A modified Kullback divergence for direct fault detection in large scale systems

Hamadouche, Anis; Kouadri, Abdelmalek; Bakdi, Azzeddine

doi:10.1016/j.jprocont.2017.09.004

Cited by 15 publications

(16 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The traditional KLD approach is expelled from performance comparison since it is completely impractical to consider recursive estimation of online to reference density ratio for such 27-dimensional space. The approximation multivariate KLD approach [34] is of high complexity for this RMPV system and data with a computation time measured around weeks in addition to out-of-memory problems. ) and fault-free (H) situations, more importantly, the components of the residual subspace are even more sensitive than those of the principal subspace showing some sort of separation of fault clusters.…”

Section: Resultsmentioning

confidence: 99%

“…Due to the fast dynamics and high-frequency high-dimensional data of grid-integrated RMPV systems, computation efficiency is important to realize the online real-time mismatch detection and power quality monitoring. A KL method such as [34] requires a computation time of several weeks in such applications with out-of-memory problems and it cannot be used in reality even if it is theoretically proved effective. More importantly, any approach must be checked for its proved reliability of detecting different types of RMPV system faults such as array mismatches, inverter faults, and grid perturbations.…”

Section: Resultsmentioning

confidence: 99%

“…Therefore, the most sensitive features are selected to detect and measure any operation deviation using an information gain named Kullback-Leibler (KL) divergence. Recently, KL divergence has proved its effectiveness in a considerable number of research items in multivariate process monitoring [34]. However, the KL divergence method is inefficient due to its high computational complexity that limits the application scope to low frequency (3-minutes sampled) data as reported in [34].…”

Section: Introductionmentioning

confidence: 99%

“…Recently, KL divergence has proved its effectiveness in a considerable number of research items in multivariate process monitoring [34]. However, the KL divergence method is inefficient due to its high computational complexity that limits the application scope to low frequency (3-minutes sampled) data as reported in [34]. [35] and [36] employed univariate KL divergence on multivariate principal scores obtained from a PCA model, this procedure was extended in [37] to incipient faults.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Nonparametric Kullback-divergence-PCA for intelligent mismatch detection and power quality monitoring in grid-connected rooftop PV

Bakdi

Bounoua

Mekhilef

et al. 2019

Energy

View full text Add to dashboard Cite

In parallel to sustainable growth in solar fraction, continuous reductions in Photovoltaic (PV) module and installation costs fuelled a profound adoption of residential Rooftop Mounted PV (RMPV) installations already reaching grid parity. RMPVs are promoted for economic, social, and environmental factors where they not only improve energy performance and reduce greenhouse effects but also contribute to bill savings.RMPV modules and energy conversion units are frequently subject to various types of anomalies which compromise power quality and promote fire risk and safety hazards for the personnel for which reliable protection is crucial. This article analyses historical data and presents a novel design that easily integrates with data storage units of RMPV systems to automatically process real-time data streams for reliable supervision. Dominant Transformed Components (TCs) are online extracted through multiblock Principal Component Analysis (PCA), most sensitive components are selected and their time-varying characteristics are recursively estimated in a moving window using smooth Kernel Density Estimation (KDE). Novel monitoring indices are developed as preventive alarms using Kullback-Leibler Divergence (KLD). This work exploits data records during 2015-2017 from thin-film, monocrystalline, and polycrystalline RMPV energy conversion systems. Fourteen test scenarios include array faults (line-to-line, line-to-ground, transient arc faults); DC-side mismatches (shadings, open circuits); grid-side anomalies (voltage sags, frequency variations); in addition to inverter anomalies and sensor faults.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Nonparametric Kullback-divergence-PCA for intelligent mismatch detection and power quality monitoring in grid-connected rooftop PV

Bakdi

Bounoua

Mekhilef

et al. 2019

Energy

View full text Add to dashboard Cite

show abstract

“…A novel control performance monitoring method based on KLD is proposed and applied to a multi-input-multi-output (MIMO) control system [12]. Hamadouche et al proposed a modified KLD detection algorithm based on non-parametric approximation, which was applied to the fault detection of large-scale industrial systems with high coupling in a noisy environment [13]. A method based on data-driven using the statistical feature is proposed, which uses KLD as a nonparametric fault indicator, and evaluates the severity of the fault through the characteristics of small cracks [14].…”

Section: Introductionmentioning

confidence: 99%

Optimized KLD-Based Fault Detection Method for Complex System Under Multi-Operation Conditions

Shi

Zhou

et al. 2020

IEEE Access

View full text Add to dashboard Cite

With the increasing development of industrial technology, fault detection technology has been widely applied in many complex systems. Aiming at the problems of multi-operation conditions and the data length needed for fault detection using Kullback-Leibler Divergence (KLD), a novel fault detection method for complex systems based on optimized KLD under multi-operation conditions is proposed in this paper. In the first place, based on the historical data of the system, the complex operation conditions of the system are divided into several simple mutually exclusive operation conditions, and the division standard is established. In the next place, the optimal length can be quickly determined by autocorrelation analysis and applied to various operation conditions. After the next, in the training stage, the KLD values of all training data are calculated with the benchmark that is the initial optimal data length of each operation condition. And the maximum value is taken as the threshold for fault detection. Afterward, in the test phase, it starts by judging the type of operation condition that the data belongs to, then the corresponding KLD value is calculated, which is compared with the corresponding threshold, so as to determine whether the fault occurs. Eventually, this method is applied to the suspension system of the maglev train and respectively compared with the fault detection methods based on Euclidean distance or Mahalanobis distance. The results show that the proposed method possesses a low false alarm rate and high sensitivity.

show abstract

The Evidence of the “No Free Lunch” Theorems and the Theory of Complexity in Business Artificial Intelligence

Gamoura

Koruca

Gülmez

et al. 2021

Trends in Data Engineering Methods for Intelligent Systems

View full text Add to dashboard Cite

A modified Kullback divergence for direct fault detection in large scale systems

Cited by 15 publications

References 32 publications

Nonparametric Kullback-divergence-PCA for intelligent mismatch detection and power quality monitoring in grid-connected rooftop PV

Nonparametric Kullback-divergence-PCA for intelligent mismatch detection and power quality monitoring in grid-connected rooftop PV

Optimized KLD-Based Fault Detection Method for Complex System Under Multi-Operation Conditions

The Evidence of the “No Free Lunch” Theorems and the Theory of Complexity in Business Artificial Intelligence

Contact Info

Product

Resources

About