Reusable Big Data System for Industrial Data Mining - A Case Study on Anomaly Detection in Chemical Plants

Borrison, Reuben; Klöpper, Benjamin; Chioua, Moncef; Dix, Marcel; Sprick, Barbara

doi:10.1007/978-3-030-03493-1_64

Cited by 6 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, this was a necessary first step in starting to look at the prediction of the break as it could differentiate between normal deviations and values that in fact led to a problem situation. The data preparation process also included decompressing the row data, resampling it at a common sampling rate and segmenting it to break trajectories, which are the bases for a break prediction modeling and are often done using big data frameworks such as Spark. , The next step was to select the important set of variables from the dataset that may have a causal relationship and thus can be relevant for predicting the break. The selected variables can further be consolidated and denoised through dimensionality reduction techniques at this stage.…”

Section: Main Results and Reflections On The Research Questionsmentioning

confidence: 99%

Synergistic and Intelligent Process Optimization: First Results and Open Challenges

Harjunkoski

Ikonen

Mostafaei

et al. 2020

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Data science has become an important research topic across scientific disciplines. In Process Systems Engineering, one attempt to create true value from process data is to use it proactively to improve the quality and accuracy of production planning as often a schedule based on statistical average data is outdated already when reaching the plant floor. Thus, due to the hierarchical planning structures, it is difficult to quickly adapt a schedule to changing conditions. This challenge has also been investigated in integration of scheduling and control studies (Touretzky et al. AIChE J. 2017, 63 (66), 1959−1973. The project SINGPRO investigated the merging of big data platforms, machine learning, and data analytics with process planning and scheduling optimization. The goal was to create online, reactive, and anticipative tools for more sustainable and efficient operation. In this article, we discuss selected outcomes of the project and reflect the topic of combining optimization and data science in a broader scope.

show abstract

Section: Main Results and Reflections On The Research Questionsmentioning

confidence: 99%