Coal mine risk early warning system based on big data analysis

Abstract

The invention relates to a coal mine risk early warning system based on big data analysis, and the system comprises a data collection module which is used for collecting data in coal mine operation in real time; the data storage module is configured to store historical data records acquired by the data acquisition module; the data processing module is used for processing the stored data and identifying potential risk factors by adopting a big data analysis technology; the risk evaluation module is used for evaluating the risk levels of coal mine operation according to the analysis result of the data processing module, and the risk levels comprise a low level, a middle level and a high level; and the early warning module is used for sending an early warning signal to related personnel when the risk level reaches a preset threshold value. According to the invention, multi-dimensional data in a coal mine can be collected in real time, and safety risk early warning of a coal mine environment is realized through data processing, analysis and evaluation of the model. The system has the capabilities of efficient data acquisition, accurate risk assessment, timely early warning and emergency response, and effectively improves the safety of coal mine operation.

Description

Technical Field

[0001] The present application relates to the field of coal mine safety management, and specifically, to a coal mine risk early warning system based on big data analysis. Background Art

[0002] The coal mine production process involves a complex underground environment and multiple safety risk factors, including but not limited to gas leakage, fire, equipment failure, and sudden changes in environmental conditions. Traditional coal mine safety monitoring methods often rely on manual inspections and single sensor monitoring, resulting in slow response speed, incomplete coverage of monitoring data, and poor accuracy of the early warning system.

[0003] As the coal mine operating environment becomes increasingly complex, coal mine safety management faces more and more challenges, which are mainly reflected in the following aspects:

[0004] 1. Complex and changeable environmental conditions: The working environment in coal mines is extremely complex and contains many potential safety hazards, such as gas, dust, temperature, humidity, equipment failure, etc. A single sensor can only monitor some of these environmental factors and cannot fully grasp the overall safety status of the mine.

[0005] 2. High real-time requirements: Coal mine accidents often occur very quickly, and multiple risk factors are intertwined. Traditional safety monitoring methods are difficult to provide sufficient real-time data and dynamic responses. For example, accidents such as gas leaks and fires occur very quickly. If they cannot be discovered and warned in the first place, the consequences of the accident may be extremely serious.

[0006] 3. The amount of data is huge and complex: With the expansion of coal mine production, the amount of data in the monitoring system has exploded. How to effectively extract valuable safety information from massive data and conduct a comprehensive analysis of multiple risk factors has become a huge challenge.

[0007] In recent years, the application of big data analysis technology in various industries has gradually matured. Through the real-time collection, analysis and processing of massive data, big data technology can effectively improve the intelligence and accuracy of the system. In the coal mining industry, the application of big data analysis technology has begun to gradually penetrate, especially in the field of coal mine safety monitoring. Some companies have tried to combine big data analysis with safety early warning systems to carry out coal mine risk management.

[0008] However, the current coal mine risk early warning system based on big data technology still faces some technical and implementation challenges, including:

[0009] 1. Insufficient data processing capabilities: Although a large number of sensors have been deployed in coal mines and rich data has been collected, how to process and analyze these massive amounts of data remains a challenge. Some existing systems have limited processing capabilities and it is difficult to conduct efficient data analysis in real time.

[0010] 2. Risk assessment models are not accurate enough: Existing risk assessment models mostly rely on simple threshold settings or assessments based on a single indicator, and fail to fully consider the combined effects of various risk factors in the mine environment. Therefore, the early warning accuracy and sensitivity are often low, and cannot effectively respond to complex and changing safety environments.

[0011] 3. Low system integration: Different monitoring equipment and data analysis modules often operate independently. There is a lack of a unified data platform and comprehensive risk assessment system, which leads to serious information island problems and affects the overall real-time and accuracy of the system.

[0012] Therefore, there is an urgent need for an intelligent, accurate and real-time coal mine safety risk early warning system to ensure the safety of coal mine operations. Summary of the invention

[0013] The purpose of this application is to provide a coal mine risk early warning system based on big data analysis, which can collect multi-dimensional data in coal mines in real time, and realize safety risk early warning of coal mine environment through data processing, analysis and evaluation models. The system has efficient data collection, accurate risk assessment, timely early warning and emergency response capabilities, effectively improving the safety of coal mine operations.

[0014] In order to solve the above technical problems, the technical solution provided by this application is: a coal mine risk early warning system based on big data analysis, comprising:

[0015] The data acquisition module is used to collect data from coal mine operations in real time, including gas concentration C m , temperature T, humidity H and equipment status, where the gas concentration includes methane concentration, and its calculation formula is:

[0016]

[0017] Where Vg is the volume of methane and Vt is the total gas volume;

[0018] a data storage module, configured to store at least 1000 historical data records collected by the data collection module;

[0019] The data processing module uses big data analysis technology to process the stored data and identify potential risk factors. The analysis includes the following calculations: Risk score calculation formula:

[0020] R=w1·Cm +w2·T+w3·H+w4·S

[0021] Where R is the risk score, S is the equipment status score, S is 0 or 1; w1, w2, w3, and w4 are the weight coefficients of gas concentration, temperature, humidity, and equipment status, respectively, where 0 <w i <1, and w1+w2+w3+w4=1;

[0022] The risk assessment module assesses the risk level of coal mine operation according to the analysis results of the data processing module, including three levels: low, medium and high. The risk level is determined by the following formula: Risk level L:

[0023]

[0024] The early warning module sends an early warning signal to at least three relevant personnel when the risk level reaches a preset threshold. The early warning signal generation formula is:

[0025]

[0026] Where P is the warning level.

[0027] Furthermore, the risk assessment module is based on a fuzzy logic algorithm to evaluate the gas concentration C m , temperature T and the equipment status S expressed in numerical values ​​are comprehensively evaluated to generate the risk score calculation formula:

[0028] R f =a·C m +b·T+c·S+d

[0029] Where R f is the fuzzy risk score, a, b, c, d are the corresponding weight coefficients and constant terms.

[0030] Furthermore, the risk assessment module further includes a time series analysis unit, which performs time series prediction on the data collected by the sensor based on the historical data and real-time data of the coal mine, so as to predict the future risk change trend and generate early warning.

[0031] Furthermore, the early warning module includes an audible and visual alarm device and a mobile terminal notification function, which notifies the on-site staff within 5 seconds. The time delay D of the early warning notification is calculated as follows:

[0032]

[0033] where t i is the response time of each notification, and N is the number of notifications.

[0034] Furthermore, the early warning module further includes a voice prompt unit. When the risk level reaches medium or high, the voice prompt unit broadcasts detailed safety prompt information through a loudspeaker to guide coal mine workers to take corresponding emergency measures.

[0035] Furthermore, the data acquisition module includes at least 10 sensors for real-time monitoring of the coal mine environment and equipment status.

[0036] Furthermore, the machine learning algorithm adopted by the data processing module is a random forest algorithm. The data processing module dynamically adjusts the weight coefficient of the model according to the collected historical data to optimize the precision and accuracy of risk assessment.

[0037] Furthermore, the data acquisition module is used to access external devices and share data with existing monitoring equipment in the coal mine through a wireless network.

[0038] Furthermore, the data storage module uses cloud storage technology to support remote access to data and supports a maximum data storage capacity of 10TB.

[0039] Furthermore, it also includes a user interface module for displaying various coal mine data, risk assessment results and early warning information in real time, and the interface is updated once per second.

[0040] The application has the following advantages: The application is applicable to the safety management of various coal mining enterprises, especially to the safety monitoring and risk warning of medium and large coal mines. The system can be applied in a variety of mining environments, including deep mines, low-oxygen mines and mines with high gas content.

[0041] 1. Real-time monitoring and comprehensive data collection: Through the joint application of multiple sensors, the system can comprehensively monitor multiple risk factors in the coal mine environment to ensure the comprehensiveness and real-time nature of the data.

[0042] 2. Efficient analysis and accurate early warning: Combined with big data analysis technology, the system can accurately assess the risks in coal mine operations and provide precise early warnings based on data analysis, avoiding the lag of traditional manual monitoring.

[0043] 3. Intelligent response and automated management: The system not only provides early warning functions, but also has an emergency response module, which automatically activates the emergency mechanism when risks occur, quickly responds to changes in the coal mine environment, and ensures personnel safety.

[0044] 4. Flexible expansion and strong adaptability: The coal mine risk early warning system of the present invention can flexibly configure sensors and analysis models according to the needs of different coal mines, and has strong adaptability and scalability. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1is a system block diagram according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The present application is further described in detail below in conjunction with embodiments.

[0047] This embodiment provides a specific implementation scheme of a coal mine risk early warning system based on big data analysis. The system can monitor coal mine environmental data in real time and conduct risk assessment, and issue early warning signals in a timely manner to ensure the safe operation of the coal mine.

[0048] Example 1: System architecture

[0049] The coal mine risk early warning system is mainly composed of the following modules:

[0050] 1. Data acquisition module:

[0051] The module consists of at least 10 sensors, which are used to monitor parameters such as methane concentration, temperature, humidity and equipment status in the coal mine. Each sensor is equipped with a corresponding data acquisition unit, which transmits the collected data to the data storage module in real time through a wireless network.

[0052] The methane sensor can measure the methane concentration C in real time. m (0-5%), and transmit the data to the system at a frequency of once per second.

[0053] The data acquisition module further includes an ambient light sensor for monitoring the light intensity inside the coal mine, and the data collected is used to calculate the impact of environmental factors on the safety of coal mine operations, and is used for risk assessment together with other monitoring data through the data processing module. The data acquisition module can access external devices and share data with existing monitoring equipment in the coal mine through a wireless network, so that the system can comprehensively consider the monitoring data of different equipment, working conditions and external environment in the coal mine, further improving the comprehensiveness and accuracy of risk assessment.

[0054] 2. Data storage module:

[0055] This module uses cloud storage technology and supports at least 10TB of data storage capacity. It can store historical data records from the data acquisition module, including at least 1,000 records. These data can be used for subsequent analysis and model training.

[0056] The stored data includes the sensor's timestamp, various monitoring data (including C m , T, H), and equipment status (operating or faulty).

[0057] 3. Data processing module:

[0058] The data processing module is responsible for analyzing the stored data using big data analysis techniques, including machine learning and statistical analysis.

[0059] The machine learning algorithm used in the data processing module is the random forest algorithm, and the module can dynamically adjust the weight coefficient of the model based on the collected historical data to optimize the precision and accuracy of risk assessment.

[0060] The machine learning algorithms used include support vector machines, decision trees, and neural networks. The data processing module will train at least 2,000 historical data samples to generate a risk identification model.

[0061] The calculation formula of risk score RR is as follows:

[0062] R=w1·C m +w2·T+w3·H+w4·S

[0063] Among them, w1, w2, w3, and w4 are the weights of the corresponding parameters, which are adjusted through the optimization algorithm to improve the accuracy of risk identification.

[0064] 4. Risk Assessment Module:

[0065] Based on the analysis results of the data processing module, the risk assessment module will classify the risks into the following levels:

[0066]

[0067] The module generates a risk level based on each assessment and stores historical assessment results for subsequent inquiries.

[0068] The risk assessment module further includes a time series analysis unit, which performs time series prediction on the data collected by the sensors based on the historical data and real-time data of the coal mine, so as to predict the future trend of risk changes and generate early warnings.

[0069] 5. Early warning module:

[0070] When the risk level reaches medium or high, the early warning module will sound an alarm and notify at least 3 relevant personnel. The early warning signal generation formula is:

[0071]

[0072] The module includes an audible and visual alarm device that can notify on-site staff of alarm information through a mobile application within 5 seconds.

[0073] The early warning module further includes a voice prompt unit, which can broadcast detailed safety prompt information through a speaker to guide coal mine workers to take appropriate emergency measures when the risk level reaches medium or high.

[0074] Example 2: System architecture and parameters

[0075] Data acquisition module:

[0076] The methane concentration C m The range is 0-5%, the temperature T range is -10℃ to +40℃, the humidity H range is 20%-90%, and the equipment status includes operation and failure.

[0077] 1. Sensor configuration:

[0078] Methane sensor: Equipped with 10 methane sensors, the monitoring range is 0-5%. Its sensitivity is 0.1% and its accuracy is ±0.05%. Each sensor transmits data at a frequency of 1 second.

[0079] Temperature sensor: Equipped with 5 temperature sensors, the operating temperature range is -10℃ to +40℃, the sensitivity is 0.5℃, and the accuracy is ±0.2℃.

[0080] Humidity sensor: Equipped with 5 humidity sensors, the working range is 20%-90%RH, the sensitivity is 1%RH, and the accuracy is ±2%RH.

[0081] Equipment status monitoring: Three status sensors are used to monitor the operation of the equipment (normal / fault).

[0082] 2. Data storage module:

[0083] Using cloud storage technology, it supports at least 10TB of data storage. The system can store approximately 100,000 data records per day and can save at least 5 years of historical data.

[0084] 3. Data processing module:

[0085] Support vector machine (SVM) is used to train the risk identification model, and the training sample is at least 2000 historical data records.

[0086] The risk score calculation formula is:

[0087] R=0.4·C m +0.3·T+0.2·H+0.1·S

[0088] Among them, C m is the methane concentration, T is the temperature (unit: °C), H is the humidity (unit: %), and S is the equipment status (normal is 1, fault is 0).

[0089] 4. Risk Assessment Module:

[0090] The risk levels are as follows:

[0091]

[0092] 5. Early warning module:

[0093] When the risk level L reaches medium or high, the sound and light alarm device will sound an alarm. At the same time, the early warning information will notify three designated staff members through the mobile application.

[0094] The early warning signal generation formula is:

[0095]

[0096] 6. Operation process

[0097] Data collection: During the operation of the coal mine, each sensor monitors and collects data in real time, and the data collection module transmits the monitored data to the data storage module every second.

[0098] Data analysis: The data storage module stores the received data in time series, and the data processing module periodically calls the stored data for analysis and processing to calculate the risk score R.

[0099] Risk assessment: The data processing module calculates the risk score based on the preset formula and historical data, and passes the score result to the risk assessment module to evaluate the current risk level L.

[0100] Warning notification: When the risk level L is medium or high, the warning module will automatically sound an audible and visual alarm and notify relevant personnel of the warning information through the mobile application to ensure that they can take prompt response measures.

[0101] Specifically, (1) Data collection: sensors monitor data in real time in coal mines. At a certain moment, the methane concentration C m The measured value is 1.2%, the temperature T is 25℃, and the humidity H is 45%. The sensor updates once a second and sends the data to the cloud storage module.

[0102] Data storage: The data storage module receives sensor data and stores it with a timestamp. The two records received are:

[0103] C m =1.2%, T=25℃, H=45%;

[0104] C m =1.3%, T=25.5℃, H=44%.

[0105] The system accumulates a large amount of data every day for subsequent analysis.

[0106] (2) Data analysis: The data processing module regularly analyzes historical data and calculates risk scores.

[0107] R=0.4*1.2+0.3*25+0.2*45+0.1*1=0.48+7.5+9+0.1=17.08

[0108] Determine the current risk level based on the risk score:

[0109] R=17.08R=17.08 corresponds to risk level L=low.

[0110] (3) Risk assessment:

[0111] As time goes by, assume that the measurement data at the next moment is updated to C m =2.5%, T=30℃, H=50%.

[0112] R=0.4*2.5+0.3*30+0.2*50+0.1*1=1+9+10+0.1=20.1

[0113] At this time, the risk level is still low and the system continues to monitor.

[0114] (4) Warning Notice:

[0115] At one point, the methane concentration rose sharply to 4.5% (C m =4.5%, T=32℃, H=55%):

[0116] R=0.4*4.5+0.3*32+0.2*55+0.1*1=1.8+9.6+11+0.1=22.5

[0117] After continued monitoring, if C m Reach 5.0% (ie R exceeds 30), calculated as:

[0118] R=0.4*5.0+0.3*32+0.2*55+0.1*0=2+9.6+11+0=22.6

[0119] When R reaches 70 or above (such as C m =5.2%), triggering an early warning and notifying staff.

[0120] Response measures: The early warning module immediately sounds an audible and visual alarm and sends notifications to three staff members through the mobile application, ensuring that they quickly take necessary safety measures, such as evacuating the scene or initiating an emergency response.

[0121] This implementation method introduces specific parameters and describes in detail the workflow of the coal mine risk early warning system, which can effectively monitor changes in the coal mine environment and issue early warnings in a timely manner, thereby ensuring the safety of coal mine operations to the greatest extent and reducing the risk of accidents. The real-time and intelligent analysis capabilities of the system give it significant safety management advantages in practical applications.

[0122] This embodiment section describes the system architecture, operation process and advantages in detail to ensure that the implementation of the invention is fully understood and explained. Specific technical details and parameters can be adjusted and supplemented according to actual applications.

[0123] Although the present invention has been shown and described primarily with reference to certain embodiments, it will be appreciated by those skilled in the art that numerous changes may be made thereto in terms of construction scheme and details, etc., without departing from the scope of protection defined by the claims. Thus, the scope of protection of the present invention is determined by the claims and includes all changes that fall within the meaning or equivalent scope of the claims.

Claims

1. A coal mine risk early warning system based on big data analysis, characterized in that: include: The data acquisition module is used to collect data from coal mine operations in real time, including gas concentration C m , temperature T, humidity H and equipment status, where the gas concentration includes methane concentration, and its calculation formula is: Where Vg is the volume of methane and Vt is the total gas volume; a data storage module, configured to store at least 1000 historical data records collected by the data collection module; The data processing module uses big data analysis technology to process the stored data and identify potential risk factors. The analysis includes the following calculations: Risk score calculation formula: R=w1·C m +w2·T+w3·H+w4·S Where R is the risk score, S is the equipment status score, S is 0 or 1; w1, w2, w3, and w4 are the weight coefficients of gas concentration, temperature, humidity, and equipment status, respectively, where 0 <w i <1, and w1+w2+w3+w4=1; The risk assessment module assesses the risk level of coal mine operation according to the analysis results of the data processing module, including three levels: low, medium and high. The risk level is determined by the following formula: Risk level L: The early warning module sends an early warning signal to at least three relevant personnel when the risk level reaches a preset threshold. The early warning signal generation formula is: Where P is the warning level.

2. A coal mine risk early warning system based on big data analysis according to claim 1, characterized in that: The risk assessment module is based on fuzzy logic algorithm to evaluate the gas concentration C m , temperature T and the equipment status S expressed in numerical values ​​are comprehensively evaluated to generate the risk score calculation formula: R f =a·C m +b·T+c·S+d Where R f is the fuzzy risk score, a, b, c, d are the corresponding weight coefficients and constant terms.

3. A coal mine risk early warning system based on big data analysis according to claim 2, characterized in that: The risk assessment module further includes a time series analysis unit, which performs time series prediction on the data collected by the sensor based on the historical data and real-time data of the coal mine, so as to predict the future risk change trend and generate early warning.

4. The coal mine risk early warning system based on big data analysis according to claim 1 is characterized by: The early warning module includes an audible and visual alarm device and a mobile terminal notification function, which notifies the on-site staff within 5 seconds. The calculation formula for the time delay D of the early warning notification is: where t i is the response time of each notification, and N is the number of notifications.

5. A coal mine risk early warning system based on big data analysis according to claim 4, characterized in that: The early warning module further includes a voice prompt unit. When the risk level reaches medium or high, the voice prompt unit broadcasts detailed safety prompt information through a loudspeaker to guide coal mine workers to take corresponding emergency measures.

6. The coal mine risk early warning system based on big data analysis according to claim 1 is characterized by: The data acquisition module includes at least 10 sensors for real-time monitoring of the coal mine environment and equipment status.

7. The coal mine risk early warning system based on big data analysis according to claim 1 is characterized by: The machine learning algorithm adopted by the data processing module is the random forest algorithm. The data processing module dynamically adjusts the weight coefficient of the model according to the collected historical data to optimize the precision and accuracy of risk assessment.

8. The coal mine risk early warning system based on big data analysis according to claim 1 is characterized by: The data acquisition module is used to access external equipment and share data with existing monitoring equipment in the coal mine through a wireless network.

9. The coal mine risk early warning system based on big data analysis according to claim 1 is characterized by: The data storage module uses cloud storage technology to support remote access to data and supports a maximum data storage capacity of 10TB.

10. The coal mine risk early warning system based on big data analysis according to claim 1, characterized in that: It also includes a user interface module, which is used to display various coal mine data, risk assessment results and early warning information in real time. The interface is updated once per second.

Images