Abstract # 169 – Paper
10/16/2018 – 1:20 PM – 1:40 PM – Tulip Room

Optimizing Gas Chromatography
Brian Rohrback – Infometrix

The heartbeat of the process environment is in the data we collect, but we are not always efficient in translating our data streams into actionable information. The richest source of hydrocarbon process information comes from spectrometers and chromatographs and, for many applications, gas chromatography is the cheapest, most adaptable, and most reliable technology available.  We can use tech borrowed from other fields to provide more consistent and objective GC results, automate translation of the raw traces into real-time information streams, and create databases that can be used across plant sites or even across industries.

Abstract # 145 – Paper
10/16/2018 – 10:45 AM – 11:05 AM – Tulip Room

Automating Spectroscopy Calibrations
Brian Rohrback – Infometrix, Inc.

A consortium of companies has undertaken a project to reduce the effort devoted to producing, maintaining, and stabilizing optical spectroscopy performance in routine quality assessment. Over a five-year period, the group has examined an unprecedented historical collection of spectra from multiple spectrometers spanning 1-5 years from sixteen oil refineries, with the goal of developing and maintaining stable models for long-term deployment. Even though the data are tied to petroleum work, the lessons learned are true for all applications. The technologies utilized follow a pattern of best practices, including the use of Robust outlier diagnostics, local and hierarchical modeling, and model augmentation. The effort has resulted in significant progress towards automation of model creation, stability, and maintenance in an industrial process. Additionally, we will share a comparison of prediction capabilities of different spectroscopy technologies and form-factors that can lead to a significant reduction in deployment and maintenance cost.