MACHINE LEARNING-DRIVEN SENSOR EDGE DEVICE FOR INDUSTRIAL GAS TURBINE DUCT MONITORING AND CONTROL USING LORA AND NRF IOT GATEWAY TECHNOLOGY

Abstract

A machine learning-driven sensor edge device for industrial gas turbine duct monitoring and control using lora and nrf iot gateway technology comprises ControlSystem Mote offers a temporal data fetching and immediate alerts on the anomaly of the test ducts equipped with the Atmega2560 board, LoRa RF Module, temperature sensor, vibration sensor, a current sensor, buzzer and power supply, which allows for a continuous monitoring and the maintenance of duct risk. This improves operational safety and maintenance practice for turbines the DataRouter Mote features an Atmega2560 board, LoRa RF Module, nRF Module, OLED Display and power supply, this device assists in expanding the operational capabilities by transferring information through several hops within a network and allowing the operators to see the data directly and making sure that the operators can see the changes in the duct condition and act promptly.

Specification

Description:FIELD OF THE INVENTION
This invention relates to machine learning-driven sensor edge device for industrial gas turbine duct monitoring and control using lora and nrf iot gateway technology.
BACKGROUND OF THE INVENTION
This development offers an edge device system of artificial intelligence type for observation and control of industrial gas turbine duct health. This system consists of several numerous nodes with fixed sensors designed to monitor key parameters such as temperature, vibration, and current flowing through the duct on a real time basis. Data is sent through an IoT deployed that is easily adjusted to move across various protocols for effective communication over different distances and operating conditions. The information is obtained and transmitted to a specialized cloud server where it undergoes processing through machine learning algorithms that detect patterns, identify irregularities, and suggest maintenance in advance. Authorized persons are able to check the present and past regarding data at the display and dashboard integrated and web secure respectively, so that the measures can be taken in advance. In addition, when such conditions are met, the system detects the ducts and alerts operators on the spot for effective action. This subsequently helps to improve duct safety, prevent and repeat maintenance processes, and finally prolong equipment life.
This project tackles a serious challenge, which is the absence of predictive and condition based maintenance in the industrial gas turbine ducts for issues such as overheating, excessive vibration or abnormal current failure which can result in duct rupture, unscheduled outages and other safety concerns. Most of the existing approaches employ monitoring techniques that are not able to detect wear and degradation in gas turbine components high stressed zones as gas turbines operate which leads to less efficient and costlier maintenance practices described as corrective maintenance. The proposed process address these limitations by vividly describing each condition when ductal's components collect and transmit vital data and allowing for timely identification of major abnormalities as well as promoting proactive maintenance strategies. Their timely execution prevents unplanned outages, ensuring equipment safety and increasing the lifespan of the gas turbine duct.
US10436073B2: A power plant includes an exhaust duct downstream from an outlet of a turbine which receives exhaust gas from the turbine outlet, a first ejector having a primary inlet that is fluidly coupled to a turbine extraction port and an outlet that is in fluid communication with the exhaust duct. The power plant further includes a second ejector having a primary inlet fluidly coupled to the compressor extraction port, a suction inlet in fluid communication with an air supply and an outlet in fluid communication with a suction inlet of the first ejector. The first ejector cools the stream of combustion gas via compressed air extracted from the compressor and cooled via the second ejector. The cooled combustion gas mixes with the exhaust gas within the exhaust duct to provide a heated exhaust gas mixture downstream from the exhaust duct.
RESEARCH GAP: The novelty of this system is its machine learning-driven edge device for real-time gas turbine duct monitoring and control using a multihop LoRa and nRF IoT gateway.
EP3376003A1: A method (90) for operating a gas turbine system (10) includes utilizing a gas turbine controller (46) to determine (94) a schedule (70) for a firing temperature for operative burners (28) of a second combustor (18) located downstream (8) of a first combustor (14) when the gas turbine system (10) is operating in a low part load mode. During the low part load mode, multiple burners (28) for the second combustor (18) are switched-off. Further, the schedule (70) is determined based on a position of inlet guide vanes (30) of a compressor (12) of the gas turbine system (10) located upstream (6) of both the first and second combustors (14, 18). The method (90) also includes controlling (96) the firing temperature of the operative burners (28) utilizing the schedule (70) during the low part load mode to keep the gas turbine system (10) within relevant operational limits of the gas turbine system (10).
RESEARCH GAP: The novelty of this system is its machine learning-driven edge device for real-time gas turbine duct monitoring and control using a multihop LoRa and nRF IoT gateway.
SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
This invention is based on a system of interrelated nodes which provide real time monitoring, analysis and reporting of the conditions of duct work pertaining to industrial gas turbines. It begins with the Control Mote which maps critical metrics like temperature, vibration and current from various sensors located in the turbine duct. This mote is intended to work in tandem with the turbine, providing a range of accurate readings while in the field of operation of the duct. If there is an increase in weight or a change in momentum that is immediate the ControlSystem Mote issues a warning signal via an attached buzzer alerting the relevant personnel of the dangerous circumstances. Data collected by the ControlSystem Mote is sent to the system using methods. It is aided by both the LoRa and nRF of IoT network protocols. This process is referred to as the DataRouter Mote. This device acts as a third party so to speak and performs the task of forwarding data when massive distances or barriers exist. The DataRouter Mote acts to enhance the communication system and provides an OLED monitor that displays the site information thus allowing the operators to see the condition of the duct and act upon it before damages occur. The multihop function of the network further aids to ensure that data transmission remains seamless even in harsh industrial environments, enabling uninterrupted data transmission for precise monitoring.
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
FIGURE 1: SYSTEM ARCHITECTURE
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein 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 scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms "a"," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises," "comprising," "includes" and/or "including," when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", "third", and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
This invention is based on a system of interrelated nodes which provide real time monitoring, analysis and reporting of the conditions of duct work pertaining to industrial gas turbines. It begins with the Control Mote which maps critical metrics like temperature, vibration and current from various sensors located in the turbine duct. This mote is intended to work in tandem with the turbine, providing a range of accurate readings while in the field of operation of the duct. If there is an increase in weight or a change in momentum that is immediate the ControlSystem Mote issues a warning signal via an attached buzzer alerting the relevant personnel of the dangerous circumstances. Data collected by the ControlSystem Mote is sent to the system using methods. It is aided by both the LoRa and nRF of IoT network protocols. This process is referred to as the DataRouter Mote. This device acts as a third party so to speak and performs the task of forwarding data when massive distances or barriers exist. The DataRouter Mote acts to enhance the communication system and provides an OLED monitor that displays the site information thus allowing the operators to see the condition of the duct and act upon it before damages occur. The multihop function of the network further aids to ensure that data transmission remains seamless even in harsh industrial environments, enabling uninterrupted data transmission for precise monitoring.
Following this, the IoT data is relayed to the IoTforwarder Mote, which collates this data and secures its transfer to an appropriate cloud server. This mote supports both GSM and WiFi for sending information depending on which access point is available, meaning data is always guaranteed to reach the cloud. In the cloud server, machine learning is employed to receive and analyze the duct, looking for evidence of wear, stress, or defects. Therefore, it also provides the user with predictive maintenance recommendations in order to carry out effective planning so that the problems don't worsen. Once approved, the data can be viewed genuinely on the web interface and at the practical site through an OLED display showing how the duct is performing. It offers up-to-date information, and previous information extending the history of events for better trend analysis in maintenance issues. Furthermore, onsite alerts send feedback to operators to prevent critical problems from becoming a catastrophic case in which machinery can break down. This breakthrough integrates the functionality of monitoring, data transfer and prediction of problems through the development of a gas turbine duct's competent health management system, which improves safety, reduces downtime and extends the efficient time of the duct.
BEST METHOD OF WORKING
The ControlSystem Mote offers a temporal data fetching and immediate alerts on the anomaly of the test ducts equipped with the Atmega2560 board, LoRa RF Module, temperature sensor, vibration sensor, a current sensor, buzzer and power supply, which allows for a continuous monitoring and the maintenance of duct risk. This improves operational safety and maintenance practice for turbines.
The DataRouter Mote features an Atmega2560 board, LoRa RF Module, nRF Module, OLED Display and power supply. This device assists in expanding the operational capabilities by transferring information through several hops within a network and allowing the operators to see the data directly and making sure that the operators can see the changes in the duct condition and act promptly.
The IoTforwarder Mote features an ESP32 board, nRF Module, GSM Modem, power indicator LED, and power supply. This installation allows forwarding of the data to a custom cloud that supports machine learning and AI-based analytics and recommendations for the health and scheduled maintenance of ducts.
The OLED Display mounted on the DataRouter Mote gives the operator of the system on-site basic controls that permit the visualization of the duct temperature and other parameters in real time that helps the operators to have a better understanding of the situational characteristics and when to carry out the maintenance of the duct systems.
The significant advantage of having the GSM Modem in the IoTforwarder Mote is that it allows dependable, long-distance data transmission to the cloud server and makes it possible to constantly monitor the duct even in unfavorable Wi-Fi conditions which improves the chances this data will be accessed remotely for up to analysis and taking action.
ADVANTAGES OF THE INVENTION
1. Equipped with an Atmega2560 board, temperature sensor, vibration sensor, current sensor and a buzzer, the ControlSystem Mote allows the in-situ collection of data and provide onsite notifications in real-time, therefore enabling the Mote operators to act quickly when any abnormal condition arises in the turbine duct.
2. The Mote consists of an Atmega2560 board, a LoRa RF Module, and also an nRF Module. This enables multihop communication with respect to a significant distance. This allows communication even in large or communication-scarce industrial setups, ensuring the monitoring of the duct conditions is not compromised.
3. In the IoTforwarder Mote powered by the ESP32 board, an nRF module and a GSM modem, the data is cloud-based enabling machine learning predictive analytics that offer an early warning of buildings AI-based maintenance to make better decisions thus making duct systems more reliable.
4. Through the OLED Display, authorized users have a simple means of monitoring the conditions within the DataRouter Mote. Real time data is also sent to an authorized personnel through a custom cloud server and web dashboard making it easy to plan for a maintenance exercise.
5. The IoTforwarder Mote's features of the GSM Modem and WiFi allow on a cloud adaptive data transfer, thus data is uploaded irrespective of the network status in the industrial environment.
, Claims:1. A machine learning-driven sensor edge device for industrial gas turbine duct monitoring and control using lora and nrf iot gateway technology comprises ControlSystem Mote offers a temporal data fetching and immediate alerts on the anomaly of the test ducts equipped with the Atmega2560 board, LoRa RF Module, temperature sensor, vibration sensor, a current sensor, buzzer and power supply, which allows for a continuous monitoring and the maintenance of duct risk. This improves operational safety and maintenance practice for turbines.
2. The device as claimed in claim 1, wherein the DataRouter Mote features an Atmega2560 board, LoRa RF Module, nRF Module, OLED Display and power supply, this device assists in expanding the operational capabilities by transferring information through several hops within a network and allowing the operators to see the data directly and making sure that the operators can see the changes in the duct condition and act promptly.
3. The device as claimed in claim 1, wherein the IoTforwarder Mote features an ESP32 board, nRF Module, GSM Modem, power indicator LED, and power supply, this installation allows forwarding of the data to a custom cloud that supports machine learning and AI-based analytics and recommendations for the health and scheduled maintenance of ducts.
4. The device as claimed in claim 1, wherein the OLED Display mounted on the DataRouter Mote gives the operator of the system on-site basic controls that permit the visualization of the duct temperature and other parameters in real time that helps the operators to have a better understanding of the situational characteristics and when to carry out the maintenance of the duct systems.
5. The device as claimed in claim 1, wherein the significant advantage of having the GSM Modem in the IoTforwarder Mote is that it allows dependable, long-distance data transmission to the cloud server and makes it possible to constantly monitor the duct even in unfavorable Wi-Fi conditions which improves the chances this data will be accessed remotely for up to analysis and taking action.

Documents