Resource-Aware Steel Production Through Data Mining
نویسندگان
چکیده
Steel is one of the most important materials for building a wide variety of products. The downside of a wide usage of steel is the energy-intensive production process and the high output of carbon dioxide. In our efforts to make the production of steel more sustainable, we focus on one step of the steel production only, the conversion of raw iron to high quality steel in a Basic Oxygen Furnace (BOF). With the help of data mining, in particular the Support Vector Regression, we analyse the relation between commonly used static features of the conversion process, some new constructed dynamic features from time series data, like the offgas composition and some quality and performance indicators. The experimental offline results indicate, that the quality of prediction generated by our approach is comparable or even better than the quality of methods used by steel companies, like ArcelorMittal. In future work we will integrate our prediction models in a recommendation system. It will be evaluated in how far this supports the melter such that he can optimize the process in order to increase sustainability.
منابع مشابه
Challenges for Data Mining on Sensor Data of Interlinked Processes
In industries like steel production, interlinked production processes leave no time for assessing the physical quality of intermediate products. Failures during the process can lead to high internal costs when already defective products are passed through the entire value chain. However, process data like machine parameters and sensor data which are directly linked to quality can be recorded. B...
متن کاملResource-Aware Very Fast K-Means for Ubiquitous Data Stream Mining
Developments in data streams, coupled with the growth in mobile and pervasive devices, have led to the emergence of Ubiquitous Data Mining (UDM). UDM aims to perform data stream mining in a ubiquitous environment with resourceconstrained and/or mobile devices. Over the past few years, stream mining techniques have attracted the attention of the data mining community. However these techniques ha...
متن کاملAn Architecture for Context-Aware Adaptive Data Stream Mining
In resource-constrained devices, adaptation of data stream processing to variations of data rates, availability of resources and environment changes is crucial for consistency and continuity of running applications. Context-aware and resource-aware adaptation, as a new dimension of research in data stream mining, enhances and improves distributed data stream processing tasks. Context-awareness ...
متن کاملOpen Mobile Miner: A Toolkit for Building Situation-Aware Data Mining Applications
In organizational computing and information systems, data mining techniques have been widely used for analyzing customer behaviour and discovering hidden patterns. Mobile Data Mining is the process of intelligently analysing continuous data streams on mobile devices. The use of mobile data mining for realtime business intelligence applications can be greatly advantageous. Past research has show...
متن کامل