data science for manufacturing

On year 3 of the Predictive Analytics World – Manufacturing annual conference (2016), we continued to build on the momentum from the first two years. Our primary focus areas have remained more or less the same and we continue to get interest from practitioners and executives for the following areas.

  1. Preventive Maintenance/Fault Detection/Failure Prediction

How can we detect faults or failure before the problems happen? This is where maintenance using predictive analytics comes in. Data mining concepts and methods can be employed in several ways for preventive maintenance. Production data, machine functional data, and sensor data are all aggregated for analysis and used to build models for predicting machine failure or poor product quality reducing failure times and costs. This process is in principle, no different than the ones currently used in fields as diverse as fraud detection in financial services or customer retention in marketing.

  1. Big data and predictive analytics for Supply chains (including Cyber security)

Whether a global giant or an SMM, the effectiveness and agility of your supply chain can have significant effects on business performance. Keeping tabs on your suppliers is the only way to control the impact they have on your business, and analytics are a key player in that. Analytics derived from this data can be used to benchmark suppliers against industry averages, and other customers, predict supplier performance, or even maximize margins by optimizing order volumes based on production analysis. Informed use of predictive analytics can have a significant and positive impact on supply chain performance, driving down baseline costs. 

  1. Internet of Things

As more and more devices get connected to each other to form the IoT, it becomes inevitable that the predictive analytics will become a part of underlying method by which most decisions are made, because it is impossible for the human user to be a part of every decision making loop! Nowhere is this more important than in manufacturing where asset utilization and supply chain functions are very critical. Cisco estimates that the total potential value from combining analytics with IoT can exceed $5 trillion in these two areas alone. As we move forward, data (even big data) may get commoditized, but decision making using these commodities will always be valued.

  1. Predictive analytics for digital manufacturing

The role of data science in manufacturing has traditionally been understated. Manufacturing generates about a third of all data today, and this is certainly going increase significantly in the future. Data forms the backbone of all Digital Manufacturing technologies, which will be the centerpiece of the strategy for advancing Manufacturing in the 21st century.

Data science for manufacturing will have key enablers to best leverage this new data. There are many different application areas of manufacturing where predictive analytics and big data have proven to be game changers: forecastingcost and price modelingwarranty data analytics, text mining for product development, among others.

Originally posted on Mon, Nov 23, 2015 @ 01:03 PM

No responses yet

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.