A digital thread in the age of machine learning demands data sharing

by Michael Schuldenfrei | April 14, 2019

Electronics and the components that power them are more complex and advanced than ever. With these products an integral part of our daily lives, their reliability has become nothing less than mission-critical. As the demand for components accelerates, it is important that quality is not compromised under the pressure to meet quantity requirements. Otherwise we’re going to be seeing a lot of recalls at the end of the digital supply chain. According to NHTSA data from 2007 to 2016 the automotive industry encountered this very issue, with car recalls due to electronics increasing threefold.
To ensure that product reliability keeps pace with the complexity and sheer volume of today’s electronics, a novel and holistic approach must be implemented across the supply chain: building a digital thread with Machine Learning and IoT analytics.  

The benefits of digital threads

A digital thread tracks the genealogy and data of a product—from each component right through to the end-product. Given their significant benefits, it is only a matter of time before digital threads become standard operating procedure in manufacturing supply chains. This will bring many benefits:

  • Lower RMA costs: Through board-to-chip correlations, faster root cause analysis, running online RMA prevention rules, reducing No-Trouble-Found (NTF) rates and, in the worst case, implementing highly targeted recalls.
  • Improved quality and time-to-quality: By reducing time to reach acceptable Defective-Parts-Per-Million (DPPM) goals for new products, creating an online quality link between chips and boards, and using advanced failure prediction techniques such as escape prevention and outlier detection.
  • More efficient test processes: Via adaptive testing that uses component data to test “suspect” parts more and “perfect” parts less.
  • Better system performance: By avoiding in-spec chips with marginal performance and pairing the right chips with the right board.

But digital threads require data sharing

The fundamental principle of a digital thread is that data is shared—inside the organization and with every company along the supply chain. For electronics manufacturers, that could mean data from each component’s fabrication and test phases, through assembly, inspection and rework and finally to usage data from the field.
But in today’s competitive environment most companies won’t even entertain the idea of opening up their proprietary data. They cite many concerns such as exposing IP to potential competitors, releasing data that can be leveraged against involved parties, and liability risks.
There is a way, however, that companies can benefit from digital threads without exposing their data: a third-party hub.

A data sharing hub

The data sharing hub is a trusted entity that facilitates Machine Learning and analytics while hiding the “raw” data from the other members of the supply chain. It is only the insights derived from the data that are shared among the different parties. In the meantime, the hub has the visibility across the entire supply chain that is required to track down where issues stem from—issues that otherwise may have not been discovered until the very end of the supply chain.
The hub makes heavy use of Machine Learning to overcome the inherent difficulty of handling the multi-dimensional complexity and huge volumes of data that make up the digital thread. It provides suppliers and customers with insights that reduce time-to-quality and time-to-market for new products and quickly identify the root-cause of complex issues. It can even enable targeted recalls of faulty systems before they fail.

A final note

Meeting the zero-defect requirements for the components that power high quality electronic products is the new key to competitive success. As technologies advance and avoiding product failures and recalls becomes a primary business objective, digital threads and data sharing will become common practice across the value chain. Manufacturers will be expected to demonstrate that they’re doing everything they can to deliver the best product possible.