Strip mine area safety early warning method and system based on holographic data

Abstract

The invention discloses a holographic data-based strip mine area safety early warning method and system. The method comprises the steps of S1, constructing a strip mine dynamic data set; s2, generating a dynamic holographic data model; s3, calculating the potential risk level of each risk factor based on fuzzy reasoning; s4, generating a risk distribution result and carrying out grading division on risk grades; s5, generating an optimal risk distribution scheme; s6, generating dynamic safety early warning information based on the optimal risk distribution scheme; and S7, according to the dynamic safety early warning information and the optimal risk distribution scheme, combining an emergency response rule base to automatically generate an optimal emergency response scheme. The precision, the response speed and the intelligent level of safety early warning of the strip mine area are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of safety early warning, and in particular to an open-pit mine area safety early warning method and system based on holographic data. Background Art

[0002] As open-pit mines become high-risk workplaces with complex geological structures, changeable environmental factors, and frequent equipment operation, potential safety hazards such as landslides, collapses, and equipment failures pose a huge threat to production operations. In order to ensure the safety of personnel and equipment and improve the efficiency of mine management, an efficient safety early warning technology is urgently needed. However, the current safety monitoring and early warning technology still has many shortcomings in practical applications.

[0003] Existing technologies mainly rely on a single type of data monitoring equipment, such as geological displacement sensors or meteorological monitoring equipment, which collect single-dimensional data for safety assessment. Although they can monitor the risk status of mining areas to a certain extent, they face the following limitations:

[0004] Insufficient multi-source data fusion and analysis: Current safety monitoring systems usually use isolated equipment to collect a single type of data and lack the ability to integrate multi-source data in real time. Due to the wide variety of data and their strong interrelationships, existing technologies make it difficult to effectively integrate these data for global analysis, resulting in insufficient control over the overall risk situation in open-pit mining areas.

[0005] Low accuracy in identifying risk factors: Traditional early warning technologies rely on preset threshold rules or simple algorithm models to judge risk status. They are unable to cope with the complex geological environment and changeable climatic conditions of open-pit mines, and are prone to false alarms or missed alarms in high-risk scenarios, seriously affecting the accuracy of early warnings.

[0006] Weak dynamic risk assessment capabilities: Existing technologies for assessing mining risks are usually based on qualitative analysis of static data. They lack the ability to model real-time dynamic data and find it difficult to accurately predict the temporal and spatial evolution trends of risks. This results in existing technologies having slow responses and insufficient decision-making support when dealing with sudden disasters.

[0007] Limited degree of optimization and intelligence: Existing early warning systems are mostly based on manual rule configuration and lack intelligent optimization tools. Risk distribution optimization is usually based on human experience, without combining algorithmic tools to achieve global optimization. This is not only inefficient, but also difficult to adapt to dynamic changes in complex scenarios.

[0008] In summary, the existing technology has significant deficiencies in the fusion and analysis of multi-source data, accurate identification of risk factors, dynamic risk assessment capabilities and intelligent optimization, and it is difficult to meet the needs of modern open-pit mine safety management for efficiency, accuracy and intelligence. Therefore, a new method and system based on holographic data, fuzzy logic and intelligent optimization algorithm is urgently needed to solve the above problems and improve the scientificity and reliability of open-pit mine area safety warning. Summary of the invention

[0009] One purpose of the present invention is to provide an open-pit mine area safety early warning method and system based on holographic data, which significantly improves the accuracy, response speed and intelligence level of open-pit mine area safety early warning.

[0010] According to an embodiment of the present invention, a method for early warning of open-pit mine area safety based on holographic data comprises the following steps:

[0011] S1. Collect geological displacement data, meteorological condition data, equipment vibration data and environmental monitoring data to build a dynamic data set for open pit mines;

[0012] S2. Perform denoising, data missing completion and normalization on the open-pit mine dynamic data set to form a pre-processed standardized open-pit mine dynamic data set, integrate the standardized open-pit mine dynamic data set through a holographic data fusion algorithm, and generate a dynamic holographic data model;

[0013] S3. Extract geological risk factors, meteorological risk factors, equipment risk factors and environmental risk factors based on the dynamic holographic data model, use the fuzzy logic rule base to fuzzify the key risk factors, construct a fuzzy set of risk factors, and calculate the potential risk level of each risk factor based on fuzzy reasoning;

[0014] S4. Establish a dynamic risk assessment model based on the potential risk level and the dynamic holographic data model, evaluate the potential risks of the open-pit mine area through the dynamic risk assessment model, generate risk distribution results and classify the risk levels;

[0015] S5. Use the coronavirus herd immunity optimizer to optimize the risk distribution results generated by the dynamic risk assessment model, simulate the diffusion process of key risk factors in the open-pit mine area, and dynamically adjust the distribution weights of risk factors in combination with the dynamic holographic data model to generate the optimal risk distribution plan;

[0016] S6. Generate dynamic safety warning information based on the optimal risk distribution scheme;

[0017] S7. Based on dynamic safety warning information and the optimal risk distribution plan, the optimal emergency response plan is automatically generated in combination with the emergency response rule library. The optimal emergency response plan includes personnel evacuation suggestions, equipment operation adjustment plans and on-site rescue strategies, and the emergency response plan is implemented through the emergency command system.

[0018] Optionally, the S1 includes the following steps:

[0019] S11. Collect geological displacement data of rock mass displacement through displacement sensors deployed in the open-pit mine area g ;

[0020] S12. Collect meteorological data including temperature, humidity, wind speed and rainfall through weather stations installed in the open pit area. w ;

[0021] S13. Collect equipment vibration data during equipment operation through vibration sensors installed on open-pit mine equipment e ;

[0022] S14. Collect environmental monitoring data including air quality, noise level and dust concentration through environmental monitoring equipment distributed in the open-pit mine area. c ;

[0023] S15. Collected geological displacement data D g , meteorological conditions data D w , Equipment vibration data D e and environmental monitoring data c Perform preliminary integration to build a dynamic dataset for open-pit mines:

[0024] D=∪ x∈{g,w,e,c} D x .

[0025] Optionally, S2 includes the following steps:

[0026] S21. Eliminate the noise data in the open-pit mine dynamic data set D due to sensor error or external interference by using a noise filtering algorithm to obtain a denoised open-pit mine dynamic data set D';

[0027] S22. Filling the missing data points in the denoised open-pit mine dynamic data set D' by interpolation to obtain a completed open-pit mine dynamic data set D";

[0028] S23. Map the numerical ranges of different data dimensions in the completed open-pit mine dynamic data set D” to a unified interval [0,1] through a normalization function to obtain the normalized open-pit mine dynamic data set D s ;

[0029] S24. The open-pit mine dynamic data set D is integrated into the open-pit mine dynamic data set D by holographic data fusion algorithm. s The geological displacement data, meteorological condition data, equipment vibration data and environmental monitoring data are integrated in multiple dimensions to generate a dynamic holographic data model M:

[0030]

[0031] Among them, m k is the kth data point describing the open pit area in the dynamic holographic data model, N is the total number of data points contained in the dynamic holographic data model, τ is the time variable, T is the total length of the time period, is the normalized data set D s The kth data point in type x, where type x includes geology, meteorology, equipment or environment, λ x is the fusion weight coefficient of data type x, which is dynamically adjusted according to the importance of the data type. is the feature fusion function, Ω k is the spatial characteristic matrix, Γ x is a specific weight matrix of data type x, Φ x (τ) is the time series weight function, which is used to describe the dynamic changes of data type x in the time dimension.

[0032] Optionally, S3 includes the following steps:

[0033] S31. Based on the dynamic holographic data model M, the geological displacement data, meteorological condition data, equipment vibration data and environmental monitoring data are respectively extracted to obtain the geological risk factor set F g , meteorological risk factor set F w , Equipment risk factor set F e And the environmental risk factor set F c :

[0034] F x ={f x,k ∣f x,k =ω(m k ,Θ x ),m k ∈M,x∈{g,w,e,c}};

[0035] Among them, ω(m k ,Θ x ) is the factor extraction function, Θ x is the set of extraction parameters associated with the data type x, f x,k is the kth risk factor, which is used to characterize the multidimensional factors affecting safety in open-pit mine areas;

[0036] S32. Combine the geological risk factor set, meteorological risk factor set, equipment risk factor set and environmental risk factor set, and use the multi-level fuzzy membership function to perform deep fuzzification processing on the risk factors to generate the fuzzy risk factor set F':

[0037]

[0038] in, It is a multi-level fuzzy membership function, which assigns different membership mappings to different intensity intervals r of risk factors, and is used to characterize the uncertainty of multi-dimensional risks in open-pit mine areas in time and space;

[0039] S33. Perform adaptive fuzzy logic reasoning on the fuzzy risk factor set F', using a hierarchical fuzzy rule base Π={Π g ,Π w ,Π e ,Π c} Perform inference calculation on each type of risk factor to obtain the potential risk level R of each risk factor x :

[0040]

[0041] Among them, σ(·) is the inference function of the hierarchical fuzzy rule base, which is used to integrate the fuzzy membership of the risk factor and the corresponding rule set Π x Perform multi-level reasoning, r x,k is the potential risk level of the kth risk factor;

[0042] S34. The calculated potential risk level R g ,R w ,R e ,R c Perform dynamic weighted synthesis to form a comprehensive risk level distribution matrix Λ:

[0043]

[0044] Among them, λ i,j It represents the comprehensive risk level score corresponding to the i-th risk type and the j-th risk factor.

[0045] Optionally, S4 includes the following steps:

[0046] S41. Based on the dynamic holographic data model M, the comprehensive risk level distribution matrix Λ and the potential risk level R x , the dynamic risk assessment model E is constructed by dynamically analyzing the multidimensional data. The risk assessment result of each assessment point in the dynamic risk assessment model is calculated as:

[0047]

[0048] Among them, e k is the risk assessment result of the kth assessment point, which is used to characterize the comprehensive risk level of this point in the open-pit mine area. τ is the time variable, T is the total length of the assessment time period, and λ i,j is the comprehensive risk weight of the i-th risk type and the j-th risk factor in the comprehensive risk level distribution matrix, Φ x,i (m k ,τ) is the spatial weight function of the i-th risk factor in the dynamic holographic data model, Ψ i,j (m k ,τ) is the time series weight function, which is used to characterize the characteristics of risk factors changing over time, Δ x,j is the dynamic adjustment parameter associated with risk factor type x, Ω k is the external environment correction term of the kth evaluation point;

[0049] S42. The dynamic risk assessment model E is combined with the time series and spatial distribution characteristics of the open-pit mine area to generate a risk distribution result R. The risk distribution value of each assessment point in the risk distribution result is calculated as:

[0050]

[0051] Among them, r k is the risk distribution value of the evaluation point k, Ω k is the spatial coverage of the evaluation point k, e k is the risk assessment result of the assessment point k, G(α k ,β k ) is the spatial correlation function, which is used to describe the risk propagation effect of the surrounding area of ​​the assessment point, α k and β k is the spatial propagation characteristic parameter, Θ k is the regional weighting factor, which is used to consider the importance of the region where the evaluation point is located, σ k is the random error correction term of the evaluation point, which is used to deal with unpredictable external interference;

[0052] S43. Classify the risk level of the assessment point according to the risk distribution result R, and generate a hierarchical risk level set L:

[0053]

[0054] Among them, l k is the risk level of the kth assessment point in the hierarchical risk level set, C is the total number of risk level categories, Υ c (r k ) is the risk distribution value r k Membership function at risk level c, Γ cIt is the threshold coefficient of risk level c, which is used to adjust the strictness of the level classification.

[0055] Optionally, S5 includes the following steps:

[0056] S51. Based on the risk distribution results R generated by the dynamic risk assessment model E and the dynamic holographic data model M, the coronavirus herd immunity optimizer is initialized and the optimized population P is constructed:

[0057]

[0058] in, is the state of the i-th individual in the population corresponding to the k-th evaluation point, indicating the spread of the key risk factor at this point, r k is the initial risk distribution value of the evaluation point k, is the weight parameter of individual i, which is used to simulate the influence of risk factors in the transmission process, m k is the holographic data of the evaluation point k in the dynamic holographic data model, S is the population size, indicating the number of individuals in the optimizer, and N is the total number of evaluation points;

[0059] S52. Simulate the propagation effect of key risk factors in the open-pit mine area in each generation of optimization, and adjust the weight parameters through the virus infection propagation mechanism Calculate the individual states of the next generation population

[0060]

[0061] in, is the weight parameter of individual i after optimization, is the risk distribution value of the optimized evaluation point k, is the spatial correlation propagation function, which describes the propagation effect of risk factors in time and space, η is the dynamic adjustment coefficient of infection propagation, δ is the adjustment coefficient of diffusion effect, α k ,β k ,γ k ,θ k is the spatial propagation parameter associated with the evaluation point k

[0062] S53. When the optimizer population reaches the preset immune threshold, the optimal solution of the individual state in the population is used to generate the final risk distribution scheme R * :

[0063]

[0064] in, is the final risk distribution value of the optimized evaluation point k, which represents the risk distribution result of this point after the coronavirus herd immunity optimization, R *The optimal risk distribution scheme.

[0065] Optionally, the S6 comprises the following steps:

[0066] S61. Based on the optimal risk distribution scheme and the dynamic holographic data model, the risk distribution value of the assessment point and the regional characteristics are combined to determine the scope of the warning area and mark the key areas with potential safety hazards;

[0067] S62. Calculate the risk level of each warning area based on the graded risk level and the optimal risk distribution plan, and identify potential influencing factors in the area in combination with the dynamic holographic data model, including key factors in geology, meteorology, equipment and environment;

[0068] S63. Generate dynamic safety warning information based on the warning area scope, risk level and potential influencing factors. The dynamic safety warning information includes the warning area scope, corresponding risk level, potential influencing factors and recommended emergency measures.

[0069] An open-pit mine area safety early warning system based on holographic data implements an open-pit mine area safety early warning method based on holographic data, characterized in that it includes:

[0070] The multi-source data acquisition module is used to collect geological displacement data, meteorological condition data, equipment vibration data and environmental monitoring data through geological displacement sensors, meteorological monitoring equipment, equipment vibration sensors and environmental monitoring equipment deployed in the open-pit mine area to build an open-pit mine dynamic data set;

[0071] The data preprocessing and fusion module is used to perform denoising, data missing completion and normalization on the collected open-pit mine dynamic data set to form a standardized dynamic data set. The standardized data set is integrated with multi-dimensional features through the holographic data fusion algorithm to generate a dynamic holographic data model. The dynamic holographic data model describes the multi-source data status of the open-pit mine area and its time series and spatial distribution characteristics.

[0072] The risk factor extraction and analysis module is used to extract geological risk factors, meteorological risk factors, equipment risk factors and environmental risk factors based on the dynamic holographic data model, and use the fuzzy logic rule base to fuzzify the key risk factors, build a fuzzy risk factor set, and calculate the potential risk level of each risk factor through fuzzy reasoning to provide input for dynamic risk assessment;

[0073] Dynamic risk assessment module, which is used to establish a dynamic risk assessment model based on potential risk levels and dynamic holographic data models, assess the potential risks of open-pit mine areas, generate risk distribution results, and classify risk levels to form risk level distribution;

[0074] The risk distribution optimization module, including the coronavirus herd immunity optimizer, is used to optimize the risk distribution results generated by the dynamic risk assessment model, simulate the diffusion process of key risk factors in the open-pit mine area, and dynamically adjust the distribution weights of risk factors in combination with the dynamic holographic data model to generate the optimal risk distribution plan;

[0075] Dynamic safety warning generation module, used to generate dynamic safety warning information based on the optimal risk distribution scheme. The dynamic safety warning information includes the warning area range, risk level, potential influencing factors and recommended emergency measures. It provides intuitive and effective warning information by calculating and analyzing the risk distribution characteristics of each area in the dynamic holographic data model;

[0076] The information output and notification module is used to output dynamic safety warning information through a visualization platform, text messages, voice reminders, etc. It supports displaying the warning area range, risk level and potential influencing factors in the form of distribution maps and reports on the mining area management platform, notifying relevant managers and suggesting specific emergency response measures;

[0077] The system iterative optimization module is used to iteratively adjust the parameters of the dynamic holographic data model, fuzzy logic rule base and coronavirus herd immunity optimizer based on the emergency response execution effect and feedback information, and continuously optimize the evaluation accuracy and response efficiency of the safety early warning system.

[0078] The beneficial effects of the present invention are:

[0079] (1) The present invention uses holographic data fusion technology to achieve efficient dynamic fusion and consistency analysis of multi-dimensional data of geology, meteorology, equipment vibration and environmental monitoring in open-pit mine areas. Holographic data modeling technology is used to uniformly express spatiotemporal characteristics to ensure the comprehensiveness and accuracy of data processing. In addition, dynamic normalization and spatiotemporal weighting mechanisms are introduced in the data fusion process to make the fused model closer to the actual state of the mining area, thereby providing a more comprehensive and accurate data basis for risk assessment.

[0080] (2) The present invention adopts a fuzzy logic rule base to perform multi-level fuzzy processing on key risk factors. Combined with a dynamic holographic data model, the present invention realizes accurate quantification and classification of potential risks in open-pit mine areas through multi-level fuzzy membership functions and adaptive reasoning rules. Through the flexible reasoning of fuzzy logic, it can handle nonlinear, multi-dimensional interactions of complex risk factors and dynamically adjust risk level assessment rules, which significantly improves the accuracy and adaptability of risk assessment and provides mine managers with more reliable risk information.

[0081] (3) The present invention introduces the coronavirus herd immunity optimizer into the field of open-pit mine safety warning. By simulating the spatial diffusion process of risk factors and the herd immunity mechanism, the risk distribution results generated by the dynamic risk assessment model are globally optimized. Compared with traditional optimization algorithms, the coronavirus herd immunity optimizer has dynamic adaptability and global search capabilities, and can dynamically adjust the distribution weights of risk factors in different time and space dimensions, thereby generating an optimal risk distribution plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0083] Figure 1 The present invention provides a flow chart of an open-pit mine area safety early warning method and system based on holographic data. DETAILED DESCRIPTION

[0084] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0085] refer to Figure 1 , an open-pit mine area safety early warning method based on holographic data, comprising the following steps:

[0086] S1. Collect geological displacement data, meteorological condition data, equipment vibration data and environmental monitoring data to build a dynamic data set for open pit mines;

[0087] S2. Perform denoising, data missing completion and normalization on the open-pit mine dynamic data set to form a pre-processed standardized open-pit mine dynamic data set, integrate the standardized open-pit mine dynamic data set through a holographic data fusion algorithm, and generate a dynamic holographic data model;

[0088] S3. Extract geological risk factors, meteorological risk factors, equipment risk factors and environmental risk factors based on the dynamic holographic data model, use the fuzzy logic rule base to fuzzify the key risk factors, construct a fuzzy set of risk factors, and calculate the potential risk level of each risk factor based on fuzzy reasoning;

[0089] S4. Establish a dynamic risk assessment model based on the potential risk level and the dynamic holographic data model, evaluate the potential risks of the open-pit mine area through the dynamic risk assessment model, generate risk distribution results and classify the risk levels;

[0090] S5. Use the coronavirus herd immunity optimizer to optimize the risk distribution results generated by the dynamic risk assessment model, simulate the diffusion process of key risk factors in the open-pit mine area, and dynamically adjust the distribution weights of risk factors in combination with the dynamic holographic data model to generate the optimal risk distribution plan;

[0091] S6. Generate dynamic safety warning information based on the optimal risk distribution scheme;

[0092] S7. Based on dynamic safety warning information and the optimal risk distribution plan, the optimal emergency response plan is automatically generated in combination with the emergency response rule library. The optimal emergency response plan includes personnel evacuation suggestions, equipment operation adjustment plans and on-site rescue strategies, and the emergency response plan is implemented through the emergency command system.

[0093] In this implementation, S1 includes the following steps:

[0094] S11. Collect geological displacement data of rock mass displacement through displacement sensors deployed in the open-pit mine area g ;

[0095] S12. Collect meteorological data including temperature, humidity, wind speed and rainfall through weather stations installed in the open pit area. w ;

[0096] S13. Collect equipment vibration data during equipment operation through vibration sensors installed on open-pit mine equipment e ;

[0097] S14. Collect environmental monitoring data including air quality, noise level and dust concentration through environmental monitoring equipment distributed in the open-pit mine area. c ;

[0098] S15. Collected geological displacement data D g , meteorological conditions data D w , Equipment vibration data D e and environmental monitoring data c Perform preliminary integration to build a dynamic dataset for open-pit mines:

[0099] D=∪ x∈{g,w,e,c} D x .

[0100] In this implementation, S2 includes the following steps:

[0101] S21. Eliminate the noise data in the open-pit mine dynamic data set D due to sensor error or external interference by using a noise filtering algorithm to obtain a denoised open-pit mine dynamic data set D';

[0102] S22. Filling the missing data points in the denoised open-pit mine dynamic data set D' by interpolation to obtain a completed open-pit mine dynamic data set D";

[0103] S23. Map the numerical ranges of different data dimensions in the completed open-pit mine dynamic data set D” to a unified interval [0,1] through a normalization function to obtain the normalized open-pit mine dynamic data set D s ;

[0104] S24. The open-pit mine dynamic data set D is integrated into the open-pit mine dynamic data set D by holographic data fusion algorithm. s The geological displacement data, meteorological condition data, equipment vibration data and environmental monitoring data are integrated in multiple dimensions to generate a dynamic holographic data model M:

[0105]

[0106] Among them, m k is the kth data point describing the open pit area in the dynamic holographic data model, N is the total number of data points contained in the dynamic holographic data model, τ is the time variable, T is the total length of the time period, is the normalized data set D s The kth data point in type x, where type x includes geology, meteorology, equipment or environment, λ x is the fusion weight coefficient of data type x, which is dynamically adjusted according to the importance of the data type. is the feature fusion function, Ω k is the spatial characteristic matrix, Γ x is a specific weight matrix of data type x, Φ x (τ) is the time series weight function, which is used to describe the dynamic changes of data type x in the time dimension.

[0107] In this implementation, S3 includes the following steps:

[0108] S31. Based on the dynamic holographic data model M, the geological displacement data, meteorological condition data, equipment vibration data and environmental monitoring data are respectively extracted to obtain the geological risk factor set F g , meteorological risk factor set F w , Equipment risk factor set F e And the environmental risk factor set F c :

[0109] F x ={f x,k ∣f x,k =ω(m k ,Θ x ),m k ∈M,x∈{g,w,e,c}};

[0110] Among them, ω(m k ,Θ x ) is the factor extraction function, Θ x is the set of extraction parameters associated with the data type x, f x,k is the kth risk factor, which is used to characterize the multidimensional factors affecting safety in open-pit mine areas;

[0111] S32. Combine the geological risk factor set, meteorological risk factor set, equipment risk factor set and environmental risk factor set, and use the multi-level fuzzy membership function to perform deep fuzzification processing on the risk factors to generate the fuzzy risk factor set F':

[0112]

[0113] in, It is a multi-level fuzzy membership function, which assigns different membership mappings to different intensity intervals r of risk factors, and is used to characterize the uncertainty of multi-dimensional risks in open-pit mine areas in time and space;

[0114] S33. Perform adaptive fuzzy logic reasoning on the fuzzy risk factor set F', using a hierarchical fuzzy rule base Π={Π g ,Π w ,Π e ,Π c} Perform inference calculation on each type of risk factor to obtain the potential risk level R of each risk factor x :

[0115]

[0116] Among them, σ(·) is the inference function of the hierarchical fuzzy rule base, which is used to integrate the fuzzy membership of the risk factor and the corresponding rule set Π x Perform multi-level reasoning, r x,k is the potential risk level of the kth risk factor;

[0117] S34. The calculated potential risk level R g ,R w ,R e ,R c Perform dynamic weighted synthesis to form a comprehensive risk level distribution matrix Λ:

[0118] Λ=[λ i,j ] i＝1..4,j＝1..|Rx| ;

[0119] Among them, λ i,j It represents the comprehensive risk level score corresponding to the i-th risk type and the j-th risk factor.

[0120] In this implementation, S4 includes the following steps:

[0121] S41. Based on the dynamic holographic data model M, the comprehensive risk level distribution matrix Λ and the potential risk level R x , the dynamic risk assessment model E is constructed by dynamically analyzing the multidimensional data. The risk assessment result of each assessment point in the dynamic risk assessment model is calculated as:

[0122]

[0123] Among them, e k is the risk assessment result of the kth assessment point, which is used to characterize the comprehensive risk level of this point in the open-pit mine area. τ is the time variable, T is the total length of the assessment time period, and λ i,j is the comprehensive risk weight of the i-th risk type and the j-th risk factor in the comprehensive risk level distribution matrix, Φ x,i (m k ,τ) is the spatial weight function of the i-th risk factor in the dynamic holographic data model, Ψ i,j (m k ,τ) is the time series weight function, which is used to characterize the characteristics of risk factors changing over time, Δ x,j is the dynamic adjustment parameter associated with risk factor type x, Ω k is the external environment correction term of the kth evaluation point;

[0124] S42. The dynamic risk assessment model E is combined with the time series and spatial distribution characteristics of the open-pit mine area to generate a risk distribution result R. The risk distribution value of each assessment point in the risk distribution result is calculated as:

[0125]

[0126] Among them, r k is the risk distribution value of the evaluation point k, Ω k is the spatial coverage of the evaluation point k, e k is the risk assessment result of the assessment point k, G(α k ,β k ) is the spatial correlation function, which is used to describe the risk propagation effect of the surrounding area of ​​the assessment point, α k and β k is the spatial propagation characteristic parameter, Θ k is the regional weighting factor, which is used to consider the importance of the region where the evaluation point is located, σ k is the random error correction term of the evaluation point, which is used to deal with unpredictable external interference;

[0127] S43. Classify the risk level of the assessment point according to the risk distribution result R, and generate a hierarchical risk level set L:

[0128]

[0129] Among them, l k is the risk level of the kth assessment point in the hierarchical risk level set, C is the total number of risk level categories, Υ c (r k ) is the risk distribution value r k Membership function at risk level c, Γ c It is the threshold coefficient of risk level c, which is used to adjust the strictness of the level classification.

[0130] In this implementation, S5 includes the following steps:

[0131] S51. Based on the risk distribution results R generated by the dynamic risk assessment model E and the dynamic holographic data model M, the coronavirus herd immunity optimizer is initialized and the optimized population P is constructed:

[0132]

[0133] in, is the state of the i-th individual in the population corresponding to the k-th evaluation point, indicating the spread of the key risk factor at this point, r k is the initial risk distribution value of the evaluation point k, is the weight parameter of individual i, which is used to simulate the influence of risk factors in the transmission process, m k is the holographic data of the evaluation point k in the dynamic holographic data model, S is the population size, indicating the number of individuals in the optimizer, and N is the total number of evaluation points;

[0134] S52. Simulate the propagation effect of key risk factors in the open-pit mine area in each generation of optimization, and adjust the weight parameters through the virus infection propagation mechanism Calculate the individual states of the next generation population

[0135]

[0136]

[0137] in, is the weight parameter of individual i after optimization, is the risk distribution value of the optimized evaluation point k, is the spatial correlation propagation function, which describes the propagation effect of risk factors in time and space, η is the dynamic adjustment coefficient of infection propagation, δ is the adjustment coefficient of diffusion effect, α k ,β k ,γ k ,θ k is the spatial propagation parameter associated with the evaluation point k

[0138] S53. When the optimizer population reaches the preset immune threshold, the optimal solution of the individual state in the population is used to generate the final risk distribution scheme R * :

[0139]

[0140] in, is the final risk distribution value of the optimized evaluation point k, which represents the risk distribution result of this point after the coronavirus herd immunity optimization, R * The optimal risk distribution scheme.

[0141] In this implementation, S6 includes the following steps:

[0142] S61. Based on the optimal risk distribution scheme and the dynamic holographic data model, the risk distribution value of the assessment point and the regional characteristics are combined to determine the scope of the warning area and mark the key areas with potential safety hazards;

[0143] S62. Calculate the risk level of each warning area based on the graded risk level and the optimal risk distribution plan, and identify potential influencing factors in the area in combination with the dynamic holographic data model, including key factors in geology, meteorology, equipment and environment;

[0144] S63. Generate dynamic safety warning information based on the warning area scope, risk level and potential influencing factors. The dynamic safety warning information includes the warning area scope, corresponding risk level, potential influencing factors and recommended emergency measures.

[0145] The open-pit mine area safety early warning system based on holographic data of claim 1 implements an open-pit mine area safety early warning method based on holographic data, comprising:

[0146] The multi-source data acquisition module is used to collect geological displacement data, meteorological condition data, equipment vibration data and environmental monitoring data through geological displacement sensors, meteorological monitoring equipment, equipment vibration sensors and environmental monitoring equipment deployed in the open-pit mine area to build an open-pit mine dynamic data set;

[0147] The data preprocessing and fusion module is used to perform denoising, data missing completion and normalization on the collected open-pit mine dynamic data set to form a standardized dynamic data set. The standardized data set is integrated with multi-dimensional features through the holographic data fusion algorithm to generate a dynamic holographic data model. The dynamic holographic data model describes the multi-source data status of the open-pit mine area and its time series and spatial distribution characteristics.

[0148] The risk factor extraction and analysis module is used to extract geological risk factors, meteorological risk factors, equipment risk factors and environmental risk factors based on the dynamic holographic data model, and use the fuzzy logic rule base to fuzzify the key risk factors, build a fuzzy risk factor set, and calculate the potential risk level of each risk factor through fuzzy reasoning to provide input for dynamic risk assessment;

[0149] Dynamic risk assessment module, which is used to establish a dynamic risk assessment model based on potential risk levels and dynamic holographic data models, assess the potential risks of open-pit mine areas, generate risk distribution results, and classify risk levels to form risk level distribution;

[0150] The risk distribution optimization module, including the coronavirus herd immunity optimizer, is used to optimize the risk distribution results generated by the dynamic risk assessment model, simulate the diffusion process of key risk factors in the open-pit mine area, and dynamically adjust the distribution weights of risk factors in combination with the dynamic holographic data model to generate the optimal risk distribution plan;

[0151] Dynamic safety warning generation module, used to generate dynamic safety warning information based on the optimal risk distribution scheme. The dynamic safety warning information includes the warning area range, risk level, potential influencing factors and recommended emergency measures. It provides intuitive and effective warning information by calculating and analyzing the risk distribution characteristics of each area in the dynamic holographic data model;

[0152] The information output and notification module is used to output dynamic safety warning information through a visualization platform, text messages, voice reminders, etc. It supports displaying the warning area range, risk level and potential influencing factors in the form of distribution maps and reports on the mining area management platform, notifying relevant managers and suggesting specific emergency response measures;

[0153] The system iterative optimization module is used to iteratively adjust the parameters of the dynamic holographic data model, fuzzy logic rule base and coronavirus herd immunity optimizer based on the emergency response execution effect and feedback information, and continuously optimize the evaluation accuracy and response efficiency of the safety early warning system.

[0154] Embodiment 1:

[0155] Example On July 5, 2024, due to abnormal geological activities in an open-pit mine area due to continuous rainfall, the mine manager activated the open-pit mine area safety early warning system based on holographic data.

[0156] At 14:30 in the afternoon, the system detected multiple abnormal signals through the geological displacement sensors deployed in the northwest mine area. The growth rate of the displacement rate data continued to exceed 1.5 mm / minute, which was much higher than the normal value (0.3 mm / minute). The source points of the abnormal signals sent back by the displacement sensors were concentrated in the "Northwest Mine-Section 3" (area identification number S3). The devices with sensor IDs "GW-0018" and "GW-0020" recorded abnormal displacement increments for 3 consecutive minutes. At the same time, the meteorological monitoring station numbered "WX-005" detected that the rainfall in the S3 area reached 25 mm per hour, and the radar signal showed that the rainfall would continue in the next 30 minutes.

[0157] The system immediately denoised and completed the multi-source data returned by the sensors, combined with environmental monitoring data and historical geological landslide records, and generated a risk assessment report using the dynamic holographic data model:

[0158] Sensor points where the displacement rate exceeds the threshold: 3 (IDs are "GW-0015", "GW-0018", and "GW-0020").

[0159] Abnormal rainfall area: The accumulated rainfall in S3 has reached 80 mm (in the past 3 hours).

[0160] Risk factor classification: geological landslide risk weight 60%, equipment vibration secondary disaster weight 25%, environmental dust diffusion risk weight 15%.

[0161] Through fuzzy logic reasoning, the system concluded that the comprehensive risk level of the S3 area was "high risk", and compared this level with other areas. S3 became the highest priority warning area in the current mining area.

[0162] The coronavirus herd immunity optimizer dynamically adjusted the risk factors in the S3 area, simulated the nonlinear relationship between displacement growth rate and rainfall, and redistributed the risk weights of each sensor point through the optimization algorithm to generate the optimal risk distribution plan. The optimization results show that the northern slope of the S3 area (specific coordinates: N23.5643, E112.3545) is the core point where landslides are most likely to occur, and the probability of landslides is expected to be 85% in the next hour.

[0163] The system generated dynamic security warning information at 15:00, including:

[0164] Warning area scope: northern slope of S3 area (N23.5643, E112.3545).

[0165] Risk level: High risk.

[0166] Potential influencing factors: geological landslide (major risk), equipment operation interruption (secondary risk).

[0167] Recommended emergency measures:

[0168] 1. Immediately evacuate all personnel in the S3 area.

[0169] 2. Stop the operation of equipment numbers "EQ-1056" and "EQ-1128".

[0170] 3. Lay out debris flow interception barriers at the bottom of the slope.

[0171] The early warning information is sent to the mobile phone of Manager Zhang, the person in charge of the mine area, via text message, and is visualized in real time through the mine area monitoring platform.

[0172] After receiving the warning, Manager Zhang activated the emergency plan at 15:05, notified the on-site personnel in the S3 area to evacuate, and issued an equipment shutdown order through the platform. The emergency team completed the regional blockade at 15:30 and deployed a temporary interception barrier. At 16:10, a landslide occurred on the north side of the slope, and about 200 cubic meters of rock fell. Due to the timely warning, no casualties or equipment losses were caused.

[0173] This embodiment verifies the real-time and reliability of the system of the present invention in complex open-pit mine areas. Its advantages in multi-source data fusion, dynamic risk assessment and intelligent early warning have significantly improved the safety management level of the mining area.

[0174] The present invention uses holographic data fusion technology to achieve efficient dynamic fusion and consistency analysis of multi-dimensional data of geology, meteorology, equipment vibration and environmental monitoring in open-pit mine areas. Holographic data modeling technology is used to uniformly express spatiotemporal characteristics to ensure the comprehensiveness and accuracy of data processing. In addition, dynamic normalization and spatiotemporal weighting mechanisms are introduced in the data fusion process to make the fused model closer to the actual state of the mining area, thereby providing a more comprehensive and accurate data basis for risk assessment.

[0175] The present invention adopts a fuzzy logic rule base to perform multi-level fuzzy processing on key risk factors, and combines it with a dynamic holographic data model to achieve accurate quantification and classification of potential risks in open-pit mine areas through multi-level fuzzy membership functions and adaptive reasoning rules. Through the flexible reasoning of fuzzy logic, it can handle nonlinear, multi-dimensional interactions between complex risk factors and dynamically adjust risk level assessment rules, which significantly improves the accuracy and adaptability of risk assessment and provides mine managers with more reliable risk information.

[0176] The present invention introduces the coronavirus herd immunity optimizer into the field of open-pit mine safety early warning. By simulating the spatial diffusion process of risk factors and the herd immunity mechanism, global optimization is performed on the risk distribution results generated by the dynamic risk assessment model. Compared with traditional optimization algorithms, the coronavirus herd immunity optimizer has dynamic adaptability and global search capabilities, and can dynamically adjust the distribution weights of risk factors in different time and space dimensions, thereby generating an optimal risk distribution plan.

[0177] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for early warning of open-pit mine area safety based on holographic data, characterized in that: The steps include: S1. Collect geological displacement data, meteorological condition data, equipment vibration data and environmental monitoring data to build a dynamic data set for open pit mines; S2. Perform denoising, data missing completion and normalization on the open-pit mine dynamic data set to form a pre-processed standardized open-pit mine dynamic data set, integrate the standardized open-pit mine dynamic data set through a holographic data fusion algorithm, and generate a dynamic holographic data model; S3. Extract geological risk factors, meteorological risk factors, equipment risk factors and environmental risk factors based on the dynamic holographic data model, use the fuzzy logic rule base to fuzzify the key risk factors, construct a fuzzy set of risk factors, and calculate the potential risk level of each risk factor based on fuzzy reasoning; S4. Establish a dynamic risk assessment model based on the potential risk level and the dynamic holographic data model, evaluate the potential risks of the open-pit mine area through the dynamic risk assessment model, generate risk distribution results and classify the risk levels; S5. Use the coronavirus herd immunity optimizer to optimize the risk distribution results generated by the dynamic risk assessment model, simulate the diffusion process of key risk factors in the open-pit mine area, and dynamically adjust the distribution weights of risk factors in combination with the dynamic holographic data model to generate the optimal risk distribution plan; S6. Generate dynamic safety warning information based on the optimal risk distribution scheme; S7. Based on dynamic safety warning information and the optimal risk distribution plan, the optimal emergency response plan is automatically generated in combination with the emergency response rule library. The optimal emergency response plan includes personnel evacuation suggestions, equipment operation adjustment plans and on-site rescue strategies, and the emergency response plan is implemented through the emergency command system.

2. The open-pit mine area safety early warning method based on holographic data according to claim 1 is characterized in that: The S1 comprises the following steps: S11. Collect geological displacement data of rock mass displacement through displacement sensors deployed in the open-pit mine area g ; S12. Collect weather condition data including temperature, humidity, wind speed and rainfall through weather stations installed in the open pit area. w ; S13. Collect equipment vibration data during equipment operation through vibration sensors installed on open-pit mine equipment e ; S14. Collect environmental monitoring data including air quality, noise level and dust concentration through environmental monitoring equipment distributed in the open-pit mine area. c ; S15. Collected geological displacement data D g , meteorological conditions data D w , Equipment vibration data D e and environmental monitoring data c Perform preliminary integration to build a dynamic dataset for open-pit mines: D=∪ x∈{g,w,e,c} D x 。 3. The open-pit mine area safety early warning method based on holographic data according to claim 1 is characterized in that: The S2 comprises the following steps: S21. Eliminate the noise data in the open-pit mine dynamic data set D due to sensor error or external interference by using a noise filtering algorithm to obtain a denoised open-pit mine dynamic data set D'; S22. Filling the missing data points in the denoised open-pit mine dynamic data set D' by interpolation to obtain a completed open-pit mine dynamic data set D"; S23. Map the numerical ranges of different data dimensions in the completed open-pit mine dynamic data set D” to a unified interval [0,1] through a normalization function to obtain the normalized open-pit mine dynamic data set D s ; S24. The open-pit mine dynamic data set D is integrated into the open-pit mine dynamic data set D by holographic data fusion algorithm. s The geological displacement data, meteorological condition data, equipment vibration data and environmental monitoring data are integrated in multiple dimensions to generate a dynamic holographic data model M: Among them, m k is the kth data point describing the open pit area in the dynamic holographic data model, N is the total number of data points contained in the dynamic holographic data model, τ is the time variable, T is the total length of the time period, is the normalized data set D s The kth data point in type x, where type x includes geology, meteorology, equipment or environment, λ x is the fusion weight coefficient of data type x, which is dynamically adjusted according to the importance of the data type. is the feature fusion function, Ω k is the spatial characteristic matrix, Γ x is a specific weight matrix of data type x, Φ x (τ) is the time series weight function, which is used to describe the dynamic changes of data type x in the time dimension.

4. The open-pit mine area safety early warning method based on holographic data according to claim 1 is characterized in that: The S3 comprises the following steps: S31. Based on the dynamic holographic data model M, the geological displacement data, meteorological condition data, equipment vibration data and environmental monitoring data are respectively extracted to obtain the geological risk factor set F g , meteorological risk factor set F w , Equipment risk factor set F e And the environmental risk factor set F c : F x ={f x,k ∣f x,k =ω(m k ,Θ x ),m k ∈M,x∈{g,w,e,c}}; Among them, ω(m k ,Θ x ) is the factor extraction function, Θ x is the set of extraction parameters associated with the data type x, f x,k is the kth risk factor, which is used to characterize the multidimensional factors affecting safety in open-pit mine areas; S32. Combine the geological risk factor set, meteorological risk factor set, equipment risk factor set and environmental risk factor set, and use the multi-level fuzzy membership function to perform deep fuzzification processing on the risk factors to generate the fuzzy risk factor set F': in, It is a multi-level fuzzy membership function, which assigns different membership mappings to different intensity intervals r of risk factors, and is used to characterize the uncertainty of multi-dimensional risks in open-pit mine areas in time and space; S33. Perform adaptive fuzzy logic reasoning on the fuzzy risk factor set F', using a hierarchical fuzzy rule base Π={Π g ,Π w ,Π e ,Π c } Perform inference calculation on each type of risk factor to obtain the potential risk level R of each risk factor x : Among them, σ(·) is the inference function of the hierarchical fuzzy rule base, which is used to integrate the fuzzy membership of the risk factor and the corresponding rule set Π x Perform multi-level reasoning, r x,k is the potential risk level of the kth risk factor; S34. The calculated potential risk level R g ,R w ,R e ,R c Perform dynamic weighted synthesis to form a comprehensive risk level distribution matrix Λ: Among them, λ i,j It represents the comprehensive risk level score corresponding to the i-th risk type and the j-th risk factor.

5. The open-pit mine area safety early warning method based on holographic data according to claim 1 is characterized in that: The S4 comprises the following steps: S41. Based on the dynamic holographic data model M, the comprehensive risk level distribution matrix Λ and the potential risk level R x , the multi-dimensional data is dynamically analyzed to construct a dynamic risk assessment model E. The risk assessment result of each assessment point in the dynamic risk assessment model is calculated as: Among them, e k is the risk assessment result of the kth assessment point, which is used to characterize the comprehensive risk level of this point in the open-pit mine area. τ is the time variable, T is the total length of the assessment time period, and λ i,j is the comprehensive risk weight of the i-th risk type and the j-th risk factor in the comprehensive risk level distribution matrix, Φ x,i (m k ,τ) is the spatial weight function of the i-th risk factor in the dynamic holographic data model, Ψ i,j (m k ,τ) is the time series weight function, which is used to characterize the characteristics of risk factors changing over time, Δ x,j is the dynamic adjustment parameter associated with risk factor type x, Ω k is the external environment correction term of the kth evaluation point; S42. The dynamic risk assessment model E is combined with the time series and spatial distribution characteristics of the open-pit mine area to generate a risk distribution result R. The risk distribution value of each assessment point in the risk distribution result is calculated as: Among them, r k is the risk distribution value of the evaluation point k, Ω k is the spatial coverage of the evaluation point k, e k is the risk assessment result of the assessment point k, G(α k ,β k ) is the spatial correlation function, which is used to describe the risk propagation effect of the surrounding area of ​​the assessment point, α k and β k is the spatial propagation characteristic parameter, Θ k is the regional weighting factor, which is used to consider the importance of the region where the evaluation point is located, σ k is the random error correction term of the evaluation point, which is used to deal with unpredictable external interference; S43. Classify the risk level of the assessment point according to the risk distribution result R, and generate a hierarchical risk level set L: Among them, l k is the risk level of the kth assessment point in the hierarchical risk level set, C is the total number of risk level categories, Υ c (r k ) is the risk distribution value r k Membership function at risk level c, Γ c It is the threshold coefficient of risk level c, which is used to adjust the strictness of the level classification.

6. The open-pit mine area safety early warning method based on holographic data according to claim 1 is characterized in that: The S5 comprises the following steps: S51. Based on the risk distribution results R generated by the dynamic risk assessment model E and the dynamic holographic data model M, the coronavirus herd immunity optimizer is initialized and the optimized population P is constructed: in, is the state of the i-th individual in the population corresponding to the k-th evaluation point, indicating the spread of the key risk factor at this point, r k is the initial risk distribution value of the evaluation point k, is the weight parameter of individual i, which is used to simulate the influence of risk factors in the transmission process, m k is the holographic data of the evaluation point k in the dynamic holographic data model, S is the population size, indicating the number of individuals in the optimizer, and N is the total number of evaluation points; S52. Simulate the propagation effect of key risk factors in the open-pit mine area in each generation of optimization, and adjust the weight parameters through the virus infection propagation mechanism Calculate the individual states of the next generation population in, is the weight parameter of individual i after optimization, is the risk distribution value of the optimized evaluation point k, ·,· is the spatial correlation propagation function, which describes the propagation effect of risk factors in time and space, η is the dynamic adjustment coefficient of infection propagation, δ is the adjustment coefficient of diffusion effect, α k ,β k ,γ k ,θ k is the spatial propagation parameter associated with the evaluation point k S53. When the optimizer population reaches the preset immune threshold, the optimal solution of the individual state in the population is used to generate the final risk distribution scheme R * : in, is the final risk distribution value of the optimized evaluation point k, which represents the risk distribution result of this point after the coronavirus herd immunity optimization, R * The optimal risk distribution scheme.

7. The open-pit mine area safety early warning method based on holographic data according to claim 1 is characterized in that: The S6 comprises the following steps: S61. Based on the optimal risk distribution scheme and the dynamic holographic data model, the risk distribution value of the assessment point and the regional characteristics are combined to determine the scope of the warning area and mark the key areas with potential safety hazards; S62. Calculate the risk level of each warning area based on the graded risk level and the optimal risk distribution plan, and identify potential influencing factors in the area in combination with the dynamic holographic data model, including key factors in geology, meteorology, equipment and environment; S63. Generate dynamic safety warning information based on the warning area scope, risk level and potential influencing factors. The dynamic safety warning information includes the warning area scope, corresponding risk level, potential influencing factors and recommended emergency measures.

8. The open-pit mine area safety early warning system based on holographic data according to claim 1, implements the open-pit mine area safety early warning method based on holographic data according to claims 1-7, characterized in that: include: The multi-source data acquisition module is used to collect geological displacement data, meteorological condition data, equipment vibration data and environmental monitoring data through geological displacement sensors, meteorological monitoring equipment, equipment vibration sensors and environmental monitoring equipment deployed in the open-pit mine area to build an open-pit mine dynamic data set; The data preprocessing and fusion module is used to perform denoising, data missing completion and normalization on the collected open-pit mine dynamic data set to form a standardized dynamic data set. The standardized data set is integrated with multi-dimensional features through the holographic data fusion algorithm to generate a dynamic holographic data model. The dynamic holographic data model describes the multi-source data status of the open-pit mine area and its time series and spatial distribution characteristics. The risk factor extraction and analysis module is used to extract geological risk factors, meteorological risk factors, equipment risk factors and environmental risk factors based on the dynamic holographic data model, and use the fuzzy logic rule base to fuzzify the key risk factors, build a fuzzy risk factor set, and calculate the potential risk level of each risk factor through fuzzy reasoning to provide input for dynamic risk assessment; Dynamic risk assessment module, which is used to establish a dynamic risk assessment model based on potential risk levels and dynamic holographic data models, assess the potential risks of open-pit mine areas, generate risk distribution results, and classify risk levels to form risk level distribution; The risk distribution optimization module, including the coronavirus herd immunity optimizer, is used to optimize the risk distribution results generated by the dynamic risk assessment model, simulate the diffusion process of key risk factors in the open-pit mine area, and dynamically adjust the distribution weights of risk factors in combination with the dynamic holographic data model to generate the optimal risk distribution plan; Dynamic safety warning generation module, used to generate dynamic safety warning information based on the optimal risk distribution scheme. The dynamic safety warning information includes the warning area range, risk level, potential influencing factors and recommended emergency measures. It provides intuitive and effective warning information by calculating and analyzing the risk distribution characteristics of each area in the dynamic holographic data model; The information output and notification module is used to output dynamic safety warning information through a visualization platform, text messages, voice reminders, etc. It supports displaying the warning area range, risk level and potential influencing factors in the form of distribution maps and reports on the mining area management platform, notifying relevant managers and suggesting specific emergency response measures; The system iterative optimization module is used to iteratively adjust the parameters of the dynamic holographic data model, fuzzy logic rule base and coronavirus herd immunity optimizer based on the emergency response execution effect and feedback information, and continuously optimize the evaluation accuracy and response efficiency of the safety early warning system.

Images