FFT-based deep learning for efficient combustion instability prediction: A comparative study of time and frequency-domain approaches

This study presents a deep learning-based approach for real-time prediction of combustion instability. Two LSTM models were developed: one trained on time-series data of pressure and heat release rate (OH* intensity), and another on frequency-domain features derived via fast Fourier transform (FFT). The dataset includes measurements taken under varying power levels (15–30 kW), hydrogen content (0%–80%), air flow rates (400–600 slpm), and downstream acoustic conditions with blockage ratios of 0, 0.73, and 0.85. Both models demonstrated high accuracy within a 100 ms window, 93.67% for the time-series model and 95.11% for the FFT-based model. However, the FFT-based model achieved 4.8 × faster inference, making it more suitable for real-time deployment. Even at smaller windows, it maintained comparable accuracy (94.28% vs. 94.76%). Additionally, both models were tested on transitional regimes (stable to unstable and vice versa) labeled using the Rayleigh Index. The models showed strong alignment with these transitions, particularly for unstable-to-stable cases, confirming their reliability in dynamic operating conditions. • Developed LSTM-based models to predict combustion instability in hydrogen- enriched flames. • Compared time-series and FFT-based approaches using pressure and OH* signals. • FFT-based model achieved comparable accuracy (95.11%) with 4.8 × faster inference speed. • Validated on transitional regimes labeled via Rayleigh Index for reliability. • Offers an efficient tool for real-time hydrogen combustion monitoring.