Success Story: Smart Test – Failure forecast for zero defects

NCC presenting the success story

NCC Spain

Client/user profile:

The aim of this challenge is to predict failures in the electronic board manufacturing chain, based on the patterns and correlations detection between the multiple sensor measurements.  These measurements can lead to failures in electrical and functional tests, which can be detected to prevent possible failures in early stages, to correct or rectify the causes in time.

Impact:

Reduction of failures in electrical and functional testing processes with a consequent reduction of scrap material.

Key points before agreeing on project:

• Data confidentiality
• IPR
• Efficient implementation
• Secured infrastructure access
• Migration to client infrastructure

Technical/scientific Challenge:

The aim of this challenge is to predict failures in the electronic board manufacturing chain, based on the patterns and correlations detection between the multiple sensor measurements.  These measurements can lead to failures in electrical and functional tests, which can be detected to prevent possible failures in early stages, to correct or rectify the causes in time.

Solution:

Starting from the raw data as solder paste volume, solder paste temperature, optical measurements, electrical measurements (resistance, inductance, capacitance coefficient), etc. These variables were processed and filtered to be able to proceed to the design of failure prediction models. With the implementation of this “failure forecast for zero defects” process at this technology-based company, a better understanding of which variables are the main causes of failures in the quality analysis processes was achieved.

Benefits:

Reduction of failures in electrical and functional testing processes with a consequent reduction of scrap material.