Fault detection and isolation | EPFL Graph Search

Fault detection, isolation, and recovery (FDIR) is a subfield of control engineering which concerns itself with monitoring a system, identifying when a fault has occurred, and pinpointing the type of fault and its location. Two approaches can be distinguished: A direct pattern recognition of sensor readings that indicate a fault and an analysis of the discrepancy between the sensor readings and expected values, derived from some model. In the latter case, it is typical that a fault is said to be detected if the discrepancy or residual goes above a certain threshold. It is then the task of fault isolation to categorize the type of fault and its location in the machinery. Fault detection and isolation (FDI) techniques can be broadly classified into two categories. These include model-based FDI and signal processing based FDI. Model-based FDI In model-based FDI techniques some model of the system is used to decide about the occurrence of fault. The system model may be

Fault Detection and Diagnosis with Imbalanced and Noisy Data: A Hybrid Framework for Rotating Machinery

Amin Kaboli

Fault diagnosis plays an essential role in reducing the maintenance costs of rotating machinery manufacturing systems. In many real applications of fault detection and diagnosis, data tend to be imbalanced, meaning that the number of samples for some fault classes is much less than the normal data samples. At the same time, in an industrial condition, accelerometers encounter high levels of disruptive signals and the collected samples turn out to be heavily noisy. As a consequence, many traditional Fault Detection and Diagnosis (FDD) frameworks get poor classification performances when dealing with real-world circumstances. Three main solutions have been proposed in the literature to cope with this problem: (1) the implementation of generative algorithms to increase the amount of under-represented input samples, (2) the employment of a classifier being powerful to learn from imbalanced and noisy data, (3) the development of an efficient data preprocessing including feature extraction and data augmentation. This paper proposes a hybrid framework which uses the three aforementioned components to achieve an effective signal based FDD system for imbalanced conditions. Specifically, it first extracts the fault features, using Fourier and wavelet transforms to make full use of the signals. Then, it employs Wasserstein Generative Adversarial with Gradient Penalty Networks (WGAN-GP) to generate synthetic samples to populate the rare fault class and enrich the training set. Moreover, to achieve a higher performance a novel combination of Convolutional Long Short-term Memory (CLSTM) and Weighted Extreme Learning Machine (WELM) is also proposed. To verify the effectiveness of the developed framework, different bearing datasets settings on different imbalance severities and noise degrees were used. The comparative results demonstrate that in different scenarios GAN-CLSTM-ELM significantly outperforms the other state-of-the-art FDD frameworks.

MDPI2022

Scalable Monitoring of Interconnected Stochastic Systems

Marcello Farina, Giancarlo Ferrari Trecate

In this paper, we propose a novel distributed fault detection method to monitor the state of a linear system, partitioned into interconnected subsystems. The approach hinges on the definition of a partition-based distributed Luenberger estimator, based on the local model of the subsystems and that takes into account the dynamic coupling terms between the subsystems. The proposed methodology computes – in a distributed way – a bound on the variance of a properly defined residual signal, considering the uncertainty related to the state estimates performed by the neighboring subsystems. This bound allows the computation of suitable local thresholds with guaranteed maximum false-alarms rate. The implementation of the proposed estimation and fault detection method is scalable, allowing Plug & Play operations and the possibility to disconnect the faulty subsystem after fault detection. Theoretical conditions guaranteeing the convergence of the estimates and of the bounds are provided. Simulation results show the effectiveness of the proposed method.

2016

Distributed Fault Detection for Interconnected Large-Scale Systems: A Scalable Plug & Play Approach

Marcello Farina, Giancarlo Ferrari Trecate

In this paper, we propose a novel distributed fault detection method to monitor the state of a-possibly large scale-linear system, partitioned into interconnected subsystems. The approach hinges on the definition of a partition-based distributed Luenberger-like estimator, based on the local model of the subsystems and that takes into account their dynamic coupling. The proposed methodology computes-in a distributed way-a bound on the variance of a properly defined residual signal. This bound depends on the uncertainty affecting the state estimates computed by the neighboring subsystems and it allows the computation of local fault detection thresholds, as well as the maximum false-alarm rate. The implementation of the proposed estimation and fault detection method is scalable, allowing Plug & Play operations, and the possibility to disconnect the faulty subsystem after fault detection. Theoretical conditions on the convergence properties of the estimates and of the estimation error bounds are provided. Simulation results on a power network benchmark show the effectiveness of the proposed method.

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2019

Fault Detection and Diagnosis with Imbalanced and Noisy Data: A Hybrid Framework for Rotating Machinery

Amin Kaboli

MDPI2022