Burner Operating State Detection Using Sensor Data Baselines
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Detecting faulty burner operation in large quantities of burners within furnaces is difficult and time-intensive, often requiring manual inspections and technical expertise, and existing solutions using acoustic and image sensors are costly to install and operate.
Innovation Solution
A method and apparatus using machine learning to determine burner operating states by comparing monitoring data from sensors with baseline characteristic data, which includes sound, image, and process data, allowing for efficient fault detection without the need for robust sensor installations, utilizing available imaging and acoustic data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual inspections of individual burners are performed, then faulty burner operation can be detected, but the process becomes extremely time-intensive and requires scarce technical expertise
Solution Approach 1:
The patent replaces manual mechanical inspection with an automated machine learning system that uses acoustic and image sensors to detect burner faults. The system automatically captures sensor data, processes it through trained machine learning models, and identifies faulty burners without requiring human inspectors to physically examine each burner, thereby eliminating time loss while maintaining detection accuracy
Solution Approach 2:
The system enables burners to self-diagnose their operational status through automated monitoring. The machine learning model continuously analyzes sensor data from each burner and automatically identifies faults without requiring external manual inspection, allowing the system to monitor itself and report issues autonomously
2Measurement precision
If robust sensor installations are used for detection, then measurement precision improves, but manufacturing costs increase significantly
Solution Approach 1:
The patent employs cost-effective acoustic and image sensors instead of expensive specialized detection equipment. These standard sensors can be easily installed and replaced, providing sufficient measurement precision for fault detection without the high manufacturing and installation costs associated with robust specialized sensor systems
Solution Approach 2:
The system uses multi-functional machine learning models that can detect various types of burner faults using the same sensor installation. The trained models analyze both acoustic and image data to identify multiple fault conditions, eliminating the need for separate specialized sensors for each fault type and reducing overall system cost while maintaining comprehensive detection precision
Data Source
AI summary
A method is provided for determining an operating state of a burner. The method includes receiving baseline characteristic data for a plurality of burner operating states. The baseline characteristic data for each burner operating state of the plurality of burner operating states comprises baseline data of a plurality of data types indicative of a corresponding burner operating state. The method also includes receiving monitoring data captured for a burner by a plurality of burner sensors. The method further includes using to machine learning to compare at least a portion of the monitoring data captured for the burner with the baseline characteristic data. The method still further includes determining an operating state of the burner based at least in part on results of comparing the at least a portion of the monitoring data with the baseline characteristic data. A corresponding apparatus and computer program product are also provided.