Fault Detection In Complex Systems Research Articles

Interpretable Recurrent Variational State-Space Model for Fault Detection of Complex Systems Based on Multisensory Signals

It is necessary to develop a health monitoring system (HMS) for complex systems to improve safety and reliability and prevent potential failures. Time-series signals are collected from multiple sensors installed on the equipment that can reflect the health condition of them. In this study, a novel interpretable recurrent variational state-space model (IRVSSM) is proposed for time-series modeling and anomaly detection. To be specific, the deterministic hidden state of a recursive neural network is used to capture the latent structure of sensor data, while the stochastic latent variables of a nonlinear deep state-space model capture the diversity of sensor data. Temporal dependencies are modeled through a nonlinear transition matrix; an automatic relevance determination network is introduced to selectively emphasize important sensor data. Experimental results demonstrate that the proposed algorithm effectively captures vital information within the sensor data and provides accurate and reliable fault diagnosis during the steady-state phase of liquid rocket engine operation.

BiGraphormer: A Bidirectional Graphormer on Directed Causal Graph for Fault Detection in Complex Systems

BiGraphormer: A Bidirectional Graphormer on Directed Causal Graph for Fault Detection in Complex Systems

Inverse fuzzy fault model for fault detection and isolation with least angle regression for variable selection

Fault detection is paramount in industrial processes because expensive reparations can be avoided, and the normal flow of operations is not disrupted. However, it is difficult to use a model-based method for fault detection in complex systems. Thus, a data-driven approach is implemented in the Tennessee Eastman process for fault detection and isolation (FDI). As a contribution, this paper proposes an inverse fuzzy fault model to detect and isolate faults. To reduce the amount of data to process, the least angle regression is applied for variable selection. To compare the detection and isolation times obtained using the fuzzy fault model, a fuzzy classifier is described; where the signals are preprocessed with the wavelet transform to highlight the faulty signals. The inverse fuzzy fault model has only four fuzzy rules and shows a smaller isolation time than the required using the fuzzy classifier.

Fault detection via nonlinear profile monitoring using artificial neural networks

AbstractFault detection is the characterization of a normal behavior of a system using a response function or profile of interest and the identification of any deviation from such normal behavior. As system complexity grows, predicting the underlying structure or form of response function becomes challenging if not impossible. This article presents a data‐driven approach for fault detection of complex systems using multivariate statistical process control based on artificial neural network (ANN) characterization. In this approach, the quality of a system is characterized where one explanatory variable is adequately explained as a function of the other variables using an ANN model. The vector of weights and biases of the ANN model is monitored by using Hotelling T2 through control charts. The proposed method is tested and compared with existing methods such as polynomial and sum of sine function regression for 3 cases from the literature. Moreover, it is applied to a 4‐story reinforced concrete building that uses continuous monitoring to avoid potentially catastrophic failures. The proposed ANN approach outperforms the existing methods for small shifts (deviations) from healthy states. For large and medium shifts, it provides comparable results that are on the conservative side.

A new adaptive PCA based thresholding scheme for fault detection in complex systems

For large scale and complex processes, data-driven analysis methods are receiving increasing attention for fault detection and diagnosis to improve process operation by detecting when abnormal process operations exist and diagnosing the sources of the abnormalities. Common methods based on multivariate statistical analysis are widely used and particularly principal component analysis (PCA), fault detection indices used along with PCA including the Hotelling T² statistic and the sum of squared prediction error (SPE) known as the Q statistic can be used to identify faults. This paper develops a new adaptive thresholding scheme based on a modified exponentially weighted moving average (EWMA) control chart statistic, which is effective in detecting small changes and abrupt shifts in the process operation. The aim is to enhance the performance of PCA methods for process monitoring, while maintaining a low false alarm rate with good sensitivity of anomalies. The performance of the developed scheme is compared to a conventional fixed thresholding technique by evaluating the detection performance across various types of faults that occurred in the Tennessee Eastman Process, The results demonstrate the promising capabilities of our proposed scheme.

Modeling and Tracking of Transaction Flow Dynamics for Fault Detection in Complex Systems

With the prevalence of Internet services and the increase of their complexity, there is a growing need to improve their operational reliability and availability. While a large amount of monitoring data can be collected from systems for fault analysis, it is hard to correlate this data effectively across distributed systems and observation time. In this paper, we analyze the mass characteristics of user requests and propose a novel approach to model and track transaction flow dynamics for fault detection in complex information systems. We measure the flow intensity at multiple checkpoints inside the system and apply system identification methods to model transaction flow dynamics between these measurements. With the learned analytical models, a model-based fault detection and isolation method is applied to track the flow dynamics in real time for fault detection. We also propose an algorithm to automatically search and validate the dynamic relationship between randomly selected monitoring points. Our algorithm enables systems to have self-cognition capability for system management. Our approach is tested in a real system with a list of injected faults. Experimental results demonstrate the effectiveness of our approach and algorithms

A Probabilistic Resource Allocating Network for Novelty Detection

The detection of novel or abnormal input vectors is of importance in many monitoring tasks, such as fault detection in complex systems and detection of abnormal patterns in medical diagnostics. We have developed a robust method for novelty detection, which aims to minimize the number of heuristically chosen thresholds in the novelty decision process. We achieve this by growing a gaussian mixture model to form a representation of a training set of “normal” system states. When previously unseen data are to be screened for novelty we use the same threshold as was used during training to define a novelty decision boundary. We show on a sample problem of medical signal processing that this method is capable of providing robust novelty decision boundaries and apply the technique to the detection of epileptic seizures within a data record.