Coal mine risk early warning system based on big data analytics

Abstract

A coal mine risk early warning system based on big data analytics, the coal mine risk early warning system comprising: a data collection module, used for collecting data in real time during coal mine operation; a data storage module, configured to store historical data records collected by the data collection module; a data processing module, which uses big data analytics technology to process the stored data and identify potential risk factors; a risk assessment module, which assesses the risk level of coal mine operation on the basis of analysis results of the data processing module, there being three risk levels: low, medium, and high; and an early warning module, which sends an early warning signal to relevant personnel when the risk level reaches a preset threshold.

Description

A coal mine risk early warning system based on big data analysis TECHNICAL FIELD

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

[0002] The production process of coal mine involves complex underground environment and various 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 inspection and single sensor monitoring, resulting in slow response, incomplete monitoring data coverage, and poor accuracy of early warning systems.

[0003] With the increasing complexity of coal mine operating environment, the safety management of coal mines is facing more and more challenges, mainly reflected in the following aspects:

[0004] 1. Complex and variable environmental conditions: The underground working environment of 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 a part of the 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 various risk factors are intertwined. Traditional safety monitoring methods are difficult to provide sufficient real-time data and dynamic response. For example, gas leakage, fire, and other accidents occur extremely quickly, and if they cannot be discovered and warned in the first time, the consequences may be extremely serious.

[0006] 3. Large and complex data volume: With the expansion of coal mine production scale, the data volume of the monitoring system shows explosive growth. How to effectively extract valuable safety information from massive data and conduct comprehensive analysis of various risk factors has become a great challenge.

[0007] In recent years, big data analysis technology has gradually matured in various industries. Through 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 industry, the application of big data analysis technology has begun to penetrate, especially in the field of coal mine safety monitoring, some enterprises 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 capacity: Despite the deployment of a large number of sensors in coal mines, collecting rich data, how to process and analyze these massive data remains a problem. Some existing systems have limited processing capacity and are difficult to perform efficient data analysis in real time.

[0010] 2. Inaccurate risk assessment model: Existing risk assessment models rely on simple threshold settings or assessment based on a single indicator, failing to fully consider the combined effects of various risk factors in the mine environment. Therefore, the warning accuracy and sensitivity are often low, and the complex and variable safety environment cannot be effectively responded to.

[0011] 3. Low system integration: Different monitoring devices and data analysis modules often operate independently, lack a unified data platform and comprehensive risk assessment system, resulting in a serious information island problem, affecting the real-time and accuracy of the system as a whole.

[0012] Therefore, an intelligent, accurate and real-time coal mine safety risk warning system is urgently needed to ensure the safety of coal mine operations. SUMMARY

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

[0014] To solve the above technical problems, the technical scheme provided by the present application is: a coal mine risk warning system based on big data analysis, comprising:

[0015] A data acquisition module for acquiring data in real time during coal mine operation, the data including gas concentration C m , temperature T, humidity H and equipment status, wherein the gas concentration includes methane concentration, and the calculation formula is:

[0016] wherein Vg is the volume of methane, and Vt is the total gas volume;

[0017] A data storage module configured to store at least 1000 historical data records collected by the data acquisition module;

[0018] A data processing module using big data analysis technology to process stored data and identify potential risk factors, the analysis including the following calculations: risk score calculation formula: R = w1·C m +w2·T+w3·H+w4·S

[0019] wherein R is the risk score, S is the device status score, S takes the value of 0 or 1; w1, w2, w3, w4 are the weight coefficients of the gas concentration, temperature, humidity and device status respectively, wherein 0 < w1, w2, w3, w4 < 1, and w1 + w2 + w3 + w4 = 1. i <1, and w1 + w2 + w3 + w4 = 1.

[0020] a risk assessment module, according to the analysis result of the data processing module, assesses the risk level of the coal mine operation, including low, medium and high three levels, wherein the risk level is determined by the following formula, risk level L:

[0021] a warning module, when the risk level reaches a preset threshold, sends a warning signal to at least 3 related personnel, and the warning signal generation formula is:

[0022] wherein P is the warning level.

[0023] Further, wherein the risk assessment module based on fuzzy logic algorithm, gas concentration C m , temperature T and device status S represented by a numerical value are comprehensively evaluated, and the calculation formula of the risk score is: R f = a·C m +b·T+c·S+d

[0024] wherein R f is the fuzzy risk score, a, b, c, d are the corresponding weight coefficients and constant terms.

[0025] Further, the risk assessment module further comprises 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, to predict the future risk change trend and generate a warning in advance.

[0026] Further, wherein the warning module comprises an audible and visual alarm device and a mobile terminal notification function, which notifies the on-site staff within 5 seconds, and the time delay D of the warning notification is calculated by the formula:

[0027] wherein t i is the response time of each notification, and N is the number of notifications.

[0028] Further, the warning module further comprises 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 the coal mine staff to take corresponding emergency measures.

[0029] Further, wherein the data acquisition module comprises at least 10 sensors for real-time monitoring of the coal mine environment and device status.

[0030] Further, the machine learning algorithm adopted by the data processing module is a random forest algorithm, and the data processing module dynamically adjusts the weight coefficient of the model according to the collected historical data, thereby optimizing the accuracy and precision of risk assessment.

[0031] Further, the data acquisition module is used to access external devices and share data with existing monitoring devices in coal mines through wireless networks.

[0032] Further, the data storage module uses cloud storage technology to support remote access of data, and supports a data storage capacity of up to 10 TB.

[0033] Further, the user interface module is further included for real-time display of coal mine data, risk assessment results and early warning information, and the interface update frequency is once per second.

[0034] The present application has the following advantages: The present application is suitable for safety management of various coal mine enterprises, and is particularly suitable for safety monitoring and risk early warning of medium and large coal mines. The system can be applied in various mine environments, including deep mines, low-oxygen mines and mines with high gas content.

[0035] 1. Real-time monitoring and comprehensive data acquisition: Through the joint application of multiple sensors, the system can comprehensively monitor multiple risk factors in the coal mine environment, ensuring the comprehensiveness and real-time nature of the data.

[0036] 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 accurate early warning based on data analysis, avoiding the lag of traditional manual monitoring.

[0037] 3. Intelligent response and automated management: The system not only provides early warning functions, but also has an emergency response module that automatically starts the emergency mechanism when risks occur, quickly responds to changes in the coal mine environment, and ensures personnel safety.

[0038] 4. Flexible expansion and strong adaptability: The coal mine risk early warning system of the present application can flexibly configure sensors and analysis models according to the needs of different coal mines, and has strong adaptability and expandability. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 is a system block diagram according to an embodiment of the present application. DETAILED DESCRIPTION

[0040] The present application will be further described in detail below in conjunction with the embodiments.

[0041] The 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 timely issue warning signals to ensure the safe operation of coal mines.

[0042] Embodiment 1: System architecture

[0043] The coal mine risk early warning system mainly consists of the following modules:

[0044] 1. Data acquisition module:

[0045] The module is composed of at least 10 sensors for monitoring 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.

[0046] The methane sensor can measure the methane concentration C m (0-5%) in real time and transmit the data to the system at a frequency of once per second.

[0047] The data acquisition module further includes an ambient light sensor for monitoring the light intensity inside the coal mine. The data collected by the ambient light sensor is used to calculate the impact of environmental factors on the safety of coal mine operations, and is processed by the data processing module together with other monitoring data for risk assessment. The data acquisition module can access external devices and share data with existing monitoring devices 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.

[0048] 2. Data storage module:

[0049] The module uses cloud storage technology and supports at least 10TB of data storage capacity, which can store historical data records from the data acquisition module, including at least 1000 records. These data can be used for subsequent analysis and model training.

[0050] The stored data includes the timestamp of the sensor, various monitoring data (including C m , T, H), and equipment status (running or failure).

[0051] 3. Data processing module:

[0052] The data processing module is responsible for analyzing the stored data, using big data analysis techniques including machine learning and statistical analysis.

[0053] The machine learning algorithm used by the data processing module is a random forest algorithm, and the module can dynamically adjust the weight coefficients of the model based on the collected historical data to optimize the accuracy and precision of risk assessment.

[0054] The machine learning algorithm used includes support vector machine, decision tree and neural network, etc. The data processing module will train at least 2000 historical data samples to generate a risk identification model.

[0055] The calculation formula of risk score RR is as follows: R = w1·C m +w2·T+w3·H+w4·S

[0056] Where w1, w2, w3, w4 are the weights of the corresponding parameters, which are adjusted by optimization algorithm to improve the accuracy of risk identification.

[0057] 4. Risk assessment module:

[0058] According to the analysis results of the data processing module, the risk assessment module will be divided into the following risk levels:

[0059] The module will generate a risk level for each assessment and store the historical assessment results for subsequent queries.

[0060] The risk assessment module further includes a time series analysis unit, which is based on historical data and real-time data of coal mines, and performs time series prediction on the data collected by the sensor to predict the future risk trend and generate early warning in advance.

[0061] 5. Warning module:

[0062] When the risk level reaches the medium or high level, the warning module will issue an alarm to notify at least 3 relevant personnel. The warning signal generation formula is:

[0063] The module includes a sound and light alarm device, which can notify the on-site workers through the mobile terminal application program within 5 seconds.

[0064] The warning module further includes a voice prompt unit, which can broadcast detailed safety prompt information through the loudspeaker when the risk level reaches medium or high, guiding the coal mine workers to take appropriate emergency measures.

[0065] Example 2: System architecture and parameters

[0066] Data acquisition module:

[0067] Where the methane concentration C m ranges from 0-5%, the temperature T ranges from -10℃ to +40℃, the humidity H ranges from 20%-90%, and the equipment status includes running and failure.

[0068] 1. Sensor configuration:

[0069] 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.

[0070] Temperature sensors: Equipped with 5 temperature sensors, with an operating temperature range of -10℃ to +40℃, a sensitivity of 0.5℃, and an accuracy of ±0.2℃.

[0071] Humidity sensor: Equipped with 5 humidity sensors, with an operating range of 20%-90%RH, a sensitivity of 1%RH, and an accuracy of ±2%RH.

[0072] Equipment status monitoring: Three status sensors are used to monitor the operation of the equipment (normal / faulty).

[0073] 2. Data storage module:

[0074] Utilizing cloud storage technology, it supports data storage of at least 10TB. The system can store approximately 100,000 data records per day and retain at least 5 years of historical data.

[0075] 3. Data Processing Module:

[0076] The risk identification model is trained using a support vector machine (SVM), with at least 2,000 historical data records as training samples.

[0077] The risk score calculation formula is: R = 0.4·C m +0.3·T+0.2·H+0.1·S

[0078] Among them, C m T is the methane concentration, H is the temperature (°C), S is the humidity (%), and S is the equipment status (1 for normal and 0 for fault).

[0079] 4. Risk Assessment Module:

[0080] The risk levels are classified as follows:

[0081] 5. Early warning module:

[0082] When the risk level L reaches medium or high, the audible and visual alarm device will sound an alarm, and at the same time, the warning information will be notified to three designated staff members via a mobile application.

[0083] The formula for generating the warning signal is:

[0084] 6. Operation Process

[0085] Data Collection: During the operation of the coal mine, each sensor monitors and collects data in real time. The data collection module transmits the monitored data to the data storage module every second.

[0086] Data Analysis: The data storage module stores the received data in chronological order. The data processing module periodically calls the stored data for analysis and processing, calculating the risk score R.

[0087] Risk Assessment: The data processing module calculates the risk score based on the preset formula and historical data, and transmits the score result to the risk assessment module to assess the current risk level L.

[0088] Early Warning Notification: When the risk level L is medium or high, the warning module will automatically issue an audible and visual alarm, and notify relevant personnel through the mobile application to ensure that they can take prompt measures.

[0089] Specifically, (1) Data Collection: Sensors monitor data in real time within the coal mine. At a certain time, the methane concentration C m measured is 1.2%, the temperature T is 25°C, and the humidity H is 45%. The sensor updates every second and sends the data to the cloud storage module.

[0090] Data Storage: The data storage module receives sensor data and stores it in timestamp format. The two received records are: C m = 1.2%, T = 25°C, H = 45%; C m = 1.3%, T = 25.5°C, H = 44%.

[0091] The system accumulates a large amount of data every day for subsequent analysis.

[0092] (2) Data Analysis: The data processing module periodically analyzes historical data and calculates the risk score. R = 0.4 * 1.2 + 0.3 * 25 + 0.2 * 45 + 0.1 * 1 = 0.48 + 7.5 + 9 + 0.1 = 17.08

[0093] According to the risk score, the current risk level is determined: R = 17.08 R = 17.08 corresponds to the risk level L = low.

[0094] (3) Risk Assessment:

[0095] Over time, assume that the next time the measurement data is updated to C m = 2.5%, T = 30°C, H = 50%. R = 0.4 * 2.5 + 0.3 * 30 + 0.2 * 50 + 0.1 * 1 = 1 + 9 + 10 + 0.1 = 20.1

[0096] At this time, the risk level is still low, and the system continues to monitor.

[0097] (4) Early warning notification:

[0098] At a certain moment, the methane concentration sharply rises to 4.5% (C m = 4.5%, T = 32°C, H = 55%): R = 0.4*4.5 + 0.3*32 + 0.2*55 + 0.1*1 = 1.8 + 9.6 + 11 + 0.1 = 22.5

[0099] After continuous monitoring, if C m reaches 5.0% (i.e. R exceeds 30), the calculation is: R = 0.4*5.0 + 0.3*32 + 0.2*55 + 0.1*0 = 2 + 9.6 + 11 + 0 = 22.6

[0100] When R reaches 70 or above (e.g. C m = 5.2%), an early warning is triggered, notifying the staff.

[0101] Response measures: The early warning module immediately issues an audible and visual alarm, and sends notifications to 3 staff members through a mobile application, ensuring they promptly take necessary safety measures such as evacuating the site or initiating emergency response.

[0102] This embodiment details the working process of the coal mine risk early warning system by introducing specific parameters, effectively monitoring changes in the coal mine environment and issuing timely warnings to maximize safety in coal mine operations and reduce the risk of accidents. The real-time and intelligent analysis capabilities of the system make it a significant advantage in safety management in practical applications.

[0103] This example partially describes the system's architecture, operation process, and advantages, ensuring a full understanding and description of the invention. Specific technical details and parameters can be adjusted and supplemented according to actual applications.

[0104] Although the invention has been shown and described with reference to specific embodiments, it will be understood by those skilled in the art that numerous changes in form and detail can be made without departing from the scope of the invention as defined by the claims. Therefore, the scope of protection of the invention is determined by the claims, and includes all changes falling within the meaning or equivalent range of the claims.

Claims

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

2. The coal mine risk early warning system based on big data analysis according to claim 1, characterized in that: Wherein the risk assessment module is based on fuzzy logic algorithm, the gas concentration C m , temperature T and the device state S are comprehensively evaluated, and the calculation formula of the risk score is: 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. The 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 that performs time series prediction on the data collected by the sensors based on historical coal mine data and real-time data to predict future risk trends and generate early warnings.

4. The coal mine risk early warning system based on big data analysis according to claim 1, characterized in that: The pre-warning module comprises an acousto-optic alarm device and a mobile terminal notification function, and notifies the on-site staff within 5 seconds; the time delay D of the pre-warning notification is calculated according to the following formula: where t i is the response time for each notification, and N is the number of notifications.

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

6. The coal mine risk early warning system based on big data analysis according to claim 1, characterized in that: Wherein the data acquisition module includes at least 10 sensors that monitor the coal mine environment and equipment status in real time.

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

8. The coal mine risk early warning system based on big data analysis according to claim 1, characterized in that: The data acquisition module is used to access external devices and share data with existing monitoring devices in the coal mine through a wireless network. 9.The coal mine risk early warning system based on big data analysis of claim 1, wherein: Wherein the data storage module uses cloud storage technology to support remote access of data, with 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 for real-time display of coal mine data, risk assessment results and warning information, with an interface update frequency of once per second.

Images