Artificial intelligence

by

IFPAC 2025 – Infometrix Presentations. Don’t Miss it.

Date: Monday, March 2-5, 2025
Venue:  Bethesda, MD (Washington, D.C.)
website: www.ifpacglobal.org

For more information, contact info@infometrix.com.

Topic:
Sensors/Soft Sensors/Probes/Optics

Advanced Separations: FastGC, HPLC & Data Systems

Author: Brian Rohrback, President

Real Time Data Analysis for Process Development: UPDATE (Abstract #139)

Abstract: We have been musing in the broader business community about broad AI approaches to data analysis, but a narrower focus is much more likely to generate near-term results. Luckily, we have tools that can be placed into the process that simplify the effort of building custom integrated systems.  Here we will discuss current techniques and show how the value of the information stream can be improved by more timely integrated data analysis.  But there is still effort to expend and timeliness is not the only issue. Any desired property metric will likely be only lightly correlated to the bits of data being assembled, so blending the information from disparate sources is necessary.  Looking at the options for data and model fusion shows that improvement is possible, and the answer is mostly free.  What results is a customizable system that can cater to any process or even personalized health evaluation.

Minimizing Error in Calibrating Spectrometers (Abstract #286)

Abstract: The adage “you can’t control what you don’t measure” may be old but it will always hold true. In industrial quality control settings, we choose to deploy optical spectrometers as a mechanism for measuring the chemistry and the physical attributes of the products we produce.  Spectroscopy’s advantage is that it is non-destructive, extremely fast, can be run on-line, and provides quantitative information through the characterization of functional groups in the sample.  Understanding the limits to spectroscopy’s accuracy and precision for a given application is governed by factors we can control and understand plus those that are out of our control.  To minimize error in spectroscopy assessments, there are three primary software-related areas to tackle, two of which the practitioner only needs to do once.

  1. At the start, a method needs to be set that optimizes how future spectra will be manipulated and involves choice of preprocessing and wavelength range plus algorithm selection.
  2. The other early process is to understand the precision of the laboratory methods and how they impact models.
  3. On a continuous basis, a maintenance effort is required to determine the optimum number of factors and identify outliers that degrade model performance.

The History of Chemometrics in Routine Chromatographic Analysis (Abstract #2)

Abstract: There is a rich history of the use of chemometrics both for signal processing and for pattern recognition analysis that dates back a half century now.  The first documented commercial implementations began in the early 1980s, predating the use of “personal” computers.  In considering use for routine quality measurements, the technology divides between signal processing (alignment, curve resolution) and automated interpretation (classification, quantitation, mixture analysis).  The use of standard chemometrics technology vastly reduces the time required to process chromatographic data in a quality control environment and it enables unsupervised chromatographic analysis and interpretation.

Bio:

Brian Rohrback is the President and CEO of Infometrix and has managed the company for several decades.  He has steered Infometrix into position as the dominant independent supplier of chemometrics technology to analytical instrument companies, process analyzer suppliers, and their customers.  His expertise is in the integration of multivariate data processing for process analyzers and laboratory instruments catering to routine quality analysis. Rohrback holds a B.S. and Ph.D. in chemistry specializing in the processing of chromatographic data, plus went to the dark side to get an MBA. His publications span 50 years and cover topics in petroleum exploration, chemical plant optimization, clinical and pharmaceutical diagnostics, informatics, pattern recognition, and multivariate analysis.  In 2016, he was presented the ISA Excellence in Analytical Technical Innovation Award for revolutionary work in the field of chromatography. He has a passion for Classic cars and nearly all aspects of chemistry and process science.

by

PITTCON 2024 – Spectroscopy and the Intersection with Machine Learning

Pittcon 2024Venue: February 24-28, 2024 San Diego Convention Center Presented by: Brian Rohrback, Ph.D., MBA, President, Infometrix, Inc. Abstract: 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:
  1. Optimizing the instrument settings for a given application;
  2. Optimizing the method parameters – preprocessing, transformations, wavelength ranges;
  3. Handling of calibration transfer; and
  4. 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. Register at www.pittcon.org/register/.
by

Gulf Coast Conference 2021 – Managing Calibrations for Optical Spectroscopy

GCC 2021 event

GCC 2021

Join Brian Rohrback on 10/12/2021 at the Orchid Room, 9:40 AM – 10:10 AM.

Abstract:
A multi-industry consortium got together 8 years ago to rethink how calibrations need to be performed for spectroscopy instruments and analyzers. The priority was on solutions that are non-disruptive, fully utilize legacy systems, and lessen the workload rather than layer on additional requirements. The result is a foolproof, simple approach that can be used with any type of brand of spectrometer, any type or brand of chemometrics, and ensures robust and reliable calibrations. For more information, email info@infometrix.com.

by

2021 AFPM Summit – The Role of Artificial Intelligence in Manufacturing and Petroleum Refining

2021 AFPM SummitJoin Brian Rohrback on October 5th at 11:00 am – 12:00 pm CST for panel discussion on The Role of Artificial Intelligence in Manufacturing and Petroleum Refining at the 2021 AFPM Summit.

 

Session Description:
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. For more information, email info@infometrix.com.