EAS 2021 – ChemMLometrics. Perform. Repeat. , Brian Rohrback

EAS 2021 ChemMLometrics. Perform.Repeat. Join Brian Rohrback for his talk on ChemMLometrics. Perform. Repeat., November 16th at 10:15AM.

ChemMLometrics. Perform. Repeat.

Doing a one-off research project can be very satisfying, but in industry the money is made when the results of such a project can be placed into routine quality assessment.  There is much discussion today revolving around machine learning and some of this discussion has invaded the space that has been occupied by chemometrics over the last few decades. There is a large overlap as these techniques are applied in instruments aimed at process quality control.  To a large extent, any differentiation will simply be a question of the jargon chosen. An on-line Stanford University class on machine learning covers Principal Components Analysis, Principal Components Regression, Partial Least Squares, K-Nearest Neighbor, and other mainstays of the chemometrics toolbox.  However, there are techniques that are new in the machine learning realm that can be employed for targeted tasks, improving the traditional chemometrics regime of supervised learning.  The key is to narrow the focus for each component in a system and to understand the extent to which you can control the inputs.  This talk highlights examples in optical spectroscopy calibration particularly for the identification of outliers, and in chromatography for both signal processing and the management of chromatographic libraries. The emphasis is to highlight both the similarities and the uniqueness of machine learning and chemometrics and show how they combine to form robust solutions for industry.

EAS 2021 – Automating Calibrations for Optical Spectroscopy

EAS 2021 Automating Calibrations for Optical Spectroscopy Join Brian Rohrback for his talk on Automating Calibrations for Optical Spectroscopy, November 16th at 1:30PM.

Automating Calibrations for Optical Spectroscopy

This talk represents a summary of a multi-industry consortium established eight years ago to re-evaluate how the calibration process in optical spectroscopy could be managed more efficiently.  The idea is to enable a shift from current practices to approaches that take better advantage of the computational power and some newer concepts supplied by research into machine learning algorithms.  The result is a solution that is not disruptive of any legacy instruments or software already in place and lessens the workload rather than laying on additional requirements. The approach uses all readily available components and can be assembled easily for any specified purpose.  The use of commercial components reduces the cost of deployment and assembling pieces in a plug-and-play manner minimizes the impact of any previous selections of hardware and software.

ISA 2020 – Rethinking Calibration for Process Spectrometers II

The Long Beach Convention Center
Long Beach, CA
1:30pm, April 27th

 

Brian Rohrback
Infometrix, Inc.
Will Warkentin
Chevron Richmond Refinery

 

KEYWORDS
Best Practices, Calibration, Cloud Computing, Database, Gasoline Blending, Optical Spectroscopy, PLS, Process Control

ABSTRACT
Optical spectroscopy is a favored technology to measure chemistry and is ubiquitous in the hydrocarbon processing industry. In a previous paper, we focused on a generic, machine-learning approach that addressed the primary bottlenecks of mustering data, automating analyzer calibration, and tracking data and model performance over time. The gain in efficiency has been considerable, and the fact that the approach does not disturb any of the legacy (i.e., no changes or alterations to any analyzer or software in place) made deployment simple.

We also standardized a procedure for doing calibrations that, adheres to best practices, archives all data and models, provides ease of access, and delivers the models in any format. What remains is to assess the speed of processing and the quality of the models. To that end a series of calibration experts were tasked with model optimization, restricting the work to selecting the proper samples to include in the computation and setting the number of factors in PLS.  The amount of time and the quality of the models were then compared.  The automated system performed the work in minutes rather than hours and the quality of the predictions at least matched the best experts and performed significantly better than the average expert.  The conclusion is that there is a large amount of recoverable giveaway that can be avoided through automation of this process and the consistency it brings to the PLS model construction.

INTRODUCTION
There is a lot of mundane work tied to the assembly of spectra and laboratory reference values to enable quality calibration work.  There is also insufficient guidance when it comes to the model construction task.  How much time should be spent on this task?  How to best assess whether a spectrum-reference pair is an outlier or not? How many cycles of regression-sample elimination make sense? Where do we switch over from improving the model by adding PLS factors to overfitting and incorporating destabilizing noise?

For more information or the full paper, contact us.

Rethinking Calibration for Process Spectrometers

Click on image to view the full paper.

 

 

Title:
Rethinking Calibration for Process Spectrometers

Authors:
Will Warkentin, Chevron
Brian Rohrback, Infometrix

Abstract:
Optical spectroscopy is a great source of process chemistry knowledge. It has the advantage of speed, sensitivity, and simple safety requirements. As one of very few analyzer technologies that can measure chemistry, it has become a workhorse in the hydrocarbon processing industry. What if we could put a spectroscopy system in place and have it handle the application and communicate results as soon as it is turned on? Then, if predictions do not match legacy standards, the system dials itself in or calls for help. And, we are not constrained on either the hardware or the software front. In this paper, we address the primary bottleneck of mustering data, automating analyzer calibration, and tracking data and model performance over time.

Keywords:
Best Practices, Calibration, Cloud Computing, Database, Optical Spectroscopy, PLS, Process Control