GAS LEAKAGE DETECTION SYSTEM

Abstract

ABSTRACT The present invention discloses a gas leakage detection system with automatic shut-off capabilities. In the present invention, the system (1) integrates advanced sensors with machine learning algorithms, ensuring unparalleled precision in gas (8) leak detection. It comprises of Microcontroller (2), Gas Sensor (3), Communication Module (9), Actuation Mechanism (4), User Interface (5), Alarm System (6), Machine Learning Processor (7). The system's (1) adaptive capabilities mitigate false alarms arising from environmental variations, particularly in dynamic spaces like kitchens. The standout feature is its automatic shut-off mechanism, swiftly triggered upon confirming a gas leak, preventing potential hazards. User centric design defines system (1), offering intuitive controls as the system facilitates remote monitoring through SMS alerts, providing real-time notifications, even when users are away and make system (1) a crucial component in modern safety protocols. In summary, system (1) represents a paradigm shift in gas safety technology, combining intelligence, adaptability, and proactive measures to enhance safety in domestic environments.

Specification

Description:GAS LEAKAGE DETECTION SYSTEM

Field of Invention
The present invention relates to the gas leakage detection system. More particularly, a gas leakage detection system with automatic shut-off capabilities.

Background of the Invention
Gas leakage detection is the process of identifying the presence of gas in an area and alerting people to the leak. Gas leak detectors can be used in both residential and commercial settings. The gas leakage detection at proper time can protect peoples from any kind of accidents.
There are certain prior arts that detect the gas leakage such as:
1. Banik, A., Aich, B., & Ghosh, S. (2018, March). Microcontroller based low cost gas leakage detector with SMS alert. In 2018 Emerging Trends in Electronic Devices and Computational Techniques (EDCT) (pp. 1-3). IEEE.
2. Keshamoni, K., & Hemanth, S. (2017, January). Smart gas level monitoring, booking & gas leakage detector over IoT. In 2017 IEEE 7th international advance computing conference (IACC) (pp. 330-332). IEEE.
3. Leavline, E. J., Singh, D. A. A. G., Abinaya, B., & Deepika, H. (2017). LPG gas leakage detection and alert system. International Journal of Electronics Engineering Research, 9(7), 1095-1097.
4. Mahalingam, A., Naayagi, R. T., & Mastorakis, N. E. (2012). Design and implementation of an economic gas leakage detector. Recent Researches in Applications of Electrical and Computer Engineering, (3), 20-24.
The current technologies available in the market that provide solution for the same scientific problem are:
Traditional gas Alarms: Conventional gas alarms, like those from Kidde or First Alert, provide audible alerts when gas concentrations reach a dangerous level.
Automated Gas Shut-off valves: Some products, such as the "Smart Valve" by companies like FortrezZ or similar devices, can automatically shut off the gas supply in case of a potential leak.
Smart gas Detectors: Companies like Nest, Honeywell, and Xiaomi offer smart gas detectors that can detect various gases, including LPG. These devices often provide real-time alerts through smartphone apps.
Drawback: Some smart gas detectors rely on predefined threshold levels, leading to occasional false alarms, especially in dynamic or changing environments. The sensitivity of these devices needs manual adjustments. These devices lack advanced features like machine learning to differentiate between actual leaks and harmless fluctuations, potentially causing inconvenience due to false responses. In some technologies, the alarms lack advanced communication features, such as sending SMS alerts.
The present invention overcomes the drawback of the prior arts by providing an automatic shutoff in addition to incorporating machine learning for false alarm reduction can be a unique advancement in the field with the fine-tuning of sensitivity and specificity to ensure accurate detection without triggering false alarms.


Objectives of the Invention
The prime objective of the present invention is to provide a gas leakage detection system with automatic shut-off capabilities.

Another object of this invention is to provide the gas leakage detection system that utilizes advanced sensors and technology to detect gas leaks promptly and accurately in order to provide a heightened level of sensitivity to potential gas leakage, ensuring early detection.

Another objective of the present invention is to provide the gas leakage detection system where Machine learning algorithms have been incorporated to analyses and interpret data from the gas sensor.

Another objective of the present invention is to provide the gas leakage detection system where an automatic shut-off mechanism is used to cease the gas supply in the event of a confirmed gas leak.

Yet another object of this invention is to provide the gas leakage detection system that has user-friendly controls, easy to manufacture, cost effective, have accurate results.

These and other objects of the present invention will be apparent from the drawings and descriptions herein. Every object of the invention is attained by at least one embodiment of the present invention.
Summary of the Invention
In one aspect of the present invention provides the gas leakage detection system with automatic shut-off capabilities that significantly reduce false alarms by enabling the system to differentiate between normal fluctuations in gas concentrations and actual gas leaks.
In one of the aspects, in the present system, the automatic shut-off mechanism ceases the gas supply in the event of a confirmed gas leak, it enhances safety by preventing the further release of gas and mitigating potential hazards.
In one of the aspects, in the present invention, the remote monitoring of the gas leakage detection system is enabled through SMS alerts, it keeps users informed about potential gas leaks even when they are not physically present at the location.

Brief Description of Drawings
The drawings described herein are for illustrative purposes only of selected embodiments and not all possible implementations, and are not intended to limit the scope of the present disclosure. Further objectives and advantages of this invention will be more apparent from the ensuing description when read in conjunction with the accompanying drawing and wherein:
Figure 1 illustrates the block diagram according to the preferred embodiment of the present invention.
Figure 2 illustrates the Process Flowchart for Training ML model according to an embodiment of the present invention.

DETAIL DESCRIPTION OF INVENTION
Unless the context requires otherwise, throughout the specification which follow, the word "comprise" and variations thereof, such as, "comprises" and "comprising" are to be construed in an open, inclusive sense that is as "including, but not limited to".

In the following description, numerous specific details are set forth in order to provide a thorough understanding of embodiments of the present invention. It will be apparent to one skilled in the art that embodiments of the present invention may be practiced without some of these specific details.

Reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
As used in this specification and the appended claims, the singular forms "a," "an," and "the" include plural referents unless the content clearly dictates otherwise. It should also be noted that the term "or" is generally employed in its sense including "and/or" unless the content clearly dictates otherwise.

The embodiments are in such detail as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosure as defined by the appended claims.

The headings and abstract of the invention provided herein are for convenience only and do not interpret the scope or meaning of the embodiments. Reference will now be made in detail to the exemplary embodiments of the present invention.
The present invention discloses the gas leakage detection system with automatic shut-off capabilities, involving the use of advanced sensors to detect gas leakages, an intelligent system applying machine learning to minimize false alarms, and an automatic shut-off mechanism to enhance safety by preventing further gas leakage.

In describing the preferred embodiment of the present invention, reference will be made herein to like numerals refer to like features of the invention.

According to preferred embodiment of the invention, referring to Figure 1, the gas leakage detection system (1) with automatic shut-off capabilities comprises of Microcontroller (2), Gas Sensor (3), Communication Module (9), Actuation Mechanism (4), User Interface (5), Alarm System (6), Machine Learning Processor (7),
Microcontroller (2): It processes data from various sensors, executes control algorithms, and manages communication with other components. The Microcontroller (2) used for this invention offer features like Wi-Fi connectivity (9) with ample processing power, suitable for adding some additional functionalities including machine learning algorithms.

Gas Sensor (3): MOS (Metal Oxide Semiconductor) Sensor is used to detect the gas (8) leakage. MOS sensors operate based on the change in electrical conductivity of a metal oxide semiconductor when it comes into contact with a specific gas, such as LPG. The gas molecules adsorb onto the surface of the semiconductor, leading to a change in resistance that is measurable and indicative of the gas concentration. It is highly sensitive to gas (8), have quick response time and is suitable for detecting low concentrations of gases. It is integrated for compact and cost-effective sensor system. Gas Sensor (3) is used to Detect LPG Gas (8) Leakage and to setup an SMS based Alert Mechanism (6) and send alert message and notification to specified mobile number, the input is given in the microcontroller (2) program. It is an easy-to-use LPG sensor which helps in sensing the LPG, which is mainly composed of butane and propane. The sensor (3) can detect any level of concentration of gas (8) like from 200-10,000ppm operating at a temperature range from -10 to 50-degree Celsius.
• Gas Sensor Interface: A dedicated interface or circuitry for connecting and reading data from gas sensors (3). This component facilitates the integration of multiple gas sensors and manages their outputs.

Communication Module (9): A module for enabling communication between the gas detection system and external devices. This could involve wireless communication protocols such as Wi-Fi, Bluetooth, or Zigbee for remote monitoring and alerts.
• WIFI Module (9): Utilizing Wi-Fi allows the vending machine to connect to the internet, enabling real-time communication with a central server. This facilitates data updates, transaction processing, and remote monitoring.
Actuation Mechanism (4): An electrically controlled valve that serves as the actuation mechanism (4) for the automatic shut-off feature. This valve can be controlled by the microcontroller (2) based on the gas sensor (3) readings.
User Interface (5): User interface components such as buttons, LEDs, or an LCD screen to provide a visual indication of the system's (1) status and allow users to interact with the device. LED Indicators used to provide visual feedback, indicating the status of the machine, successful shut off during any danger situation showcasing "out of danger", or any alerts that users need to be aware of.
Alarm System (6): An audible or visual alarm system to alert occupants in case of a gas leak or other hazardous conditions.
Machine Learning processor (7): For avoiding false alarming situations, Machine Learning based model is used. The following steps were followed to prevent false alarms using ML algorithms:
• Data preprocessing
• Feature Engineering
• Algorithm Selection
• Model Training
• Anomaly Detection
• Feedback Loop, and
• Ensemble Methods

According to another embodiment of the invention, in the gas leakage detection system (1) with auto shut off capabilities have following Implementing Procedure (7) for Machine Learning (ML).
The ML based technique used for false alarm elimination in Gas leakage detection system (1) are based on the combination of sensor technology and machine learning algorithm.
Gas Sensor (3): High-quality gas sensor (MQ-6) that is sensitive to the target gas (8) and have low cross sensitivity to other gases is utilized and it must ensure comprehensive coverage and accurate detection.
Feature Extraction - A signal processing technique is applied to sensor data to enhance the detection of gas (8) leakage patterns by analyzing relevant features such as gas concentration levels, temperature, humidity, and pressure.
Sensor data analysis: Gas concentration levels, temperature, humidity, and pressure are analyzed. Signal processing technique: Applied to preprocess the data and enhance gas leakage pattern detection.
ML Model - The ML classifier based on SVM model is used to effectively separate classes in high-dimensional feature spaces and model are trained based on historical sensor data in order to classify normal conditions and confirmed gas leakage events. The process flowchart is given in Figure 2.
The Support Vector Machine (SVM) Model is incorporated into the gas leakage detection system by training it on a dataset that includes various patterns of sensor readings during both actual gas leak events and non-leak scenarios. The SVM model learns to classify these patterns into two categories: gas leak and non-leak.
During operation, the sensor (3) data from the gas detection system (1) is fed into the SVM model for real-time analysis. The SVM model then evaluates the incoming data and makes a prediction based on the learned patterns. If the SVM model determines that the sensor readings indicate a gas leak based on the learned patterns, it triggers the alarm (6) and initiates the SMS notification process. On the other hand, if the SVM model classifies the sensor (3) data as a non-leak scenario, it prevents false alarms from being triggered, thereby enhancing the system's accuracy and reliability.
Threshold optimization: Dynamic thresholds will be set based on learned model to trigger alarms only in condition of confirmed leakage.
Continuous Monitoring and Feedback: The performance of detection system (1) is monitored continuously and feedback is collected for improving the model over time.

According to another embodiment of the invention, the combination of advanced sensor technologies with the integration of machine learning algorithms and real time response makes the present invention, a robust gas leakage detection system and eliminates the occurrence of false alarms and ensure timely and accurate detection of confirmed gas leaks.

According to another embodiment of the invention, the gas leakage detection system with auto shut off capabilities have probable industrial application in residential and commercial settings where the use of liquefied petroleum gas (LPG) is prevalent and gas-powered appliances such as stoves, ovens, and water heaters are commonly fuelled by LPG. It is seamlessly integrated into these environments to enhance safety by detecting potential gas leaks early and initiating automatic shut-off procedures.
Some key application areas for this invention can also be an apartment buildings, commercial kitchens, hotels, hospitality, and educational institutions and alike.

According to another embodiment of the invention, the gas leakage detection system with auto shut off capabilities have following features:
Machine Learning Algorithms: The use of ML algorithms introduces a dynamic and adaptive intelligence to the gas detection system, setting it apart from traditional devices. The system (1) leverages the pattern recognition capability of ML Algorithms to identify and distinguish between normal fluctuations in gas concentrations (such as those caused by cooking activities) and abnormal patterns indicative of an actual gas leak. This feature significantly reduces the likelihood of false alarms.
Adaptive Sensitivity: This capability sets the invention apart by allowing the system to dynamically adjust its sensitivity levels based on varying environmental conditions and usage patterns. Traditional gas detection systems typically operate with fixed sensitivity levels, which may lead to either false alarms or delayed response in dynamic environments. The system (1) Adaptive Sensitivity overcomes this limitation by dynamically responding to changes in gas concentration patterns, making it more responsive and adaptable. The system operates seamlessly without the need for constant manual adjustments, providing a level of automation that simplifies the user experience and ensures consistent safety.
Automatic Shut-off Mechanism: Upon confirming a gas leak through the intelligent analysis of sensor data, the system (1) triggers an automatic shut-off of the gas supply. This swift response helps prevent the escalation of potential hazards. Unlike traditional gas detectors that primarily provide alerts, system (1) takes a decisive step by halting the gas supply. Users benefit from the Automatic Shut-Off Mechanism as it provides a hands-free response to gas leaks. In the event of a confirmed leak, the system takes immediate action without requiring manual intervention, enhancing convenience and peace of mind.
Remote Monitoring: Remote Monitoring provides users with real-time information even when they are not physically present. It enables users to receive real-time alerts and notifications on their mobile devices. This ensures instant awareness of any potential gas leaks or system events, contributing to prompt decision-making.
Proactive Safety Measures: this sets the invention apart by introducing a level of intelligence that goes beyond traditional gas detection systems. Upon confirming a gas leak, system (1) takes immediate and proactive action by triggering an automatic shut-off of the gas supply. This swift response minimizes the potential for hazards by preventing further gas release, contributing to a safer environment. Traditional gas detection systems may rely solely on alarms to alert users, requiring manual intervention. The system (1) Proactive Safety Measures significantly reduce response time by automating the shut-off process, ensuring a faster and more efficient reaction to confirmed gas leaks.

Although a preferred embodiment of the invention has been illustrated and described, it will at once be apparent to those skilled in the art that the invention includes advantages and features over and beyond the specific illustrated construction. Accordingly it is intended that the scope of the invention be limited solely by the scope of the hereinafter appended claims, and not by the foregoing specification, when interpreted in light of the relevant prior art.
List of Reference Numbers

1. gas leakage detection system (1) 2. Microcontroller
3. Gas Sensor 4. Actuation Mechanism
5. User Interface 6. Alarm System
7. Machine Learning Processor (7) 8. Gas
9. Communication Module


, Claims:We Claim;
1. A gas leakage detection system (1) with automatic shut-off capabilities comprises of a microcontroller (2), a gas sensor (3), a communication module (9), an actuation mechanism (4), a user interface (5), an alarm system (6), a machine learning processor (7), wherein
• The microcontroller (2) processes data from various sensors, executes control algorithms, and manages communication with other components;
• The Gas Sensor (3) is used to detect the gas (8) leakage, it operates based on the change in electrical conductivity of a metal oxide semiconductor when it comes into contact with a specific gas, such as LPG, Gas Sensor (3) detect LPG Gas (8) Leakage and to setup an SMS based Alert Mechanism (6) and send alert message and notification to specified mobile number, the input is given in the microcontroller (2) program;
• Gas Sensor Interface: the interface for connecting and reading data from gas sensors (3), this facilitates the integration of multiple gas sensors and manages their outputs;
• Communication Module (9) is for enabling communication between the gas detection system and external devices, including wireless communication protocols for remote monitoring and alerts;
• the WIFI Module (9) allows the vending machine to connect to the internet, enabling real-time communication with a central server, facilitates data updates, transaction processing, and remote monitoring;
• Actuation Mechanism (4) is an electrically controlled valve that serves as the actuation mechanism (4) for the automatic shut-off feature, controlled by the microcontroller (2) based on the gas sensor (3) readings;
• User Interface (5) components such as buttons, LEDs, or an LCD screen to provide a visual indication of the system's (1) status and allow users to interact with the device, the LED Indicators used to provide visual feedback, indicating the status of the machine, successful shut off during any danger situation showcasing "out of danger", or any alerts that users need to be aware of;
• Alarm System (6) is an audible or visual alarm system to alert occupants in case of a gas leak or other hazardous conditions;
• Machine Learning processor (7) avoids false alarming situations, the following steps were followed to prevent false alarms using ML algorithms:
o Data preprocessing,
o Feature Engineering,
o Algorithm Selection,
o Model Training,
o Anomaly Detection,
o Feedback Loop, and
o Ensemble Methods
2. The gas leakage detection system (1) with automatic shut-off capabilities as claimed in claim 1, wherein the Machine Learning Procedure (7) is as follows:
• Gas Sensor (3) ensure comprehensive coverage and accurate detection;
• Feature Extraction: A signal processing technique is applied to sensor data to enhance the detection of gas (8) leakage patterns by analysing relevant features such as gas concentration levels, temperature, humidity, and pressure;
• Sensor data analysis: Gas concentration levels, temperature, humidity, and pressure are analysed,
• Signal processing technique is applied to preprocess the data and enhance gas leakage pattern detection;
• ML Model: the ML classifier based on SVM model is used to effectively separate classes in high-dimensional feature spaces and model are trained based on historical sensor data in order to classify normal conditions and confirmed gas leakage events;
• The Support Vector Machine (SVM) Model is incorporated into the gas leakage detection system by training it on a dataset that includes various patterns of sensor readings during both actual gas leak events and non-leak scenarios, the SVM model classify these patterns into two categories: gas leak and non-leak;
• During operation, the sensor (3) data from the gas detection system (1) is fed into the SVM model for real-time analysis, it then evaluates the incoming data and makes a prediction based on the learned patterns,
o if the SVM model determines that the sensor readings indicate a gas leak based on the learned patterns, it triggers the alarm (6) and initiates the SMS notification process,
o On the other hand, if the SVM model classifies the sensor (3) data as a non-leak scenario, it prevents false alarms from being triggered, thereby enhancing the system's accuracy and reliability;
• Threshold optimization: Dynamic thresholds will be set based on learned model to trigger alarms only in condition of confirmed leakage;
• Continuous Monitoring and Feedback: The performance of detection system (1) is monitored continuously and feedback is collected for improving the model over time.
3. The gas leakage detection system (1) with automatic shut-off capabilities as claimed in claim 1, wherein the system (1) leverages the pattern recognition capability of ML Algorithms to identify and distinguish between normal fluctuations in gas concentrations and abnormal patterns indicative of an actual gas leak.

Documents