(119b) Future of Latent Variable Methods for Big Data Analytics in the Process Industry 4.0

In modern industries adopting the Industry 4.0 paradigm, the result of Industrial Internet of Things (IIoT) connecting intelligent physical entities to each other allows complex equipment units to have embedded sensors and special modules (agents) providing connection to the monitoring center. This is leading to the so-called Big Data problem in Industry 4.0.

Big data exhibit high volume and correlation, rank deficiency, low signal-to-noise ratio, changing structure, and missing values. Data in process/manufacturing industries are especially complex in structure and the useful information is often subtle.

Apart from the infrastructure (hardware) needed to manage these Big Data streams, the key point is how to analyze them to effectively extract information to give organizations new insights about their products, customers and services and steer the decision-making process. This can be particularly valuable when it is critical to maintain quality and uptime, such as in process monitoring applications, by quickly detecting and diagnosing abnormal activities, predicting the time-to-failure of equipment units or when rapid new products development is critical for company survival.

In this talk we illustrate the potential of latent variable-based multivariate statistical methods for Big Data Analytics to analyze and visualize extracted information in a way that is easily interpreted and that is useful for process understanding, real time process monitoring, fault detection & identification, process improvement, predictive maintenance, and optimization.

A discussion on the pros/cons of latent variable models with classical statistical and machine learning methods in Big Data environments will also be addressed.