Fault Detection in Industrial Process

with Autoencoder Ensemble

Data Science Projects

Big Data Tutorials

Fire Detection with YOLO

Crypto Lags Analysis

Reseach papers

Comparison of autoencoder architectures for fault detection in industrial processes

This work evaluates autoencoder architectures for fault detection using the Tennessee Eastman Process. Sparse designs, especially variational and deep denoising autoencoders, showed superior performance, highlighting their effectiveness across diverse false alarm rate thresholds.

BibMon: An open source Python package for process monitoring, soft sensing, and fault diagnosis

BibMon is a Python package that provides deviation-based predictive models for fault detection, soft sensing, and process condition monitoring.

About me

I am deeply passionate about Data Science and Machine Learning as we can use these tools to extract useful information from data to solve complex real-world problems across different industries.

With a background in Chemical Engineering, I have worked on applied research on Process Monitoring and Fault Detection for the oil and gas industry using neural networks, focusing on their ability to forecast long-term time series data.

In my free time, I enjoy playing chess, exercising, playing the guitar and getting up to date with the new developments in AI.