< Back to the Insider

Bringing Sci-Fi to Manufacturing with Self-Aware Machines

Share This Article: Connect with us on LinkedIn Like us on Facebook Follow us on Twitter

Self-aware machines are no longer a thing of science fiction, says Dr. Linxia Liao, a researcher at the Palo Alto Research Center (PARC). Self-aware machines will positively impact production time, cost and quality of any manufacturing plant by reducing unplanned downtimes, adapting for workpiece variability and enabling specification of fault-tolerant process plans.

“We are trying to build an intelligent machine which has the capability to be aware of what’s going on,” says Dr. Liao. With the ability of a machine to detect and analyze its own operating data, as well as surrounding workplace conditions, it will become possible to predict future maintenance and operation of the machine based on its analytics model. The first step, continues Liao, is data fusion. Using a combination of MTConnect and machine-sensor data, operators can better monitor their machines for operational problems and maintenance needs in real time. The second step, according to Dr. Liao, is machine connection with Industry 4.0. This connectivity is consistent with their vision of the future of self-aware machines: full autonomy – the ability of the machines to talk to each other to complete tasks.

But what is the roll of the human in this process? “The human, actually, is very important,” says Dr. Liao. He continues, “The expertise and the knowledge about the systems and how they should operate is actually in the human brain.” With the human integrated with this process, the machines will actually become smarter. The human in the loop provides valuable feedback and data which is included in the first data fusion step.

Dr. Liao explains that the biggest challenges they anticipate over the next few years are with gathering useful, actionable data through the data fusion process. Their goal is to allow generation of recommendations about performance and short term maintenance, based on the analytics model from the data fusion process, to ultimately reduce downtime and increase productivity. These recommendations will also allow the operator to make decisions on how to adjust the machines to run more efficiently and perform better over their full useful life.

Watch the full video of Dr. Liao’s interview above to find out more!

Watch more videos in the IMTSTV Library!

Save the Date:
2016 [MC]2 Conference | April 19-21, 2016 | Dallas, Texas

Read More Manufacturing Technology