EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimisation and Calibration of Bayesian Neural Network for Probabilistic Prediction of Biogas Performance in an Anaerobic Lagoon

Benjamin Steven Vien iD, Thomas Kuen iD, Louis Raymond Francis Rose, Wing Kong Chiu iD

Sensors · 2024

DOI: 10.3390/s24082537 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Benjamin Steven Vien und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mechanical and Aerospace Engineering, Monash University, Wellington Rd, Clayton, VIC 3800, Australia. Hauptthemen laut MEDLINE: Bayes Theorem, Neural Networks, Computer, Biofuels. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Australian Research Council, Melbourne Water Corporation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study aims to enhance diagnostic capabilities for optimising the performance of the anaerobic sewage treatment lagoon at Melbourne Water’s Western Treatment Plant (WTP) through a novel machine learning (ML)-based monitoring strategy. This strategy employs ML to make accurate probabilistic predictions of biogas performance by leveraging diverse real-life operational and inspection sensor and other measurement data for asset management, decision making, and structural health monitoring (SHM). The paper commences with data analysis and preprocessing of complex irregular datasets to facilitate efficient learning in an artificial neural network. Subsequently, a Bayesian mixture density neural network model incorporating an attention-based mechanism in bidirectional long short-term memory (BiLSTM) was developed. This probabilistic approach uses a distribution output layer based on the Gaussian mixture model and Monte Carlo (MC) dropout technique in estimating data and model uncertainties, respectively. Furthermore, systematic hyperparameter optimisation revealed that the optimised model achieved a negative log-likelihood (NLL) of 0.074, significantly outperforming other configurations. It achieved an accuracy approximately 9 times greater than the average model performance (NLL = 0.753) and 22 times greater than the worst performing model (NLL = 1.677). Key factors influencing the model’s accuracy, such as the input window size and the number of hidden units in the BiLSTM layer, were identified, while the number of neurons in the fully connected layer was found to have no significant impact on accuracy. Moreover, model calibration using the expected calibration error was performed to correct the model’s predictive uncertainty. The findings suggest that the inherent data significantly contribute to the overall uncertainty of the model, highlighting the need for more high-quality data to enhance learning. This study lays the groundwork for applying ML in transforming high-value assets into intelligent structures and has broader implications for ML in asset management, SHM applications, and renewable energy sectors.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bayes TheoremNeural Networks, ComputerBiofuelsAnaerobiosisCalibrationMonte Carlo MethodSewageMachine Learning

Stichwörter der Autor:innen

Bayesian neural networkMonte Carlo dropoutanaerobic lagoondeep learninghyperparameter optimisationlong short-term memorymachine learningmixture densitymodel calibration

Substanzen

BiofuelsSewage

Autor:innen und Institutionen

  • Department of Mechanical and Aerospace Engineering, Monash University, Wellington Rd, Clayton, VIC 3800, Australia.
  • Melbourne Water Corporation, 990 La Trobe Street, Docklands, VIC 3008, Australia.
  • Defence Science & Technology Group, Fishermans Bend, VIC 3207, Australia.

ORCID-Profile: Benjamin Steven Vien, Thomas Kuen, Wing Kong Chiu

Förderung

  • Australian Research Council
  • Melbourne Water Corporation

Zitieren

APA

Vien, B. S., Kuen, T., Rose, L. R. F., & Chiu, W. K. (2024). Optimisation and Calibration of Bayesian Neural Network for Probabilistic Prediction of Biogas Performance in an Anaerobic Lagoon. Sensors. https://doi.org/10.3390/s24082537

Vancouver

Vien BS, Kuen T, Rose LRF, Chiu WK. Optimisation and Calibration of Bayesian Neural Network for Probabilistic Prediction of Biogas Performance in an Anaerobic Lagoon. Sensors. 2024. doi:10.3390/s24082537

BibTeX
@article{Vien2024,
  author = {Vien, Benjamin Steven and Kuen, Thomas and Rose, Louis Raymond Francis and Chiu, Wing Kong},
  title = {Optimisation and Calibration of Bayesian Neural Network for Probabilistic Prediction of Biogas Performance in an Anaerobic Lagoon},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24082537}
}
Kostenlos starten →