Data driven modeling to reduce fossil fuel consumption in a lime kiln integrated with biomass gasifier, TAPPI Journal September 2026

 


Application: This study is designed for those looking to better understand how to assess two systems, such as gasification and lime kiln, using data driven modeling methods.

TAPPI conference proceedings and presentations, technical papers, and publication articles provide technical and management data and solutions on topics covering the Pulp, Paper, Tissue, Corrugated Packaging, Flexible Packaging, Nanotechnology and Converting Industries.

Simply select the quantity, add to your cart and your conference paper, presentation or article will be available for immediate download.

Author: M. M. Rossetto. G. Espìndola De Ara?jo, L. Antonio De Mauro, and M. Teles Dos Santos
Data driven modeling to reduce fossil fuel consumption in a
ABSTRACT: Biomass gasification, although already known and applied, is currently being consolidated as a sustainable alternative in the pulp industry, contributing to the reduction of fossil carbon dioxide (CO2) emissions and to the utilization of forest residues. In this context, pulp mills are beginning to adopt biomass gasification within their chemical recovery cycles by integrating the technology with lime kilns. However, further process studies are still needed to support and optimize this application. Thus, the present study aimed to analyze lime mud feed temperature by applying an artificial neural network model to a gasification system integrated with a lime kiln. For this evaluation, 10 periods of system stability throughout 2024 were selected under different operational conditions. Data from 28 potential predictive variables were collected, a total of 348 observations. This dataset was then processed using R software, where data treatment and model dimensionality reduction were performed, resulting in 10 predictive variables between gasifier and kiln. Next, the dataset was randomly divided into training (70% of the observations) and testing data. The established neural network model (using “neuralnet” package) was optimized, resulting in a configuration containing one hidden layer with three neurons. This setup enabled optimal estimation of the flue gas kiln outlet temperature, with mean absolute error (MAE) = 3.0°C and root mean square error (RMSE) = 4.1°C, applying the resilient backpropagation algorithm with backtracking — both below the thermocouple’s measurement error (±5.0°C) for the evaluated average temperature range (668.2°C). When the same dataset was modeled using the resilient backpropagation algorithm without backtracking, even better results were achieved: MAE = 2.5°C and RMSE = 3.7°C. Thus, after evaluating these and other configurations, it was concluded that the best model required 10 predictive variables and the backpropagation algorithm without backtracking to determine flue gas kiln outlet temperature. These results provide a better understanding of how gasifier and kiln variables influence the temperature in the lime kiln, which is essential to improve control and optimize the calcination process, avoiding supplementary fossil fuel consumption.
0.00

New Releases

TAPPI PRESS Catalog eBook 2026


Experience the Power of Publications in 2026


Open
 

Kraft Recovery Boilers, Third Edition  


Sponsored by the Recovery Boiler Program R&D Subcommittee of the American Forest & Paper Association (AF&PA) and published by TAPPI Press.


Purchase
 

Handbook For Pulp and Paper Technologists (The SMOOK Book), Fourth Edition

The best-selling text to introduce the entire technology of pulp and paper manufacture.

Purchase
 

Guidelines for Safe Assessment and Operation of Yankee Dryers  


A project of the Yankee Dryer Safety & Reliability Committee.

Purchase
 

Check our newest additions.


TAPPI Press offers some of the most in-depth resources and references for the forest products and related industries. 

See More
   
 

Available for Purchase – Conference Proceedings


TAPPI maintains a record of key conference papers, presentations, and other conference publications, available for purchase in a variety of formats.

See More