Monitoring and fault detection in a reverse osmosis plant using principal component analysis

Garcia-Alvarez, D.; Fuente, José Luis de la; Palacin, Luis

doi:10.1109/cdc.2011.6160345

Cited by 7 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For real situations, it should be obtained a batch of models according to different water content ranges and, once the current ballast water content is measured, the suitable model should be used for the classification process. A similar solution is proposed in [43].…”

Section: Discussionmentioning

confidence: 99%

Advanced monitoring of rail breakage in double-track railway lines by means of PCA techniques

Espinosa

Garcı́a

Hernández

et al. 2018

Applied Soft Computing

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Advanced monitoring of rail breakage in double-track railway lines by means of PCA techniques

Espinosa

Garcı́a

Hernández

et al. 2018

Applied Soft Computing

View full text Add to dashboard Cite

“…Another approach proposed hybrid minimal structurally overdetermined sets for hybrid systems formulated as a binary integer linear programming optimization problem [17]. Furthermore, the analysis of the most similar approaches to the one proposed in this paper revealed that the unfold principal component analysis (UPCA) and principal component analysis (PCA) [13,14] were applied for monitoring reverse osmosis processes. However, in this case the application of these two techniques was not considered appropriate since PCA does not allow for the management of process nonlinearities and UPCA is more suitable for batch production, which is absent in the process under analysis.…”

Section: Introductionmentioning

confidence: 90%

“…As previously mentioned, the reverse osmosis process has a crucial role in pharmaceutical processes, and it is therefore a critical aspect that should be carefully managed in pharmaceutical manufacturing, especially when considering semisolid and liquid products [12]. The issue of maintenance of this installation category is therefore an important and highly debated matter for which several approaches have been suggested over the years [13][14][15]. Nevertheless, the existing literature on the subject of reverse osmosis process monitoring is limited.…”

Section: Introductionmentioning

confidence: 99%

Monitoring a Reverse Osmosis Process with Kernel Principal Component Analysis: A Preliminary Approach

et al. 2021

View full text Add to dashboard Cite

The water purification process is becoming increasingly important to ensure the continuity and quality of subsequent production processes, and it is particularly relevant in pharmaceutical contexts. However, in this context, the difficulties arising during the monitoring process are manifold. On the one hand, the monitoring process reveals various discontinuities due to different characteristics of the input water. On the other hand, the monitoring process is discontinuous and random itself, thus not guaranteeing continuity of the parameters and hindering a straightforward analysis. Consequently, further research on water purification processes is paramount to identify the most suitable techniques able to guarantee good performance. Against this background, this paper proposes an application of kernel principal component analysis for fault detection in a process with the above-mentioned characteristics. Based on the temporal variability of the process, the paper suggests the use of past and future matrices as input for fault detection as an alternative to the original dataset. In this manner, the temporal correlation between process parameters and machine health is accounted for. The proposed approach confirms the possibility of obtaining very good monitoring results in the analyzed context.

show abstract

“…The current approach to data collection, interpretation, and utilization is not suitable for rapid identification of malfunction, swift control and adjustment under transient fluctuations, or efficient decision-making regarding facility operations. This is because these traditional models are mainly based on statistics, − which are valid only for a limited operating range and cannot capture the time-varying or nonlinear behavior of dynamic systems. In contrast, ML models can adapt to fast-changing situations and, because they do not rely on predetermined rules, they can use varied, dynamic data to update themselves for better predictions. , …”

Section: How Does ML Address Ese Problems?mentioning

confidence: 99%

Machine Learning: New Ideas and Tools in Environmental Science and Engineering

Zhong

Zhang

Bagheri

et al. 2021

Environ. Sci. Technol.

245

254

View full text Add to dashboard Cite

The rapid increase in both the quantity and complexity of data that are being generated daily in the field of environmental science and engineering (ESE) demands accompanied advancement in data analytics. Advanced data analysis approaches, such as machine learning (ML), have become indispensable tools for revealing hidden patterns or deducing correlations for which conventional analytical methods face limitations or challenges. However, ML concepts and practices have not been widely utilized by researchers in ESE. This feature explores the potential of ML to revolutionize data analysis and modeling in the ESE field, and covers the essential knowledge needed for such applications. First, we use five examples to illustrate how ML addresses complex ESE problems. We then summarize four major types of applications of ML in ESE: making predictions; extracting feature importance; detecting anomalies; and discovering new materials or chemicals. Next, we introduce the essential knowledge required and current shortcomings in ML applications in ESE, with a focus on three important but often overlooked components when applying ML: correct model development, proper model interpretation, and sound applicability analysis. Finally, we discuss challenges and future opportunities in the application of ML tools in ESE to highlight the potential of ML in this field.

show abstract

Monitoring and fault detection in a reverse osmosis plant using principal component analysis

Cited by 7 publications

References 20 publications

Advanced monitoring of rail breakage in double-track railway lines by means of PCA techniques

Advanced monitoring of rail breakage in double-track railway lines by means of PCA techniques

Monitoring a Reverse Osmosis Process with Kernel Principal Component Analysis: A Preliminary Approach

Machine Learning: New Ideas and Tools in Environmental Science and Engineering

Contact Info

Product

Resources

About