Scientists from Fraunhofer FIT have developed a new modular AI platform to optimize the design and testing of printed circuit boards (PCBs).
A PCB is the platform upon which minuscule electronic components interact with one another.
Found in increasingly complex applications today, these circuit boards have to nevertheless pass through many stringent requirements like avoiding any electrical interference and ensuring electromagnetic compatibility.
While designing a PCB for a new application, every care is taken to make best possible use of the available space and to position components as close together as possible without risking a failure.
At present, this process relies largely on the experience of engineers, whose designs must then be tested in real trials.
A further complication is that results are not stringently documented, meaning that error-prone designs undergo repeat testing, which leads to increased costs.
The Fraunhofer FIT team has now come up with a new future inspection process featuring a modular AI platform.
Just like in conventional automated optical inspection (AOI), a camera records images of the PCB. This improves the quality of the decisions made by the algorithms.
Here, it is vital that the modules are provided with high-quality training data. Initially, the modules for machine learning and deep learning are fed with a good selection of data.
“The modular design means we can harness several algorithms, which continually enhance their own performance,” opines Fraunhofer FIT project manager Timo Brune.
“Data generated by ongoing automated inspection of components flows back to the algorithm. This then provides the basis for a process of self-learning by the artificial intelligence module.”
“This permanent feedback enhances the database and optimizes the true negative rate. Early estimates from industry indicate this could reduce the use of production resources by around 20 percent.”
According to the scientists, users can train the modules themselves on the basis of their own process and production data, offering them greater control over their own data.
Once trained, the algorithms can also be used to design new PCBs. This ends the lengthy and costly procedure of trial and error whereby components are arranged on the board until the optimal configuration is found.
Image and content: Fraunhofer FIT