arXiv subjects

Lin-Feng Mei

Publications and source records attributed to Lin-Feng Mei.

3 recordsLinked to original sources

arXiv2025

Bayesian Learning in Structural Dynamics: A Comprehensive Review and Emerging Trends

Bayesian learning has emerged as a compelling and vital research direction in the field of structural dynamics, offering a probabilistic lens to understand and refine the analysis of complex dynamical systems. This review meticulously traces the three-decade evolution of Bayesian learning in structural dynamics, illuminating core principles, groundbreaking methodologies, and diverse applications that have significantly influenced the field. The narrative commences by delving into the basics of Bayesian theory, clarifying essential concepts, and introducing primary methods for deriving posterior distributions, with an in-depth exploration of three types: Laplace approximation, stochastic sampling, and variational inference. Subsequently, the text explores the implementation of two types of Bayesian learning in structural dynamics: physical model learning and data-centric statistical model learning. Physical model learning emphasizes inferring physical model parameters within a Bayesian framework for system identification and prediction, while statistical model learning integrates Bayesian learning methodologies into data-centric statistical modeling within probabilistic machine learning. Both types resonate across various applications, such as modal analysis, model updating, damage detection, and reliability updating, highlighting their pivotal role in enhancing comprehension of dynamical systems and decision-making. The paper also navigates obstacles by proposing ways to enhance existing Bayesian inference strategies. Distinguished from previous research, this study offers a thorough examination of both traditional and cutting-edge Bayesian methods. It not only underscores the transformative influence of Bayesian approaches but also serves as a beacon, guiding researchers in the judicious selection and refinement of suitable methods for various challenges in structural dynamics.

physics.data-an↗

arXiv2024

DPGIIL: Dirichlet Process-Deep Generative Model-Integrated Incremental Learning for Clustering in Transmissibility-based Online Structural Anomaly Detection

Clustering based on vibration responses, such as transmissibility functions (TFs), is promising in structural anomaly detection. However, most existing methods struggle to determine the optimal cluster number, handle high-dimensional streaming data, and rely heavily on manually engineered features due to their shallow structures. To address these issues, this work proposes a novel clustering framework, referred to as Dirichlet process-deep generative model-integrated incremental learning (DPGIIL), for online structural anomaly detection, which combines the advantages of deep generative models (DGMs) in representation learning and the Dirichlet process mixture model (DPMM) in identifying distinct patterns in observed data. Within the context of variational Bayesian inference, a lower bound on the log marginal likelihood of DPGIIL, tighter than the evidence lower bound, is derived analytically, which enables the joint optimization of DGM and DPMM parameters, thereby allowing the DPMM to regularize the DGM's feature extraction process. Additionally, a greedy split-merge scheme-based coordinate ascent variational inference method is devised to accelerate the optimization. The summary statistics of the DPMM, along with the network parameters, are used to retain information about previous data for incremental learning. For online structural anomaly detection, DPGIIL can not only detect anomalies by dynamically assigning incoming data to new clusters but also indicate different structural states using distinct clusters, thereby providing additional information about the operating conditions of the monitored structure compared to traditional anomaly detectors. Three case studies demonstrate the dynamic adaptability of the proposed method and show that it outperforms some state-of-the-art approaches in both structural anomaly detection and clustering.

cs.LG↗

arXiv2024

Navigating Uncertainties in Machine Learning for Structural Dynamics: A Comprehensive Survey of Probabilistic and Non-Probabilistic Approaches in Forward and Inverse Problems

In the era of big data, machine learning (ML) has become a powerful tool in various fields, notably impacting structural dynamics. ML algorithms offer advantages by modeling physical phenomena based on data, even in the absence of underlying mechanisms. However, uncertainties such as measurement noise and modeling errors can compromise the reliability of ML predictions, highlighting the need for effective uncertainty awareness to enhance prediction robustness. This paper presents a comprehensive review on navigating uncertainties in ML, categorizing uncertainty-aware approaches into probabilistic methods (including Bayesian and frequentist perspectives) and non-probabilistic methods (such as interval learning and fuzzy learning). Bayesian neural networks, known for their uncertainty quantification and nonlinear mapping capabilities, are emphasized for their superior performance and potential. The review covers various techniques and methodologies for addressing uncertainties in ML, discussing fundamentals and implementation procedures of each method. While providing a concise overview of fundamental concepts, the paper refrains from in-depth critical explanations. Strengths and limitations of each approach are examined, along with their applications in structural dynamic forward problems like response prediction, sensitivity assessment, and reliability analysis, and inverse problems like system identification, model updating, and damage identification. Additionally, the review identifies research gaps and suggests future directions for investigations, aiming to provide comprehensive insights to the research community. By offering an extensive overview of both probabilistic and non-probabilistic approaches, this review aims to assist researchers and practitioners in making informed decisions when utilizing ML techniques to address uncertainties in structural dynamic problems.

cs.LG↗