Cristiano Fontes

Fuzzy control of a nylon polymerization semi-batch reactor

Batch and semi-batch polymerization reactors with specified trajectories for certain process variables present challenging control problems. This work reports, results and procedures related to the application of PI (proportional and integral) fuzzy control in a semi-batch reactor for the production of nylon 6. Closed loop simulation results were based on a phenomenological model adjusted for a commercial reactor and they attest to the potential benefits and versatility of the use of PI fuzzy control in polymerization systems.

Pattern recognition in multivariate time series - A case study applied to fault detection in a gas turbine

Advances in information technology, together with the evolution of systems in control, automation and instrumentation have enabled the recovery, storage and manipulation of a large amount of data from industrial plants. This development has motivated the advancement of research in fault detection, especially based on process history data. Although a large amount of work has been conducted in recent years on the diagnostics of gas turbines, few of them present the use of clustering approaches applied to multivariate time series, adopting PCA similarity factor (SPCA) in order to detect and/or prevent failures. This paper presents a comprehensive method for pattern recognition associated to fault prediction in gas turbines using time series mining techniques. Algorithms comprising appropriate similarity metrics, subsequence matching and fuzzy clustering were applied on data extracted from a Plant Information Management System (PIMS) represented by multivariate time series. A real case study comprising the fault detection in a gas turbine was investigated. The results suggest the existence of a safe way to start the turbine that can be useful to support the development of a dynamic system for monitoring and predicting the probability of failure and for decision-making at operational level. Real case study comprising the fault detection in a gas turbine.Comprehensive method for pattern recognition associated to fault prediction in gas turbines.Results show the efficiency of the proposed approach for decision-making at operational level.The whole three step method presented is flexible and portable.An extended version of the FCM algorithm suitable for the clustering of multivariate time series is applied.

A model-based approach to quality monitoring of a polymerization process without online measurement of product specifications

Quality monitoring and support for decision-making in a complex industrial process.Comprehensive approach to select and estimate parameters of a complex model.Dynamic monitoring of a process without on-line measurement of quality variables.Control of product quality with impact on productivity and customer satisfaction.A novel orthogonalization algorithm able to ensure estimability. This paper presents a model-based approach for on-line monitoring of difficult-to-measure quality variables with the description of their dynamic behavior. The strategy comprises the use of a Virtual On-line Analyzer (VOA), based on an empirical model, whose development is supported on the one hand by experimental data, and on the other hand by a complex phenomenological model. A systematic approach to the selection and estimation of parameters of the phenomenological model from experimental data is also presented in order to adjust this model to the behavior of the industrial process. Regarding the experimental data, this complete model has additional information (such as the dynamic behavior of the process, embedded in the knowledge used in its formulation) and it is able to provide synthetic data for VOA training which comprises a NARX (Non-linear AutoRegressive with Exogeneous inputs) neural network model. A real case study comprising quality monitoring in a polymerization system is investigated. The available measurements of the main polymer properties are performed at a low frequency and are not able to represent the dynamic behavior and support decision-making at the operational level, especially during online grade transitions (changes in product specifications). The results show the ability of the neural model to predict the quality variables with a high frequency (small sampling period), enabling and supporting decision-making for quality monitoring of the polymer in real time.

A wavelet-based clustering of multivariate time series using a Multiscale SPCA approach

Case study comprising the fault detection in a benchmark industrial process.Comprehensive and novel method for clustering multivariate time series.Multiscale approach provides improvement in clustering quality.Multiscale approach represents a useful technique in FDD problems.Results show the ability of the method in recognizing normal and fault patterns. Clustering and pattern recognition from data can be used as means to extract knowledge of a process which may be useful for control, predicting failures and supporting decision making, among other functions. This paper presents a method to recognize patterns in multivariate time series based on a combination of wavelet features, PCA (Principal Component Analysis) similarity metrics and fuzzy clustering. The signal analysis of some process variables is performed based on the Wavelet Transform (WT), and a Multiscale PCA Similarity factor (SPCAms) is proposed to consider the distances between objects (multivariate time series) according to a multi-resolution approach. A database extracted from the benchmark Tennessee Eastman (TE) process is used to show the efficiency of the method compared with traditional approaches in a fault detection and diagnosis problem. The clustering using SPCAms provides the recognition of a fault pattern which may be useful to support decision-making at the operational level allowing real-time monitoring of failure probability.

Um indicador para a avaliação do desempenho docente em instituições de ensino superior

This paper presents a quantitative index to measure professor performance (IAD-Indicador de Avaliacao Docente, professor evaluation index) that can be used as a tool for the evaluation of professors in higher education institutions. This index is in accordance with the institutional indicators established by REUNI (a government program to support the reorganization and expansion of Brazilian federal universities), and also has important features such as robustness and exogenous practice, considering other aspects of the professors actuation in higher education institutions such as retirement, academic management, extension activities and qualified scientific production, that are not included in the formulation of REUNI indicators. Other fundamental aspects are also included, such as the quality of undergraduate courses and the efficiency of graduate courses, through accounting for the rate of titled students. Therefore, IAD provides a complete professor evaluation considering the whole of their activities, namely, teaching, research, extension and academic management, in both undergraduate and graduate courses. The results show that the indicator is robust and the attainment of the aims proposed is feasible. The IAD can be used as a valuable tool in the academic policy and management of the institutions in accordance with government and state policies. Some parameters of the indicator can be adjusted in order to satisfy specific goals and academic policies of the institutions.This paper presents a quantitative index to measure professor performance (IAD-Indicador de Avaliacao Docente, professor evaluation index) that can be used as a tool for the evaluation of professors in higher education institutions. This index is in accordance with the institutional indicators established by REUNI (a government program to support the reorganization and expansion of Brazilian federal universities), and also has important features such as robustness and exogenous practice, considering other aspects of the professors actuation in higher education institutions such as retirement, academic management, extension activities and qualified scientific production, that are not included in the formulation of REUNI indicators. Other fundamental aspects are also included, such as the quality of undergraduate courses and the efficiency of graduate courses, through accounting for the rate of titled students. Therefore, IAD provides a complete professor evaluation considering the whole of their activities, namely, teaching, research, extension and academic management, in both undergraduate and graduate courses. The results show that the indicator is robust and the attainment of the aims proposed is feasible. The IAD can be used as a valuable tool in the academic policy and management of the institutions in accordance with government and state policies. Some parameters of the indicator can be adjusted in order to satisfy specific goals and academic policies of the institutions.

Failure analysis and design of a front bumper using finite element method along with durability and rig tests

This work presents a case study that comprises the application of the Finite Element Method (FEM) to the design of a front bumper to predict possible failures caused by fatigue. Stress distribution and damage estimates were obtained by using FEM together with rig tests results. Vehicle durability tests were also performed, and geometric changes were proposed in the design of the component analysed based on the simulation results obtained from FEM. A good agreement between experimental data and FEM predictions was found. The case study and results demonstrate that time and cost can be reduced in the course of the product development phase in the automotive industry. FEM also can be used to support decision-making during the design phase of the product.

Pattern Recognition using Multivariate Time Series for Fault Detection in a Thermoeletric Unit

Abstract This paper presents a methodology for recognition of operating patterns of a gas turbine in a thermoelectric power plant (Brazilian Oil Company). Patterns related to the normal starts (without failure) and starts with failure (trip) were recognized. The process data were obtained from the plant information management system (PIMS) and techniques of data mining suitable for multivariable time series were adopted with emphasis on similarity metrics, linear scan and clustering, among others. The recognized patterns represent important and useful results to support the development of dynamic system for the monitoring and predicting the probability of failure in the equipment.

Um modelo para o dimensionamento do corpo docente para o apoio à tomada de decisão no planejamento de instituições de ensino superior

Este trabalho propoe, desenvolve e aplica um modelo para o dimensionamento do corpo docente de unidades universitarias (departamentos, faculdades, escolas, institutos ou ate mesmo a universidade como um todo) e para o projeto da composicao de regime de trabalho otima desse corpo docente. A importância, contribuicao e oportunismo contemporâneo do trabalho se justificam especialmente em face da nova lei do professor-equivalente. O modelo contempla todas as atividades pertinentes a pratica docente universitaria (ensino de graduacao e pos-graduacao, pesquisa e orientacao, extensao, gestao e capacitacao) e, embora talhado especialmente para instituicoes federais de ensino superior (IFES), pode ser facilmente adequado para sua utilizacao em IES (instituicoes de ensino superior) de outras esferas governamentais e mesmo em IES comunitarias, confessionais ou privadas. Alem disso, o modelo e complementar e nao concorrente aos indicadores estabelecidos pelo Reuni (Programa de Apoio a Planos de Reestruturacao e Expansao das Universidades Federais), podendo ser considerado uma ferramenta de projeto de unidades universitarias, enquanto os segundos podem ser considerados como instrumentos de acompanhamento da operacao dessas unidades. O modelo e bastante generico, permitindo sua ampla aplicacao em diversos tipos de unidades universitarias, e alguns dos seus parâmetros podem ser ajustados a fim de satisfazer metas e politicas especificas dessas unidades. A aplicacao do modelo desenvolvido ao estudo de caso de um departamento mostra a sua consistencia e utilidade, inclusive como poderoso instrumento de apoio a tomada de decisao no planejamento e na gestao de recursos docentes em IES.

Valuation of Clean Technology Projects: An Application of Real Options Theory

Abstract The valuation of investment in technologies that minimize the environmental impacts is not an easy task. Investment and environmental damages are partially or totally irreversible, the forecast period for the analysis of such investment is usually long and there are economic and environmental uncertainties which are still enhanced by the fact that environmental damages is not a linear function of the impacts. A better understanding of the behavior of these uncertainties and of the strategies to incorporate these uncertainties in the design valuation would be useful in the decision making associated to the investment with relevant environmental impacts. This work presents an extensive review about the application of the Real Options Analysis in the investment decision associated to the environmental problems and discusses the potential of this technique in the investment analysis of these cases. The aspects discussed denote that the approach of Real Options Analysis is better than the traditional methods and possibly is capable of predicting the benefit obtained with the reduction of the environmental risks provided by the use of clean technology.

A hybrid clustering approach for multivariate time series – A case study applied to failure analysis in a gas turbine

A clustering problem involving multivariate time series (MTS) requires the selection of similarity metrics. This paper shows the limitations of the PCA similarity factor (SPCA) as a single metric in nonlinear problems where there are differences in magnitude of the same process variables due to expected changes in operation conditions. A novel method for clustering MTS based on a combination between SPCA and the average-based Euclidean distance (AED) within a fuzzy clustering approach is proposed. Case studies involving either simulated or real industrial data collected from a large scale gas turbine are used to illustrate that the hybrid approach enhances the ability to recognize normal and fault operating patterns. This paper also proposes an oversampling procedure to create synthetic multivariate time series that can be useful in commonly occurring situations involving unbalanced data sets.