Pattern trees uses triangular norms, triangular conorms, and arithmetic operators while the conventional decision trees uses only triangular norms operators.
This study applied pattern trees to build a soft-sensor, or virtual sensor, of HMT by using real operation data of a blust furnace.
Abstract— A blast furnace is a huge counter-current reactor, which is used for reducing iron ores to hot metal in the ironmaking industry.
Feb 2, 2019 · In this paper, a novel ensemble pattern trees model is proposed for predicting HMT in the blast furnace.
People also ask
Pattern trees modeling for prediction and control of hot metal temperature in blast furnace ironmaking. In: Control Conference (ASCC), 2017 11th Asian. IEEE ...
Apr 22, 2021 · We proposed a data-driven modeling approach for an automated extraction of prediction and explanation models for hot metal temperature, silicon concentration, ...
Nov 14, 2023 · The FFBPN model has been trained, tested, and validated, and it has got 96% correlation coefficient of HMT prediction of combination of all data ...
The Hot Metal Temperature (HMT) is an important indicator of the state of the blast furnace, as well as an important determinant of the quality of pig iron ...
The paper discusses several ML-based models that have been used for blast furnace predictive modeling. The paper is very general and examines many issues that ...
Oct 4, 2020 · This article presents a new soft sensor for predicting the HMT and HMSC during hot metal manufacturing process and it is based on a combination of the FCM and ...