MANUFACTURING
AI-Powered Optical Inspection Can Find Nanoscale PCB Defects
Sapera Software Suite makes it easier to use machine learning in AOI with surprisingly few samples. By Bruno Ménard, Software Director, Teledyne DALSA
T
he size and competitiveness of the mobile phone industry has driven investment and innovation in many industries, from imaging to software to even metallurgy. Few industries have been as affected as the semiconductor market, where demand for higher performance in smaller packages has been unrelenting for a few decades. Recently, Apple released its latest iPhones, some powered by its new A17 Bionic chips, built on TSMC’s new 3nm manufacturing process. Apple is reportedly buying up everything that TSMC can manage to make. These chips are reportedly smaller, faster, cooler, and more power- effi cient than their 5nm predecessors. According to Apple, each chip features 19 billion transistors, some so small that their elements are only 12 silicon atoms wide. The same pressures extend to printed circuit board manufacturing; Apple will reportedly switch to using resin coated copper (RCC) foil for their new PCB material, allowing the company to make them even thinner. This will be challenging for manufacturers, as RCC foil is very delicate, with researchers publishing in IEEE that its especially vulnerable to heat and pressure in the laminating process.
It’s not enough to be innovative; you must return a profi t. New reporting from The Information describes the favourable terms
22
Fig 1 Example PCB Defects. Huang, W., Wei, P., Zhang, M. & Liu, H. Hripcb: A challenging dataset for PCB defects detection and classifi cation. J. Eng.
https://doi.org/10.1049/joe.2019.1183
that Apple has secured to keep its costs down in return for the huge orders TSMC has to absorb the costs of defective processor dies. While fabs like TSM are touting their competitiveness with ways to develop smaller node processes to reduce chip size and lower power consumption, they will have tough challenges on the quality side.
APRIL 2024 | ELECTRONICS FOR ENGINEERS
Automated Optical Inspection for PCB Quality Inspection
For many companies, quality control is the major bottleneck in the PCB manufacturing chain, including reliability testing and reworking defective PCBs. Improving the speed and effi cacy of quality control can signifi cantly increase the production yield
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54
