September 27, 2023
At PCB West (Santa Clara, California, September 19-20), Kyle Miller, Research and Product Manager at the ECAD software maker Zuken, got ready to join a panel titled “AI in Electronics: What Can We Expect?” Miller had also shared his thoughts on ChatGPT, the AI-powered chatbot that opened a floodgate of discussion, in a blog post. Miller and his colleagues at Zuken were ready to unveil what they described as the first milestone in their ambitious roadmap to AI-powered PCB Design.
“We've seen a skill shortage in PCB layout. More and more engineers are getting involved in PCB layout, which is not their skill set, which is probably isn't what they want to do. So why not use AI to plug that gap?” Miller reasoned.
At the show, Zuken showcased its new offering, AIPR (Autonomous Intelligent Place and Route), powered by AI. The company will make it available to customers using the CR-8000 software, its flagship PCB product.
Bob Potock, Zuken's VP of Marketing, explained, “AIPR learns from the best practices of all the PCB experts who have been laying out boards for years. We're essentially transferring the design knowledge and essence of those boards. The AI tool, through machine learning, can now apply all of that knowledge and expertise to the new boards you are designing.”
AI Brain Training in Four Steps
AIPR is part of Zuken's ambitious four-step transformation toward AI-powered PCB design. “This product enables Mimic Route and Smart Autorouter together with Zuken’s AI-based products,” Zuken wrote.
Miller said AI-driven optimized layout tends to be cleaner, simpler, with fewer clashes, because the software could process design hierarchy and signal clusters much better than human experts. He also pointed out AIPR works much faster than the Autorouter. “What takes Autorouter a setup time of 30 mins and autorouting time of 15 mins, might just take AIPR 30 seconds,” said he said. The AIPR is GPU-accelerated, he added.
In Zuken's roadmap, the next step is to apply machine learning to all the PCB design available in Zuken's library. The outcome is what the company calls the Basic Brain, which “enhances the user experience by routing the design utilizing the Smart Autorouter based on learned approaches and strategies.”
The next step is to offer a tool that Zuken's customers can use to apply machine learning to their own library. The company calls it the Dynamic Brain, which “learns from your PCB designers, utilizing past design examples and integrating them into AI algorithms.”
The ultimate goal is the Autonomous Brain, “an AI-driven powerhouse in continuous learning mode, pushing the boundaries of creativity.”
AIPR will be an add-on, priced beginning $64K per year. Salary.com lists the median salary of a PCB designer in the U.S. as $69K per year. In the future, Zuken plans to sell AIPR bundled with CR-8000, available as subscription or perpetual license.
For more, watch DE 24/7's interview with Kyle Miller above.