Flame Detector Classification for Friendly Flame Reflections
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing flame detectors struggle to differentiate between actual fires and reflections of friendly flames, such as those from flare stacks or bright lights, leading to false alarms.
Innovation Solution
A system utilizing a flame detector with IR sensors and photodiodes, coupled with a processor that converts radiation signals into ADC signals, applies machine learning models to analyze statistical, frequency-based, and time-based features to distinguish between fires, friendly flames, and their reflections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing flame detectors are used to detect fires, then fire detection capability is provided, but false alarms occur due to inability to distinguish between actual fires and reflections of friendly flames
Solution Approach 1:
The system segments the detection task by analyzing multiple characteristics (statistical features, frequency-based features, time-based features) separately and then combining them through a machine learning model to make a comprehensive determination, rather than relying on a single detection metric
Solution Approach 2:
The system changes the detection parameters by using a machine learning model that evaluates multiple transformed features (statistical, frequency, time-based) of the radiation signals, rather than relying on simple threshold detection of raw signals
2Measurement precision
If flame detectors detect all radiation signals, then detection sensitivity is improved, but false alarms increase from bright lights and welding activities
Solution Approach 1:
The system applies different analysis methods to different characteristics of the detected signals, extracting statistical features, frequency-based features, and time-based features separately, then using a machine learning model to determine the appropriate classification based on the specific pattern observed
Solution Approach 2:
The machine learning model is trained using historical data and provides feedback by continuously improving its classification accuracy, allowing the system to learn from past detections and reduce false alarms over time
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Accurately identifies fires while avoiding false alarms from friendly flame reflections, ensuring timely and precise fire detection in industrial and household environments.
Implementation Method 1
The system comprises at least one flame detector configured to detect one or more radiations within a field of view (FOV)
Implementation Method 2
The at least one flame detector comprises at least one of infrared (IR) sensors, photodiodes, or a combination of the IR sensors and the photodiodes
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system is disclosed. The system comprises a flame detector configured to detect radiations within a field of view (FOV) and convert into one or more analog to digital converter (ADC) signals. The at least one processor is operationally coupled to the at least one flame detector. The at least one processor is configured to receive the one or more ADC signals from the at least one flame detector and determine a plurality of characteristics from the one or more ADC signals. Further, the plurality of characteristics comprises at least one of statistical features, frequency based features, or time-based features. Thereafter, the at least one processor is configured to determine whether the one or more ADC signals are indicative of a fire, a friendly flame, or a reflection of a friendly flame based at least on the plurality of characteristics using a trained machine learning (ML) model.