Host Dr. Jerry Workman speaks with Dr. Brian G. Rohrback to discuss to his research and experience in automating the process of building multivariate calibrations.
Enjoy the podcast. For more information and further conversation, contact us at info@infometrix.com.
Click to access Analytically Speaking Podcast Ep.33
The Analyzer Technology Conference for 2025 is coming up in April and is likely the best source of information for process instrumentation and application reviews in the chemical and petroleum industries. Infometrix has been describing the automation of chemometric calibrations in this forum since 2015 independently and in concert with Chevron and Yokogawa. Most recently, the fundamentals of quality control employing optical spectroscopy were presented and the paper is available for download.
Click to access rohrback-atc-2024-paper.pdf
Chemometric plus Automation equals Machine Learning and Best Practices.
A calibration model tends to improve as additional calibration samples are added to the library. If the samples reflect variation in the chemical composition, the model then expands its zone of relevance. Ultimately, as these new zones expand calibration scope, the model can degrade in performance due to nonlinearities and may require adding to the model rank, which can make the model fragile. Building local models is one answer to gain the best of both worlds, but optimizing a locally weighted model is tricky and time consuming. Automating the optimization of locally weighted models is a solution.
http://doi.org/10.1002/cem.3637
For additional information or questions, contact info@infometrix.com.
#chemometrics #LWR #spectroscopy #regression
Venue:
September 3-5, 2024
Cartagena, Colombia
Booth: 52
Latin American Refining Technology Conference (LARTC) is the number one downstream event in Latin America where major refiners will gather to network and share the latest in technology and collaboration opportunities. Infometrix will be at booth #52. Come visit us as we share solutions to save time, resources, and to reduce manual workload. Eliminating retention time shifts in chromatography and automating calibration for optical spectrometers to enable better models and optimize use of personnel will be the focus. We look forward to seeing you. LARTC 2024
Venue:
October 15-16, 2024
Moody Gardens Convention Center, Galveston, Texas 77554
Presented by: Brian Rohrback – Infometrix, Inc.
Abstract Number: 119
Abstract: 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 provide practical guidance for making progress in this complicated set of fields. Machine Learning is critical to interpreting output from any type of spectrometer and improves the flow of information providing a significant leg up for process understanding. The key is to fully automate spectroscopic calibration. Gulf Coast Conference 2024
infometrix.com 