historical effect feedback to obtain the baseline control parameters; The matching and judgment module is used to determine the degree of matching between the real-time operating condition features and the historical operating condition features; The first response module is used to determine the target control parameters based on the benchmark control parameters corresponding to the historical operating condition features that match the real-time operating condition features in response to the matching degree meeting the preset conditions. The second response module is used to respond to the fact that the matching degree does not meet the preset condition, and based on the correlation between the changes in operating condition characteristics and the changes in control parameters, import the difference information between the real-time operating condition characteristics and the historical operating condition characteristics into the preset data model for deduction to obtain the target control parameters. The command control module is used to generate blasting control commands based on the target control parameters in order to control the gas blasting equipment to perform blasting operations.

[0013] Thirdly, this application provides an electronic device that adopts the following technical solution: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: execute a gas explosion control method as described in any of the first aspects.

[0014] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform a gas explosion control method as described in any of the first aspects.

[0015] In summary, this application includes at least one of the following beneficial technical effects: By using closed-loop correction of historical control parameters based on historical effect feedback, a highly reliable benchmark parameter library was established, overcoming the drift problem of traditional experience parameters over time and with environmental changes. Simultaneously, when the matching degree between the current operating condition and historical operating conditions is insufficient, instead of simply rejecting or continuing with old parameters, it dynamically generates target control parameters adapted to the current scenario based on the inherent correlation between changes in operating condition characteristics and changes in control parameters, combined with a preset data model, and differentiated extrapolation. This dual adaptive mechanism of benchmark correction and differentiated extrapolation improves the adaptability of gas blasting control parameters to complex operating conditions and transitional scenarios, which is beneficial for improving the consistency of blasting effects, parameter control accuracy, and operational safety, while reducing reliance on human experience and promoting the intelligent development of blasting engineering. Attached Figure Description

[0016] Figure 1 This is a schematic flowchart of a gas explosion control method provided in an embodiment of this application.

[0017] Figure 2 This is a schematic diagram of a gas explosion control system provided in an embodiment of this application.

[0018] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] The following is in conjunction with the appendix Figure 1-3 This application will be described in further detail.

[0020] This specific embodiment is merely an explanation of this application and is not intended to limit it. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they are within the scope of this application.

[0021] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0023] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0024] This application provides a method for controlling a gas explosion, executed by an electronic device. This electronic device can be a standalone physical electronic device, a cluster of multiple physical electronic devices, a distributed system, or a cloud electronic device providing cloud computing services. This application does not impose limitations on this method. Figure 1 As shown, the method includes: Step S10: Obtain historical operating conditions, historical control parameters, and historical effect feedback for the gas explosion scenario.

[0025] Specifically, historical operating condition characteristics refer to environmental and geological condition data recorded in past blasting operations, such as rock hardness coefficient, fracture development degree, free face distance, and ambient temperature and humidity; historical control parameters refer to the actual blasting setpoints executed under those historical operating conditions, such as carbon dioxide charge amount, detonation delay time, and fracturing device spacing; historical effect feedback refers to the actual result data collected through on-site surveys or sensors after blasting, such as blast block size distribution, peak vibration velocity, and flyrock distance. These three types of data do not exist in isolation but are stored in a linked manner as a "operating condition-parameter-effect" triple, forming the data foundation for subsequent adaptive control. It should be understood that historical data can be obtained by reading from a local database, synchronizing from a cloud server, or importing back through on-site sensing devices; this application does not limit this.

[0026] Step S11: Correct the historical control parameters based on historical effect feedback to obtain the baseline control parameters.

[0027] In practical engineering, due to factors such as equipment performance degradation, gradual changes in geological conditions, or insufficient precision in early manual settings, the historical control parameters recorded in the original records are often not the optimal solution under current conditions. For example, although a historical blasting operation completed its task, the feedback showed a high percentage of large blocks, indicating that the filling volume at that time was actually insufficient for the specific working conditions. Therefore, this embodiment uses historical feedback as a correction signal to compensate for or adjust the original historical control parameters, thereby generating benchmark control parameters that better represent the current technological level. This correction mechanism enables the system to "distinguish between true and false" historical experience, avoiding the accumulation of errors caused by blindly inheriting erroneous experiences, and significantly improving the reliability and timeliness of the benchmark parameters.

[0028] Step S12: Obtain the real-time operating condition characteristics of the gas explosion scenario and determine the matching degree between the real-time operating condition characteristics and the historical operating condition characteristics.

[0029] In this approach, the dimensions of real-time operating condition features collected should be consistent with those of historical operating conditions to ensure comparability. The calculation of the matching degree abandons the stringent requirement of "absolute consistency" of operating conditions found in traditional solutions, as it is almost impossible for two blasting environments to be exactly the same in a construction site. This embodiment uses similarity metrics or weighted distance calculations to quantify the closeness between real-time and historical operating conditions. The matching degree, as a continuous variable or hierarchical index, is used to characterize the degree to which the current scenario is covered by historical experience. This design transforms the discrete "match / mismatch" binary judgment into a continuous confidence assessment, providing a quantitative basis for the smooth switching of subsequent control strategies and effectively solving the problem of frequent control strategy jumps caused by minor fluctuations in operating conditions.

[0030] Step S13: In response to the matching degree meeting the preset conditions, determine the target control parameters based on the benchmark control parameters corresponding to the historical operating condition characteristics that match the real-time operating condition characteristics.

[0031] In this embodiment, when the matching degree meets the preset conditions (e.g., similarity is higher than the threshold), the system determines that the current working condition is within the effective coverage of historical experience, and directly reuses the modified benchmark control parameters as the target control parameters, thus ensuring control stability and computational efficiency in normal scenarios.

[0032] Step S14: In response to the mismatch not meeting the preset conditions, based on the correlation between changes in operating condition characteristics and changes in control parameters, the difference information between real-time operating condition characteristics and historical operating condition characteristics is imported into the preset data model for deduction to obtain the target control parameters.

[0033] In this embodiment, when the matching degree does not meet the preset conditions, it means that a complex working condition or transitional scenario that has not been encountered before has been encountered. At this time, the system automatically switches to the inference path. In the inference path, the "correlation between changes in working condition characteristics and changes in control parameters" plays a key physical prior guiding role. For example, an increase in rock hardness usually requires a linear increase in filling volume, and a decrease in free face requires an extension of the delay. These correlations representing physical laws are imported together with specific difference information into the preset data model, so that the model is no longer a pure data fitting black box, but an inference engine that integrates engineering mechanisms. The preset data model here performs an online inference function, that is, it fits the target control parameters adapted to the new working condition in real time based on the input differential features and correlation constraints. This combination of "experience reuse + mechanism inference" not only ensures efficient processing of known scenarios, but also gives the system the ability to generalize and adapt to unknown scenarios.

[0034] Step S15: Generate blasting control commands based on target control parameters to control the gas blasting equipment to perform blasting operations.

[0035] In this embodiment, the target control parameters are typically an abstract set of values ​​that need to be converted into execution commands recognizable by the gas blasting equipment. For example, the target filling amount is converted into valve opening duration or flow meter setpoint, and the target detonation delay is converted into timer trigger time. The generated blasting control commands can be directly sent to the field controller or forwarded via an intermediate gateway. Through the above-described entire process, this embodiment achieves complete closed-loop control from historical data mining, benchmark parameter self-calibration, real-time operating condition adaptation to final command generation, fundamentally solving the technical problem that traditional fixed parameter methods are difficult to cope with complex and variable blasting scenarios, and improving the safety, economy, and consistency of blasting operations.

[0036] As one implementation method, historical control parameters are corrected based on historical effect feedback to obtain benchmark control parameters, including: comparing historical effect feedback with the expected blasting target to determine the blasting deviation; and compensating and correcting the historical control parameters based on the blasting deviation to obtain benchmark control parameters.

[0037] Specifically, the expected blasting target refers to the ideal effect indicators set during the blasting design phase based on engineering requirements, such as the average target block size and the maximum allowable peak particle vibration velocity. The system compares the actual historical effect feedback with the expected blasting target to calculate the quantified blasting deviation. For example, if the average particle size of the actual blasted blocks is 35 cm, while the expected target is 30 cm, a positive deviation occurs, indicating that the fragmentation effect has not met the standard. If the actual vibration velocity is 8 cm / s, while the safety threshold is 10 cm / s, although it does not exceed the standard, it is close to the critical value and may also be identified as a negative margin deviation that needs optimization. Based on this quantified deviation, the system does not simply discard unqualified data, but treats it as a correction signal, reverses the deduction of deficiencies or redundancies in historical control parameters, and then compensates and corrects them. This mechanism transforms the originally discrete historical feedback data, which was only used for acceptance, into the core driving force for continuously optimizing control accuracy, effectively eliminating the accumulation of systematic errors caused by equipment aging, geological changes, or rough early manual settings, so that the generated benchmark control parameters can dynamically approach the optimal solution under the current working conditions.

[0038] As one implementation method, historical effect feedback includes at least one of the following: blasting block size distribution index, vibration velocity index, and scattering distance index; the historical control parameters include at least one of the following: charge quantity parameter, pressurization value parameter, and detonation delay parameter. Based on this, the specific logic for compensating and correcting the historical control parameters based on blasting deviation includes: if the blasting block size distribution index deviates from the expected block size distribution in the expected blasting target, then the charge quantity parameter is adjusted according to a first preset mapping rule; if the vibration velocity index or the scattering distance index deviates from the expected safety threshold in the expected blasting target, then the detonation delay parameter and / or the charge quantity parameter are adjusted according to a second preset mapping rule; the adjusted charge quantity and / or detonation delay parameter is used as the benchmark control parameter.

[0039] The blasting block size distribution index characterizes the effect of gas blasting energy release on rock mass fragmentation. A high proportion of large blocks or excessively large average particle size usually indicates insufficient blasting energy per unit volume of rock. In this case, the first preset mapping rule guides the system to increase the filling quantity parameter. Conversely, excessively fine blocks or a high proportion of fine ore may indicate excess energy, requiring a reduction in the filling quantity. The vibration velocity index and flyaway distance index primarily characterize the external effects and safety of blasting energy. When these two indices exceed or approach the safety threshold, it is often related to excessive instantaneous release pressure energy or unreasonable timing of adjacent blasting units. In this case, the second preset mapping rule guides the system to adjust the initiation delay parameter, for example, by extending the inter-hole or inter-row delay to stagger vibration peaks, or by optimizing the delay sequence to improve free surface conditions and suppress flyrock. It should be understood that the implementation of the first and second preset mapping rules is not limited to a single mathematical formula; it can be a linear compensation coefficient, a piecewise function, a polynomial fitting curve, or a lookup table constructed based on a large amount of engineering calibration data. More importantly, these mapping rules themselves have dynamic update capabilities. As new data accumulates and the correction effects are verified, the system can periodically recalibrate the rule parameters to ensure they always conform to the actual rock mass response characteristics of the current mine or tunnel. The baseline control parameters obtained after the above-mentioned fine-tuning will be labeled with the corresponding working condition feature tags and stored in the database, replacing or associating with the original coarse records.

[0040] As one implementation method, in response to a mismatch condition, based on the correlation between changes in operating conditions and changes in control parameters, the difference information between real-time operating conditions and historical operating conditions is imported into a preset data model for deduction to obtain target control parameters. This includes: determining the correlation between changes in operating conditions and changes in control parameters; concatenating the difference information and the correlation to obtain model input features; and importing the model input features into the preset data model for deduction and fitting to output target control parameters. Based on this, the specific execution logic of feature concatenation and deduction fitting includes: vectorizing the difference information to obtain difference feature vectors; structurally representing the correlation to obtain a correlation weight matrix; and concatenating and dimensionality-reducing the difference feature vectors and the correlation weight matrix to obtain model input features.

[0041] The difference information typically consists of multi-dimensional raw observation differences (such as differences in hardness, humidity, and pore depth), which are converted into computer-processable numerical tensors, i.e., difference feature vectors, through vectorized encoding. The correlation is pre-structured into a correlation weight matrix, where each element represents the strength and direction of the influence of a specific working condition dimension change on a specific control parameter dimension. Concatenating these two elements essentially fuses the "current situation deviation" and the "adjustment strategy," enabling the model to not only know "where the difference is" but also "which direction and how much to adjust." Subsequent dimensionality reduction aims to eliminate redundant information and environmental noise, extracting the core feature combination most explanatory to the blasting effect, thereby reducing model computational complexity and improving generalization ability. It should be understood that the specific algorithms for the above vectorized encoding, structured representation, and dimensionality reduction can be implemented using various existing technologies such as principal component analysis, autoencoders, or attention mechanisms. This application does not limit these methods, as long as they can achieve semantic alignment and compression of heterogeneous information.

[0042] After obtaining high-quality model input features, the system performs forward computation on the model input features through a multilayer perceptron in the preset data model and outputs a fitting parameter vector. Based on the preset parameter parsing rules, the fitting parameter vector is mapped to physical control quantities to obtain the target control parameters, which include the target filling amount, the target pressurization value, and the target detonation delay.

[0043] It is worth noting that the forward computation of the multilayer sensing network here refers to the online inference process after the model parameters have been fixed, without involving any offline R&D steps such as training, learning, or backpropagation. The model output fitting parameter vector is usually a dimensionless normalized value, which needs to be converted into an engineering control quantity with a clear physical unit through a preset parameter parsing rule. For example, if the model outputs a filling volume fitting value of 0.75, the parameter parsing rule will convert it into a specific target filling volume of 4.5kg based on the maximum allowable filling upper limit (e.g., 6kg) and minimum lower limit (e.g., 2kg) of the current working area through a linear or nonlinear mapping formula; similarly, the fitting parameter vector can also include fitting parameters corresponding to the target pressurization value, and the target pressurization value is mapped based on a preset pressure parameter parsing rule; the fitting value of the detonation delay will also be mapped to a precise delay time in milliseconds.

[0044] As one implementation method, determining the matching degree between real-time operating condition features and historical operating condition features includes: performing multi-dimensional feature extraction on real-time and historical operating condition features respectively to obtain real-time feature vectors and historical feature vectors, wherein the multi-dimensional feature extraction covers feature encoding of geological conditions, environmental parameters, and equipment status; determining the weight coefficients corresponding to each dimension, wherein the weight coefficients are determined based on the historical correlation strength between each dimension and the blasting effect; calculating the weighted similarity between the real-time feature vector and the historical feature vector based on the weight coefficients to obtain a weighted similarity index; and determining the matching degree based on the weighted similarity index.

[0045] Specifically, this embodiment abandons the one-sided approach of relying solely on a single parameter (such as comparing only rock hardness or only ambient temperature) for matching. Instead, it constructs a comprehensive feature space encompassing three core dimensions: geology, environment, and equipment. The geological condition dimension includes, but is not limited to, rock Protodyakonov hardness coefficient, fracture development density, and stratum dip angle; the environmental parameter dimension includes ambient temperature, humidity, distance from the free face, and groundwater seepage flow; and the equipment status dimension includes fracturing device model, valve response time, and pipeline residual pressure. By normalizing and feature-encoding the raw data of these three dimensions, they are transformed into numerical vectors that can be processed by a computer. More importantly, the weight coefficients of each dimension are not fixed but dynamically determined based on the actual impact of changes in each dimension on the blasting effect (such as block size distribution and vibration peak value) in historical data. For example, in the historical data statistics of a hard rock mine, if it is found that the impact of changes in rock hardness on blast block size is significantly greater than the impact of changes in ambient temperature, then a higher weight coefficient is automatically assigned to the geological condition dimension when calculating the matching degree. Weighted similarity calculation can be implemented using various algorithms such as cosine similarity, Euclidean distance, or Mahalanobis distance. Its core idea is to quantify the degree of closeness between the current working condition and the historical benchmark in a multi-dimensional feature space.

[0046] Based on this, the criteria for determining the matching degree include: a matching degree greater than or equal to a preset threshold if the matching degree meets the preset conditions; and a matching degree less than the preset threshold if the matching degree does not meet the preset conditions. In this embodiment, the preset threshold can be flexibly adjusted according to engineering accuracy requirements. For example, a higher threshold can be set in safety-sensitive areas to ensure the reliability of reused parameters, while the threshold can be appropriately lowered in exploratory tunneling faces to increase the opportunity for experience reuse. This threshold can be a globally uniform constant or an adaptive variable dynamically set according to different working condition categories.

[0047] As one implementation method, generating blasting control commands based on target control parameters to control a gas blasting device to perform blasting operations includes: generating a timing control command containing multiple time nodes based on the target filling amount, target pressurization value, and target detonation delay included in the target control parameters; performing safety verification on the current equipment status parameters and current environmental safety parameters of the gas blasting device to obtain a safety verification result; in response to the safety verification result meeting preset safety conditions, issuing the timing control command to the gas blasting device; controlling the gas blasting device to sequentially execute filling, pressurization, and detonation actions at corresponding time nodes, and collecting action completion status information within the execution interval of adjacent actions; and triggering the execution of the next action after confirming that the execution conditions for the next action are met based on the action completion status information; wherein, the execution parameters of the filling action are determined by the target filling amount, the execution parameters of the pressurization action are determined by the target pressurization value, and the triggering time of the detonation action is determined by the target detonation delay.

[0048] Specifically, target control parameters are typically a static set of values, while blasting operations are a strictly time-series dynamic process. This embodiment first maps the target filling volume, target pressurization value, and target detonation delay into a sequence of time-series control commands with precise timestamps, such as "open the filling valve at time T0 until the flow rate reaches X kg," "start the booster pump at time T1 until the pressure reaches Y MPa," and "trigger the blasting execution unit at time T2." Before issuing commands, the system enforces dual safety checks: on the one hand, it checks equipment status parameters (such as whether the tank level is sufficient, whether the valves are in their initial reset state, and whether sensor communication is normal); on the other hand, it checks environmental safety parameters (such as whether there are any intrusion signals within the warning area, whether the gas concentration exceeds the standard, and whether the wind speed is within the allowable range). Only when both checks pass will the command be unlocked and issued, thus eliminating the risk of operating with defects or violating regulations from the outset.

[0049] During the execution phase, this embodiment employs a step-by-step status confirmation mechanism, reflecting the inherently safe design philosophy. The system does not issue all action commands at once, but strictly follows a closed-loop logic of "execution-feedback-confirmation-next step." For example, after the filling action is completed, the system collects flow meter readings or weight sensor data in real time as action completion status information. Only after confirming that the deviation between the actual filling volume and the target value is within the allowable range and the valve is closed is the subsequent pressurization action allowed. Similarly, only when the pressure sensor feedback value stably reaches the target pressurization value and the pressure holding test is passed is the detonation countdown allowed. If the status confirmation at any intermediate stage fails, the system will immediately pause and issue an alarm, rather than blindly executing subsequent high-risk actions. This mechanism effectively prevents action errors or accidental energy release caused by equipment failure, signal delay, or external interference, improving the safety and reliability of the intelligent decision-making and execution process. It should be understood that although this embodiment uses three typical actions—filling, pressurizing, and detonation—as examples for illustration, in actual applications, depending on the specific type of gas explosion equipment and the process flow, the timing control instructions may also include other auxiliary actions such as depressurization, cooling, and data acquisition. As long as the core logic of the above-mentioned safety verification and step confirmation is followed, they should all be considered within the scope of protection of this application.

[0050] The following describes a gas explosion control system provided by an embodiment of this application. The gas explosion control system described below can be referred to in conjunction with the gas explosion control method described above. Figure 2 , Figure 2 This is a schematic diagram of the structure of a gas explosion control system 20 provided in an embodiment of this application, including: The data acquisition module 21 is used to acquire historical operating condition characteristics, historical control parameters and historical effect feedback of the gas explosion scenario, and to acquire real-time operating condition characteristics of the gas explosion scenario. Parameter correction module 22 is used to correct historical control parameters based on historical effect feedback to obtain baseline control parameters; The matching judgment module 23 is used to determine the matching degree between real-time operating condition features and historical operating condition features; The first response module 24 is used to determine the target control parameters based on the benchmark control parameters corresponding to the historical operating condition characteristics that match the real-time operating condition characteristics in response to the matching degree meeting the preset conditions. The second response module 25 is used to respond to the fact that the matching degree does not meet the preset conditions, and based on the correlation between the changes in operating condition characteristics and the changes in control parameters, import the difference information between the real-time operating condition characteristics and the historical operating condition characteristics into the preset data model for deduction to obtain the target control parameters. The instruction control module 26 is used to generate blasting control instructions based on target control parameters to control the gas blasting equipment to perform blasting operations.

[0051] In one possible implementation of this application embodiment, when the parameter correction module 22 corrects the historical control parameters based on historical effect feedback to obtain the baseline control parameters, it is specifically used for: By comparing historical results with the expected blasting target, blasting deviations can be determined. Based on the blasting deviation, the historical control parameters are compensated and corrected to obtain the baseline control parameters.

[0052] Another possible implementation of this application embodiment is that the historical effect feedback includes at least one of the following: blasting block size distribution index, vibration velocity index, and scattering distance index; the historical control parameters include at least one of the following: filling quantity parameter, pressurization value parameter, and detonation delay parameter. When parameter correction module 22 compensates and corrects historical control parameters based on blasting deviation to obtain baseline control parameters, it is specifically used for: If the blasting block size distribution index deviates from the expected block size distribution in the expected blasting target, the filling quantity parameter shall be adjusted according to the first preset mapping rule; If the vibration velocity index or the scattering distance index deviates from the expected safety threshold in the expected blasting target, the detonation delay parameter and / or the filling amount parameter shall be adjusted according to the second preset mapping rule. Use the adjusted charge quantity parameters and / or detonation delay parameters as the baseline control parameters.

[0053] In another possible implementation of this application embodiment, when the second response module 25 responds to the fact that the matching degree does not meet the preset conditions, and imports the difference information between the real-time operating condition characteristics and the historical operating condition characteristics into the preset data model for deduction based on the correlation between the changes in operating condition characteristics and the changes in control parameters to obtain the target control parameters, it is specifically used for: Determine the correlation between changes in operating conditions and changes in control parameters; The difference information and the correlation are concatenated to obtain the model input features; The input features of the model are imported into a preset data model for extrapolation and fitting, and the target control parameters are output.

[0054] In another possible implementation of this application embodiment, when the second response module 25 performs feature concatenation between the difference information and the correlation relationship to obtain the model input features, it is specifically used for: The difference information is vectorized and encoded to obtain the difference feature vector; The relationships are represented in a structured manner to obtain the relationship weight matrix; The difference feature vectors and the correlation weight matrix are concatenated and dimensionality reduced to obtain the model input features; The model input features are imported into a preset data model for extrapolation and fitting, and the target control parameters are output, including: The model input features are forward-computed using a multilayer perceptron in a pre-defined data model, and the resulting fitted parameter vector is output. Based on the preset parameter parsing rules, the fitted parameter vector is mapped to physical control quantities to obtain the target control parameters, which include the target filling amount, the target pressurization value, and the target detonation delay.

[0055] In another possible implementation of this application embodiment, when determining the matching degree between real-time operating condition features and historical operating condition features, the matching judgment module 23 is specifically used for: Multi-dimensional feature extraction is performed on real-time operating condition features and historical operating condition features respectively to obtain real-time feature vectors and historical feature vectors. The multi-dimensional feature extraction covers feature encoding of geological conditions, environmental parameters and equipment status. Determine the weight coefficients for each dimension, where the weight coefficients are determined based on the historical correlation strength between each dimension and the explosion effect; Based on the weight coefficients, a weighted similarity calculation is performed between the real-time feature vector and the historical feature vector to obtain a weighted similarity index. The matching degree is determined based on a weighted similarity index; In response to the matching degree meeting preset conditions, including: the matching degree is greater than or equal to a preset threshold; In response to a mismatch condition, including a mismatch degree less than a preset threshold.

[0056] In another possible implementation of this application embodiment, when the instruction control module 26 generates blasting control instructions based on target control parameters to control the gas blasting equipment to perform blasting operations, it is specifically used for: Based on the target control parameters, including the target filling amount, target pressurization value, and target detonation delay, a timing control command containing multiple time nodes is generated. Perform safety verification on the current equipment status parameters and current environmental safety parameters of the gas explosion equipment, and obtain the safety verification results; In response to the safety verification result meeting the preset safety conditions, a timing control command is sent to the gas explosion equipment; The gas explosion control device sequentially executes the filling action, pressurization action, and detonation action at the corresponding time nodes, and collects the action completion status information during the execution interval of adjacent actions. After confirming that the execution conditions of the next action are met based on the action completion status information, the execution of the next action is triggered. Among them, the execution parameters of the filling action are determined by the target filling amount, the execution parameters of the pressurization action are determined by the target pressurization value, and the triggering time of the detonation action is determined by the target detonation delay.

[0057] This application provides an electronic device, such as... Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3 The illustrated electronic device 300 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 300 does not constitute a limitation on the embodiments of this application.

[0058] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in connection with the embodiments of this application. Processor 301 may also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0059] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0060] The memory 303 may be a ROM (Read-Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or it may be an EEPROM (Electrically Erasable Programmable Read-Only Memory), a CD-ROM (Compact Disc Read-Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0061] The memory 303 is used to store application code that executes the scheme of the embodiments of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0062] Among them, electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0063] The following describes a computer-readable storage medium provided by an embodiment of this application. The computer-readable storage medium described below can be referred to in correspondence with the method described above.

[0064] This application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the gas explosion control method described above.

[0065] Since the embodiments of the computer-readable storage medium portion correspond to the embodiments of the method portion, please refer to the description of the embodiments of the method portion for the embodiments of the computer-readable storage medium portion.

[0066] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0067] The above are only some embodiments of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for controlling gas explosion, characterized in that, include: Acquire historical operational characteristics, historical control parameters, and historical effect feedback of gas explosion scenarios; Based on the historical performance feedback, the historical control parameters are corrected to obtain the baseline control parameters; Obtain the real-time operating condition characteristics of the gas explosion scenario, and determine the matching degree between the real-time operating condition characteristics and the historical operating condition characteristics; In response to the matching degree meeting the preset conditions, the target control parameters are determined based on the benchmark control parameters corresponding to the historical operating condition features that match the real-time operating condition features. In response to the matching degree not meeting the preset condition, based on the correlation between the changes in operating condition characteristics and the changes in control parameters, the difference information between the real-time operating condition characteristics and the historical operating condition characteristics is imported into a preset data model for deduction to obtain the target control parameters. Based on the target control parameters, blasting control commands are generated to control the gas blasting equipment to perform blasting operations.

2. The gas explosion control method according to claim 1, characterized in that, The step of correcting the historical control parameters based on the historical performance feedback to obtain baseline control parameters includes: The historical results are compared with the expected blasting target to determine the blasting deviation; The historical control parameters are compensated and corrected based on the blasting deviation to obtain the baseline control parameters.

3. The gas explosion control method according to claim 2, characterized in that, The historical effect feedback includes at least one of the following: blasting block size distribution index, vibration velocity index, and scattering distance index; the historical control parameters include at least one of the following: filling quantity parameter, pressurization value parameter, and detonation delay parameter. The historical control parameters are compensated and corrected based on the blasting deviation to obtain the baseline control parameters, including: If the blasting block size distribution index deviates from the expected block size distribution in the expected blasting target, the filling quantity parameter is adjusted according to the first preset mapping rule; If the vibration velocity index or the scattering distance index deviates from the expected safety threshold in the expected blasting target, the detonation delay parameter and / or the filling amount parameter shall be adjusted according to the second preset mapping rule. The adjusted filling quantity parameter and / or the detonation delay parameter shall be used as the baseline control parameter.

4. The gas explosion control method according to claim 1, characterized in that, In response to the mismatch condition, based on the correlation between changes in operating condition characteristics and changes in control parameters, the difference information between the real-time operating condition characteristics and the historical operating condition characteristics is imported into a preset data model for deduction to obtain the target control parameters, including: Determine the correlation between changes in operating conditions and changes in control parameters; The difference information and the correlation relationship are concatenated to obtain the model input features; The input features of the model are imported into a preset data model for extrapolation and fitting, and the target control parameters are output.

5. The gas explosion control method according to claim 4, characterized in that, The step of concatenating the difference information with the association relationship to obtain the model input features includes: The difference information is vectorized and encoded to obtain the difference feature vector; The relationships are represented in a structured manner to obtain the association weight matrix; The difference feature vector and the correlation weight matrix are concatenated and dimensionality reduced to obtain the model input features; The model input features are imported into a preset data model for extrapolation and fitting, and the target control parameters are output, including: The model input features are forward-computed using a multilayer perceptron in a pre-defined data model, and the resulting fitted parameter vector is output. Based on the preset parameter parsing rules, the fitted parameter vector is mapped to physical control quantities to obtain the target control parameters, which include the target filling amount, the target pressurization value, and the target detonation delay.

6. The gas explosion control method according to claim 1, characterized in that, Determining the matching degree between the real-time operating condition features and the historical operating condition features includes: Multi-dimensional feature extraction is performed on the real-time operating condition features and the historical operating condition features respectively to obtain real-time feature vectors and historical feature vectors. The multi-dimensional feature extraction covers feature encoding of geological conditions, environmental parameters and equipment status. Determine the weight coefficients corresponding to each dimension, wherein the weight coefficients are determined based on the historical correlation strength between each dimension and the explosion effect; Based on the weighting coefficients, a weighted similarity calculation is performed between the real-time feature vector and the historical feature vector to obtain a weighted similarity index. The matching degree is determined based on the weighted similarity index; In response to the matching degree satisfying a preset condition, including: the matching degree being greater than or equal to a preset threshold; In response to the matching degree not meeting the preset condition, including: the matching degree being less than the preset threshold.

7. The gas explosion control method according to claim 6, characterized in that, The step of generating blasting control commands based on the target control parameters to control the gas blasting equipment to perform blasting operations includes: Based on the target control parameters, including the target filling amount, target pressurization value, and target detonation delay, a timing control command containing multiple time nodes is generated. The current equipment status parameters and current environmental safety parameters of the gas explosion device are verified to obtain the safety verification results. In response to the safety verification result meeting the preset safety conditions, the timing control command is sent to the gas explosion device; The gas blasting device is controlled to sequentially perform filling, pressurizing and detonation actions at the corresponding time nodes, and action completion status information is collected during the execution interval of adjacent actions. After confirming that the execution conditions of the next action are met based on the action completion status information, the execution of the next action is triggered. The execution parameters of the filling action are determined by the target filling amount, the execution parameters of the pressurization action are determined by the target pressurization value, and the triggering time of the detonation action is determined by the target detonation delay.

8. A gas explosion control system, characterized in that, include: The data acquisition module is used to acquire historical operating condition characteristics, historical control parameters, and historical effect feedback of the gas explosion scenario, and to acquire the real-time operating condition characteristics of the gas explosion scenario. The parameter correction module is used to correct the historical control parameters based on the historical effect feedback to obtain the baseline control parameters; The matching and judgment module is used to determine the degree of matching between the real-time operating condition features and the historical operating condition features; The first response module is used to determine the target control parameters based on the benchmark control parameters corresponding to the historical operating condition features that match the real-time operating condition features in response to the matching degree meeting the preset conditions. The second response module is used to respond to the fact that the matching degree does not meet the preset condition, and based on the correlation between the changes in operating condition characteristics and the changes in control parameters, import the difference information between the real-time operating condition characteristics and the historical operating condition characteristics into the preset data model for deduction to obtain the target control parameters. The command control module is used to generate blasting control commands based on the target control parameters in order to control the gas blasting equipment to perform blasting operations.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: perform a gas explosion control method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, include: The computer program is stored and can be loaded by a processor and executed as described in any one of claims 1-7.