Density profile modeling for real-time estimation of liquid level in anaerobic digester using multiple pressure meters

Comparison of different machine learning algorithms to estimate liquid level for bioreactor management

“…1). The experimental system (i.e., the bioreactor and instrumentation), data collection, and the development of polynomial models in the previous study [8] are summarized in section 2.2. Four widely-applied ML methods were utilized to predict the liquid level in this study as detailed in section 2.3 (Fig.…”

“…The anaerobic bioreactor system and the experimental data were published previously [8]. Briefly, a pilot-scale (0.33 m 3 working volume; 1.4 m height; 1.2 m liquid level) bioreactor was equipped with seven pressure sensors at approximately 0.1, 0.3, 0.4, 0.6, 0.7, 0.9, and 1.25 m from the bottom (Fig.…”

“…The bioreactor was placed in a temperature-controlled room (36℃). The anaerobic bioreactor showed a stable digestion performance in terms of pH, biogas production, and volatile fatty acid accumulation (see Rhee et al [8] for details). All the sensor-derived data (i.e., pressure, temperature, and biogas) were recorded at an interval of one min or less.…”

“…2, P 0 (headspace pressure) is subtracted from P 1 as a reference value because the anaerobic bioreactor usually keeps positive pressure at the headspace. The previous study compared polynomial models (linear to quintic) between P and ρ, and concluded that the top layer (ρ 1 ) is well depicted by a cubic model [8].…”

“…Our previous study suggested a method to overcome this limitation by predicting the unequal density profiles using multiple pressure meters [8]. A pilot-scale digester (0.33m 3 working volume, 1.4 m height, 1.2 m liquid level) was operated to collect data for the water level prediction model.…”