Hierarchical Bayesian modeling for knowledge transfer across engineering fleets via multitask learning

LA Bull, D Di Francesco, M Dhada… - … ‐Aided Civil and …, 2023 - Wiley Online Library
A population‐level analysis is proposed to address data sparsity when building predictive
models for engineering infrastructure. Utilizing an interpretable hierarchical Bayesian …

[HTML][HTML] On the hierarchical Bayesian modelling of frequency response functions

TA Dardeno, K Worden, N Dervilis, RS Mills… - Mechanical Systems and …, 2024 - Elsevier
Structural health monitoring (SHM) strategies seek to evaluate, predict, and maintain
structural integrity, to improve the safety and design service life of structures in operation …

A Bayesian Data Driven Multi-Fidelity Modelling Approach for Experimental Under-Sampled Flow Reconstruction

GG Cruz, C Babin, X Ottavy… - … Expo: Power for …, 2023 - asmedigitalcollection.asme.org
This work showcases a multi-fidelity approach, which couples experimental techniques with
numerical models within a Bayesian data-driven framework, thus enabling a direct …

Lessons learned toward estimating the high-pressure turbine inlet temperature profile using measurements acquired at the high-pressure turbine exit

X Zhu, K Zhou, X Zheng, F Lou - … of Engineering for …, 2023 - asmedigitalcollection.asme.org
To achieve higher thermal efficiency, gas turbines operate at increasingly higher turbine
inlet temperatures, leading to the need for advanced cooling methods such as film cooling …

Resolving nonuniform flow in gas turbines: challenges, progress, and moving forward

F Lou - The Aeronautical Journal, 2024 - cambridge.org
The flow in gas turbines exhibits a highly unsteady, complex and nonuniform manner, which
presents two main challenges. Firstly, it introduces instrumentation errors, contributing to …

Bayesian mass averaging in rigs and engines

P Seshadri, A Duncan… - Journal of …, 2022 - asmedigitalcollection.asme.org
This paper introduces the Bayesian mass average and details its computation. Owing to the
complexity of flow in an engine and the limited instrumentation and the precision of the …

[HTML][HTML] Towards Improved Turbomachinery Measurements: A Comprehensive Analysis of Gaussian Process Modeling for a Data-Driven Bayesian Hybrid …

GG Cruz, X Ottavy, F Fontaneto - International Journal of Turbomachinery …, 2024 - mdpi.com
A cost-effective solution to address the challenges posed by sensitive instrumentation in
next-gen turbomachinery components is to reduce the number of measurement samples …

Spatial anomaly detection with optimal transport

P Seshadri, AB Duncan, G Thorne, RV Diaz - arXiv preprint arXiv …, 2022 - arxiv.org
This manuscript outlines an automated anomaly detection framework for jet engines. It is
tailored for identifying spatial anomalies in steady-state temperature measurements at …

Physics-Driven Priors for Improved Spatial Models and Averages

P Seshadri, AB Duncan… - … Expo: Power for …, 2023 - asmedigitalcollection.asme.org
This paper proposes a new physics-driven prior structure for engine spatial models. It is
designed to be used on engine measurements, with the objective of obtaining more …

Statistical hierarchical modelling for industrial collaborative prognosis

M Dhada - 2022 - repository.cam.ac.uk
Recent advancements in computing, telecommunications, and metrology have propelled
data-driven decision making across the industries. Industrial health management in …