Fault detection in a wastewater treatment plant based on neural networks and PCA

Fuente, José Luis de la; Garcia-Alvarez, D.; Sainz-Palmero, G.I.; Vega, Pastora

doi:10.1109/med.2012.6265729

Cited by 11 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this context, traditional methods include the Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Independent Component Analysis (ICA), Multidimensional Scaling, and polynomial approximation [1]. Moreover, CI techniques have also been used for feature extraction, including Feed-Forward Neural Networks [61]- [63], Self-Organizing Maps (SOM) [64]- [66], and deep learning [67]. Regressive models based on Radial Basis Function (RBF) Neural Networks have also been used for feature extraction [68].…”

Section: Feature Extraction and Selectionmentioning

confidence: 99%

Computational intelligence for industrial and environmental applications

Labati

Genovese

Muñoz

et al. 2016

2016 IEEE 8th International Conference on Intelligent Systems (IS)

View full text Add to dashboard Cite

Computational Intelligence (CI) techniques are being increasingly used for automatic monitoring and control systems, especially regarding industrial and environmental applications, due to their performance, their capabilities in fusing noisy or incomplete data obtained from heterogeneous sensors, and the ability in adapting to variations in the operational conditions. Moreover, the increase in the computational power and the decrease of the size of the computing architectures allowed a more pervasive use of CI techniques in a great variety of situations. In this paper, we propose a brief review of the most important CI techniques applied in each step of the design of a monitoring and control system for industrial and environmental applications, and describe how these techniques are integrated in the development of efficient industrial and environmental applications.

show abstract

Section: Feature Extraction and Selectionmentioning

confidence: 99%

Computational intelligence for industrial and environmental applications

Labati

Genovese

Muñoz

et al. 2016

2016 IEEE 8th International Conference on Intelligent Systems (IS)

View full text Add to dashboard Cite

show abstract

“…LDA is used for data classification dimensionality reduction and provides better performance than PCA for high-dimensional data. 21 However, LDA faces the problem of singularities. 22 OFNDA techniques are mostly used in medical data analysis 23 and provide better feature reduction performance compared to PCA and LDA.…”

Section: Approaches To Fault Diagnosismentioning

confidence: 99%

Neural network fault diagnosis of a trolling motor based on feature reduction techniques for an unmanned surface vehicle

Abed

Sharma

Sutton

2015

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

This article presents a novel approach to the diagnosis of unbalanced faults in a trolling motor under stationary operating conditions. The trolling motor being typically of that used as the propulsion system for an unmanned surface vehicle, the diagnosis approach is based on the use of discrete wavelet transforms as a feature extraction tool and a time-delayed neural network for fault classification. The time-delayed neural network classifies between healthy and faulty conditions of the trolling motor by analysing the stator current and vibration. To overcome feature redundancy, which affects diagnosis accuracy, several feature reduction methods have been tested, and the orthogonal fuzzy neighbourhood discriminant analysis approach is found to be the most effective method. Four faulty conditions were analysed under laboratory conditions, where one of the blades causing damage to the trolling motor is cut into 10%, 25%, half and then into full to simulate the effects of propeller blades being damaged partly or fully. The results obtained from the real-time simulation demonstrate the effectiveness and reliability of the proposed methodology in classifying the different faults faster and accurately.

show abstract

“…In order to account for the non-linearity of the system, different literature studies have reported new methodologies to extend the applicability of PCA in dynamic non-linear problems, using a model-based PCA approach. − These hybrid methods integrate different machine learning methods, like neural networks, to remove the nonlinearity information from the raw data, and then, the resulting residuals between the model and sensor are analyzed by PCA to generate monitoring charts. , …”

Section: Introductionmentioning

confidence: 99%

“…Fault-detection studies have often been applied under noncommon in situ- operating conditions. Some studies have focused on large faults, that is, complete sensor failures, loss of signal, and abnormal measurement ranges, which can be more easily identified. ,, Others have often relied on simulated sensor signal disruptions, which can be unrealistic and cannot successfully replicate the actual behavior of an erratic sensor. , Only a few studies have applied their models on real sensor data affected by partial faults under typical operating conditions, but they often require a large number of grab sample laboratory analysis , or they analyze sensor faults using SBR laboratory or pilot-scale reactors which is a very controlled environment. , …”

Section: Introductionmentioning

confidence: 99%

Soft Sensing for On-Line Fault Detection of Ammonium Sensors in Water Resource Recovery Facilities

Cecconi¹,

Rosso

2021

Environ. Sci. Technol.

View full text Add to dashboard Cite

The increasing demand for online sensors applied to advanced control strategies in water resource recovery facilities has resulted in the increasing investigation of fault-detection methods to improve the reliability of sensors installed in harsh environments. The study herein focuses on the fault detection of ammonium sensors, especially for effluent monitoring, given their potential in ammonium-based aeration control applications. An artificial neural network model was built to predict the ammonium content in the effluent by employing the information from five other sensors installed in the activated sludge tank: NH4 +, pH, ORP, DO, and TSS. The residual between the model prediction and the effluent ammonium sensor signal was utilized in a fault-detection mechanism based on principal component analysis and Shewhart monitoring charts. In contrast to previous studies, the present work utilizes typical faults collected from a 1 year historic dataset of an actual sensor setup. Treatment process anomalies, calibration bias faults, and fouling drifts were the most common issues identified from the historic dataset, and they were promptly identified by the proposed fault-detection methodology. Once a fault is detected, the model prediction can be actively used in place of the sensor for process control without affecting the treatment process by utilizing faulty datasets.

show abstract

Fault detection in a wastewater treatment plant based on neural networks and PCA

Cited by 11 publications

References 14 publications

Computational intelligence for industrial and environmental applications

Computational intelligence for industrial and environmental applications

Neural network fault diagnosis of a trolling motor based on feature reduction techniques for an unmanned surface vehicle

Soft Sensing for On-Line Fault Detection of Ammonium Sensors in Water Resource Recovery Facilities

Contact Info

Product

Resources

About