SUMMARY Being able to predict future temperatures on the wall lining is key when controlling and scheduling maintenance for large industrial smelting furnaces. In this paper, we propose and test a machine learning approach for predicting lining temperatures in a ferronickel smelting furnace. This approach was deployed and evaluated in a real‐world scenario, i.e., in one of Cerro Matoso S.A.'s (CMSA) industrial plant furnaces. Different techniques were tested, and finally, a multitarget regression (MTR) model showed the best performance. Previous state of the art focused on predicting only one target sensor; in contrast, our model is capable of predicting up to 12 targets. Two MTR models were tested: the incremental structured output prediction tree (iSOUP‐Tree) and the stacked single‐target Hoeffding tree regressor (SST‐HT). The SST‐HT method had the best behavior in terms of the average mean absolute error (AMAE) and average root mean square error (ARMSE). The results indicate that the developed MTR models can accurately predict the measured temperature on multiple point sensors. Results of this work are expected to help the process of structural control and health monitoring of the furnace linings located at CMSA's plant.
In the industrial process of ferronickel production from lateritic minerals, the influence of design factors, constructive and dimensional aspects on the heat transfer and energy performance of the equipment have been little addressed. The literature focuses on cement kilns or iron and steel production applications. This work compares the influence of the approaches considered in the early phases of the design process on heat transfer and energy performance for two ferronickel rotary kilns. For this purpose, a retrospective analysis was realized identifying requirements, operating principles, and approaches applied in the definition of specification and conceptual design. This analysis was carried out, taking into account one operation year data of two rotary calcining kilns of 185 meters and 135 meters in length, both of 6 meters in diameter and similar feeding rate between 170,000 and 180000 kilograms per hour. The analysis showed that kiln 1 had a functional approach in the early phases of the design process, while kiln 2 additionally has an environmental and energy approach, which allowed to improve the heat transfer and energy performance. This was verified with software based on the AHP method. The software results showed that counter-current and cross-flow rotary kiln 2 is a better conceptual design alternative for environmental and energy requirements than counter-current rotary kiln 1.
Nickel is essential in many consumer, industrial, military, transport, aerospace, marine, and architectural products due to its outstanding physical and chemical properties. This work focuses on the calcination and pre-reduction of laterite nickel ore to produce ferronickel. Ferronickel is an alloy containing nickel (about 30% wt.) and iron used for manufacturing stainless steel. Calcination and pre-reduction entail removing chemically bonded water from partially dried ore and removing oxygen from mineral oxides in the calcine. Here we combine a proprietary database with operation data of two rotary kilns and model predictions of Mean Residence Time, shell losses, intraparticle evaporation, and intraparticle temperature distribution. The kilns feature notable differences in length, inclination angle, excess air, but the predicted Mean Residence Times are similar. A fitted profile of experimental solids bed temperature represented particles surface temperature. The model considered slab-like mineral particles with surface-to-center distances of 13, 25, and 38 mm. Results show notable differences in the drying zone length and average surface-to-center temperature differences. Surface-to-center distances higher than 25 mm result in average surface-to-center temperature differences higher than 80°C. The following steps are improvements in the particle model and its coupling with the gas and wall temperature profiles.
In the ferronickel production process, mineral calcination is one of the most energy-intensive stages. In a typical rotary kiln calciner, particulate solids and combustions gases move counter currently, while solids undergo drying, pre-reduction, and partial reduction reactions. The combustion of natural gas provides the thermal energy for drying and reduction reactions. About 80 to 85% of the incoming laterite ore leaves the reactor as calcined ore, while the flue gases entrain part of the solids as dust. This work presents a theoretical analysis contrasted with experimental results to evaluate the partial reduction of laterite ores in two rotary kilns of 185 m and 135 m length. The study focused on the water formed in the process, including a comparative analysis of water consumption by two different solids recovery technologies, a gas scrubber and an electrostatic precipitator. Simulations allowed evaluating the water and greenhouse gas formation in the main streams of the process. Among the tested operation conditions, the moisture content in the pellets, consisting of agglomerated dust, strongly influenced the amount of water released in the process and the energy consumption. Furnace RK-2 needs approximately 56% more energy to evaporate the moisture content in the feedstock. Furthermore, furnace RK-2 released 55.4 m3h−1 of water into the atmosphere, which represented two times the amount released by furnace RK-1. Gas scrubber analysis showed that as the liquid water increased, more H2O in the gases was condensed; however, the destroyed exergy also increased. Electrostatic precipitators appear as an adequate technology for reducing water and energy consumption in the ferronickel industry.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.