Rock burst intelligent early warning system and method based on multi-data fusion

Abstract

The invention relates to the field of rock burst intelligent early warning, in particular to a rock burst intelligent early warning system and method based on multi-data fusion. The method comprises the steps that multi-source original data are collected and subjected to standardization processing, standardized data and dynamic relevance between sampling points and construction positions are comprehensively analyzed through a spatial weighted multi-source data fusion algorithm, and spatial fusion risk factors of each type of standardized data are generated; fusing the spatial fusion risk factors of each type of standardized data through a multi-source data coupling risk assessment algorithm to generate a coupling risk index; and performing early warning grade division based on the coupling risk index. The problems that a traditional rock burst early warning method depends on single sensor data, and consequently the rock burst prediction result is one-sided are solved; the dynamic distance and direction difference between a sampling point and a construction position are ignored, so that local stress concentration caused by mining disturbance cannot be accurately captured; the nonlinear interaction effect between data cannot be effectively captured, and the early warning precision is limited.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of rock burst intelligent early warning, and in particular to a rock burst intelligent early warning system and method based on multi-data fusion. BACKGROUND

[0002] Rock burst is a common dynamic disaster phenomenon in deep mine exploitation, which is caused by geological stress concentration due to mining activities. When the critical condition is reached, the accumulated energy will be suddenly released, causing severe damage to coal and rock mass and even triggering an earthquake effect. Rock burst not only threatens the safety of mine workers, but also may cause significant economic losses and equipment damage. With the increasing depth of coal resource exploitation in China, the frequency and intensity of rock burst have significantly increased, becoming a key technical problem restricting safe and efficient mining in deep mines.

[0003] However, traditional rock burst early warning methods have the problems of insufficient prediction accuracy of dynamic disasters in deep mines, insufficient adaptability of early warning systems, inefficiency of multi-source data integration and analysis, and neglect of the dynamic impact of mining disturbance. Therefore, it is of great significance to study a rock burst intelligent early warning system based on multi-data fusion, which can realize multi-dimensional and dynamic risk monitoring, overcome the limitations of single monitoring means, and through the application of artificial intelligence and big data technology, automatically learn and adapt to complex geological conditions, improve the intelligent level of early warning, and provide technical support for mine safety production, reducing the risk of rock burst disasters. SUMMARY

[0004] The present application provides a rock burst intelligent early warning system and method based on multi-data fusion to solve the technical problem that traditional rock burst early warning methods rely on single sensor data, cannot comprehensively reflect the synergistic effect of stress, ground sound, microseismic and mine pressure and other factors, leading to one-sided rock burst prediction results, ignoring the dynamic distance and direction difference between sampling points and construction positions, resulting in inability to accurately capture local stress concentration caused by mining disturbance, and traditional linear weighting methods cannot effectively capture the nonlinear interaction effect between data, limiting the early warning accuracy.

[0005] The present application provides a rock burst intelligent early warning system and method based on multi-data fusion, which specifically includes the following technical solutions: A rock burst intelligent early warning method based on multi-data fusion includes the following steps: S1, collect multi-source original data and perform standardization processing to obtain standardized data; through a spatial weighted multi-source data fusion algorithm, comprehensively analyze the standardized data and the dynamic correlation between the sampling points and the construction positions, and generate a spatial fusion risk factor for each type of standardized data; S2. Through a multi-source data coupling risk assessment algorithm, spatial fusion risk factors of each type of standardized data are integrated to generate a coupling risk index; based on the coupling risk index, early warning levels are classified.

[0006] Preferably, S1 specifically includes: In the implementation of the spatial weighted multi-source data fusion algorithm, real-time three-dimensional coordinate information of sampling points and construction locations is collected, and the dynamic distance between sampling points and construction locations is calculated. An exponential decay function is introduced to process the dynamic distance to obtain the exponentially decayed dynamic distance.

[0007] Preferably, S1 specifically includes: In the implementation of the spatially weighted multi-source data fusion algorithm, a directional factor, a correlation factor, and a volatility factor are introduced, and dynamic weights are calculated by combining the dynamic distance after exponential decay.

[0008] Preferably, S1 specifically includes: The direction factor is calculated based on the vector between the sampling point and the construction location and the principal stress direction vector of the mining operation.

[0009] Preferably, S1 specifically includes: Based on dynamic weights, the standardized data of the sampling points are weighted and summed to generate a spatial fusion risk factor for each type of standardized data.

[0010] Preferably, S2 specifically includes: In the implementation of the multi-source data coupling risk assessment algorithm, the spatial fusion risk factor of each type of standardized data is first squared. Then, based on the spatial fusion risk factor of each type of standardized data and a coupling coefficient is introduced, the coupling relationship between different data categories is quantified, and finally the coupling risk index is obtained.

[0011] Preferably, S2 specifically includes: By combining historical coupling risk indices, the coupling risk index is normalized to obtain a normalized coupling risk index. The normalized coupling risk index is then compared with a preset warning threshold, and warning levels are assigned accordingly.

[0012] A smart early warning system for rockburst based on multi-data fusion includes the following components: The system includes a data acquisition module, a data preprocessing module, a multi-data fusion module, a multi-source data coupling risk assessment module, and an early warning decision-making module. Data acquisition module: Real-time acquisition of multi-source raw data from sampling points, and simultaneously, real-time 3D coordinate information of sampling points and construction locations; outputs multi-source raw data to data preprocessing module, and outputs real-time 3D coordinate information of sampling points and construction locations to multi-data fusion module; Data preprocessing module: Standardizes the multi-source raw data collected in real time by the data acquisition module to obtain standardized data; outputs the standardized data to the multi-data fusion module; Multi-data fusion module: Through a spatial weighted multi-source data fusion algorithm, it comprehensively analyzes the standardized data from the data preprocessing module and the real-time three-dimensional coordinate information of the sampling points and construction locations from the data acquisition module to generate spatial fusion risk factors for each type of standardized data; and outputs the spatial fusion risk factors for each type of standardized data to the multi-source data coupling risk assessment module. Multi-source data coupling risk assessment module: Through the multi-source data coupling risk assessment algorithm, spatial fusion risk factors of each type of standardized data from multiple data fusion modules are integrated to generate a coupling risk index; combined with historical coupling risk indices, the coupling risk index is normalized to obtain a normalized coupling risk index; the normalized coupling risk index is output to the early warning decision module; Early warning decision module: compares the normalized coupling risk index from the multi-source data coupling risk assessment module with the preset early warning threshold and classifies the early warning level.

[0013] The beneficial effects of the technical solution of the present invention are: 1. By integrating multiple types of data such as stress, ground sounds, microseismic activity, and mine pressure, the triggering factors of rockbursts are comprehensively captured, overcoming the information limitations of traditional single-data source methods, significantly improving the accuracy and reliability of early warning, and providing more comprehensive data support for mine safety management.

[0014] 2. By introducing dynamic distance and direction factors between sampling points and construction locations, the impact of mining activities on the local stress field is accurately reflected, enhancing the sensitivity to the risk of rockburst caused by mining disturbances and improving the pertinence and timeliness of early warning.

[0015] 3. By adopting a dynamic weight design, combining volatility factors, dynamic distance, direction factors, and correlation factors, the importance of sampling points and data categories is dynamically adjusted, highlighting the contribution of high-risk areas and abnormal data. This enables the intelligent early warning system for rockbursts to identify potential dangerous areas more quickly and optimizes the allocation of prevention and control resources. Attached Figure Description

[0016] Figure 1 This is a structural diagram of an intelligent early warning system for rockburst based on multi-data fusion, as described in this invention. Figure 2 This is a flowchart of an intelligent early warning method for rockburst based on multi-data fusion, as described in this invention. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0019] The following description, in conjunction with the accompanying drawings, details a specific scheme for an intelligent early warning system and method for rockburst based on multi-data fusion provided by the present invention.

[0020] See attached document Figure 1 The diagram illustrates a structural diagram of a smart rockburst early warning system based on multi-data fusion, according to an embodiment of the present invention. The system includes the following components: The system includes a data acquisition module, a data preprocessing module, a multi-data fusion module, a multi-source data coupling risk assessment module, and an early warning decision-making module. Data acquisition module: In key areas of the mine, a multi-sensor network is deployed to collect multi-source raw data from multiple sampling points in real time. At the same time, the real-time three-dimensional coordinate information of the sampling points and construction locations is collected. The multi-source raw data is output to the data preprocessing module, and the real-time three-dimensional coordinate information of the sampling points and construction locations is output to the multi-data fusion module. Data preprocessing module: Standardizes the multi-source raw data collected in real time by the data acquisition module to obtain standardized data; outputs the standardized data to the multi-data fusion module; Multi-data fusion module: Through a spatial weighted multi-source data fusion algorithm, it comprehensively analyzes the standardized data from the data preprocessing module and the real-time three-dimensional coordinate information of the sampling points and construction locations from the data acquisition module to generate spatial fusion risk factors for each type of standardized data; and outputs the spatial fusion risk factors for each type of standardized data to the multi-source data coupling risk assessment module. Multi-source data coupling risk assessment module: Through the multi-source data coupling risk assessment algorithm, it integrates the spatial fusion risk factors of each type of standardized data from multiple data fusion modules to generate a coupling risk index; combined with the statistical characteristics of historical coupling risk indices, it normalizes the coupling risk index to obtain a normalized coupling risk index; and outputs the normalized coupling risk index to the early warning decision module. Early warning decision module: compares the normalized coupling risk index from the multi-source data coupling risk assessment module with the preset early warning threshold and classifies the early warning level.

[0021] See attached document Figure 2 The diagram illustrates a flowchart of an intelligent early warning method for rockburst based on multi-data fusion, according to an embodiment of the present invention. The method includes the following steps: S1. Collect raw data from multiple sources and perform standardization processing to obtain standardized data; through a spatial weighted multi-source data fusion algorithm, comprehensively analyze the standardized data and the dynamic correlation between sampling points and construction locations to generate spatial fusion risk factors for each type of standardized data. In key areas of the mine, including roadways, mining faces, and stress concentration zones, [the following is] arranged: Each sampling point is equipped with multiple sensors to ensure sufficient spatial coverage to capture the heterogeneity of the geological and stress fields. These sensors collect multi-source raw data in real time, including stress, geophony, microseismic activity, and mineral pressure. The Z-score standardization method is used to standardize the multi-source raw data to obtain standardized data; the Z-score standardization method is a well-known technique in the art and will not be described in detail here. By collecting raw data from multiple sources and performing standardized processing, the data quality and analysis accuracy were significantly improved, providing a reliable basis for early warning of rockbursts. By employing a spatially weighted multi-source data fusion algorithm, the standardized data and the dynamic correlation between sampling points and construction locations are comprehensively analyzed to generate spatial fusion risk factors for each type of standardized data. The specific implementation process of the spatially weighted multi-source data fusion algorithm is as follows: First, the dynamic distance from each sampling point to the current construction location is calculated to reflect the spatial proximity of the sampling point to the disturbance source of the mining operation. Specifically, based on the existing 3D model of the mine, the real-time 3D coordinates of each sampling point are obtained. and real-time three-dimensional coordinates of the construction location Furthermore, the straight-line distance between the sampling point and the construction location, i.e., the dynamic distance, is calculated using the Euclidean distance formula to ensure that the disturbance impact of mining activities on the sampling point is accurately reflected. An exponential decay function is introduced to process the dynamic distance to obtain the exponentially decayed dynamic distance, so as to ensure that sampling points with closer dynamic distances can obtain higher weights. Furthermore, the direction factor is calculated to quantify the directional influence of stress transmission. Specifically, based on the vector between the sampling point and the construction location and the principal stress direction vector of the mining operation, the cosine similarity is directly calculated through the vector dot product normalization form to obtain the direction factor. The value of the direction factor ranges from -1 to 1. The absolute value of the direction factor is taken. The larger the value, the closer the sampling point is to the principal stress direction of the mining operation, and the more significant the influence of mining disturbance is. Furthermore, a volatility factor is introduced to measure the degree of abnormal change in the standardized data at the current moment, in order to identify violent fluctuations that may indicate a rockburst. Specifically, by comparing the standardized data at the current moment with the standardized data at the previous moment, the rate of change of the standardized data at each sampling point is calculated as the volatility factor. The time interval is set to 60 seconds to capture short-term dynamic changes. The larger the value of the volatility factor, the higher the degree of abnormality of the standardized data at the current moment, which may be related to the triggering mechanism of rockburst. Furthermore, a correlation factor is introduced to reflect the importance of the standardized data from the sampling points for early warning of rockbursts. The correlation factor is obtained by regression analysis of the historical standardized data from the sampling points and historical rockburst events, with a value ranging from 0 to 1. The larger the value of the correlation factor, the more important the standardized data from the sampling points is for predicting rockbursts. The introduction of the correlation factor ensures that the weight allocation takes into account the characteristics of historical events. The regression analysis method is a well-known technique to those skilled in the art and will not be described in detail here. Furthermore, the dynamic distance, direction factor, correlation factor, and volatility factor after exponential decay are multiplied to obtain dynamic weights. Based on these dynamic weights, the standardized data of the sampling points are weighted and summed to generate a spatial fusion risk factor for each type of standardized data. The calculation formula is as follows: in, Indicates time No. Spatial fusion risk factors for standardized data; This represents the weighted contribution of all sampling points. Indicates the number of sampling points; Indicates time No. The sampling point of the first sampling point Standardized data; Indicates time No. The sampling point of the first sampling point The dynamic weights of the standardized data are calculated using the following formula: in, This means that the dynamic distance is processed using an exponential decay function to ensure that sampling points with smaller dynamic distances receive higher weights; Indicates time No. The straight-line distance between each sampling point and the construction location, i.e. the dynamic distance, is calculated using the Euclidean distance formula, which is a well-known technique to those skilled in the art and will not be elaborated upon here. The angle between the vector between the sampling point and the construction location and the principal stress direction of the mining operation is indicated. The principal stress direction of the mining operation is the main direction of stress transmission in the geological environment, such as the tunnel axis direction. Represents the absolute value of the direction factor; Indicates the direction factor; This represents the correlation factor, i.e., over time. No. The sampling point of the first sampling point Correlation coefficients between standardized data and historical rockburst events; Indicates time No. The sampling point of the first sampling point The volatility factor of the standardized data measures the degree of anomalous change in the standardized data at the current moment. The calculation formula is as follows: , Indicates time No. The sampling point of the first sampling point Standardized data; The time interval is set by the intelligent early warning system for rockbursts. By combining dynamic distance and direction factors, the system accurately captures local stress concentrations caused by mining disturbances, significantly improving the identification accuracy of high-risk areas. At the same time, by introducing volatility and correlation factors, the system can dynamically adjust weights based on real-time data anomalies and historical experience to adapt to different mine geological conditions and mining stages.

[0022] S2. Through a multi-source data coupling risk assessment algorithm, spatial fusion risk factors of each type of standardized data are integrated to generate a coupling risk index; based on the coupling risk index, early warning levels are classified.

[0023] A multi-source data coupling risk assessment algorithm is used to fuse spatial fusion risk factors from each type of standardized data to generate a coupled risk index, which is used to assess the probability of rockburst occurrence. The specific implementation process of the multi-source data coupling risk assessment algorithm is as follows: First, the spatial fusion risk factor of each type of standardized data is squared to amplify the impact of outliers; Then, considering the interaction effect between multiple categories of data, the synergistic effect is captured by calculating the product of the spatial fusion risk factors of the standardized data between all data categories, which reflects the coupling relationship between different data categories, and a coupling coefficient is introduced for each product term to control the strength of the interaction effect. The formula for calculating the coupling risk index is: in, Indicates time The coupling risk index; This represents the sum of the squared contributions from all data categories; This represents the total number of categories for all standardized data. Indicates time The The spatial fusion risk factors of the standardized data are squared. This represents the coupling coefficient, used to control the strength of the interaction effect. It is set based on engineering experience, and its value range is [value range missing]. ; This indicates the summation of all data category interactions to capture the effects of cross-references. Indicates time No. Spatial fusion risk factors for standardized data.

[0024] Based on the statistical characteristics of the historical coupling risk index, the coupling risk index is normalized to obtain the normalized coupling risk index. Specifically, the mean and standard deviation of the historical coupling risk index are calculated. The mean reflects the average level of the coupling risk index, while the standard deviation characterizes the degree of fluctuation of the coupling risk index. The current coupling risk index is subtracted from the mean of the historical coupling risk index, and then divided by the standard deviation of the historical coupling risk index to obtain the normalized coupling risk index. This eliminates the difference in magnitude caused by changes in geological conditions or mining dynamics, making the coupling risk index comparable in different mines or different mining stages. The normalized coupling risk index is compared with the early warning threshold, and the early warning levels are classified. The early warning threshold is set with reference to the statistical characteristics of the standard normal distribution, using low-risk and high-risk thresholds. If the normalized coupling risk index is lower than the low-risk threshold, the current state is determined to be low-risk, and it is recommended to maintain normal mining and conduct routine monitoring. If the normalized coupling risk index is between the low-risk and high-risk thresholds, the state is determined to be medium-risk, and it is recommended to increase the monitoring frequency and take preventive measures, such as releasing local stress through borehole decompression or hydraulic fracturing. If the normalized coupling risk index reaches or exceeds the high-risk threshold, the state is determined to be high-risk, and it is recommended to immediately suspend mining operations and implement emergency prevention and control measures, such as reinforcing roadway support or optimizing the mining sequence to reduce stress concentration.

[0025] In summary, a smart early warning system and method for rockburst based on multi-data fusion has been developed.

[0026] The order of the embodiments is for illustrative purposes only and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0027] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0028] 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 the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for intelligent early warning of rockburst based on multi-data fusion, characterized in that, Includes the following steps: S1. Collect raw data from multiple sources and perform standardization processing to obtain standardized data; through a spatial weighted multi-source data fusion algorithm, comprehensively analyze the standardized data and the dynamic correlation between sampling points and construction locations to generate spatial fusion risk factors for each type of standardized data. S2. By using a multi-source data coupling risk assessment algorithm, spatial fusion risk factors of each type of standardized data are integrated to generate a coupling risk index. Early warning levels are classified based on the coupled risk index.

2. The intelligent early warning method for rockburst based on multi-data fusion according to claim 1, characterized in that, S1 specifically includes: In the implementation of the spatial weighted multi-source data fusion algorithm, real-time three-dimensional coordinate information of sampling points and construction locations is collected, and the dynamic distance between sampling points and construction locations is calculated. An exponential decay function is introduced to process the dynamic distance to obtain the exponentially decayed dynamic distance.

3. The intelligent early warning method for rockburst based on multi-data fusion according to claim 2, characterized in that, S1 specifically includes: In the implementation of the spatially weighted multi-source data fusion algorithm, a directional factor, a correlation factor, and a volatility factor are introduced, and dynamic weights are calculated by combining the dynamic distance after exponential decay.

4. The intelligent early warning method for rockburst based on multi-data fusion according to claim 3, characterized in that, S1 specifically includes: The direction factor is calculated based on the vector between the sampling point and the construction location and the principal stress direction vector of the mining operation.

5. The intelligent early warning method for rockburst based on multi-data fusion according to claim 3, characterized in that, S1 specifically includes: Based on dynamic weights, the standardized data of the sampling points are weighted and summed to generate a spatial fusion risk factor for each type of standardized data.

6. The intelligent early warning method for rockburst based on multi-data fusion according to claim 1, characterized in that, S2 specifically includes: In the implementation of the multi-source data coupling risk assessment algorithm, the spatial fusion risk factor of each type of standardized data is first squared. Then, based on the spatial fusion risk factor of each type of standardized data and a coupling coefficient is introduced, the coupling relationship between different data categories is quantified, and finally the coupling risk index is obtained.

7. The intelligent early warning method for rockburst based on multi-data fusion according to claim 6, characterized in that, S2 specifically includes: By combining historical coupling risk indices, the coupling risk index is normalized to obtain a normalized coupling risk index. The normalized coupling risk index is then compared with a preset warning threshold, and warning levels are assigned accordingly.

8. A rockburst intelligent early warning system based on multi-data fusion, applied to the rockburst intelligent early warning method based on multi-data fusion as described in claim 1, characterized in that, Includes the following parts: The system includes a data acquisition module, a data preprocessing module, a multi-data fusion module, a multi-source data coupling risk assessment module, and an early warning decision-making module. Data acquisition module: Real-time acquisition of multi-source raw data from sampling points, and simultaneously, real-time 3D coordinate information of sampling points and construction locations; outputs multi-source raw data to data preprocessing module, and outputs real-time 3D coordinate information of sampling points and construction locations to multi-data fusion module; Data preprocessing module: Standardizes the multi-source raw data collected in real time by the data acquisition module to obtain standardized data; outputs the standardized data to the multi-data fusion module; Multi-data fusion module: Through a spatial weighted multi-source data fusion algorithm, it comprehensively analyzes the standardized data from the data preprocessing module and the real-time three-dimensional coordinate information of the sampling points and construction locations from the data acquisition module to generate spatial fusion risk factors for each type of standardized data; and outputs the spatial fusion risk factors for each type of standardized data to the multi-source data coupling risk assessment module. Multi-source data coupling risk assessment module: Through the multi-source data coupling risk assessment algorithm, spatial fusion risk factors of each type of standardized data from multiple data fusion modules are integrated to generate a coupling risk index; By combining historical coupling risk indices, the coupling risk index is normalized to obtain the normalized coupling risk index. The normalized coupled risk index is output to the early warning decision module; Early warning decision module: compares the normalized coupling risk index from the multi-source data coupling risk assessment module with the preset early warning threshold and classifies the early warning level.

Images