Adaptive data-derived anomaly detection in the activated sludge process of a large-scale wastewater treatment plant

Haimi, Henri; Mulas, Michela; Corona, Francesco; Marsili-Libelli, Stefano; Lindell, Paula; Heinonen, Mari; Vahala, Riku

doi:10.1016/j.engappai.2016.02.003

Cited by 31 publications

(14 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The APCA can be classified into two algorithms: 29,31 (1) recursive principal component analysis (RPCA) using recursive adaptation techniques 17–19,27,30 and (2) Moving window linear PCA (MWPCA) using moving window techniques. 12,15,18,23,28–31 The MWPCA uses the moving window along the sequential data stream to adapt the intrinsic change of the normal condition. On the other hand, the RPCA has an advanced version of the IPCA.…”

Section: Proposed Methods Using Online Learning Algorithm With Variablmentioning

confidence: 99%

“…To address these issues, variable moving window linear principal component analysis (VMWPCA) has been recently proposed. 15,23,28,30 The most popular method for the variable moving window is to use the changes of the mean and covariance structures. Figure 5 shows the difference between the fixed and variable moving window in the MWPCA.…”

Section: Proposed Methods Using Online Learning Algorithm With Variablmentioning

confidence: 99%

“…Essentially, the linear PCA is a linear tool. Since the previous VMWPCA 15,23,28,30 is rooted in the linear PCA, these methods cannot deal with non-linear dependency effectively. To overcome this limitation, the proposed variable moving window strategy is developed using the block-wise linearization concept with online learning framework.…”

Section: Proposed Methods Using Online Learning Algorithm With Variablmentioning

confidence: 99%

“…However, the CPV is a subjective approach, so that the value of the CPV was typically determined from 80% to 99% in the previous studies. 3,12,17–19 Rather than using the heuristic choice of the CPV, this study uses the eigengap technique 20–23 for the optimal number of PCs. When eigenvalues are ranked in descending order, the eigengap is calculated as…”

Section: Pca-based Spmmentioning

confidence: 99%

See 3 more Smart Citations

Vibration-based damage detection using online learning algorithm for output-only structural health monitoring

Jin

Jung

2017

Structural Health Monitoring

View full text Add to dashboard Cite

Damage-sensitive features such as natural frequencies are widely used for structural health monitoring; however, they are also influenced by the environmental condition. To address the environmental effect, principal component analysis is widely used. Before performing principal component analysis, the training data should be defined for the normal condition (baseline model) under environmental variability. It is worth noting that the natural change of the normal condition may exist due to an intrinsic behavior of the structural system. Without accounting for the natural change of the normal condition, numerous false alarms occur. However, the natural change of the normal condition cannot be known in advance. Although the description of the normal condition has a significant influence on the monitoring performance, it has received much less attention. To capture the natural change of the normal condition and detect the damage simultaneously, an adaptive statistical process monitoring using online learning algorithm is proposed for output-only structural health monitoring. The novelty aspect of the proposed method is the adaptive learning capability by moving the window of the recent samples (from normal condition) to update the baseline model. In this way, the baseline model can reflect the natural change of the normal condition in environmental variability. To handle both change rate of the normal condition and non-linear dependency of the damage-sensitive features, a variable moving window strategy is also proposed. The variable moving window strategy is the block-wise linearization method using k-means clustering based on Linde–Buzo–Gray algorithm and Bayesian information criterion. The proposed method and two existing methods (static linear principal component analysis and incremental linear principal component analysis) were applied to a full-scale bridge structure, which was artificially damaged at the end of the long-term monitoring. Among the three methods, the proposed method is the only successful method to deal with the non-linear dependency among features and detect the structural damage timely.

show abstract

Section: Proposed Methods Using Online Learning Algorithm With Variablmentioning

confidence: 99%

Section: Proposed Methods Using Online Learning Algorithm With Variablmentioning

confidence: 99%

Section: Proposed Methods Using Online Learning Algorithm With Variablmentioning

confidence: 99%

Section: Pca-based Spmmentioning

confidence: 99%

See 2 more Smart Citations

Vibration-based damage detection using online learning algorithm for output-only structural health monitoring

Jin

Jung

2017

Structural Health Monitoring

View full text Add to dashboard Cite

show abstract

“…Labelled training data is it pertains to system attacks is however not as easily available making this a major limiting factor. The process dynamics of real world critical water infrastructure will evolve over time meaning that proposed anomaly detection schemes should take this into consideration [ 62 ]. The use of simulated data is useful in determining the viability of the proposed schemes but may not adequately portray the challenges of practically deployed full-scale system.…”

Section: Anomaly Detection In Water Systemsmentioning

confidence: 99%

A Survey of Anomaly Detection in Industrial Wireless Sensor Networks with Critical Water System Infrastructure as a Case Study

Ramotsoela

Abu‐Mahfouz

Hancke

2018

Sensors

115

View full text Add to dashboard Cite

The increased use of Industrial Wireless Sensor Networks (IWSN) in a variety of different applications, including those that involve critical infrastructure, has meant that adequately protecting these systems has become a necessity. These cyber-physical systems improve the monitoring and control features of these systems but also introduce several security challenges. Intrusion detection is a convenient second line of defence in case of the failure of normal network security protocols. Anomaly detection is a branch of intrusion detection that is resource friendly and provides broader detection generality making it ideal for IWSN applications. These schemes can be used to detect abnormal changes in the environment where IWSNs are deployed. This paper presents a literature survey of the work done in the field in recent years focusing primarily on machine learning techniques. Major research gaps regarding the practical feasibility of these schemes are also identified from surveyed work and critical water infrastructure is discussed as a use case.

show abstract

Technology status and trends of industrial wastewater treatment: A patent analysis

et al. 2022

View full text Add to dashboard Cite

Adaptive data-derived anomaly detection in the activated sludge process of a large-scale wastewater treatment plant

Cited by 31 publications

References 39 publications

Vibration-based damage detection using online learning algorithm for output-only structural health monitoring

Vibration-based damage detection using online learning algorithm for output-only structural health monitoring

A Survey of Anomaly Detection in Industrial Wireless Sensor Networks with Critical Water System Infrastructure as a Case Study

Technology status and trends of industrial wastewater treatment: A patent analysis

Contact Info

Product

Resources

About