Sensor Fusion for Fault Detection and Classification in Distributed Physical Processes

This paper proposes a feature extraction and fusion methodology to perform fault detection & classification in distributed physical processes generating heterogeneous data. The underlying concept is built upon a semantic framework for multi-sensor data interpretation using graphical models of Probabilistic Finite State Automata (PFSA).While the computational complexity is reduced by pruning the fused graphical model using an information-theoretic approach, the algorithms are developed to achieve high reliability via retaining the essential spatiotemporal characteristics of the physical processes. The concept has been validated on a simulation test bed of distributed shipboard auxiliary systems.

• Publication year

  2014

• Venue

  Frontiers in Robotics and AI

• Publication date

  2014-12-17

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.3389/frobt.2014.00016
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• State splitting and merging in probabilistic finite state automata for signal representation and analysis

  2014cited by this paper
• Real-time estimation of lead-acid battery parameters: A dynamic data-driven approach

  2014cited by this paper
• Performance comparison of feature extraction algorithms for target detection and classification

  2013cited by this paper
• An inner product space on irreducible and synchronizable probabilistic finite state automata

  2012influential reference
• An inner product space on irreducible and synchronizable probabilistic finite state automata

  2012cited by this paper
• Efficient information-theoretic graph pruning for graph-based SLAM with laser range finders

  2011cited by this paper
• Review and comparative evaluation of symbolic dynamic filtering for detection of anomaly patterns

  2009cited by this paper
• Mining abnormal patterns from heterogeneous time‐series with irrelevant features for fault event detection

  2009cited by this paper
• Pattern Recognition and Machine Learning

  2006cited by this paper
• Elements of information theory (2. ed.)

  2006cited by this paper
• A Scoring Function for Learning Bayesian Networks based on Mutual Information and Conditional Independence Tests

  2006cited by this paper
• Hidden Markov Models and Gaussian Mixture Models for Bearing Fault Detection Using Fractals

  2006cited by this paper
• Symbolic time series analysis via wavelet-based partitioning

  2006cited by this paper
• Elements of Information Theory

  2005cited by this paper
• Argonaute—a database for gene regulation by mammalian microRNAs

  2005cited by this paper
• Particle methods for change detection, system identification, and control

  2004cited by this paper
• Symbolic dynamic analysis of complex systems for anomaly detection

  2004cited by this paper
• Kernel Methods for Pattern Analysis

  2004cited by this paper
• Statistical Pattern Recognition, Second Edition

  2002cited by this paper
• Fault detection method for nonlinear systems based on probabilistic neural network filtering

  2002cited by this paper
• Dynamic bayesian networks: representation, inference and learning

  2002cited by this paper
• Kalman Filtering: Theory and Practice Using MATLAB

  2001cited by this paper
• Particle filtering based likelihood ratio approach to fault diagnosis in nonlinear stochastic systems

  2001cited by this paper
• A new method for the nonlinear transformation of means and covariances in filters and estimators

  2000cited by this paper
• A fault tolerant flight control system for sensor and actuator failures using neural networks

  2000cited by this paper
• Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999

  2000cited by this paper
• Mutual information relevance networks: functional genomic clustering using pairwise entropy measurements.

  1999cited by this paper
• A multiple model predictive scheme for fault-tolerant flight control design

  1998cited by this paper
• Deterministic nonlinear observer-based approaches to fault diagnosis: A survey

  1997cited by this paper
• Neural Networks: A Comprehensive Foundation

  1994cited by this paper
• Survey of model-based failure detection and isolation in complex plants

  1988cited by this paper
• Applied optimal estimation

  1976cited by this paper

• Bidirectional linear recurrent models for sequence-level multisource fusion

  2025cites this paper
• Bidirectional Linear Recurrent Models for Sequence-Level Multisource Fusion

  2025cites this paper
• Optimized Fuzzy Slope Entropy: A Complexity Measure for Nonlinear Time Series

  2024influential citation
• EagleCam: a 1.5U Low-Cost CubeSat Mission for a Novel Third-Person View of a Lunar Landing

  2023cites this paper
• An unsupervised anomaly detection approach using spatiotemporal feature in hot strip rolling

  2023cites this paper
• Multimodal sensor fusion framework for residential building occupancy detection

  2022cites this paper
• Development of a Methodology Using Artificial Neural Network in the Detection and Diagnosis of Faults for Pneumatic Control Valves

  2021cites this paper
• Efficient Anomaly Detection in a Laser-Surface Heat-Treatment Process via Laser-Spot Tracking

  2021cites this paper
• Traffic System Anomaly Detection using Spatiotemporal Pattern Networks

  2020cites this paper
• Traffic sensor health monitoring using spatiotemporal graphical modeling

  2020cites this paper
• Autonomous root-cause fault diagnosis using symbolic dynamic based causality analysis

  2020cites this paper
• Ten questions concerning occupant health in buildings during normal operations and extreme events including the COVID-19 pandemic

  2020cites this paper
• A New Method of Planetary Gearbox Fault Detection Based on Multi-Sensor Information Fusion

  2019cites this paper
• Vibration propagation identification of rotor-bearing-casing system using spatiotemporal graphical modeling

  2019cites this paper
• Traffic Dynamics Exploration and Incident Detection Using Spatiotemporal Graphical Modeling

  2019influential citation
• For publication in 2019 ACC A flexible framework for building occupancy detection using spatiotemporal pattern networks

  2019cites this paper
• A New Method of Two-stage Planetary Gearbox Fault Detection Based on Multi-Sensor Information Fusion

  2019cites this paper
• Data-driven root-cause fault diagnosis for multivariate non-linear processes

  2018cites this paper
• Root-cause Analysis for Time-series Anomalies via Spatiotemporal Graphical Modeling in Distributed Complex Systems

  2018cites this paper
• Bayesian Nonparametric Modeling of Categorical Data for Information Fusion and Causal Inference

  2018cites this paper
• Building Energy Disaggregation using Spatiotemporal Pattern Network

  2018cites this paper
• Linked read technology for assembling large complex and polyploid genomes

  2018cites this paper
• Spatiotemporal Cyberspace Situation Awareness Mechanism for Backbone Networks

  2018cites this paper
• R-TAR: A Resilient Traffic Anomaly Recognition Mechanism for Backbone Network

  2018cites this paper
• Exploring Granger causality in dynamical systems modeling and performance monitoring

  2018cites this paper
• An unsupervised spatiotemporal graphical modeling approach for wind turbine condition monitoring

  2018cites this paper
• Multivariate exploration of non-intrusive load monitoring via spatiotemporal pattern network

  2018cites this paper
• A Data-driven Approach towards Integration of Microclimate Conditions for Predicting Building Energy Performance

  2018cites this paper
• Spatiotemporal graphical modeling for cyber-physical systems

  2018influential citation
• Energy prediction using spatiotemporal pattern networks

  2017cites this paper
• An unsupervised anomaly detection approach using energy-based spatiotemporal graphical modeling

  2017influential citation
• Hierarchical feature extraction from spatiotemporal data for cyber-physical system analytics

  2017cites this paper
• Merging fuzzy observer-based state estimation and database classification for fault detection and diagnosis of an actuated seat

  2017cites this paper
• Probabilistic Graphical Modeling of Distributed Cyber-Physical Systems

  2017cites this paper
• Data-driven persistent monitoring of Indoor Air Systems

  2016cites this paper
• Bridge damage detection using spatiotemporal patterns extracted from dense sensor network

  2016cites this paper
• Data-driven root-cause analysis for distributed system anomalies

  2016cites this paper
• Data driven exploration of traffic network system dynamics using high resolution probe data

  2016cites this paper
• Damage Detection of Bridge Network With Spatiotemporal Pattern Network

  2016cites this paper
• Dynamic data-driven prediction of instability in a swirl-stabilized combustor

  2016cites this paper
• Curve ) Baseline Bottleneck Dimension : 206 Bottleneck Dimension : 98 Bottleneck Dimension : 26 Bottleneck Dimension : 14 Bottleneck Dimension : 6 Bottleneck Dimension

  2016cites this paper
• PHM Decision Support under Uncertainty

  2016cites this paper
• Synthesis of Distributed Cognitive Systems: Interacting Computational Maps for Multisensory Fusion

  2016cites this paper
• Root-cause analysis for time-series anomalies via spatiotemporal causal graphical modeling

  2016cites this paper
• Deep learning for decision making and autonomous complex systems

  2016cites this paper
• Flight Anomaly Tracking for Improved Situational Awareness: Case Study of Germanwings Flight 9525

  2016cites this paper
• Dynamic data-driven symbolic causal modeling for battery performance & health monitoring

  2015cites this paper
• An Unsupervised Spatiotemporal Graphical Modeling Approach to Anomaly Detection in Distributed CPS

  2015cites this paper
• DSCC 2015-9784 UNDERSTANDING WIND TURBINE INTERACTIONS USING SPATIOTEMP ORAL PATTERN NETWORK

  2015cites this paper