http://blog.lenoxtools.com/industrial-metal-cutting/feed/

workf

Using Predictive Analytics in Ball and Roller Bearing Manufacturing

October 30, 2016 / , , , , , , , , , , , ,


In today’s competitive and quickly changing market, manufacturers are finding that it pays to be proactive—not reactive—in their strategic approaches. That’s why a growing number of industrial manufacturers are starting to take a serious look at advanced technologies like predictive analytics, which allows them to not only measure performance, but to also predict and prevent future challenges.

According to Deloitte’s 2016 Global Manufacturing Competitiveness Index, more than 500 senior manufacturing executives from around the world ranked predictive analytics as the number one technology vital to their companies’ future competitiveness. As reported here, another report from Aberdeen Group shows that 86 percent of top-performing manufacturers are already using predictive analytics to reduce risk and improve operations, compared to 38 percent of those companies with an average performance and 26 percent of those with less than stellar results.

The trend has found its way into industrial metal cutting as well. According to the LENOX Institute of Technology’s benchmark study of more than 100 industrial metal-cutting organizations, companies can gain additional productivity and efficiency on the shop floor by “investing in smarter, more predictive and more agile operations management approaches.”

What is Predictive Analytics?
Predictive analytics utilizes a variety of statistical and analytical techniques to develop mathematical models that “predict” future events or behaviors based on past data. As the Deloitte study explains, this allows companies to uncover hidden patterns, relationships, and greater insights by analyzing both structured and unstructured data.

In a manufacturing environment, companies can use predictive analytics to measure the health of production equipment and detect potential failures. However, the possibilities are virtually limitless. According to one analyst’s blog, manufacturers could potentially use software and predictive analytics to forecast potential staffing or supply-chain interruptions, such as a flu outbreak that could cause a temporary personnel shortage or even a blizzard that could disrupt deliveries.

Bearing manufacturing leader Timken has taken a different approach and is using predictive analytics to improve inventory optimization and supply chain performance in the automotive aftermarket sector. As reported by SearchAutoParts.com, Timken is leveraging sales history, registration data, and other information, along with complex analytics, to improve sales and reduce costs.

“Timken’s catalog team matches parts and vehicles, and combines that information with vehicle registration and replacement/failure rates, along with internal sales data,” the article explains. “Crunching that data using proprietary algorithms helps them predict how many parts will be needed in a given geography, and how those parts sales will fall within the premium aftermarket, economy aftermarket and OEMs.”

Common Use Cases
Because predictive analytics is an emerging technology, applications are typically specific to each manufacturer’s products and processes—as in the Timken example. However, an article from Toolbox.com describes four common use cases for predictive analytics that are applicable in most manufacturing environments:

  1. Quality Improvement. Improvements in databases and data storage and easier-to-use analytical software are the big changes for quality improvement. Standard quality improvement analysis is being pushed toward less technical analysts using new software that automates much of the analytical process. Storing more information about products and the manufacturing process also leads to analysis of more factors that influence quality.
  2. Demand Forecast. Predictive analytics takes historical sales data and applies forms of regression to predict future sales based upon past sales. Good predictive analytics modelers find additional factors that influenced sales in the past and apply those factors into forecasted sales models.
  3. Preventative Maintenance. Predictive analytics increases production equipment uptime. Knowing that a machine is likely to break down in the near future means a manufacturer can perform the needed maintenance in non-emergency conditions without shutting down production.
  4. Machine Utilization. Predictive analytics applications for machine scheduling combines forecast for demand with product mix to optimize machine utilization. Using new predictive analytics techniques improves accuracy.

Predicting Success
While there is no question that predictive analytics is still new to many ball and roller bearing manufacturers, industry leaders know that proactive strategies are key in today’s uncertain market. Finding ways to anticipate future events and reduce unplanned downtime can not only help your operation gain efficiency but, more importantly, help you stay competitive.