☆ 4.6 Article

Data-Driven Fault Diagnosis Techniques: Non-Linear Directional Residual vs. Machine-Learning-Based Methods

SENSORS (2022)

Related references

Note: Only part of the references are listed.

Article Engineering, Mechanical

Aircraft robust data-driven multiple sensor fault diagnosis based on optimality criteria

Nicholas Cartocci et al.

Summary: A robust data-driven scheme for Fault Detection, Isolation and Estimation of multiple sensor faults is proposed and validated. The scheme achieves robustness to modeling uncertainty and noise through optimized design. The proposed scheme is applied to a set of 8 sensors of a semi-autonomous aircraft and compared with other multiple Fault Diagnosis schemes.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2022)

Add to Collection

Article Computer Science, Information Systems

A distributed sensor-fault detection and diagnosis framework using machine learning

Sana Ullah Jan et al.

Summary: The work focuses on designing a sensor-fault detection and diagnosis system for the Internet of Things and Cyber-Physical Systems, utilizing machine learning algorithms for distributed monitoring and diagnosis to improve efficiency in fault detection and diagnosis.

INFORMATION SCIENCES (2021)

Add to Collection

Article Chemistry, Analytical

A Comprehensive Case Study of Data-Driven Methods for Robust Aircraft Sensor Fault Isolation

Nicholas Cartocci et al.

Summary: This paper compares data-driven sensor fault isolation and fault estimation techniques using flight data, deriving residuals from linear regression models for fault isolation. A bank of Bayesian filters is proposed to compute fault beliefs for each sensor, with the techniques validated through experiments. Ultimately, the performance of the methods is evaluated for sensor faults in air-data sensors.

SENSORS (2021)

Add to Collection

Proceedings Paper Automation & Control Systems

Data-Driven Sensor Fault Diagnosis Based on Nonlinear Additive Models and Local Fault Sensitivity

N. Cartocci et al.

Summary: This paper proposes non-linear Additive Models to characterize non-linear redundancy relations in system signals, identifying them directly from data using the MARS algorithm. These relations are then linearized to derive a time-dependent fault signature matrix for fault isolation based on residual analysis, showing improved performance compared to a state-of-the-art method relying on linear redundancy relations.

2021 20TH INTERNATIONAL CONFERENCE ON ADVANCED ROBOTICS (ICAR) (2021)

Add to Collection

Review Computer Science, Artificial Intelligence

A review on fault detection and diagnosis techniques: basics and beyond

Anam Abid et al.

Summary: This paper discusses the importance of fault detection and diagnosis methods in modern systems, reviewing both traditional model-based and signal processing-based FDD approaches, as well as AI-based methods. Additionally, typical steps involved in the design and development of automatic FDD systems are systematically presented to outline the present status of FDD.

ARTIFICIAL INTELLIGENCE REVIEW (2021)

Add to Collection

Proceedings Paper Computer Science, Cybernetics

Ensemble-Based Fault Detection and Isolation of an Industrial Gas Turbine

Mehdi Mousavi et al.

2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC) (2020)

Add to Collection

Article Engineering, Chemical

Reconstruction-Based Multivariate Process Fault Isolation Using Bayesian Lasso

Zhengbing Yan et al.

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH (2018)

Add to Collection

Article Green & Sustainable Science & Technology

Data driven sensor and actuator fault detection and isolation in wind turbine using classifier fusion

Vahid Pashazadeh et al.

RENEWABLE ENERGY (2018)

Add to Collection

Article Automation & Control Systems

Combining model-based diagnosis and data-driven anomaly classifiers for fault isolation

Daniel Jung et al.

CONTROL ENGINEERING PRACTICE (2018)

Add to Collection

Article Engineering, Electrical & Electronic

An efficient system for anomaly detection using deep learning classifier

A. R. Revathi et al.

SIGNAL IMAGE AND VIDEO PROCESSING (2017)

Add to Collection

Review Engineering, Chemical

A review on different pipeline fault detection methods

Shantanu Datta et al.

JOURNAL OF LOSS PREVENTION IN THE PROCESS INDUSTRIES (2016)

Add to Collection

Article Computer Science, Artificial Intelligence

High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning

Sarah M. Erfani et al.

PATTERN RECOGNITION (2016)

Add to Collection

Article Engineering, Industrial

A nonparametric fault isolation approach through one-class classification algorithms

Seoung Bum Kim et al.

IIE TRANSACTIONS (2011)

Add to Collection

Article Automation & Control Systems

Design and flight-testing of non-linear formation control laws

Giampiero Campa et al.

CONTROL ENGINEERING PRACTICE (2007)

Add to Collection

Article Engineering, Manufacturing

Degradation assessment and fault modes classification using logistic regression

JH Yan et al.

JOURNAL OF MANUFACTURING SCIENCE AND ENGINEERING-TRANSACTIONS OF THE ASME (2005)

Add to Collection

© Peeref 2019-2024. All rights reserved.