Big Data Analytics & AIChE Conference 2015

bigdata analyticsAttending the AIChE Spring Meeting 2015 in Austin, Texas? ProSensus will be exhibiting our desktop multivariate data analysis solution ProMV, and our online solution for real-time batch monitoring (ProBatch Online) and control (ProBatch Control). ProSensus will be demonstrating how to find the root cause of product variation, predict product quality, and find optimal operating conditions using our solutions for both batch and continuous processes. Stop by booth 118 for a quick demo and for some free swag. If you're there only for free swag that's okay too. 

In addition to exhibiting at the AIChE spring meeting, ProSensus founder and CEO Dr. John F. MacGregor will be giving two talks during the first ever Big Data Analytics session. John’s first talk will focus on how you can use the vast amounts of data you are already collecting to improve product quality, increase yield, and reduce operating costs. John will then discuss how to implement multivariate data analysis to troubleshoot your process in real-time using live data. Interested in attending both, or one of John’s talks? Read on for time, location and full abstracts. 

Continue Reading

How Multivariate Machine Vision Can Improve Operations

QuantifyMachine vision is a growing field that leading manufacturers are adopting to improve their operations, product quality, and profit margins. Forecasted to be a 26.9 billion dollar industry by 20201, it also happens to be a field where we offer our clients advanced solutions.

Benefits of Multivariate Machine Vision

Manufacturers across multiple industries are embracing machine vision to obtain new measurements to tune processes, identify off-spec product, and discover new insights into product quality. To be successful with machine vision, both the right hardware and the right software is required. Given the multitude of hardware vendors and several software options, it can be a challenging space to navigate. For this reason, we offer our clients on-site trials as a first step to a complete, all-in-one machine vision solution.

Continue Reading

Visualize Missing Data Patterns in ProMV

missingdatamapWhen was the last time you received a perfect set of data? As problem solvers in manufacturing, we are constantly analyzing data that contains correlated varables, missing values, and other messy problems that aren't handled well (or at all) by traditional regression methods.

ProMV has always handled missing data implicitly, but our latest version gives you a Missing Data Map so you can spot the missing data patterns at a glance.

Why visualize missing data patterns?

Continue Reading

Improve Product Quality in 2015: Get the RIGHT data

The fingerprint of the problem will be in the data.Big Data was a BIG buzzword last year, but reaching your 2015 product quality goals is all about this question:

Are you collecting the RIGHT data?

Day-to-day manufacturing data can help improve product quality, but simply collecting big data sets isn’t sufficient. You need the right variables, measured often enough, and you may need weeks or months of data across different seasons.

Continue Reading

Communicate Your Batch Trajectory Insights

CommunicateBatchTrajectoryFindingsAs process engineers ourselves, we know it can be challenging to communicate the results of a multivariate analysis to your colleagues and managers, especially for batch processes. In ProMV 14.08 we worked hard to help you tell your stories so your co-workers can easily grasp your findings without being experts in multivariate analysis.

Released last month, ProMV 14.08 adds visual enhancements to trajectory plots and allows you to select and plot only the key trajectories for your presentations. In addition, we've completely revamped the simulation of real-time batch process monitoring, which will provide a big WOW factor in your next meeting.

Continue Reading

Improving Product Quality in Rubber Manufacturing

RubberQualityDuring last week's International Rubber Expo in Tenessee, we introduced our BaleGuard surface inspection system to the entire rubber industry for the first time. Originally custom-designed in 2009 to detect defective rubber bales using multivariate image analysis, BaleGuard is emerging as the leading tool for quality-minded rubber bale manufacturers.

What exactly is a Rubber Bale, anyway?

Continue Reading

Misconceptions about Latent Variable Models

JohnMacGregorGeorgeBoxMedalWhile giving courses over the years, I’ve noticed that certain misconceptions about latent variable models persist among statisticians and chemometricians. At the 14th annual ENBIS conference (European Network for Business & Industrial Statistics) in September, I have decided to discuss a number of these during my plenary George Box Medal presentation. Some of the key questions include:

Continue Reading

Would you rather do 321,000 experiments? Or 12?

you're invited to join the discussion on productivity in product developmentOne of the best-kept secrets at ProSensus is that we help clients improve their return on investment in product development. Our clients can:

•  Formulate new products in half the time (compared to traditional methods)
•  Achieve 20-40% reductions in raw material costs
•  Create new-to-world products that capture huge market share and high margins

In the past 3 years, I've worked on some very specific applications, like frozen muffin batters, next-generation automotive fluids, and smart polymers for eye injections.

Now I'd like to explore some general aspects and best practices of product development with you.

Continue Reading

How to Improve Productivity Using ProMV 14.02


Released almost five months ago, ProMV 14.02 makes it fast and easy for you to customize plots and share information. Ultimately you’ll save time and increase your productivity as you execute data mining projects and build multivariate models.

The feedback from early adopters has been very positive. They like the ability to create a custom template for all ProMV plots, annotate individual plots to highlight key findings, and save their workspaces to share with colleagues for review and further analysis.

Have you explored the new features yet? If not, here’s how to get started.

Continue Reading

European Companies Invest in Better Batch Analysis

Dr. John MacGregor and team multivariate analysis batch analysis batch control ProSensusDuring our recent trip to Europe, our team met with several chemical and pharmaceutical clients to review & plan projects and conduct in-house seminars. The dominant theme of our trip was batch processes in manufacturing, and we maintained that focus as we delivered our advanced 3-day course Multivariate Analysis of Batch Processes in Basel, Switzerland.

We noted that in the chemical industry, a primary goal is to command a higher price by becoming a premium supplier, and this demands tighter quality control. In bio-pharma, some companies are strapped for capacity but would like to delay the huge capital costs of building new batch reactors. Both of these goals can be achieved with advanced tools for managing the quality and yield of each batch.

Continue Reading

3 Ways to Organize Data for Multivariate Analysis

In our courses and previous blog posts, we've described the benefits of dividing your variables into logical groups and building multi-block multivariate models. But did you know there are 3 ways you can organize your data in Excel to prepare for multi-block modeling in ProMV? We added flexibility to ProMV's data import process in version 13.08 to give you these options. This 15-minute video tutorial demonstrates the 3 different ways of organizing your data and how each strategy affects the import process. Be sure to watch it in full screen mode to see all of the details.

Download ProMV | Register for a multivariate analysis course

Continue Reading