What Happens to Process Data in Chemical Industry? From Source to Applications – an Overview
Balazs Balasko,János Abonyi +1 more
Reads0
Chats0
TLDR
This paper briefly overviews some of the commercial products on market and the applicable data analysis techniques which guide process data from source to its application: from technology to expert knowledge with the help of knowledge discovery in databases (KDD) process.Abstract:
It is globally accepted that information is a very powerful asset that can provide significant benefits and a competitive advantage to any organization, like production technologies in the chemical industry, which was driven by market forces, customer needs and perceptions, resulting in more and more complex multi-product manufacturing technologies. These technologies, due to their highly automated level, provide mountains of process data, which is applied only in daily operation and control, but it definitely can give access to the underlying structure of any system. To enhance this automation level while keep operation safe and efficient, one needs more information, i.e. knowledge about the process, which can be extracted from process data, and more tools, which can extract effectively this knowledge. To meet the growing expectations for future chemical engineering tasks, like multi-scale modelling, simulation and control or process and product design, advanced data analysis techniques can lead a way to solution. This paper briefly overviews some of the commercial products on market and the applicable data analysis techniques which guide process data from source to its application: from technology to expert knowledge with the help of knowledge discovery in databases (KDD) process. Numerous citations and their evaluation are given to show that data mining in chemical engineering can efficiently solve many data analysis related problems.read more
Citations
More filters
Journal ArticleDOI
One step forward for smart chemical process fault detection and diagnosis
TL;DR: In this article , the authors provide an overview of the concept and major challenges of smart FDD and present the researches done by their group, which they believe would be a step forward for Smart FDD.
Journal ArticleDOI
Predicting kappa number in a kraft pulp continuous digester: a comparison of forecasting methods
Flávio Marcelo Correia,José Vicente Hallak d'Angelo,Gustavo Matheus de Almeida,Sueli Aparecida Mingoti +3 more
TL;DR: This paper discusses kappa number prediction models using Single Exponential Smoothing, Multiple Linear Regression Analysis, the Time Series Method of Box-Jenkins (ARIMA) and Artificial Neural Networks, indicating that the ARIMA model showed more accurate estimation results.
Journal ArticleDOI
Predictive modelling of instant whole milk powder functional performance across three industrial plants
TL;DR: A unique dataset was constructed to compare three large-scale plants of different designs, overcoming significant challenges in alignment of disparate data sources, across six years of production and models were clearly able to differentiate plant and process changes, and by appropriate weighting of the unusual results, were able to predict functional test results.
DissertationDOI
A Machine Learning Approach to Predict Chattering Alarms
TL;DR: A Machine Learning Approach to Predict Chattering Alarms and its Applications in Chemical and Materials Engineering.
Journal Article
Four main objectives for the future of chemical and process engineering
TL;DR: In this paper, the future for the science and technologies of new materials can be summarized by four main objectives: (1) a total multiscale control of the process (or the procedure) to increase selectivity and productivity, i.e., nanotailoring of materials with controlled structure; (2) a design of novel equipment based on scientific principles and new operation modes and methods of production: process intensification; (3) product design and engineering: manufacturing end-use properties with a special emphasis on complex fluids and solids technology; (4) an implementation
References
More filters
Book
Data Mining: Practical Machine Learning Tools and Techniques
TL;DR: This highly anticipated third edition of the most acclaimed work on data mining and machine learning will teach you everything you need to know about preparing inputs, interpreting outputs, evaluating results, and the algorithmic methods at the heart of successful data mining.
Proceedings ArticleDOI
Mining association rules between sets of items in large databases
TL;DR: An efficient algorithm is presented that generates all significant association rules between items in the database of customer transactions and incorporates buffer management and novel estimation and pruning techniques.
Journal ArticleDOI
Data mining and knowledge discovery: making sense out of data
TL;DR: Without a concerted effort to develop knowledge discovery techniques, organizations stand to forfeit much of the value from the data they currently collect and store.
Journal ArticleDOI
A Nonlinear Mapping for Data Structure Analysis
TL;DR: An algorithm for the analysis of multivariate data is presented along with some experimental results that is based upon a point mapping of N L-dimensional vectors from the L-space to a lower-dimensional space such that the inherent data "structure" is approximately preserved.