A guided analytics tool for feature selection in steel manufacturing with an application to blast furnace top gas efficiency
Source abstract
Abstract
In knowledge intensive industries such as steel manufacturing, application of data analytics to optimise process performance, requires effective knowledge transfer between domain experts and data scientists. This is often an inefficient path to follow, requiring much iteration whilst being suboptimal with regard to organisational knowledge capture for the long term. With the ‘initial Guided Analytics for parameter Testing and controlband Extraction (iGATE)’ tool we created a feature selection framework that finds influential process parameters and their optimal control bands and which can easily be made available to process operators in the form of guided analytics tool, while allowing them to modify the analysis according to their expertise. The method is embedded in a work flow whereby the extracted parameters and control bands are verified by the domain expert and a report of the analysis is automatically generated. The approach allows us to combine the power of suitable statistical analysis with process-expertise, whilst dramatically reducing the time needed for conducting the feature selection. We regard this application as a stepping stone to gain user confidence in advance of introduction of more autonomous analytics approaches. We present the statistical foundations of iGATE and illustrate its effectiveness in the form of a case study of Tata Steel blast furnace data. We have made the iGATE core functionality freely available in the igate package for the R programming language.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Fault Detection and Control Systems · Neural Networks and Applications · Mineral Processing and Grinding
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (25)
Show source-provided references
1. Statistics = analytics?10.1080/08982112.2019.1633670 ↗
2. Y. Liu, T. Zhao, W. Ju, S. Shi, Materials discovery and design using machine learning, J. Materiomics 3(3) (2017) 159–177, high-throughput Experimental and Modeling Research toward Advanced Batteries.https://doi.org/10.1016/j.jmat.2017.08.002.10.1016/j.jmat.2017.08.002 ↗
3. Opportunities and challenges for machine learning in materials science10.1146/annurev-matsci-070218-010015 ↗
4. Multi-scale computation methods: their applications in lithium-ion battery research and development10.1088/1674-1056/25/1/018212 ↗
5. Machine learning assisted materials design and discovery for rechargeable batteries10.1016/j.ensm.2020.06.033 ↗
6. The challenge of quality in continuous casting processes10.1007/s11661-999-0001-4 ↗
7. Effective interdisciplinary collaboration between statisticians and other subject matter experts10.1080/08982112.2018.1530357 ↗
8. A. Ng, Machine learning and ai via brain simulations, 2013.https://forum.stanford.edu/events/2011/2011slides/plenary/2011plenaryNg.pdf (accessed 04-Oct-2019).
9. R. Bellman, Adaptive control processes, Princeton University Press, 1961.https://doi.org/10.1515/9781400874668.10.1515/9781400874668 ↗
10. Leakage in data mining: formulation, detection, and avoidance
11. Larsen · 2018
12. An interactive approach for bayesian network learning using domain/expert knowledge10.1016/j.ijar.2013.03.009 ↗
13. W. Tang, K.Z. Mao, L.O. Mak, G.W. Ng, Adaptive fuzzy rule-based classification system integrating both expert knowledge and data, in: 2012 IEEE 24th International Conference on Tools with Artificial Intelligence, vol. 1, 2012, pp. 814–821.https://doi.org/10.1109/ICTAI.2012.114.10.1109/ICTAI.2012.114 ↗
14. Multi-layer feature selection incorporating weighted score-based expert knowledge toward modeling materials with targeted properties10.1002/adts.201900215 ↗
15. A distribution-free shewhart quality control chart based on signed-ranks10.1081/QEN-120038022 ↗
16. Geerdes · 2015
17. Analysing blast furnace data using evolutionary neural network and multiobjective genetic algorithms10.1179/030192310X12683075004672 ↗
18. Revealing cohesive zone shape and location inside blast furnace10.1080/03019233.2017.1338385 ↗
19. Y. Omori, Blast Furnace Phenomena and Modelling, Elsevier, 1987.https://doi.org/10.1007/978-94-009-3431-3.10.1007/978-94-009-3431-3 ↗
20. Modeling of the thermal state change of blast furnace hearth with support vector machines10.1109/TIE.2011.2159693 ↗
21. S. Stein, igate: Guided Analytics for Testing Manufacturing Parameters, University of Warwick, r package version 0.3.3 (2019). URL:https://CRAN.R-project.org/package=igate.10.32614/CRAN.package.igate ↗
22. A quick, compact, two-sample test to duckworth’s specifications
23. Individual comparisons by ranking methods10.2307/3001968 ↗
24. On a test of whether one of two random variables is stochastically larger than the other10.1214/aoms/1177730491 ↗
25. A simple sequentially rejective multiple test procedure