28 Oct Manufacturing & Analytics – Start with the Easy Stuff
eah, data analytics can be complicated, but its application doesn’t need to be. Take discrete manufacturing for example. There’s lots of hype around more advanced analytic applications like predictive maintenance but that’s running before you even know how to walk. I know it doesn’t sound as sexy, but let’s start with operational efficiency.
For most manufacturers, especially small to mid-size ones, a 20% – 30% increase in output is huge… and relatively easy to achieve when operations are analyzed. It’s far more cost effective to increase the performance of your current equipment, than to replace it.
The first step starts with a deep dive into the process, in order to model it. This happens before this, by these types of workers, but only after these things happen, which depend on that. Scheduling, critical path solving, knowing when people need help and timing the supply chain, can all make a big difference when tuned, but without analytics, it’s extremely difficult to “see” multi-dimensionally into the areas that can be easily improved. Work on those areas that have the biggest impact first, and then move on to the next. In most cases you’ll take many steps of steady improvements before you even get to that fancy, predictive maintenance.
Here’s What We’ll Cover in this Video:
- Current output efficiency of small to mid-discrete manufacturers.
- Why domain experience is so important in data science.
- Why semantic data is so important in data science.
- How data scientists make magic in manufacturing?
- Why starting with easy things makes most sense.
Watch this video to see William Sobel discuss data analytics in manufacturing and why you should start easy before tackling sexy predictive maintenance.
Mentioned in this Episode and Other Useful Links
Have an opinion? Join the discussion in our LinkedIn group
Where should data analytics be applied in manufacturing first?Click here if you have an opinion on this video or want to see the opinions of others