Description:IoT AND AI-BASED COAL MINE RISK PREDICTION SYSTEM AND METHOD THEREOF
BACKGROUND
Technical Field
[0001] The embodiment herein generally relates to a coal mine risk prediction system and more particularly, to an Internet of Things (IoT) and Artificial intelligences (AI)-based coal mine risk prediction system and method thereof.
Description of the Related Art
[0002] Due to unstable geological conditions, exposure to poisonous gases, dust collection, and unexpected mechanical breakdowns, coal mining is one of the most dangerous industries in the world. Coal mine accidents continue to cause injuries, fatalities, and operational disruptions in spite of safety laws and technical improvements. The main issue is that these catastrophes are unpredictable, which makes it hard for mine operators to take prompt preventive action.
[0003] Unstable Geological Conditions and Structural Hazards: Because of unstable rock formations, high mining pressure, and insufficient support structures, coal mines are vulnerable to collapse. Unexpected roof collapses or ground sinking may ensnare employees and result in potentially fatal circumstances. Preventing catastrophic collapses requires the early detection of structural instability warning indicators.
[0004] Further, degradation of air quality and exposure to hazardous gases
toxic and combustible gasses such as methane (CH4), carbon monoxide (CO), and hydrogen sulfide (H2S) are frequently found in coal mines. While carbon monoxide poisoning can result in deadly respiratory failure, methane accumulation offers a serious risk of explosions. Proactive intervention may be limited by the lack of real-time analysis and forecast insights offered by traditional gas monitoring systems.
[0005] Also, the buildup of coal dust and its effect on the respiratory system. Mining operations produce fine coal dust, which is extremely flammable and capable of causing catastrophic explosions. Miners' life expectancy is lowered by prolonged exposure to coal dust, which can induce serious lung conditions such pneumoconiosis (black lung disease). Dust levels in underground mines must be kept to a minimum by efficient monitoring and mitigating techniques.
[0006] Furthermore, unexpected equipment failures and mechanical failures drills, conveyors, and ventilation systems are examples of mining equipment that is essential to maintaining both worker safety and operational effectiveness. Unexpected failures or breakdowns may lead to mishaps that injure or trap employees. To stop these kinds of accidents, mining equipment must have predictive maintenance.
[0007] The majority of current coal mine safety measures depend on sensor-based monitoring and recurring manual inspections. Alarms from traditional systems frequently sound only after hazardous situations have materialized, giving little opportunity for preventative measures. A predictive algorithm that can evaluate danger levels (low, medium, and high) in real time and issue early alerts is required.
[0008] Accordingly, there remains a need for an IoT and AI-based coal mine risk prediction system and method thereof.
SUMMARY
[0009] In view of the foregoing, embodiments herein provide an IoT and AI-based coal mine risk prediction system. The system includes one or more sensors, and a microcontroller. The one or more sensors is configured to continuously collect environmental data from a coal mine. The microcontroller is configured with a machine learning module and an AI module. The microcontroller is configured to process and analyse the collect environmental data for patterns to predict potential accidents in the coal mine. The microcontroller is configured to categorize the analysed patterns into risk levels.
[00010] Further, the risk levels comprises a low, a medium, or a high/critical level based on predefined thresholds. If the microcontroller detects the high/critical risk level, then the microcontroller triggers alerts, wherein the alert is sent to authorities or workers to take immediate action. If the microcontroller detects low or medium risk level, the microcontroller does not trigger alerts, and the microcontroller displays the low or medium risk level on a web application for monitoring purposes. The microcontroller is configured to continuously monitor the coal mine in a loop for ensuring continuous safety assessment.
[00011] In some embodiments, the one or more sensors include temperature sensor, humidity sensor, gas sensor, vibration sensor, dust sensor, and sound sensor.
[00012] In some embodiments, the AI module includes Logistic Regression and K-Means Clustering for categorizing the risk levels.
[00013] In another aspect of the embodiments herein provide a method for providing an IoT and AI-based coal mine risk prediction system. The method includes configuring, one or more sensors, to continuously collect environmental data from a coal mine. The method further includes configuring, a microcontroller, with a machine learning module and an AI module. The method further includes processing and analysing the collect environmental data for patterns to predict potential accidents in the coal mine. The method further includes categorizing the analysed patterns into risk levels, wherein the risk levels comprises a low, a medium, or a high/critical level based on predefined thresholds,
[00014] Further, the risk levels comprises a low, a medium, or a high/critical level based on predefined thresholds. If the microcontroller detects the high/critical risk level, then the microcontroller triggers alerts, wherein the alert is sent to authorities or workers to take immediate action. If the microcontroller detects low or medium risk level, the microcontroller does not trigger alerts, and the microcontroller displays the low or medium risk level on a web application for monitoring purposes. The method further includes continuously monitoring the coal mine in a loop for ensuring continuous safety assessment.
[00015] In some embodiments, the one or more sensors include temperature sensor, humidity sensor, gas sensor, vibration sensor, dust sensor, and sound sensor.
[00016] In some embodiments, the AI module includes Logistic Regression and K-Means Clustering for categorizing the risk levels.
[00017] These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein, and the embodiments herein include all such modifications.
BRIEF DESCRIPTION OF THE DRAWINGS
[00018] The embodiments herein will be better understood from the following detailed description with reference to the drawings, in which:
[00019] FIG. 1 illustrates an IoT and AI-based coal mine risk prediction system, according to some embodiments herein; and
[00020] FIG. 2 illustrates a flow chart shows a method for providing an IoT and AI-based coal mine risk prediction system, according to some embodiments herein.
DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS
[00021] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
[00022] As mentioned, there remains a need for an IoT and AI-based coal mine risk prediction system and method thereof. Referring now to the drawings, and more particularly to FIGs. 1 through 2, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments.
[00023] FIG. 1 illustrates an IoT and AI-based coal mine risk prediction system 100, according to some embodiments herein. The system includes one or more sensors, and a microcontroller 102. The one or more sensors are DHT11 (Temperature & Humidity Sensor) 104, KY-038 (Sound Sensor) 106, BMP280 (Barometric Pressure & Temperature Sensor) 112, MPU6050 (Accelerometer & Gyroscope) 114, and GP2Y1010AU0F (Dust Sensor) 116. The system 100 further includes resistor 108, bread board 110, and mini-bread board 118.The system is powered by a 12V power source. A voltage regulator steps down 12V to 3.3V for the ESP32 microcontroller 102. Capacitors are placed across the power rails to reduce noise and ensure stable voltage. The ground (GND) of all components is connected to the ESP32’s ground to maintain a common reference voltage. The ESP32 102 acts as the microcontroller, reading sensor data, processing the sensor data, and transmitting the sensor data via IoT. The microcontroller has multiple GPIO (General-Purpose Input/Output) pins to connect different sensors and modules.
[00024] Below table 1 shows sensor connections:
Sensor Pin on Sensor Pin on ESP32 Notes
DHT11 (Temperature & Humidity Sensor) VCC 3.3V Power
GND GND Ground
DATA GPIO 4
MPU6050 (Accelerometer & Gyroscope) VCC 3.3V Power
GND GND Ground
SDA GPIO 21 I2C Communication
SCL GPIO 22 I2C Communication
GP2Y1010AU0F (Dust Sensor) VCC 5V Power
GND GND Ground
LED Control GPIO 25 (via 220Ω resistor) Controls LED
Analog Output GPIO 34 Reads dust level
Vo GND (via 150Ω resistor) Required for operation
BMP280 (Barometric Pressure & Temperature Sensor) VCC 3.3V Power
GND GND Ground
SDA GPIO 21 I2C Communication (shared with MPU6050)
SCL GPIO 22 I2C Communication (shared with MPU6050)
KY-038 (Sound Sensor) VCC 3.3V Power
GND GND Ground
A0 (Analog Output) GPIO 35 Reads sound intensity
D0 (Digital Output) GPIO 32 Goes HIGH on loud noise

[00025] The LCD display is connected using the I2C protocol. SCL (Clock Line) is connected to GPIO 22, and SDA (Data Line) is connected to GPIO 21 on the ESP32. The display receives real-time sensor readings from the ESP32 and updates automatically. The ESP32 has built-in Wi-Fi, which allows it to send sensor data to the cloud. If a sensor reading exceeds a critical safety threshold, then the ESP32 sends an alert to a mobile app or SMS notification.
[00026] Further a buzzer or LED can be activated as a local alert for workers. All sensor GND pins are connected together and linked to the ESP32 GND. Power connections are properly regulated to prevent voltage mismatches. Sensors using I2C communication share the SCL and SDA lines with appropriate pull-up resistors. Sensors using analog output are connected to the ESP32’s ADC pins for data processing. The system employs a machine learning-based algorithm to analyze sensor data and predict accident risks. Based on the collected data, the model classifies risks into three levels:
• Low Risk: Normal working conditions.
• Medium Risk: Increased safety awareness required.
• High Risk: Immediate evacuation and alert generation.
[00027] The one or more sensors is configured to continuously collect environmental data from a coal mine. The microcontroller 102 is configured with a machine learning module and an AI module. The microcontroller 102 is configured to process and analyse the collect environmental data for patterns to predict potential accidents in the coal mine. The microcontroller 102 is configured to categorize the analysed patterns into risk levels.
[00028] Further, the risk levels includes a low, a medium, or a high/critical level based on predefined thresholds. If the microcontroller 102 detects the high/critical risk level, then the microcontroller triggers alerts. The alert is sent to authorities or workers to take immediate action. If the microcontroller 102 detects low or medium risk level, the microcontroller 102 does not trigger alerts, and the microcontroller 102 displays the low or medium risk level on a web application for monitoring purposes. The microcontroller 102 is configured to continuously monitor the coal mine in a loop for ensuring continuous safety assessment.
[00029] In some embodiments, the one or more sensors include temperature sensor, humidity sensor, gas sensor, vibration sensor, dust sensor, and sound sensor.
[00030] In some embodiments, the AI module includes Logistic Regression and K-Means Clustering for categorizing the risk levels.
[00031] In some embodiments, the system 100 can be used in underground mines, open-pit mines, and other hazardous workplaces. The system 100 can be adaptation for industrial applications, such as detecting harmful gas leaks in factories. The system 100 can be integrated with smart helmets for real-time alerts to miners.
[00032] FIG. 2 illustrates a flow chart shows a method 200 for providing an IoT and AI-based coal mine risk prediction system, according to some embodiments herein. At step 202, the method 200 includes configuring, one or more sensors, to continuously collect environmental data from a coal mine. At step 204, the method 200 includes configuring, a microcontroller, with a machine learning module and an AI module. At step 206, the method 200 includes processing and analysing the collect environmental data for patterns to predict potential accidents in the coal mine. At step 208, the method 200 includes categorizing the analysed patterns into risk levels. The risk levels comprises a low, a medium, or a high/critical level based on predefined thresholds. At step 210, the method 200 includes The method further includes continuously monitoring the coal mine in a loop for ensuring continuous safety assessment.
[00033] An advantage of the system 100 is that the system 100 provides real-time risk prediction using ai-based analytics.
[00034] An advantage of the system 100 is that the system 100 provides early warning system to prevent mining accidents.
[00035] An advantage of the system 100 is that the system 100 provides multi-sensor integration for comprehensive monitoring.
[00036] An advantage of the system 100 is that the system 100 provides cloud-based storage & dashboard for remote accessibility.
[00037] An advantage of the system 100 is that the system 100 provides scalability to expand with additional sensors and mines.
[00038] An advantage of the system 100 is that the system 100 provides automation of safety alerts, reducing human dependency.
[00039] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practised with modification within the scope of the appended claims.
, Claims:We claim:
1. An IoT and AI-based coal mine risk prediction system (100), comprising:
one or more sensors that is configured to continuously collect environmental data from a coal mine; and
a microcontroller (102) that is configured with a machine learning module and an AI module to:
process and analyse the collect environmental data for patterns to predict potential accidents in the coal mine;
categorize the analysed patterns into risk levels, wherein the risk levels comprises a low, a medium, or a high/critical level based on predefined thresholds,
wherein if the microcontroller (102) detects the high/critical risk level, then the microcontroller triggers alerts, wherein the alert is sent to authorities or workers to take immediate action,
wherein if the microcontroller (102) detects low or medium risk level, the microcontroller does not trigger alerts, and the microcontroller displays the low or medium risk level on a web application for monitoring purposes; and
continuously monitor the coal mine in a loop for ensuring continuous safety assessment.
2. The system (100) as claimed in claim 1, wherein the one or more sensors comprise temperature sensor, humidity sensor, gas sensor, vibration sensor, dust sensor, and sound sensor.
3. The system (100) as claimed in claim 1, wherein the AI module comprises Logistic Regression and K-Means Clustering for categorizing the risk levels.
4. A method (200) for providing an IoT and AI-based coal mine risk prediction system, the method (200) comprising:
configuring (202), one or more sensors, to continuously collect environmental data from a coal mine; and
configuring (204), a microcontroller, with a machine learning module and an AI module for:
processing and analysing (206) the collect environmental data for patterns to predict potential accidents in the coal mine;
categorizing (208) the analysed patterns into risk levels, wherein the risk levels comprises a low, a medium, or a high/critical level based on predefined thresholds,
wherein if the microcontroller detects the high/critical risk level, then the microcontroller triggers alerts, wherein the alert is sent to authorities or workers to take immediate action,
wherein if the microcontroller detects low or medium risk level, the microcontroller does not trigger alerts, and the microcontroller displays the low or medium risk level on a web application for monitoring purposes; and
continuously monitoring (210) the coal mine in a loop for ensuring continuous safety assessment.
5. The method (200) as claimed in claim 4, wherein the one or more sensors comprise temperature sensor, humidity sensor, gas sensor, vibration sensor, dust sensor, and sound sensor.
6. The method (200) as claimed in claim 4, wherein the AI module comprises Logistic Regression and K-Means Clustering for categorizing the risk levels.