Deep mine disaster big data analysis and prevention and control decision system

Abstract

The present application relates to the technical field of mine disaster monitoring and prevention, in particular to a deep mine disaster big data analysis and prevention and control decision system. The system comprises a data pollution quantification unit for collecting multi-source heterogeneous data streams and benchmark prediction data, performing noise pollution quantification analysis, and obtaining a data pollution index; a resilience entropy evaluation unit for collecting physical risk factors, calculating a basic safety entropy, correcting the basic safety entropy according to the data pollution index, obtaining a mine system resilience entropy, and performing discrimination processing on the mine system resilience entropy to obtain a risk level; a counter-fragile decision unit for dynamically adjusting a risk aversion coefficient according to the risk level, and performing utility function calculation on a preset selected decision to obtain an optimal decision; and a closed-loop scheduling control unit for matching a preset scheduling instruction set according to the optimal decision and the risk level, generating and executing hierarchical control instructions. The present application solves the problem of invalidation of traditional risk assessment models caused by serious pollution of deep mine monitoring data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mine disaster monitoring and prevention, in particular to a deep mine disaster big data analysis and prevention and control decision system. BACKGROUND

[0002] The existing data processing scheme generally adopts a batch processing architecture to realize periodic scanning, decompression and warehousing of data through task scheduling, and completes index calculation in the database; this architecture is highly dependent on disk I / O and contains multiple intermediate data storage, with a long process; at the same time, manual adaptation processing is required for heterogeneous file formats, resulting in high response delay and large repeated calculation amount of the system;

[0003] This mode can still be applied in offline statistical scenarios, but its inherent defects make it difficult to support high-frequency index update requirements and rapid fault positioning; therefore, improving the timeliness and accuracy of real-time data analysis and output is a key technical problem to be solved at present.

[0004] The above information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0005] To solve the above technical problems, the present application discloses a deep mine disaster big data analysis and prevention and control decision system, in particular, the technical scheme of the present application comprises:

[0006] The data pollution quantization unit is used to collect multi-source heterogeneous data streams and benchmark prediction data, perform noise pollution quantization analysis, and obtain a data pollution index;

[0007] The resilience entropy evaluation unit is used to collect physical risk factors, solve the basic safety entropy, and correct the basic safety entropy according to the data pollution index to obtain the mine system resilience entropy, and perform discrimination processing on the mine system resilience entropy to obtain the risk level;

[0008] The anti-fragile decision unit is used to dynamically adjust the risk aversion coefficient according to the risk level, and perform utility function calculation on the preset selected decision to obtain the optimal decision;

[0009] The closed-loop scheduling control unit is used to match the preset scheduling instruction set according to the optimal decision and the risk level, generate and execute the hierarchical control instruction.

[0010] Preferably, the noise pollution quantization analysis of the data pollution quantization unit comprises the following steps:

[0011] Obtaining real-time observation values of each sensor;

[0012] Obtain the theoretical readings output by the benchmark prediction model trained on historical data;

[0013] The relative deviation between real-time observations and theoretical readings is calculated to obtain the relative deviation of various types of data.

[0014] The relative deviations of various types of data are weighted and summed according to the preset normalization weights to obtain the data pollution index.

[0015] Preferably, the resilience entropy assessment unit calculates the basic safety entropy using the following steps:

[0016] Obtain factor observations of key physical risk factors;

[0017] Obtain the preset factor safety baseline value corresponding to the factor observation value;

[0018] Obtain the preset critical hazard value of the factor corresponding to the factor observation value;

[0019] By combining the observed values ​​of the factors with the safety baseline values ​​of the factors, and by combining the critical hazard values ​​of the factors, normalization is performed to calculate the risk level of each factor.

[0020] The risk levels of each factor are weighted and summed according to the preset factor weights to obtain the basic safety entropy.

[0021] Preferably, the resilience entropy assessment unit corrects the basic safety entropy by including the following steps:

[0022] Based on the preset pollution sensitivity coefficient and preset pollution impact index, and combined with the data pollution index, a nonlinear correction factor is constructed.

[0023] Multiplying the basic safety entropy by the nonlinear correction factor yields the mine system resilience entropy.

[0024] Preferably, the resilience entropy assessment unit performs the following steps to discriminate the resilience entropy of the mine system:

[0025] The mine system resilience entropy is compared with the preset first-level early warning threshold;

[0026] The mine system resilience entropy is compared with the preset secondary hazard threshold.

[0027] When the mine system resilience entropy is less than the first-level early warning threshold, the risk level is determined to be the normal state;

[0028] When the mine system's resilience entropy is greater than or equal to the Level 1 warning threshold and less than the Level 2 danger threshold, the risk level is determined to be Level 1 warning.

[0029] When the resilience entropy of the mine system is greater than or equal to the level 2 hazard threshold, the risk level is determined to be level 2 warning.

[0030] Preferably, the utility function calculation for the antifragile decision unit includes the following steps:

[0031] To obtain the expected economic benefits of the pre-set alternative decisions;

[0032] Calculate the system collapse probability based on the resilience entropy of the mine system;

[0033] The decision utility of the candidate decision is obtained by subtracting the product of the risk aversion coefficient and the system collapse probability from the expected economic benefits.

[0034] The candidate decision that maximizes the decision utility is identified as the optimal decision.

[0035] Preferably, the dynamic adjustment of the risk aversion coefficient by the antifragile decision-making unit includes the following steps:

[0036] When the risk level is normal, the risk aversion coefficient is set to a preset low coefficient value;

[0037] When the risk level is at Level 1 warning, the risk aversion coefficient will be switched to a preset high coefficient value;

[0038] When the risk level is at Level 2 warning, the risk aversion coefficient will be switched to a preset critical coefficient value; where the critical coefficient value is greater than the high-level coefficient value.

[0039] Among them, the high coefficient value ensures that the product of the risk aversion coefficient and the system collapse probability is greater than the expected economic benefits.

[0040] Preferably, the closed-loop scheduling control unit matching the preset scheduling instruction set includes the following steps:

[0041] The preset scheduling instruction set includes production optimal mode instructions, first-level safety mode instructions, and second-level safety mode instructions;

[0042] When the optimal decision is the production optimal solution and the risk level is normal, the hierarchical control instruction will be determined as the production optimal mode instruction.

[0043] When the optimal decision is a safe solution and the risk level is a Level 1 warning, the hierarchical control command will be switched to the Level 1 safety mode command.

[0044] When the optimal decision is a safe solution and the risk level is a level 2 warning, the hierarchical control command will be switched to the level 2 safety mode command.

[0045] Preferably, the closed-loop scheduling control unit is also used for:

[0046] After executing the Level 1 or Level 2 safety mode command, continuously monitor the mine system resilience entropy;

[0047] When the mine system resilience entropy falls below the first-level early warning threshold, the antifragile decision-making unit will restore the risk aversion coefficient to a low value.

[0048] The hierarchical control command switches back to the optimal production mode.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] 1. This invention solves the problem of traditional risk assessment models failing due to severe contamination of monitoring data in deep mines. The system utilizes a unique data contamination quantification unit to calculate and weight the relative deviations between observed and theoretical readings in real time, obtaining a precise data contamination index. This overcomes the shortcomings of existing technologies that blindly rely on data, achieving real-time quantitative perception of the overall contamination level of the data stream, and providing a solid, quantifiable data quality foundation for subsequent reliable risk assessment and decision-making.

[0051] 2. This invention penetrates the fog of dirty data, enabling a reliable assessment of mine risks. The resilience entropy assessment unit in the system not only calculates the basic safety entropy based on physical risk factors, but also innovatively constructs a nonlinear correction factor based on the data contamination index to correct the basic safety entropy. This corrected resilience entropy couples physical risk with data uncertainty risk, and can be significantly amplified even when physical indicators are distorted due to data contamination, thus providing a conservative and reliable estimate of the true risk.

[0052] 3. This invention achieves antifragile decision-making under uncertain environments. Based on the assessed risk level, the system dynamically adjusts the risk aversion coefficient in the antifragile decision-making unit. When the risk increases, the system automatically switches to a higher coefficient value, ensuring that the risk penalty term dominates the utility function calculation, thus shifting the optimal decision from producing the optimal solution to a safe solution. This design prioritizes avoiding worst-case scenarios such as system collapse, achieving the antifragile goal at the decision-making level.

[0053] 4. This invention constructs a complete dynamic resilience closed loop, from risk perception to on-site control and then to state recovery. The closed-loop scheduling and control unit matches optimal decisions with risk levels and executes hierarchical control commands. After the execution of safety commands, the system continuously monitors resilience entropy. When it falls below the safety threshold, it automatically switches the decision mode and control commands back to the optimal production state, achieving a dynamic balance between safety and efficiency on a time scale, ensuring that the system can recover to high-efficiency production after the risk is eliminated. Attached Figure Description

[0054] The present invention will be further explained below with reference to the accompanying drawings and embodiments:

[0055] Figure 1 This is a system structure diagram of the present invention. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0057] Example 1:

[0058] Please see Figure 1 The deep mine disaster big data analysis and prevention decision-making system includes:

[0059] The data pollution quantification unit is used to collect multi-source heterogeneous data streams and baseline prediction data, perform noise pollution quantification analysis, and obtain the data pollution index.

[0060] The resilience entropy assessment unit is used to collect physical risk factors, calculate the basic safety entropy, and correct the basic safety entropy according to the data pollution index to obtain the mine system resilience entropy. The mine system resilience entropy is then processed to obtain the risk level.

[0061] The antifragile decision-making unit is used to dynamically adjust the risk aversion coefficient based on the risk level and to perform utility function calculation on the preset alternative decisions to obtain the optimal decision;

[0062] The closed-loop scheduling control unit is used to generate and execute hierarchical control instructions by matching a preset set of scheduling instructions based on the optimal decision and risk level.

[0063] This embodiment provides a big data analysis and prevention and control decision system for disasters in deep mines. The system includes a data pollution quantification unit, a resilience entropy assessment unit, an anti-fragile decision unit, and a closed-loop scheduling and control unit.

[0064] Data contamination quantification unit:

[0065] The purpose of this unit is to quantify the overall reliability of the data stream collected by the monitoring system in real time, i.e. the degree of contamination. Under high noise, such as micro-vibration noise interference, sensor data may be distorted. This unit constructs a dimensionless index by comparing the deviation between real-time observations and baseline predictions.

[0066] In this embodiment, the data pollution quantification unit is used to collect multi-source heterogeneous data streams, such as real-time readings and baseline prediction data from sensors for microseismic, ground stress, and gas detection, as well as theoretical readings output by time series models trained based on historical data. By calculating the weighted relative deviation between the two, noise pollution quantification analysis is performed, ultimately yielding a comprehensive data pollution index. ; The higher the value, the less reliable the current data stream is;

[0067] Resilience Entropy Assessment Unit:

[0068] The purpose of this unit is to assess the true safety distance of a mining system. Its core innovation lies in the fact that it not only assesses known physical risks, but also the uncertainty risks caused by data contamination.

[0069] In this embodiment, the toughness entropy assessment unit is used to collect observations of physical risk factors, such as ground stress and microseismic energy. First, through normalization and weighted summation, the basic safety entropy reflecting the degree of danger of the physical indicators is calculated. This unit uses the data pollution index input from the data pollution quantification unit. Basic security entropy After applying nonlinear corrections, the final mine system resilience entropy is obtained. ; This unit integrates physical risks and data contamination risks; finally, it assesses the resilience entropy of the mine system. With preset two-level thresholds ( The system performs discrimination processing and outputs discrete risk levels, such as: normal state, level 1 warning, and level 2 warning.

[0070] Antifragile decision-making unit:

[0071] The purpose of this unit is to resolve the conflict between mine safety and profitability and to achieve antifragile decision-making, that is, when the risk increases, the decision-making system can proactively bias towards avoiding the worst situation rather than pursuing the maximum benefit;

[0072] In this embodiment, the antifragile decision-making unit is used to dynamically adjust the risk aversion coefficient in the decision-making model based on the risk level output by the resilience entropy assessment unit. When the risk level is normal, The risk level is relatively low, and decision-making is biased towards efficiency; when the risk level is at the warning level, Switch to the maximum value; simultaneously, the unit makes preset decisions on candidate solutions, such as producing the optimal solution. and security solution Perform utility function The solution shows that this function incorporates expected economic benefits. Japanese Classics probability of collapse after punishment Ultimately, the unit output makes Maximizing the optimal decision ;

[0073] Closed-loop scheduling control unit:

[0074] The purpose of this unit is to transform the optimal decision output by the upstream decision-making unit into specific operational instructions at the mine site and to achieve closed-loop control.

[0075] In this embodiment, the closed-loop scheduling control unit is used to make the optimal decision based on the output of the antifragile decision unit. The risk level output by the resilience entropy assessment unit, within a preset set of scheduling instructions, such as... The corresponding intelligent tunneling mode, The corresponding speed reduction mode, Match the corresponding shutdown mode to generate and execute specific hierarchical control instructions;

[0076] This embodiment, through the collaborative work of the four units mentioned above, constructs a complete technical closed loop, from data quality perception to comprehensive risk assessment, and then to antifragile decision-making and closed-loop control execution. It solves the significant hidden danger of decision-making errors in deep mines due to blindly trusting dirty data under high noise interference. This system can penetrate the data fog and quantify the real system risks brought about by data uncertainty, namely resilience entropy. Based on this risk, it automatically switches its decision-making logic between benefits and safety, i.e., it dynamically adjusts... This ensures that when facing conflict, the mining system always prioritizes maintaining long-term survival resilience.

[0077] Example 2:

[0078] The data pollution quantification unit performs noise pollution quantification analysis, which includes the following steps:

[0079] Acquire real-time observations from each sensor;

[0080] Obtain the theoretical readings output by the benchmark prediction model trained on historical data;

[0081] The relative deviation between real-time observations and theoretical readings is calculated to obtain the relative deviation of various types of data.

[0082] The relative deviations of various types of data are weighted and summed according to the preset normalization weights to obtain the data pollution index;

[0083] This embodiment, based on Embodiment 1, refines the specific steps for noise pollution quantification analysis of the data pollution quantification unit. The motivation for this analysis is to define a weighted relative deviation model to quantify the overall distortion of multi-source heterogeneous data with different physical dimensions under noise interference. ;

[0084] The specific steps include:

[0085] Acquire real-time observations from each sensor. :

[0086] Real-time observations, whose dimensions depend on the first... Sensors such as It could be a geostress value, measured in MPa; this value is collected in real time by a deployed distributed sensor network.

[0087] Obtain the theoretical readings output by the benchmark prediction model trained on historical data. :

[0088] The baseline prediction value, i.e., the theoretical reading, has the same dimensions as... The same; this value is output by a pre-trained baseline prediction model, such as a time-series model trained on historical data or a mechanistic model based on geomechanical parameters, to predict the sensor's position at the next moment. Theoretical readings;

[0089] For real-time observations Compared with theoretical readings Perform relative deviation calculations to obtain the relative deviations of various data types. ;

[0090] Based on the preset normalized weights Relative deviation of various types of data The data pollution index is obtained by performing a weighted summation process. ;

[0091] Steps 3 and 4 above are mathematically combined into a single formula, namely the data contamination index. Computational model:

[0092]

[0093] in, Data pollution index, dimensionless; its value is calculated by this unit and transmitted to the resilience entropy assessment unit as a key input for correcting the risk assessment results. The higher the value, the less reliable the data.

[0094] : Total number of sensors, an integer, referring to the total number of sensors included in the quantitative evaluation in the system;

[0095] Sensor number, an integer;

[0096] : No. Normalized weights for class-based data, dimensionless, and The method for determining this parameter is based on the importance of different data types to disaster prediction, such as microseismic data and geostress data. It should be higher than production data; its value can be determined through regression analysis of historical disaster data or by domain experts.

[0097] : No. The relative deviation of the data is dimensionless.

[0098] : Real-time observations, as defined in step 1;

[0099] The baseline prediction value has been defined in step 2;

[0100] : No. Data smoothing coefficient, dimensions and Same; the method for determining this parameter is: according to The typical order of magnitude is set to a very small positive number, such as The average value is 10 MPa, then Can be set to MPa is used to ensure calculation stability and prevent the denominator from being zero.

[0101] This embodiment constructs a dimensionless data pollution index through the above steps. This index enables real-time self-awareness of input data quality through weighted analysis. This reflects the heterogeneous importance of different data, through the smoothing coefficient. This ensures the robustness of the algorithm; it solves the problem of blindly trusting dirty data under high noise interference, paving the way for subsequent risk quantification and resilience entropy. It provides key, quantified inputs on uncertainty;

[0102] In addition, to ensure the long-term validity of the baseline forecast, the baseline forecast model needs to be periodically retrained using verified clean historical data to adapt to the dynamic changes in mine geological conditions and mining activities, and to prevent systematic bias in the data contamination index caused by model drift.

[0103] Example 3:

[0104] The resilience entropy assessment unit calculates the basic safety entropy through the following steps:

[0105] Obtain factor observations of key physical risk factors;

[0106] Obtain the preset factor safety baseline value corresponding to the factor observation value;

[0107] Obtain the preset critical hazard value of the factor corresponding to the factor observation value;

[0108] By combining the observed values ​​of the factors with the safety baseline values ​​of the factors, and by combining the critical hazard values ​​of the factors, normalization is performed to calculate the risk level of each factor.

[0109] The risk levels of each factor are weighted and summed according to the preset factor weights to obtain the basic safety entropy;

[0110] This embodiment, based on Embodiment 1, calculates the basic safety entropy for the resilience entropy assessment unit. The specific steps have been refined; the purpose of this calculation is to integrate different physical monitoring data, such as geostress. Micro-vibration energy gas concentration The units of measurement should be unified to construct a standardized basic risk indicator;

[0111] The specific steps include:

[0112] Obtain factor observations of key physical risk factors :

[0113] Factor observation, referring to the first factor observation. Specific observed values ​​of key physical risk factors, such as The units are not uniform, and data is collected in real time by sensors;

[0114] Obtain factor observations Corresponding preset factor safety benchmark value :

[0115] Factor safety benchmark value, dimensions and Same, such as corresponding ;

[0116] Obtain factor observations Corresponding preset factor critical risk value :

[0117] : Critical hazard value of factor, dimensions and Same, such as corresponding ;

[0118] and These are all preset thresholds, determined based on geological conditions and safety regulations, and must meet certain conditions. ;

[0119] Combining factor observations With factor safety benchmark value And combined with the critical risk value of the factor After normalization, the risk level of each factor is calculated. ;

[0120] The calculation model for this normalization process is as follows:

[0121]

[0122] The parameters in the formula are explained as follows:

[0123] : No. Individual factor risk levels, dimensionless; through... Cut off to ensure it is non-negative; when hour, ;when hour, ;when hour, This indicates that the critical danger value has been exceeded;

[0124] In this embodiment, a linear normalization model is used to simplify calculations; in other embodiments, if a specific physical risk factor has a clear nonlinear relationship with disaster risk, such as an exponential relationship, a different model can be used. The nonlinear model is normalized, where It is a nonlinear coefficient to accurately characterize the accelerated accumulation effect of risk;

[0125] Based on preset factor weights Risk level of each factor The basic security entropy is obtained by performing a weighted summation. ;

[0126] The computational model for this weighted summation process is as follows:

[0127]

[0128] The parameters in the formula are explained as follows:

[0129] Basic safety entropy, dimensionless; its value is used to calculate the resilience entropy of the mine system. Basic input;

[0130] Total number of key physical risk factors;

[0131] : No. Each factor has a weight, which is dimensionless, and The method for determining this parameter is as follows: it is determined through regression analysis of historical disaster data or expert calibration, reflecting different factors. Contribution to total risk;

[0132] Risk level, dimensionless, calculated from the previous step;

[0133] This embodiment, through the above steps, assesses the risk level. The calculation involves all physical factors with different dimensions. A unified conversion to a dimensionless risk measure solves the problem of difficulty in comparing heterogeneous data; through factor weights The weighted summation constructs the basic security entropy. This enabled a comprehensive assessment of the system's physical risks, paving the way for the subsequent introduction of a data pollution index. Risk correction provides a standardized, comparable benchmark. ).

[0134] Example 4:

[0135] The resilience entropy assessment unit corrects the basic safety entropy through the following steps:

[0136] Based on the preset pollution sensitivity coefficient and preset pollution impact index, and combined with the data pollution index, a nonlinear correction factor is constructed.

[0137] Multiplying the basic safety entropy by the nonlinear correction factor yields the mine system resilience entropy;

[0138] This embodiment, based on embodiment 3, adds a resilience entropy assessment unit to address the challenges posed by high-noise data environments, i.e., data contamination index. The problem of accurately estimating system risk at higher levels requires further analysis of the basic security entropy. Make corrections;

[0139] The motivation for this correction is: basic security entropy. It is based on dirty data, that is The calculation shows that when data pollution is severe, i.e. High time, It may appear normal, but the system is actually facing significant risks due to data distortion; therefore, it is necessary to introduce... right Make corrections to achieve penetrating perception of the system's true safe distance;

[0140] The specific steps include:

[0141] Based on the preset pollution sensitivity coefficient Compared with the preset pollution impact index And combined with the data pollution index Construct a nonlinear correction factor;

[0142] In this embodiment, the mathematical form of the nonlinear correction factor is: ;

[0143] Basic security entropy Multiplying by the nonlinear correction factor yields the toughness entropy of the mine system. ;

[0144] The revised calculation model is as follows:

[0145]

[0146] in, : Resilience entropy of a mining system, dimensionless and They have the same dimensions; their value is the final measure of the system's true risk and is used for subsequent risk level determination.

[0147] Basic security entropy, dimensionless;

[0148] Data pollution index, dimensionless; calculated and input in real time by the data pollution quantification unit;

[0149] Pollution sensitivity coefficient, dimensionless. This parameter is used to adjust the system's sensitivity to data corruption.

[0150] Pollution impact index, dimensionless, usually set as This parameter is used to reflect the amplifying effect of data contamination on risk; for example, it can be set to... To reflect exponential amplification;

[0151] and The determination method is based on a calibration dataset containing historical disaster events. Perform optimization fitting; this dataset Each record contains a set of historical monitoring data that has been used to calculate the historical baseline security entropy. Historical data pollution index And a true label representing whether a disaster has occurred. For example, 1 indicates occurrence, and 0 indicates non-occurrence; calibration and The process is to find a set of The value, which makes the calculation based on these historical data In prediction The early warning performance, such as the area under the receiver operating characteristic curve (AUC), reaches its optimal level.

[0152] When the data quality is good ( When ), nonlinear correction factor ,at this time System risk is determined by physical indicators; when data pollution is severe... When increased, the nonlinear correction factor ,at this time It will be nonlinearly amplified, that is, when Even at that time The distortion is caused by dirty data. It will also increase rapidly;

[0153] This embodiment introduces... right After performing nonlinear correction, we obtained Physical risks ( ) and the uncertainty risks brought about by data pollution This innovative approach couples the data within the same evaluation model, addressing the critical flaw of traditional security entropy models that fail in high-noise environments due to their reliance on dirty data. This enables a more accurate assessment of the system's true risk. The conservative estimate greatly enhances the penetration and reliability of risk warnings.

[0154] Example 5:

[0155] The resilience entropy assessment unit performs the following steps to determine the resilience entropy of the mine system:

[0156] The mine system resilience entropy is compared with the preset first-level early warning threshold;

[0157] The mine system resilience entropy is compared with the preset secondary hazard threshold.

[0158] When the mine system resilience entropy is less than the first-level early warning threshold, the risk level is determined to be the normal state;

[0159] When the mine system's resilience entropy is greater than or equal to the Level 1 warning threshold and less than the Level 2 danger threshold, the risk level is determined to be Level 1 warning.

[0160] When the toughness entropy of the mine system is greater than or equal to the level 2 hazard threshold, the risk level is determined to be level 2 warning.

[0161] This embodiment, based on embodiment 4, involves a toughness entropy assessment unit obtaining the toughness entropy of the mine system. Then, in order to convert it into a discrete signal that can be used by the decision-making unit, further processing is performed. Perform discrimination processing to determine the risk level;

[0162] The system needs to preset two levels of hazard thresholds, whose dimensions are similar to... Same, dimensionless:

[0163] Level 1 warning threshold; when This indicates a decrease in system resilience and an increase in data uncertainty;

[0164] Level 2 hazard threshold; when When this occurs, it indicates that the system is approaching a dangerous boundary; and the following conditions must be met. ;

[0165] The method for determining these two thresholds is as follows: by analyzing historical instability data, a threshold is determined. Value, when When this value is exceeded, historical decision-making accuracy declines or disaster risk increases significantly, which is used as a basis for... and The calibration basis;

[0166] The specific discrimination steps include:

[0167] The resilience entropy of the mining system Compared with the preset first-level warning threshold Perform a comparison;

[0168] The toughness entropy of the mining system Compared with the preset level 2 hazard threshold Perform a comparison;

[0169] when At that time, the risk level will be determined as a normal state;

[0170] when At that time, the risk level was determined to be a Level 1 warning;

[0171] when At that time, the risk level was determined to be a Level II warning.

[0172] This embodiment sets two threshold levels. and and will be continuous The value mapping represents three discrete risk levels: normal state, Level 1 warning, and Level 2 warning. This provides clear and explicit trigger signals for subsequent antifragile decision-making units, enabling the decision-making logic, i.e., the risk aversion coefficient, to be more effective. The switching can be based on these defined levels, which greatly simplifies the complexity of the decision-making model and enhances the operability of the system.

[0173] Example 6:

[0174] The utility function calculation for an antifragile decision-making unit includes the following steps:

[0175] To obtain the expected economic benefits of the pre-set alternative decisions;

[0176] Calculate the system collapse probability based on the resilience entropy of the mine system;

[0177] The decision utility of the candidate decision is obtained by subtracting the product of the risk aversion coefficient and the system collapse probability from the expected economic benefits.

[0178] Identify the candidate decision that maximizes the decision utility as the optimal decision;

[0179] Based on Example 1, this embodiment, in order to resolve the conflict between mine safety and profitability, constructs and calculates a utility function based on risk decision theory to determine the optimal decision. ;

[0180] The utility function The motivation is to provide a mathematical framework for systems to make choices between short-term benefits and long-term survival; traditional decision-making pursues... This system pursues Its core idea is that when the probability of collapse... When increasing, through the risk aversion coefficient On utility Imposing severe punishments;

[0181] The specific solution steps include:

[0182] Obtain preset candidate decisions Expected economic benefits :

[0183] : Decision-making options, such as producing the optimal solution Or secure solution ;

[0184] :decision making The expected economic benefits, in units of yuan; through a certain decision ,like The expected output is obtained by subtracting production costs from the estimated output; specifically, the decision... The expected economic benefits can be expressed as ,in The market price per unit of product. In decision-making The expected output is below This corresponds to the total production cost; for example, the optimal production solution. Corresponding to higher expected output And a safe solution For example, a slowdown mode corresponds to a lower expected output. ;

[0185] Solving for the resilience entropy of the mine system System crash probability :

[0186] System crash probability, dimensionless; a concept... an increasing function, Calculated by the resilience entropy assessment unit; for example, the function can be set as follows: The fitting coefficients Also based on the calibration dataset in Embodiment 4. The determination method is as follows: using statistical methods such as maximum likelihood estimation to find... Values ​​that make the function Best fit and The probability relationship between them;

[0187] Expected economic benefits Subtract risk aversion coefficient With system crash probability The product of these factors yields the alternative decision. Decision utility ;

[0188] The calculation model for this decision utility function is as follows:

[0189]

[0190] in, :decision making The utility, dimensions and Consistent, such as yuan;

[0191] Risk aversion coefficient, dimensions and Consistent, such as element; this parameter is The function, the value of which is dynamically adjusted by this unit according to the risk level;

[0192] and As defined in steps 1 and 2;

[0193] Determine decision utility The corresponding decision when the maximum value is reached As the optimal decision ;

[0194] Right now In other words, the decision engine will consider all potential decisions, such as... and Calculate their decision utility separately and And select the decision with the highest decision utility value as Output;

[0195] This embodiment constructs a utility function. Economic benefits and risk losses, by Quantification unifies comparisons within the same mathematical framework; it provides a calculable basis for systems to make rational choices between maximizing profits and minimizing the probability of collapse, transforming antifragile decision-making from a concept into an executable algorithm.

[0196] Example 7:

[0197] The dynamic adjustment of the risk aversion coefficient by the antifragile decision-making unit includes the following steps:

[0198] When the risk level is normal, the risk aversion coefficient is set to a preset low coefficient value;

[0199] When the risk level is at Level 1 warning, the risk aversion coefficient will be switched to a preset high coefficient value;

[0200] When the risk level is at Level 2 warning, the risk aversion coefficient will be switched to a preset critical coefficient value; where the critical coefficient value is greater than the high-level coefficient value.

[0201] Among them, the high coefficient value ensures that the product of the risk aversion coefficient and the system collapse probability is greater than the expected economic benefits;

[0202] Based on Example 6, the core step of the antifragile decision-making unit in implementing antifragile decision-making in this embodiment lies in dynamically adjusting the risk aversion coefficient according to the risk level. ;

[0203] It is not a fixed value, but... Or a piecewise function corresponding to its risk level; the system presets three coefficient values:

[0204] : Low-order coefficient values, with the dimension of yuan; for example, Yuan; this is a relatively small value, allowing the system's decisions in normal states to be primarily made by... leading;

[0205] : High-order coefficient values, with the dimension of yuan; for example, Yuan;

[0206] : Critical coefficient value, dimensionless; for example, Yuan;

[0207] in, ; and The method for determining this value must satisfy a key logic: its value must ensure that the expected loss of the risk penalty term is far greater than any other value. Potential short-term gains, such as about Yuan;

[0208] The specific adjustment steps are as follows:

[0209] When the risk level is at a normal state, the resilience entropy assessment unit determines... Risk aversion coefficient Set to the preset low-order coefficient value ;at this time ;because Very small The item is also relatively small. Decision-making will lean towards choice. The largest Produce the optimal solution;

[0210] When the risk level is Level 1 warning, that is Risk aversion coefficient Switch to preset high-order coefficient value At this point, the utility function is ;because Extremely high risk penalty item Item in The system plays an absolutely dominant role, ensuring the switch from the optimal decision to a safe solution;

[0211] When the risk level is a Level II warning, that is Risk aversion coefficient Switch to preset critical coefficient value Under this warning state, the utility function is: ;because great, Item in China holds an absolute dominant position, making It becomes a huge negative value; at this point, anything that could lead to... ,and then Slight increase ,That The city is much smaller of Safe solution Aiming to reduce Thus reducing ;

[0212] Among them, the high-order coefficient value and critical coefficient value The value of should satisfy a key constraint: ensure that under the warning state, for any candidate decision with the goal of production efficiency, its risk penalty term is greater than its expected economic benefit, so that the final utility of the decision is always negative or lower than the utility of the safe decision, thereby forcing the system to choose the safe solution as the optimal decision;

[0213] This embodiment uses the risk aversion coefficient By setting it to a non-linear piecewise function with respect to risk level, a sudden change in the decision-making logic is achieved; when the system detects risk ( Approaching the threshold At that time, the system can automatically and instantly switch from a profit-seeking model ( Switch to crash avoidance mode. When the risk further deteriorates to the level two warning threshold, When this happens, it switches to the more severe extreme avoidance mode (which has a stronger penalty). This progressive, non-linear switching forces the utility function... optimal solution Automatically from high-risk Turning to Conservatism This enables antifragile decision-making.

[0214] Example 8:

[0215] The closed-loop scheduling control unit matches the preset scheduling instruction set, including the following steps:

[0216] The preset scheduling instruction set includes production optimal mode instructions, first-level safety mode instructions, and second-level safety mode instructions;

[0217] When the optimal decision is the production optimal solution and the risk level is normal, the hierarchical control instruction will be determined as the production optimal mode instruction.

[0218] When the optimal decision is a safe solution and the risk level is a Level 1 warning, the hierarchical control command will be switched to the Level 1 safety mode command.

[0219] When the optimal decision is a safe solution and the risk level is a level 2 warning, the hierarchical control command will be switched to the level 2 safety mode command.

[0220] Based on Example 7, this embodiment uses a closed-loop scheduling and control unit to implement the optimal decision output by the antifragile decision unit. This decision The risk level information is already implicitly included, because yes and The function is transformed into specific operational instructions at the mine site;

[0221] The specific steps for this unit to match the preset scheduling instruction set are as follows:

[0222] The preset scheduling instruction set includes:

[0223] Production Optimal Mode Instruction: In this embodiment, it corresponds to the production optimal solution. This instruction corresponds to a complex intelligent tunneling mode that relies on precise data, aiming for optimal output-cost ratio.

[0224] Level 1 Security Mode Instruction: In this embodiment, the corresponding security solution One type, denoted as This instruction corresponds to a traditional, conservative operating mode, such as reducing the tunneling speed by 30% and increasing the support density by 20%.

[0225] Level 2 security mode instruction: In this embodiment, the corresponding security solution A more conservative form, denoted as This instruction corresponds to suspending tunneling operations in high-risk areas and switching to an operation mode that relies less on data, such as manual observation.

[0226] When the optimal decision is the optimal solution for production And when the risk level is normal, the graded control command will be determined as the production optimal mode command; hour, , The system executes ;

[0227] When the optimal decision is a safe solution Furthermore, when the risk level is at Level 1 warning, the tiered control command will be switched to Level 1 safety mode command. ;exist hour, , System matching The corresponding level 1 warning Instructions and execution;

[0228] When the optimal decision is a safe solution Furthermore, when the risk level is a Level 2 warning, the tiered control command will be switched to the Level 2 safety mode command. ;exist hour, , System matching The corresponding level II warning Instructions and execution;

[0229] This embodiment uses a pre-set hierarchical instruction set corresponding to risk levels and decision-making objectives. The abstract optimal decision output by the upstream decision-making unit. It is linked to the actual operation mode of the mine, such as speed reduction and production shutdown, in a precise and automatic manner; it has opened up the last mile from risk perception to anti-fragile decision-making and then to on-site physical execution, realizing a complete closed loop from algorithm to control.

[0230] Example 9:

[0231] The closed-loop scheduling control unit is also used for:

[0232] After executing the Level 1 or Level 2 safety mode command, continuously monitor the mine system resilience entropy;

[0233] When the mine system resilience entropy falls below the first-level early warning threshold, the antifragile decision-making unit will restore the risk aversion coefficient to a low value.

[0234] The hierarchical control command switches back to the optimal production mode.

[0235] Based on Example 8, this embodiment aims to form a complete resilience management closed loop, which can not only avoid danger but also recover when safe. The closed loop scheduling and control unit also has a state recovery function and is linked with the antifragile decision-making unit.

[0236] Specifically:

[0237] Executing Level 1 security mode instructions Or Level 2 security mode command Subsequently, the system continuously monitors the resilience entropy of the mine system through the resilience entropy assessment unit. ;implement or For example, reducing tunneling disturbances usually reduces physical risk factors. A decrease, thus leading to Decline, and then decline;

[0238] When the toughness entropy of the mining system Falling back to the Level 1 warning threshold After the following time and a period of stability,

[0239] Antifragile decision-making units will use risk aversion coefficients Automatically restore to low-order coefficient value The system detected that the risk level had returned to normal, and the decision-making logic automatically switched back. ;

[0240] Hierarchical control command to switch back to optimal production mode command This switch happens automatically because... Restore to Subsequently, in the utility function solution of Example 6, the antifragile decision-making unit... , making Become again The largest optimal decision The closed-loop scheduling control unit uses this information. Match and execute instruction;

[0241] This embodiment ensures that the system can not only detect... When the risk increases, the system automatically switches to dimensionality reduction. It can still be executed. lead to After returning, automatically switch back to the previous dimension. This forms a complete dynamic resilience closed loop of perception-decision-execution-recovery, avoiding permanent waste of efficiency caused by excessive conservatism, and truly achieving a dynamic balance between safety and efficiency on the time scale.

[0242] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A big data analysis and prevention decision-making system for disasters in deep mines, characterized in that: include: The data pollution quantification unit is used to collect multi-source heterogeneous data streams and baseline prediction data, perform noise pollution quantification analysis, and obtain the data pollution index. The resilience entropy assessment unit is used to collect physical risk factors, calculate the basic safety entropy, and correct the basic safety entropy according to the data pollution index to obtain the mine system resilience entropy. The mine system resilience entropy is then processed to obtain the risk level. The antifragile decision-making unit is used to dynamically adjust the risk aversion coefficient based on the risk level and to perform utility function calculation on the preset alternative decisions to obtain the optimal decision; The closed-loop scheduling control unit is used to generate and execute hierarchical control instructions by matching a preset set of scheduling instructions based on the optimal decision and risk level. The data pollution quantification unit performs noise pollution quantification analysis, which includes the following steps: Acquire real-time observations from each sensor; Obtain the theoretical readings output by the benchmark prediction model trained on historical data; The relative deviation between real-time observations and theoretical readings is calculated to obtain the relative deviation of various types of data. The relative deviations of various types of data are weighted and summed according to the preset normalization weights to obtain the data pollution index; The resilience entropy assessment unit calculates the basic safety entropy through the following steps: Obtain factor observations of physical risk factors; Obtain the preset factor safety baseline value corresponding to the factor observation value; Obtain the preset critical hazard value of the factor corresponding to the factor observation value; By combining the observed values ​​of the factors with the safety baseline values ​​of the factors, and by combining the critical hazard values ​​of the factors, normalization is performed to calculate the risk level of each factor. The risk levels of each factor are weighted and summed according to the preset factor weights to obtain the basic safety entropy; The utility function calculation for an antifragile decision-making unit includes the following steps: To obtain the expected economic benefits of the pre-set alternative decisions; Calculate the system collapse probability based on the resilience entropy of the mine system; The decision utility of the candidate decision is obtained by subtracting the product of the risk aversion coefficient and the system collapse probability from the expected economic benefits. The candidate decision that maximizes the decision utility is identified as the optimal decision.

2. The deep mine disaster big data analysis and prevention decision-making system as described in claim 1, characterized in that, The resilience entropy assessment unit corrects the basic safety entropy through the following steps: Based on the preset pollution sensitivity coefficient and preset pollution impact index, and combined with the data pollution index, a nonlinear correction factor is constructed. Multiplying the basic safety entropy by the nonlinear correction factor yields the mine system resilience entropy.

3. The deep mine disaster big data analysis and prevention decision-making system as described in claim 1, characterized in that, The resilience entropy assessment unit performs the following steps to determine the resilience entropy of the mine system: The mine system resilience entropy is compared with the preset first-level early warning threshold; The mine system resilience entropy is compared with the preset secondary hazard threshold. When the mine system resilience entropy is less than the first-level early warning threshold, the risk level is determined to be the normal state; When the mine system's resilience entropy is greater than or equal to the Level 1 warning threshold and less than the Level 2 danger threshold, the risk level is determined to be Level 1 warning. When the resilience entropy of the mine system is greater than or equal to the level 2 hazard threshold, the risk level is determined to be level 2 warning.

4. The deep mine disaster big data analysis and prevention decision-making system as described in claim 1, characterized in that, The dynamic adjustment of the risk aversion coefficient by the antifragile decision-making unit includes the following steps: When the risk level is normal, the risk aversion coefficient is set to a preset low coefficient value; When the risk level is at Level 1 warning, the risk aversion coefficient will be switched to a preset high coefficient value; When the risk level is at Level 2 warning, the risk aversion coefficient will be switched to the preset critical coefficient value; Among them, the high coefficient value ensures that the product of the risk aversion coefficient and the system collapse probability is greater than the expected economic benefits.

5. The deep mine disaster big data analysis and prevention decision-making system as described in claim 1, characterized in that, The closed-loop scheduling control unit matches the preset scheduling instruction set, including the following steps: The preset scheduling instruction set includes production optimal mode instructions, first-level safety mode instructions, and second-level safety mode instructions; When the optimal decision is the production optimal solution and the risk level is normal, the hierarchical control instruction will be determined as the production optimal mode instruction. When the optimal decision is a safe solution and the risk level is a Level 1 warning, the hierarchical control command will be switched to the Level 1 safety mode command. When the optimal decision is a safe solution and the risk level is a level 2 warning, the hierarchical control command will be switched to the level 2 safety mode command.

6. The deep mine disaster big data analysis and prevention decision-making system as described in claim 5, characterized in that, The closed-loop scheduling control unit is also used for: After executing the Level 1 or Level 2 safety mode command, continuously monitor the mine system resilience entropy; When the mine system resilience entropy falls below the first-level early warning threshold, the antifragile decision-making unit will restore the risk aversion coefficient to a low value. The hierarchical control command switches back to the optimal production mode.

Images