Plant-scale biogas production prediction based on multiple hybrid machine learning technique

Zhang, Yi; Li, Linhui; Ren, Zhonghao; Yu, Yanyan; Li, Yeqing; Pan, Junting; Lu, Yanjuan; Liu, Feng; Zhang, Weijin; Han, Yongming

doi:10.1016/j.biortech.2022.127899

Cited by 23 publications

(13 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…29 The dry fermentation system's organic matter content and VFA buildup increase as feedstock quality improve. 30 When the feedstock quality is between 0 and 235 tons, its positive effect on the CH 4 content is highly significant as it increases. When the feedstock quality is less than 235 tons, the SHAP is a negative value.…”

Section: Interpretability Analysis Of Digester Prediction Resultsmentioning

confidence: 99%

Novel Intelligent System Based on Automated Machine Learning for Multiobjective Prediction and Early Warning Guidance of Biogas Performance in Industrial-Scale Garage Dry Fermentation

et al. 2023

Self Cite

View full text Add to dashboard Cite

Industrial-scale garage dry fermentation systems are extremely nonlinear, and traditional machine learning algorithms have low prediction accuracy. Therefore, this study presents a novel intelligent system that employs two automated machine learning (AutoML) algorithms (AutoGluon and H2O) for biogas performance prediction and Shapley additive explanation (SHAP) for interpretable analysis, along with multiobjective particle swarm optimization (MOPSO) for early warning guidance of industrial-scale garage dry fermentation. The stacked ensemble models generated by AutoGluon have the highest prediction accuracy for digester and percolate tank biogas performances. Based on the interpretable analysis, the optimal parameter combinations for the digester and percolate tank were determined in order to maximize biogas production and CH4 content. The optimal conditions for the digester involve maintaining a temperature range of 35–38 °C, implementing a daily spray time of approximately 10 min and a pressure of 1000 Pa, and utilizing a feedstock with high total solids content. Additionally, the percolate tank should be maintained at a temperature range of 35–38 °C, with a liquid level of 1500 mm, a pH range of 8.0–8.1, and a total inorganic carbon concentration greater than 13.8 g/L. The software developed based on the intelligent system was successfully validated in production for prediction and early warning, and MOPSO-recommended guidance was provided. In conclusion, the novel intelligent system described in this study could accurately predict biogas performance in industrial-scale garage dry fermentation and guide operating condition optimization, paving the way for the next generation of intelligent industrial systems.

show abstract

Section: Interpretability Analysis Of Digester Prediction Resultsmentioning

confidence: 99%

Novel Intelligent System Based on Automated Machine Learning for Multiobjective Prediction and Early Warning Guidance of Biogas Performance in Industrial-Scale Garage Dry Fermentation

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…A new direction of data-driven models has been explored to replace the traditional monod-based methods and bypass the complicated reaction processes via machine learning, , in which the historical data of AD parameters and biogas production have been statistically analyzed. Machine learning algorithm (MLA) manifests outstanding prediction results compared with conventional physiochemical models. , At least 70% of prediction reliability was achieved for small-size AD systems (<1000 m 3 ) through exploiting data collected at the annual base. − The combination of microbial gene sequencing data and MLA has been performed to predict the CH 4 production through important phyla with error rate under 4% . However, there are two major problems with these MLA applications in AD systems (Figure a).…”

Section: Introductionmentioning

confidence: 99%

“…First, limited by the statistical essence, MLA can only grasp the internal correlation among the AD data at low spatiotemporal resolution, meaning that most of the transient reactions (e.g., acid–base neutralization reaction) and AD status changes (e.g., VFA accumulation, alkalinity variation) were ignored due to the lack of real-time indicators and inevitably led to the failure of predictions . Second, although the MLA possesses relatively good prediction accuracy (>70%), ,, its interpretability is inadequate at the physical system level and thus unable to provide efficient guidance for the analysis and control of AD processes.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Algorithm Integrated with Real-Time In Situ Sensors and Physiochemical Principle-Driven Soft Sensors toward an Anaerobic Digestion-Data Fusion Framework

et al. 2023

View full text Add to dashboard Cite

Insufficient real-time in situ data and complicated model parameters are severe barriers for accurate prediction and precise control of anaerobic digestion (AD) systems. This study addresses the crucial challenge by developing an advanced data acquisition technology integrating Milli-electrode Array Physical Sensors (MAPS) with Anaerobic Digestion model No.1-based Soft Sensors (ADSS) and an interpretable machine learning algorithm (MLA) equipped with post hoc analysis. AD system mechanisms are retained in hybrid physical/soft sensor data sets at the mechanistic level and can be integrated into MLA through training at the data level. The MAPS-ADSS data exhibited deviations of less than 5% from the lab-based evaluations. The integrated MAPS-ADSS-MLA methodology improved the prediction accuracy from 91% (nonlinear MLA) and 78% (linear MLA) to 99% compared to conventional MLA. Furthermore, the SHapley Additive exPlanation values and Person (r) and Spearman (r s) correlation coefficients of the predictions identified the indirect impacts of pH, alkalinity, and NH4 + on biogas production via their adverse correlation with volatile fatty acid (r = −0.93, r s = −0.92). This study presents an innovative AD-Data fusion platform for accurate and interpretable predictions in complex wastewater systems, using a sensor-model-MLA loop and employing data as the carrier to integrate physiochemical principles into training and analysis.

show abstract

“…Previous studies have primarily focused on ML models for AD operated at a lab scale (Wang et al, 2021). However, modeling AD systems at full‐scale using ML algorithms can be challenging due to inconsistent data collection, irregular operation, and fluctuation in feed stream to ADs (Zhang, Li, et al, 2022). There are very few works to predict biogas production at full‐scale WWTPs using ML algorithms such as Random Forest (RF) models, eXtreme Gradient Boosting (XGBoost), and K‐Nearest Neighbor (KNN) regression (de Clercq et al, 2019, 2020; Wang et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Prediction of biogas production in anaerobic digestion of a full‐scale wastewater treatment plant using ensembled machine learning models

Sun

Nairat

et al. 2023

Water Environment Research

View full text Add to dashboard Cite

Anaerobic digestion (AD) of sludge is a key approach to recover useful bioenergy from wastewater treatment and its stable operation is important to a wastewater treatment plant (WWTP). Because of various biochemical processes that are not fully understood, AD operation can be affected by many parameters and thus modeling AD processes becomes a useful tool for monitoring and controlling their operation. In this case study, a robust AD model for predicting biogas production was developed using ensembled machine learning (ML) model based on the data from a full-scale WWTP. Eight ML models were examined for predicting biogas production and three of them were selected as metamodels to create a voting model. This voting model had a coefficient of determination (R 2 ) at 0.778 and a root mean square error (RMSE) of 0.306, outperformed individual ML models. The Shapley additive explanation (SHAP) analysis revealed that returning activated sludge and temperature of wastewater influent were important features, although they affected biogas production in different ways. The results of this study have demonstrated the feasibility of using ML models for predicting biogas production in the absence of high-quality data input and improving model prediction through assembling a voting model. Practitioner Points• Machine learning is applied to model biogas production from anaerobic digesters at a full-scale wastewater treatment plant.• A voting model is created from selected individual models and exhibits better performance of predication.• In the absence of high quality data, indirect features are identified to be important to predicting biogas production. K E Y W O R D Sanaerobic digestion, ensembled model, sensitivity analysis, wastewater treatment plant Both Jianpeng Zhou and Zhen He are WEF members.

show abstract

Plant-scale biogas production prediction based on multiple hybrid machine learning technique

Cited by 23 publications

References 35 publications

Novel Intelligent System Based on Automated Machine Learning for Multiobjective Prediction and Early Warning Guidance of Biogas Performance in Industrial-Scale Garage Dry Fermentation

Novel Intelligent System Based on Automated Machine Learning for Multiobjective Prediction and Early Warning Guidance of Biogas Performance in Industrial-Scale Garage Dry Fermentation

Machine Learning Algorithm Integrated with Real-Time In Situ Sensors and Physiochemical Principle-Driven Soft Sensors toward an Anaerobic Digestion-Data Fusion Framework

Prediction of biogas production in anaerobic digestion of a full‐scale wastewater treatment plant using ensembled machine learning models

Contact Info

Product

Resources

About