My general research interest is in developing data-driven applications for continuous industrial systems, within the scope of Process Data Analytics (PDA).

• • Process Data Analytics (PDA)
    Analysis of historical process data from continuous industrial systems with a focus on energy consumption, emissions level, predictive maintenance, etc.

I have particular interests in the following topics involving data-driven applications.

• • Process efficiency in general

Development of applications with a focus on energy consumption reduction, emissions level reduction, operational safety increase, among other aspects.

• Process monitoring

Development of automatic and more rational decision support systems for monitoring, fault detection and diagnosis (FDD), abnormal situation management (ASM), soft sensing and so on.

• Model interpretability

Model interpretability can contribute to more reasonable, less complex and more accurate data-driven models.

The methodological work lies in the areas of machine learning, industrial statistics and data visualization.

• Machine learning

General applications involving regression, classification, clustering, sensitivity analysis, text analytics etc.

• Industrial statistics

General applications involving statistical process control (SPC), design of experiments (DOE), chemometrics, Bayesian inference etc.

• Data visualization

Model-free and model-based multidimensional visualization (relationships, patterns, trends and anomalies) with exploratory, explanatory, confirmatory and communicative goals.

There are cooperations and collaborations with researchers from distinct knowledge areas and centers worldwide.

Please find the ongoing projects and the current team.

For undergraduate and graduate opportunities, please see open positions.