Production

2025

Journals

• • Gutierrez-Rojas, D., Kalalas, C., Christou, I., Almeida, G., Eldeeb, E., Bakri, S., Marchetti, N., Sant'Ana, J.M.S., L'opez, O.L.A., Alves, H., Papadias, C., Tariq, M.H., Nardelli, P.H.J. Detection and classification of anomalies in WSN-enabled cyber-physical systems. IEEE Sensors Journal, 25(4), 7193-7204, 2025.

Book chapters

• Almeida, G.M., Naukkarinen, J., Terhi, J., Datta, S., Kuparinen, K., Vakkilainen, E. Improving the student learning process in MOOCs through the analysis of open-ended question-based assessments using natural language processing. Aue, M.E. and Rüütmann (eds.) Futureproofing Engineering Education for Global Responsibility, ICL 2024. Lecture Notes in Networks and Systems (LNNS), 1260, 525-533, Springer, 2025. 

Conferences

• • de Almeida, G., Park, S., Cardoso, S., Vakkilainen, E., Alobaid, F. Diagnosis of the overheating problem of a secondary superheater of a kraft boiler. International Chemical Recovery Conference (ICRC), Toronto, Canada, 2025.

  • de Almeida, G., Naukkarinen, J., Li, C., Matthews, S., Jantunen, T., Datta, S., Kuparinen, K., Alobaid, F., Vakkilainen, E. Automatic evaluation of open-ended questions in MOOCs using a Named-Entity Recognition System based on the Hidden Markov Model. SEFI Annual Conference, Tampere, Finland, 2025.

  • Silva, P., Ferreira, Y., Lima, I., Vakkilainen, E., Almeida, G., Braga, A. Improving interpretability for fault diagnosis in complex chemical processes using combined regularization and linearization in neural network modeling. Proceedings IEEE Symposium on Trustworthy, Explainable and Responsible Computational Intelligence (CITREx), Trondheim, Norway, 1-7, 2025.

Before 2025

Journals

• • Ng, J., Almeida, G.M., Vakkilainen, E.K., Laryshyn, Y.A., DeMartini, N.A. Comparing a linear transfer function-noise model and a neural network to model boiler bank fouling in a kraft recovery boiler. TAPPI Journal, 23(7), 374-384, 2024.

  • Condori, M.E.G., Passos, L.F.D., Michel, H.C.C., Almeida, G.M., Cardoso, M. Dynamic mathematical modelling and simulation of a primary oil separation unit. International Journal of Simulation and Process Modelling, 20(3), 201-217, 2023.

  • Gutierrez-Rojas, D., Narayanan, A., Almeida, C.R.S., Almeida, G.M., Pfau, D., Tian, Y., Yang, X., Jung, A., Nardelli, P.H.J. A perspective on the enabling technologies of explainable AI-based industrial packetized energy management. iScience, 26, 12, 108415, 1-15, 2023.

  • Quille, R.V.E., Almeida, F.V., Borycz, J., Corrêa, P.L.P., Filgueiras, L.V.L., Machicao, J., Almeida, G.M., Midorikawa, E.T., Demuner, V.R.F., Bedoya, J.A.R., Vajgel, B. Performance analysis method for robotic process automation. Sustainability, 15(4), 3702, 1-19, 2023.

  • Veloso, M.V.G., Caux, L.S., Costa, D.S., Botrel, P.C.M.G.G., Almeida, D.L.A., Zeferino, K.A.M.O., Manu, P.O.A., Neto, M.R.V., Leite, B.S., Cardoso, M., Almeida, G.M. Analysis of operational scenarios in a pulp mill evaporation plant in Brazil. The Pulp and Paper Brazilian Magazine (O Papel), 84(2), 68-73, 2023. (in Portuguese) - podcast (around 18:30)

  • Belisário, A.B., Edberg, A., Björk, M., Almeida, G.M., Vakkilainen, E.K. On the diagnosis of a fouling condition in a kraft recovery boiler combining process knowledge and data-based insights. TAPPI Journal, 22(3), 162-171, 2023.

  • Gutierrez-Rojas, D., Räsänen, P., Belisário, A.B., Dzaferagic, M., Almeida, G.M., Nardelli, P.H.J. Improving fault detection in industrial processes by event-driven data acquisition. IEEE Access, 10, 80918-80931, 2022. (IF 2021: 3.476)

  • Torres, L.C.B., Castro, C.L., Rocha, H.P., Almeida, G.M., Braga, A.P. Multi-objective neural network model selection with a graph-based large margin approach. Information Sciences, 599, 192-207, 2022. (IF 2020: 6.795)

  • Rebelo, H.D., Oliveira, L.A.F., Almeida, G.M., Sotomayor, C.A.M., Magalhães, V.S.N., Rochocz, G.L. Automatic update strategy for real-time discovery of hidden customer intents in chatbot systems. Knowledge-Based Systems, 243, 108529, 2022. (IF 2020: 8.038)

  • Aurelio, Y.S., Almeida, G.M., Castro, C.L., Braga, A.P. Cost-sensitive learning based on performance metric for imbalanced data. Neural Processing Letters, 54, 3097-3114, 2022. (IF 2020: 2.908)

  • Cunha, P.M.C., Almeida, G.M. (2021) Soft sensor for SO2 emissions classification based on k-NN (k-Nearest Neighbors). Ibero-American Journal of Environmental Science, 12(9). (in Portuguese)

• Rebelo, H.D., Oliveira, L. A.F., Almeida, G.M., Sotomayor, C.A.M., Rochocz, G.L., Melo, W.E.D. (2021) Intent identification in unattended customer queries using an unsupervised approach. Journal of Information & Knowledge Management, 20(3), 2150037.

• Vajgel, B., Corrêa, P.L.P., Tossoli, T., Quille, R.V.E., Bedoya, J., Almeida, G.M., Filgueiras, L.V.L., Demuner, V.R.S., Mollica, D. (2021) Development of intelligent robotic process automation: A utility case study in Brazil. IEEE Access, 9, 71222-71235. (IF 2019: 3.745)

• Martinez, C.L.M., Sermyagina, E., Saari, J., Jesus, M.S., Cardoso, M., Almeida, G.M., Vakkilainen, E. (2021) Hydrothermal carbonization of lignocellulosic agro-forest based biomass residues. Biomass & Bioenergy, 147, 106004. (IF 2019: 3.551)

• Pinto, C.C., Faria, F.P.C.P., Almeida, G.M. (2021) Use of a model based on principal component analysis for identification of critical conditions of surface water quality. Ibero-American Journal of Environmental Science, 12(4), 288-305. (in Portuguese)

• Martinez, C.L.M., Saari, J., Melo, Y., Cardoso, M., Almeida, G.M., Vakkilainen, E. (2021) Evaluation of thermochemical routes for the valorization of solid coffee residues to produce biofuels: A Brazilian case. Renewable and Sustainable Energy Reviews, 137, 110585. (IF 2019: 12.110)

• • Carneiro, M.V., Salis, T.T., Almeida, G.M., Braga, A.P. (2021) Prediction of mechanical properties of steel tubes using a machine learning approach. Journal of Materials Engineering and Performance, 30(1), 434-443. (IF 2019: 1.652)

  • Silva, J.P., Neto, M.R.V., Almeida, G.M., Oliveira, E.D. (2020) Computation of residue curves maps using a simple finite difference method. The Journal of Engineering and Exact Sciences, 6(5), 0770-0776. (in Portuguese)

  • Silva, J.P., Neto, M.R.V., Almeida, G.M., Oliveira, E.D. (2020) Obtaining residual curves maps for homogeneous azeotropic ternary systems: A comparative study. The Journal of Engineering and Exact Sciences, 6(5), 0655-0665. (in Portuguese)

• • Duarte, I.C.D., Almeida, G.M., Cardoso, M. (2020) Heat-loss cycle prediction in steelmaking plants through artificial neural network. Journal of the Operational Research Society, 1-12. (IF 2019: 2.175)

  • Correa, R.S., Sampaio, P.T., Braga, R.U., Lambertucci, V.A., Almeida, G.M., Braga, A.P. (2020) Prediction of mechanical properties of seamless steel tubes using ANN. International Journal of Computational Intelligence and Applications, 19(04), 2050028, 1-14. (IF 2020: 0.750)

  • Almeida, G.M., Park, S.W., Kim, S.C., Lee, C.J. (2020) A sampling-based stochastic optimization for a boiler process in a pulp industry. Korean Journal of Chemical Engineering, 37, 588-596. (IF 2018: 2.476)

  • Belisário, A.B., Faria, D.G., Chaves, D.H.S., Almeida, G.M., Cardoso, M. (2020) Experience reports of digital technologies deployment in engineering education. Higher Education Teaching Magazine/UFMG, 10, 1-18. (in Portuguese)

  • Martínez, C.L.M., Jesus, M.S., Vakkilainen, E., Cardoso, M., Almeida, G.M. (2019) Bioenergy technology solutions in Brazil. Brazilian Journal of Wood Science, 10(2), 112-122.

  • Alkmim, A.R., Almeida, G.M., Carvalho, D.M., Amaral, M.C.S., Oliveira, S.M.A.C. (2019) Improving knowledge about permeability in membrane bioreactors through sensitivity analysis using artificial neural networks. Environmental Technology, 41(19), 2424-2438. (IF 2017: 1.666)

  • Aurelio, Y.S., Almeida, G.M., Castro, C.L., Braga, A.P. (2019) Learning from imbalanced data sets with weighted cross-entropy function. Neural Processing Letters, 50, 1937–1949. (IF 2018: 1.787)

  • Correia, F.M., Almeida, G.M., Mingoti, S.A., D'Angelo, J.V.H. (2018) Predicting Kappa number in Kraft pulp continuous digester: A comparison of forecasting methods. Brazilian Journal of Chemical Engineering, 35(3), 1081-1094. (IF 2016: 1.104)

  • Luostarinen, K., Vakkilainen, E.K., Cardoso, M., Almeida, G. M., Hamaguchi, M. (2018) Variation of recovery boiler NOx emissions based on wood species, boiler age, and other operating parameters. Journal of Science & Technology for Forest Products and Processes (J-FOR), 2nd Special Edition ICRC2017, 7(3), 23-32. (IF 2016: 0.569)

  • Almeida, G.M., Park, S.W. (2017) Visual analytics: Seeking the unknown. Brazilian Magazine of Chemical Engineering (REBEQ)/Brazilian Society of Chemical Engineering (ABEQ), 33(1), 27-35. (in Portuguese)

  • Almeida, G.M., Park, S.W. (2017) Big data analytics in chemical engineering. Brazilian Magazine of Chemical Engineering (REBEQ)/Brazilian Society of Chemical Engineering (ABEQ), 33(1), 15-20. (in Portuguese)

  • Faria, A.W.C., Coelho, F.G.F., Silva, A.M., Rocha, H.P., Almeida, G.M., Lemos, A.P., Braga, A.P. (2017) MILKDE: A new approach for multiple instance learning based on positive instance selection and kernel density estimation. Engineering Applications of Artificial Intelligence, 59, 196-204. (IF 2015/2016: 2.368)

  • Lima, R.N., Almeida, G.M., Braga, A.P., Cardoso, M. (2016) Trend modelling with artificial neural networks. Case study: Operating zones identification for higher SO3 incorporation in cement clinker. Engineering Applications of Artificial Intelligence, 54, 17-25. (IF 2015/2016: 2.368)

  • Almeida, G.M., Park, S.W. (2013) Monitoring of abnormal situations in continuous industrial processes. Case study: Multiple effect evaporation system. The Pulp and Paper Brazilian Magazine (O Papel), 74, 67-72.

Winner Technical Papers ABTCP 2013

• • Almeida, G.M., Cardoso, M., Park, S.W. (2012) Detecting an abnormality in a recovery boiler using dynamic multivariate data analysis with parallel coordinate plots. Appita Journal, 65(1), 78-86. (IF 2015/2016: 0.45)

  • Almeida, G.M., Cardoso, M., Rena, D.C., Park, S.W. (2010) Graphical representation of cause-effect relationships among chemical process variables using a neural network approach. International Journal of Computational Intelligence and Applications, 9, 69-86.

Book chapters

• • Gasparoni, J.M. (in memoriam), Almeida, C.R.S.N., Almeida, G.M. (2019) Process engineering: Sizing, simulation and sensitivity analysis of multiple effect evaporation systems of Kraft pulp mills. In Impacts of technologies in chemical engineering, v.1, Voigt, C.L. (eds), Atena, ISBN 978-85-7247-237-1, Chapter 10, 80-95. (in Portuguese) [free access]

• • Park, S.W., Almeida, G.M. (2014) Utilization of process historical data in recovery boilers. In Continuous development of recovery boiler technology: 50 years of cooperation in Finland, Vakkilainen, E., Lampinen, P., Nieminen, M. (eds), Finnish Recovery Boiler Committee, ISBN 978-952-93-3984-6 (print version), ISBN 978-952-93-3985-3 (electronic copy), Chapter 6, 77-92.

Conferences

• • Almeida, G.M., Vakkilainen, E. Harnessing domain knowledge for enhanced data-driven operational diagnostics in continuous process industries. AI Day & Nordic AI Meet, Helsinki, 2024.

  • Almeida, G.M., Naukkarinen, J., Terhi, J., Datta, S., Kuparinen, K., Vakkilainen, E. Improving the student learning process in MOOCs through the analysis of open-ended question-based assessments using natural language processing. 27th International Conference on Interactive Collaborative Learning (ICL) and 53rd International Conference on Engineering Pedagogy, 1837-1844, Tallinn, Estonia, 2024.
    Best Paper Award - Winner: Short Papers

  • Mantovani, R.F., Quinino, R.C., Oliveira, E.D., Braga, A.P., Almeida, G.M. Detecção de falhas em processos químicos contínuos usando deep reinforcement learning. III Congresso Brasileiro em Engenharia de Sistemas em Processos (PSE-BR), 249, Sao Paulo, Brazil, 2024. (in Portuguese)

  • Ullah, M., Rojas, D. G., Almeida, G., Tynjälä, T. Unified framework to select an IoT platform for PtX cogeneration plants. Smart Industries and Digital Ecosystems (SIDE) Conference. 47th MIPRO ICT and Electronics Convention (MIPRO), 1859-1864, Opatija, Croatia, 2024.

  • Ng, J., Almeida, G.M., Vakkilainen, E., Lawryshyn, Y., DeMartini, N. Modelling boiler bank fouling, Annual Research Review Meeting, Pulp and Paper Centre, University of Toronto, Canada, 2023.

  • Cwienk, L.B., Almeida, T.M., Gripp, B.S.S., Almeida, G.M. Fault detection in continuous chemical processes: An approach via statistical moments, XIV Brazilian Congress of Chemical Engineering: Scientific initiation (COBEQ-IC), Brazil, 2022. (in Portuguese)

  • Moura, R.M., Mantovani, R.F., Almeida, G.M. Energy efficiency monitoring of multiple effect evaporation systems in kraft pulp mills, XIV Brazilian Congress of Chemical Engineering: Scientific Initiation (COBEQ-IC), Brazil, 2022. (in Portuguese)

  • Veloso, M.V.G., Caux, L.S., Costa, D.S., Botrel, P.C.M.G.G., Almeida, D.L.A., Zeferino, K.A.M.O., Manu, P.O.A., Neto, M.R.V., Leite, B.S., Cardoso, M., Almeida, G.M. Analysis of scenarios in a pulp mill evaporation plant in Brazil. Pulp and Paper International Congress & Exhibition (ABTCP), Brazil, 2022. (in Portuguese)
    Selected for publication in the The Pulp and Paper Brazilian Magazine (O Papel)

  • Pinto, C.C., Oliveira, S.M.A.C., Almeida, G.M. Evaluation of temporal variations in water quality via principal component analysis. IV São Francisco River Hydrographic Basin Symposium (SBHSF), Brazil, 2022. (in Portuguese)

  • Almeida, G.M., Park, S.W., Lee, C.J. A stochastic optimization based on sample average approximation for a boiler process. 13th IFAC Symposium on Dynamics and Control of Process Systems, including Biosystems (DYCOPS), 55(7), 550-555, Republic of Korea, 2022.

  • Belisário, A.B., Edberg, A., Björk, M., Almeida, G.M., Vakkilainen, E.K. Diagnosing the fouling condition in the convective heat transfer section of a kraft recovery boiler by combining process- and data-driven approaches. International Chemical Recovery Conference (ICRC), Canada, 2022. [initially in 2020; postponed due to Covid-19]

  • Almada, L.S., Barcelos, G.F.J., Reis, D.S., Costa, G.S., Almeida, G.M. (2021) Fault detection in continuous chemical processes using a PCA-based local approach. Proc. ENBIS-21 Online Conference, p28.

  • Carmo, T.M.S., Almeida, G.M. (2021) Imbalanced multi-class classification in process industries. Case study: Emission levels of SO2 from an industrial boiler. Proc. ENBIS-21 Online Conference, p34.

• • Silva, D.R.F., Almeida, C.R.S.N., Park, S.W., Almeida, G.M. (2021) Fault detection in continuous chemical processes: An approach based on ensemble learning and Bayesian inference. KIChE Spring Meeting Symposium, South Korea.

  • Belisário, A.B., Cardoso, M., Vakkilainen, E.K., Almeida, G.M. (2020) Data-driven soft sensors for emission monitoring in kraft recovery boilers: Brazilian and Finnish case studies for sulfur dioxide (SO2). International Chemical Recovery Conference (ICRC), Brazil. [postponed due to Covid-19]

• • Cunha, P.M.C., Almeida, G.M. (2020) Online prediction of alcohol content in vinasse via virtual sensor based on k-Nearest Neighbors: A real case study. 5th International Biomass Congress (CIBIO), 1-4, Brazil. (in Portuguese)

• • Lee, C.J., Almeida, G.M., Park, S.W. (2020) Exploration of optimal operating conditions of a boiler process considering cost and safety. KIChE Fall Meeting and International Symposium, South Korea.

  • Costa, G.S., Barcelos, G.F.J., Almada, L.S., Reis, D.S., Almeida, G.M. (2020) Fault detection in continuous chemical processes: A local approach via principal component analysis. V Chemical Engineering Week / UFV, Brazil. (in Portuguese) link
    Honorable mention (3rd best work award) 

  • Carmo, T.M.S., Almeida, G.M. (2020) Classification of SO2 emissions with artificial neural network. V Chemical Engineering Week / UFV, Brazil. (in Portuguese) link
    Honorable mention (2nd best work award)

• Gutierrez-Rojas, D., Ullah, M., Christou, I.T., Almeida, G.M., Nardelli, P., Carrillo, D., Sant'Ana, J.M., Alves, H., Dzaferagic, M., Chiumento, A. (2020) Three-layer approach to detect anomalies in industrial environments based on machine learning. 3rd IEEE International Conference on Industrial Cyber-Physical Systems (ICPS), Finland.

• Gomes, G.A., Lourenço, R.O., Furtado, E.C., Almeida, G.M. (2019) Classification of fluidized bed operating regimes based on image processing. 25o ABCM International Congress of Mechanical Engineering (COBEM), Brazil. (accepted but presentation not possible)

• Pinto, C.C., Faria, F.P.C.P., Almeida, G.M. (2019) Surface water quality monitoring with multivariate statistical process control. 16th National Congress of the Environment, Brazil. (in Portuguese)

• Martinez, C.L.M., Sermyagina, E., Vakkilainen, E., Cardoso, M., Almeida, G.M. (2019) Hydrothermal carbonization of lignocellulosic biomass for energy production, 14th Global Summit and Expo on Biomass and Bioenergy, Austria.

• Barcelos, G.F.J., Almada, L.S., Reis, D.S., Costa, G.S., Almeida, G.M. (2019) Fault detection in continuous chemical processes: A proposal through dimensionality reduction based on principal component analysis. Brazilian Congress of Chemical Engineering - Scientific Initiation (COBEQ-IC), Blucher, 1(6), 3157-3163, Brazil. (in Portuguese)

• Martinez, C.L.M., Mashlakov, A., Jesus, M.S., Cardoso, M., Almeida, G.M. (2019) Hydrothermal carbonization of coffee residues. 4th International Biomass Congress (CIBIO), Brazil. (in Portuguese)

• Pinto, C.C., Faria, F.P.C.P., Almeida, G.M. (2019) Water quality monitoring based on multivariate statistical process control, 30th Brazilian Congress of Sanitary and Environmental Engineering (CBESA), Brazil. (in Portuguese)

• Martinez, C.L.M., Mashlakov, A., Jesus, M.S., Cardoso, M., Almeida, G.M. (2019) Carbonization of coffee wood for charcoal production. V National Forum on Charcoal / III Seminar of Energy on Biomass Forestry, Brazil.

• Vieira, F.C., Furtado, E.C., Almeida, G.M. (2019) LQR controller for ALSTON gasifier benchmark based on a balanced and reduced order model. I Brazilian Congress on Process Systems Engineering (PSE-BR), Brazil.

• Martinez, C.L., Melo, Y.A., Valerio, P.P., Cardoso, M., Almeida, G.M. (2018) Utilization of solid waste from coffee crop as biomass for the production of added-value compounds in Brazil, 44th Brazilian Congress on Coffee Research, CD-ROM, Brazil.

• Martinez, C.L.M., Sermyagina, E., Jesus, M.S., Vakkilainen, E., Cardoso, M., Almeida, G.M. (2018) Characterization and kinetic study of the combustion of coffee-pine-based wood briquettes. IX Liekkipaiva/The 9th Finnish Flame Day, 44, Finland.

• Alkmim, A.R., Belisário, A.B., Almeida, G.M., Amaral, M.C.S., Oliveira, S.M.A.C. (2018) Monitoring filterability decrease of membrane bioreactors using multivariate statistical techniques. EuroMembrane, Spain.

• Gasparoni, J.M., Oliveira, L.A.F., Aguiar, M.O., Almeida, C.R.S.N., Almeida, G.M. (2017) Design, simulation and sensitivity analysis of multiple effect evaporation systems of Kraft pulp mills. Brazilian Congress of Chemical Engineering - Scientific initiation (COBEQ-IC), Blucher, 3335-3340, Brazil. (in Portuguese)

• Campanha, F.C., Oliveira, L.A.F., Aguiar, M.O., Furtado, E.C., Almeida, G.M. (2017) Fault detection and diagnosis in shell and tube heat exchangers. Brazilian Congress of Chemical Engineering - Scientific initiation (COBEQ-IC), Blucher, 3341-3346, Brazil. (in Portuguese)

• Oliveira., M.C.A., Oliveira, L.A.F., Aguiar, M.O., Almeida, C.R.S.N., Almeida, G.M. (2017) Modelling and simulation of a multiple effect evaporation system. Brazilian Congress of Chemical Engineering - Scientific initiation (COBEQ-IC), Blucher, 3299-3304, Brazil. (in Portuguese)

• Luostarinen, K., Vakkilainen, E.K., Cardoso, M., Almeida, G.M., Hamaguchi, M. (2017) Estimation of recovery boiler NOx-emissions based on wood species, boiler age, size, load and NCG flows. International Chemical Recovery Conference (ICRC), Canada.

• Almeida, G.M., Park, S.W. (2016) Improving process data visualization with multidimensional plots. 49th ABTCP Pulp and Paper International Congress, Brazil.

• Amaral, C.M.C., Fernandes, C.B., Mendonça, D.R., Santos, G.C., Pinheiro, M.M., Cordeiro, P.H.M., Bretz, J., Almeida, G.M., Miranda, R.C. (2016) Development and evaluation of an OTS system for vertical grinding. 16th National Meeting of Students of Metallurgical Engineering, Materials and Mining (ENEMET)/ABM (Brazilian Association of Metallurgy, Materials and Mining) Week, Brazil. (in Portuguese)

• Almeida, G.M., Park, S.W. (2016) Fault detection in continuous and periodic industrial chemical processes with hidden Markov models. 6th IASTED International Conference on Modelling, Simulation and Identification (MSI), Proc.: da Silva, F.V. (ed.), ISBN 978-0-88986-983-7, 172-179, Brazil. (focus on application)

• Almeida, G.M., Park, S.W. (2016) A hidden Markov model-based methodology for fault detection in continuous and periodic industrial processes. I Latin American Conference on Statistical Computing (LACSC), Brazil. (focus on methodology)

• Correia, F.M., Almeida, G.M., D'Angelo, J.V.H., Mingoti, S.A. (2015) An artificial neural network approach for Kappa number prediction in Eucalyptus Kraft pulp continuous digester. 7th International Colloquium on Eucalyptus Pulp (ICEP), Brazil.

• Almeida, G.M., Park, S.W. (2013) Monitoring of abnormal situations in continuous industrial processes. Case Study: Evaporation station of a pulp mill. International Pulp and Paper Congress (ABTCP), Brazil.
  Best technical paper award in the Recovery and Energy oral session

• Almeida, G.M., Park, S.W. (2013) Time-delay neural network for monitoring of abnormal situations in continuous industrial processes. Case study: Evaporation station of a pulp mill. 11th IFAC Workshop on Intelligent Manufacturing Systems (IMS), 408-413, Brazil.

• Almeida, G.M., Park, S.W. (2012) Fault detection in continuous industrial chemical processes: A new approach using the hidden Markov modeling. Case study: A boiler from a Brazilian cellulose pulp mill. 13th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL), LNCS, 7435, 743-752, Brazil.

• Almeida, G.M., Park, S.W. (2012) Performance evaluation of operations in industrial chemical processes through principal component analysis: An example from a real case study. 20th National Symposium on Probability and Statistics (SINAPE), Brazil. (in Portuguese)

• Almeida, G.M., Reis, M.S., Park, S.W. (2012) A signal processing approach for fault detection problem: Application to the DAMADICS actuator benchmark problem. 22nd European Symposium on Computer Aided Process Engineering (ESCAPE), 857-861, London.

• Almeida, G.M., Park, S.W. (2012) A new approach for monitoring of industrial processes. Case study: Evaporation stage of a Kraft pulp mill. 45th Pulp and Paper International Congress (ABTCP) and VII IberoAmerican Congress on Pulp and Paper Research (CIADICYP), CD-ROM, Brazil. (in Portuguese)

• Almeida, G.M., Park, S.W. (2009) Ash deposits monitoring in a convective heat transfer section of a Kraft recovery boiler. 10th International Symposium on Process Systems Engineering (PSE), 27, 1467-1472, Brazil.

• Almeida, G.M., Park, S.W., Cardoso, M. (2008) Detection of abnormal situations in a heat transfer section of a boiler using a hidden Markov model approach. 3rd International Symposium on Advanced Control of Industrial Processes (AdCONIP), 493-497, Canada.

• Almeida, G.M., Park, S.W. (2008) Fault detection and diagnosis in the DAMADICS benchmark actuator system - A hidden Markov model approach. 17th World Congress of The International Federation of Automatic Control (IFAC), 41(2), 12419-12424, South Korea.

• Almeida, G.M., Park, S.W. (2008) Process monitoring in chemical industries: A hidden Markov model approach. 18th European Symposium on Computer Aided Process Engineering (ESCAPE), 25, France, 1-6.

• Almeida, G.M., Park, S.W. (2005) Fault detection in a sugar evaporation process using hidden Markov models. 2nd International Symposium on Advanced Control of Industrial Processes (AdCONIP), 309-313, South Korea.

• Almeida, G.M., Park, S.W. Cardoso, M. (2004) Variables selection for neural networks identification for Kraft recovery boilers. 2nd IFAC Workshop on Advanced Fuzzy/Neural Control (AFNC), IFAC Proceedings Volumes, 37(16), 91-96, Finland.

My PhD Thesis (in Portuguese)

• • Detection of abnormal situations in chemical recovery boilers

Abstract

The greatest challenge faced by the area of process monitoring in chemical industries still resides in the fault detection task, which aims at developing reliable systems. One may say that a system is reliable if it is able to perform early fault detection and, at the same time, to reduce the generation of false alarms. Once there is a reliable system available, it can be employed to help operators, in factories, in the decisionmaking process. The aim of this study is presenting a methodology, based on the Hidden Markov Model (HMM) technique, suggesting its use in the detection of abnormal situations in chemical recovery boilers. The most successful applications of HMM are in the area of speech recognition. Some of its advantages are: probabilistic reasoning, explicit modeling and the identification based on process history data. This study discusses two applications. The first one is on a benchmark of a multiple evaporation system in a sugar factory. A HMM representative of the normal operation was identified, in order to detect five abnormal situations at the actuator responsible for controlling the syrup flow to the first evaporator. The detection result for the three abrupt situations was immediate, since the HMM was capable of detecting the statistical changes on the signal of the monitored variable as soon as they occurred. Regarding to the two incipient situations, the detection was done at an early stage. For both events, the value of vector f (responsible for representing the strength of an abnormal event over time), at the time it occurred, was near zero, equal to 2.8 and 2.1%, respectively. The second case study deals with the application of HMM in a chemical recovery boiler, belonging to a cellulose mill, in Brazil. The aim is monitoring the accumulation of ash deposits over the equipments of the convective heat transfer section, through pressure drop measures. This is one of the main challenges to be overcome nowadays, bearing in mind the interest that exists in increasing the operational efficiency of this equipment. Initially, a HMM for high values of pressure drop was identified. With this model, it was possible to check its capacity to inform the current state, and consequently, the tendency of the system (similarly as a predictor). It was also possible to show the utility of defining control limits, in order to inform the operator the relative distance between the current state of the system and the alarm levels of pressure drop.

Keywords

Chemical process monitoring, Chemical recovery boiler, Abnormal situation management, Hidden Markov model, Kraft pulp mill, Pattern recognition, Process trend analysis.