While some manufacturers have been able to lower waste and the variables in production from lean manufacturing programs, extreme variability still faces certain processing environments, including pharmaceutical, chemical and mining concerns.

Because of the vast number and complexity of the production processes in these and other industries, using advanced analytics to cull through big data can tame some variables, according to an article from McKinsey & Co.

The uses of advanced analytics in manufacturing are many, including:

  • Taking a deep dive into historical process data
  • Identifying patterns and relationships among discrete process steps
  • Optimizing factors to boost yield
  • Gathering real-time, ship-floor data to reveal critical insights

McKinsey notes that one top-five biopharmaceuticals maker is using advanced analytics to significantly increase vaccine yield without increasing capital spending. Increasing vaccine yield by more than 50 percent was worth between $5 million and $10 million for a single substance; the company produces hundreds of substances.

Moreover, one established European maker of functional and specialty chemicals for a number of industries, has had a strong history of process improvements since the 1960s, yet the company generated significant business insight from advanced analytics.

After discovering factors that reduce yield, the company has been able to cut its raw materials waste by 20 percent and energy costs by 15 percent, the article notes.

“The critical first step for manufacturers that want to use advanced analytics to improve yield is to consider how much data the company has at its disposal,” the article suggests. “Most companies collect vast troves of process data but typically use them only for tracking purposes, not as a basis for improving operations.”

Companies in this situation need to invest in the systems and skill sets to allow them to optimize their uses of existing process information. For companies with production cycles that span months or even years, the main challenge may be having enough data to be relevant when analyzed.

These companies should take a long-term focus on advanced analytics and invest in the systems and processes to collect more data, McKinsey advises. For example, they could invest incrementally and gather data about one important activity in a larger process step and apply analysis to that part of the process.

“[Advanced analytics] can be a critical tool for realizing improvements in yield, particularly in any manufacturing environment in which process complexity, process variability and capacity restraints are present,” the article concludes. “Indeed, companies that successfully build up their capabilities in conducting quantitative assessments can set themselves far apart from competitors.”

Next Steps:

  • We invite you to watch our complimentary, on-demand webcast, “Big Data Science and Intelligent Manufacturing Part 3 of 3: Yield Improvement with TIBCO Spotfire Analytics.” In this webcast, you will learn how Spotfire is used to analyze yields and provide QA/QC and root cause analysis functionality within the diesort test operations of TriQuint, a manufacturer of high-performance RF components for wireless communication.
  • Subscribe to our blog to stay up to date on the latest insights and trends in big data and big data analytics.

Comments are closed.