Untitled

Sànchez, Miquel; Cortés, Ulises; Béjar, Javier; Gracia, J. de; Lafuente, Javier; Poch, Manel

doi:10.1023/a:1008202113300

Cited by 25 publications

(14 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The other algorithm detected outliers using a concept introduced by Wang et al who treated an item having an extreme value in any one score as abnormal. When applied to a benchmark data set, the automated outlier detection gave the same results as those found manually by Wang et al and they matched the original observations about operating conditions . Additional information was generated from the clusters detected in the hierarchical tree, and in particular, additional days of operation were detected that had plant profiles similar to but less extreme than the abnormal days, suggesting that the same operational difficulties were present on those days but to a lesser extent.…”

Section: Discussionsupporting

confidence: 64%

“…Table shows the automated outlier indexes. The analysis found the abnormal days previously reported in refs and where manual inspection of a parallel coordinate plot was used. The outlier index also indicates additional days as abnormal that were not detected in previous studies.…”

Section: Case Study 1: Performance Analysis and Plant Audit Of Waste...mentioning

confidence: 89%

“…Data Set and Motivations for Analysis. Figure shows the Barcelona wastewater benchmark data set from the University of California at Irvine which has previously been analyzed in the literature. ,, After the exclusion of days with incomplete data (147 of them), there are complete data records for 380 days of operation giving the daily averages of 38 measured variables. The daily averages are static steady-state data, and there is no dynamical component present; moreover, the data are not available every day, and the horizontal day-number axis in Figure is not a continuous time axis.…”

Section: Case Study 1: Performance Analysis and Plant Audit Of Waste...mentioning

confidence: 99%

See 2 more Smart Citations

Multidimensional Visualization and Clustering of Historical Process Data

Thornhill

Melbø

Wiik

2006

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Multivariate statistical analysis using principal components can reveal patterns and structures within a data set and give insights into process performance and operation. The output medium is usually a two dimensional screen, however, so it is a challenge to visualize the multidimensional structure of a data set by means of a two-dimensional plot. A method of visualization is described in the form of a hierarchical classification tree that can be used to view the structure within a multivariate principal component model of three or more dimensions. The tree is generated from an unsupervised agglomerative hierarchical clustering algorithm which operates in the score space of the principal component model, and a recursive algorithm to draw the tree. It is readily adaptable to a wide range of multivariate analysis applications including process performance analysis and process or equipment auditing. Its application are illustrated with industrial data sets.

show abstract

Section: Discussionsupporting

confidence: 64%

Section: Case Study 1: Performance Analysis and Plant Audit Of Waste...mentioning

confidence: 89%

Section: Case Study 1: Performance Analysis and Plant Audit Of Waste...mentioning

confidence: 99%

See 1 more Smart Citation

Multidimensional Visualization and Clustering of Historical Process Data

Thornhill

Melbø

Wiik

2006

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…Each cluster should represent a group of days characterized by a particular situation of the facility. In this case we used the software Linneo + , a semiautomated machine learning tool based on classification methods for ill-structured domains. It is an unsupervised iterative clustering method, which determines useful subsets of data, assuming that observations vary in their membership degree with regard to each possible class.…”

Section: Knowledge Acquisitionmentioning

confidence: 99%

Automatic Knowledge Acquisition from Complex Processes for the Development of Knowledge-Based Systems

R-Roda¹,

Comas²,

Poch³

et al. 2001

Ind. Eng. Chem. Res.

Self Cite

View full text Add to dashboard Cite

A knowledge-based system for the supervision of a wastewater treatment plant was successfully applied to a full-scale facility. The key factor of this supporting tool development was the two-phase methodology used to acquire and fix the knowledge into the knowledge base. Both phases of the methodology are presented in the paper; the first consists of literature reviews and site interviews with domain experts, while the second is based on machine learning tools and is subdivided into four steps: data handling, classification, interpretation, and codification. The aim of this two-phase methodology is meant to ease the knowledge acquisition process. The main objective is to find the relevant issues and then reduce the space of search according to the target facility. Also, this methodology allowed the user to explore the data space to discover, if any exist, new pieces of knowledge. This methodology can be generalized to acquire specific knowledge from any (bio)chemical process, improving the development process and the efficiency of the supervisory knowledge-based system.

show abstract

“…However, the accident diagnosis and decision support in WWTPs, which can infer the reasons for accidents and provide solutions to solve them, are still conducted by human operators based on their knowledge and experience. This manual diagnosis and decision support for the stable operation and management of WWTP has some disadvantages [1][2][3]. The manual diagnosis and decision support could be performed based on the human operators' subjective judgments, which may not sometimes be generally accepted.…”

Section: Introductionmentioning

confidence: 99%

Fuzzy rule-based inference of reasons for high effluent quality in municipal wastewater treatment plant

Moon

Kim

et al. 2011

Korean J. Chem. Eng.

View full text Add to dashboard Cite

A fuzzy inference system (FIS), which could classify the state of effluent quality if it was high or not and identify visually the reasons for the high effluent quality in municipal wastewater treatment plants (WWTPs), was developed in this study. The decision tree algorithm and fuzzy technique were applied in the development of this system. By applying the classification and regression tree (CART) algorithm as a decision tree algorithm, the knowledge related to effluent quality was extracted and IF-THEN rules with crisp boundary values were generated. By applying the fuzzy technique, the fuzzification of these rules was conducted, where the trapezoidal and triangular membership function was used as a membership function type. And a Mamdani model with the Max-min operation was used as an inference model and the center of area (CoA) method was used for deffuzification. The accuracy achieved by using the developed system to classify the effluent state was confirmed by comparing the result with measured data. Furthermore, the developed system was demonstrated to be a useful tool for inferring the reasons for the high effluent quality.

show abstract

Untitled

Cited by 25 publications

References 36 publications

Multidimensional Visualization and Clustering of Historical Process Data

Multidimensional Visualization and Clustering of Historical Process Data

Automatic Knowledge Acquisition from Complex Processes for the Development of Knowledge-Based Systems

Fuzzy rule-based inference of reasons for high effluent quality in municipal wastewater treatment plant

Contact Info

Product

Resources

About