New Testing Tool can Detect Thermoacoustic Combustion Oscillations
Thermoacoustic combustion oscillations (TCO) are the peril of internal combustion engines, but detecting the phenomenon in time and taking targeted action to stop and reverse it has remained a complicated case.
A team of engineers from the Tokyo University of Science and the Japan Aerospace Exploration Agency (JAXA) have developed a promising tool that detects a precursor of TCO, thus helping to prevent it before it causes much damage.
The technical details presented in the American Institute of Aeronautics and Astronautics Journal in October, reveal that the tool relies on statistical complexity and machine learning to understand when machines are heading towards the damaging condition.
The algorithm is called ‘support vector machine’ (SVM), and it’s a system to help classify:
- Stable combustion
- Transitional combustion
The algorithm receives data feeds from the engine’s sensors to detect and appraise pressure fluctuations in the combustion chamber, measuring their periodic characteristics as well as their amplitude. These elements can help determine the magnitude of the fluctuations and their repetition patterns.
“The dynamic behavior of aperiodic small-amplitude pressure fluctuations represents chaos. The complexity-entropy causality plane effectively captures the subtle changes in the combustion state during a transition to well-developed combustion oscillations.” – from the paper.
The idea is to detect the early signs of combustion oscillations and change the air-fuel mixture accordingly so as to reduce the time during which the engine operates in TCO. Ideally, in the future, the system will remediate the situation when the combustion enters transitional status, pulling it back to stable operation.
Such systems can help internal combustion engines operate for much longer while remaining perfectly safe, which could be a game-changer for sectors like aviation, or even the automotive industry. In aerospace, TCO prevention can help make the difference between life and death.