Multi-block modeling in multivariate analysis

3blocksThinking back to when you first learned regression analysis, do you remember discussing the differences between input/predictor variables and response/ measured variables, or simply X's and Y's? As analysts, we are taught to divide our variables into these two categories. But, as data sets grow to include multiple unit operations, categories of ingredients, or categories of product features, there are better ways to think about your logical groupings, or blocks.

Grouping variables into blocks for multivariate analysis allows you to answer questions like:

•  Which unit operation has the most impact on final product quality?
•  Do raw material properties matter more than process conditions?
•  Which category of ingredients has the biggest influence on product performance?

Depending on what questions you hope to answer, these blocks can move between the X-space and Y-space in multivariate analysis. Want to learn more about multi-block modeling in multivariate analysis? Check out our multivariate analysis courses.

Soft Sensors – Predicting Complex Quality Attributes

softsensors predictingqualityattributesIn the pursuit of a better product, quality targets are constantly changing. Texture, shape, size, colour, and many other attributes are indicators of product quality, but the hardware to measure these features can be expensive and impractical to implement online. For example, how does one detect the crunchiness of a chip?

Enter soft-sensors. Using ProMV Online, multivariate models can be deployed for real-time prediction of complex quality attributes, from the crunchiness of chips on a conveyor right now to the firing-end temperature of a lime kiln two hours in advance. Do you have complex product attributes to predict? Contact us to discuss your needs, or inquire about a demo of ProMV Online.

ProSensus brings real-time MVA to the classroom

ProMV Online Classroom resizedProSensus founder Dr. John F. MacGregor was instrumental in taking multivariate analysis applications from academia to industry and continues to support technology transfer. ProSensus has partnered with the Federico Santa Maria Technical University in Valparaiso, Chile to bring real-time multivariate analysis to their fully instrumented pilot plant with ProMV Online. Using ProMV Online, students can experience multivariate SPC, conduct fault detection on raw material and process variables, and take corrective actions based on insights from contribution plots, SPE diagrams, and other control charts. Learn more about ProMV Online, or This email address is being protected from spambots. You need JavaScript enabled to view it.

ProSensus Education: September 2013

CoursesSept2013We invite you to join us in Niagara Falls, Canada, for ProSensus’ September courses in multivariate analysis. In our comprehensive course, you'll discover the many way multivariate analysis can be used in manufacturing and product development settings. In our advanced batch course, you'll take a deep dive into the particulars of multivariate analysis for batch processes.

These courses are great opportunities to learn from Dr. John F. MacGregor, network with engineers, statisticians, and quality professionals, and take home a skill that can pay big dividends for your company and your career.

Check out our events page for full details on the program, location, dates and fees

Need help convincing your boss? We've even provided a downloadable proposal template.

Got questions? This email address is being protected from spambots. You need JavaScript enabled to view it..

Product Formulation: Designing the "Next Big Thing"

productformulation nextbigthingA recent Accenture report on innovation presents some eye-opening statistics on the viewpoints of executives in large companies in the US, the UK, and France. The report indicates:

Innovation is important: 93% of executives surveyed say their companies depend on innovation for long-term success
Current innovation strategies aren’t working:  only 18% of executives believe their company derives a competitive advantage from its innovation strategy
The situation is getting worse:  executives are less satisfied with innovation performance today than they were in 2009

Imagine: these are huge organizations (revenues greater than US $100 million), with millions of dollars invested in lab equipment and pilot plants and the best and brightest scientists, but they are still struggling to come up with the “next big thing”. At ProSensus, we knew some companies like that.

Continue Reading

Get Deeper Insights From Surface Inspection

SurfaceInspectionLooking for solutions to help you with Surface Inspection?

ProSensus BaleGuard is an advanced multivariate machine vision system that enables manufacturers to monitor, predict and improve product quality by analyzing color, texture, and other surface properties of products in sheet or bale form. BaleGuard is ideal for plastics, stone, lumber, metal, and any product manufactured in sheet or bale form.

One of the worlds largest synthetic rubber manufacturers used BaleGuard to quickly identify and remove out of spec product based on a pre-determined classification. They were also able to troubleshoot process problems upstream that were causing out of spec bales, alerting operators of when a corrective action was required.  

With BaleGuard you can:

  1. Achieve 360° surface inspection with a 6-camera system
  2. Scan and analyze products for defects in less than 4 seconds
  3. Detect defects & contaminants down to 1mm
  4. Automatically quarantine out-of-spec products
  5. Exceed 95% accuracy for identifying and characterizing products

Discover how BaleGuard can help you improve product quality in real-time.

Dr. John F. MacGregor Inducted Into The Process Automation Hall Of Fame

JohnFMacGregorCongratulations Dr. MacGregor!

ProSensus founder Dr. John F. MacGregor has been inducted into the Process Automation Hall of Fame for his work in developing multivariate analysis methods used to help manufacturers monitor, control and optimize their processes.

Dr. MacGregor reflects on the future of process control and says he has “no doubt that the use of the massively increasing amounts of data that we are collecting on processes will be the most important factor influencing control engineering practice over the next few decades.” Read the complete article.

StatSoft & ProSensus Partner To Deliver Real-Time Multivariate Solutions

ComputersProSensus and StatSoft, leaders in multivariate analysis (MVA) technologies, are teaming up to deliver real-time multivariate solutions to a wider global market.  This exciting partnership will allow ProSensus and StatSoft to leverage each other’s expertise and market reach.

StatSoft is one of the largest developers of enterprise-wide quality control and improvement software systems, capable of supporting its products worldwide.

ProSensus has developed leading real-time multivariate solutions to help manufacturers monitor, predict, and improve product quality and consistency.

Explore our real-time solutions for monitoring continuous processes or monitoring and controling batch processes and see how they'll make a huge difference in your operations.

ProSensus at IFPAC 2013

ProSensus will present two exciting multivariate analysis (MVA) technologies at IFPAC this year. The first presentation (Wednesday PM, Jan 23rd) will discuss how Johnson & Johnson embedded MVA into their integrated data management (IDM) infrastructure to streamline the analysis workflow to monitor, predict and improve product quality. The second presentation (Thursday PM, Jan 24th) will discuss how Mondelez International (formerly Kraft foods) was able to better source raw materials using MVA methods, reducing product quality variability. We look forward to seeing you at IFPAC.

Continue Reading

Multivariate Analysis: Big Data, Big Money

bigdataOur President and CEO, Dr. John F. MacGregor, was interviewed by Canadian Chemical News in the July/August issue:

"We’re taking it (multivariate analysis) beyond the published literature, developing new products in a fraction of the time it used to take, and creating control systems to do things that nobody’s ever done before. It has taken off extremely well, and that’s been extremely satisfying to see."Dr. John F. MacGregor, (Canadian Chemical News, July/August 2012)

Continue reading the Q&A.