Chapter 3. Using AI-Based PQM Solutions to Solve Issues in Manufacturing, Aerospace, and Software
PQM Issues in the Manufacturing, Aerospace, and Software Industries
Resolving quality and maintenance issues is well suited by a complementary learning approach because the data necessary for decision-making is large, varied, both structured and unstructured, and processed in both batch and real time. For instance, in addition to data stored in a traditional database, engineers could be capturing their notes on handwritten pieces of papers, or invaluable information could be mined from online chats or email exchanges. In the sections that follow, we discuss some of the challenges that are being faced by businesses in the manufacturing, aerospace, and software industries that complementary predictive quality and maintenance (PQM) could address.
PQM in Manufacturing
Currently, many manufacturers still predict machine failures in assembly lines by determining root causes from maintenance notes or by depending on human subject matter experts. But they are tasked to reducing unplanned downtime and avoiding the revenue losses associated with failed lines. They must accelerate time to market while improving quality. They also need to identify similarities in parts to predict defects or failures that could occur during manufacturing and assembly, and balance cost with quality by gaining visibility into the life cycle of parts from different vendors. And corrective actions need to be taken ...