Join us at PEFTEC 2022. This year it will be hybrid and access to the exhibition and all of the technical sessions is free of charge.
Keynote speaker, Brian Rohrback of Infometrix, Inc. will present his talk on Streamlining the Use of Chemometrics
June 8th at 13:15 CEST
Artificial intelligence and machine learning are inevitable results of the work driven by the consumer side of our economy. The question is not whether it will impact refining and chemical plant operation, but how soon and how long it will take for the benefits to outstrip the costs. The goal is to distinguish between vision and hallucination and to provide some practical guidance for making progress in this complicated set of fields. There are three categories of measurements that provide us with the data that will form the basis for any interpretation system: single-purpose sensors, chromatographs, and spectrometers. Multivariate analysis can be used in all three categories and, in fact, is critical to interpreting output from any type of spectrometer. We can easily demonstrate that the use of multivariate analysis for each of the three groupings, even these data sources assembled together, gives faster response, improved flow of information derived from these data, and a significant leg up for process understanding. This information is available and is nearly cost-free.
Join Brian Rohrback of Infometrix, Inc. for his talk on Agile Process Analytics, June 14, 1:05pm EST.
Agile Process Analytics
Application knowledge and chemometrics play a vital role in the processing of all types of multivariate data into application-specific information and has been doing so for at least 50 years. There has been a not-so-subtle shift in thinking as we integrate basic concepts and the occasional hallucination in the data mining, artificial intelligence, machine learning worlds. The target is to identify combinations of our technical tools to augment or replace tasks that consume brainpower where timely response is valued, and profits are at risk. The biggest focus of chemometrics has been in the calibration of optical spectrometers. It is worth considering the subtasks:
- Optimizing the instrument settings for a given application;
- Optimizing the method parameters – preprocessing, transformations, wavelength ranges;
- Handling of calibration transfer; and
- Optimizing models for inliers and rank in pursuit of routine processing and adjusting to changes in ingredients and unit operation.
The first two tasks are a set-once method development and the third may be generic across all applications. This paper tackles subtask 4 with a project that combined traditional approaches in statistics, database organization, pattern recognition, and chemometrics with some newer concepts tied to better understanding of data mining, neurocomputing, and machine learning. The future goal is to automate spectroscopy calibrations such that it is possible to have instrument systems tune themselves.
Scott Ramos, recipient of the 2021 EAS Award for Outstanding Achievements in Chemometrics, will give his talk on “Multivariate Lessons for the Analytical Chemist”. Join us November 16th at 11am.
Multivariate Lessons for the Analytical Chemist
The field of chemometrics is a relatively new discipline, with its genesis about 40 years ago. Despite this relatively short history, it is now thriving as a vibrant area of research and practice, finding place in a wide variety of chemical applications. Some of the tools of the trade have found acceptance well outside of chemistry. For example, PLS (Partial Least Squares Regression) has become popular in statistics which was lacking methods for data with highly correlated variables.
Two main thrusts have propelled the evolution of chemometrics: innovation and evangelism. The toolkit available to practitioners is continually being augmented by improvements to current methods as well as creation of new algorithms. But, for the field to succeed, it must reach the hands of those who can benefit: the many analysts who utilize these tools in their daily work.
To meet the needs of already-overworked analysts, working solo or in teams, we can identify at least 3 ways in which multivariate tools can become part of the company work practice: hire a dedicated chemometrician, train one or more of staff members in the use of chemometrics, or contract an outside entity to provide chemometrics services.
Whichever the pathway a company chooses, understanding how best to optimize chemometrics models is paramount to success. This talk will review some of these concepts, covering issues that impact model quality, and will reflect on the viability of automating these decisions.
Chemometrics-enhanced Classification of Source Rock Samples Using their Bulk Geochemical Data: Southern Persian Gulf Basin, co-authored by Infometrix’ Scott Ramos has recently been published. See abstract below and contact us if you have any questions.
Chemometric methods can enhance geochemical interpretations, especially when working with large datasets. With this aim, exploratory hierarchical cluster analysis (HCA) and principal component analysis (PCA) methods are used herein to study the bulk pyrolysis parameters of 534 samples from the Persian Gulf basin. These methods are powerful techniques for identifying the patterns of variations in multivariate datasets and reducing their dimensionality. By adopting a “divide-and-conquer” approach, the existing dataset could be separated into sample groupings at family and subfamily levels. The geochemical characteristics of each category were defined based on loadings and scores plots. This procedure greatly assisted the identification of key source rock levels in the stratigraphic column of the study area and highlighted the future research needs for source rock analysis in the Persian Gulf basin.
Keywords: Chemometric Classification, Source Rock Geochemistry, Rock-Eval Pyrolysis Data, HCA, PCA.
Feb 23-26, 2020
See abstracts below for papers being presented at the IFPAC 2020 conference. Join us or contact us for more information.
Randy Pell – Infometrix
Scott Ramos – Infometrix
The use of chemometrics in processing spectroscopic data is far from new; the processing of NIR data in petroleum refineries dates to the early 1980s and in the food industry well before that. Although the computers have improved in performance leading to speed ups in the calibration process, the procedures being followed have not changed significantly since the 1980s. Intriguingly, we have made decisions on the corporate level that work against each other. We are installing more spectrometers and at the same time we are reducing staffing for spectrometer calibration and maintenance. A change in approach is mandated. In the spirit of automation, there are tools from both the chemometrics and the general statistics realms that can be applied to simplify the work involved in optimizing a calibration. Robust statistical techniques require some set-up of parameters, but once established for an application, they are often useable in every other instance of that application. The result is a one-pass means of selecting optimal samples for a calibration problem and, in turn, simplifies the assignment of model rank. This approach solves two problems:
Optimizing Chromatographic Interpretation
– Infometrix, Inc.
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 process information comes from spectrometers and chromatographs and, for many applications, these prove to be the cheapest, most adaptable, and most reliable technologies available. In chromatography, there is a rich history and the chemometrics role is well defined but rarely placed into routine practice. This paper will provide a retrospective of routine processing solutions that have solved problems in pharmaceutical, clinical, food, environmental, chemical, and petroleum applications. It also discusses how to 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.