Development Process

The development process for a neural network requires problem understanding, proof-of-concept testing, pre-production training, pre-production testing and finally, production acceptance testing.

  1. To understand the problem, a part description and list of defect causes and appearances are developed.
  2. To perform proof-of-concept testing a few examples of ‘good’ parts and parts with each defect are obtained. These examples should incorporate the range of ‘good’ and ‘defective’ parts.
  3. Proof-of-concept testing involves acquiring images of the example parts. These images must enable a person to correctly categorize the parts.
  4. Part delivery mechanisms (conveyors, flippers, pneumatic actuators, etc.) are developed and built.
  5. A larger number of example parts are provided. Ideally, these are obtained from different batches to capture the full range of process variations.
  6. This larger set of parts is used to obtain training images and train the neural network.
  7. Pre-production testing is performed with new parts. Network re-training may be required.
  8. Production acceptance testing is performed on freshly produced parts.