Celus brings automation to electronics design

celusa supplier of AI-powered automation electronics engineering software, aims to improve tools that help design printed circuit boards. The company has also pioneered an electronic parts search engine that is changing the way engineers select electronic components in the multi-billion dollar electronics industry.

Electronic designers typically compare target specifications through a manual search process in digital product catalogs filled with part specification tables. Celus’ approach uses a digital twin representing design choices to automatically identify suitable options and then design the circuitry around the part. A more automated approach could have as profound an impact on the way engineers find products as Google’s introduction of new search ranking techniques on the evolution of how consumers find knowledge.

Another key innovation the company is working on includes tools to help automate the layout of the individual components on a printed circuit board. Celus plans to combine machine learning and classic optimizers to improve layout, reduce size and cost, or achieve other design goals.

Engineers can essentially recompile the design to take advantage of newer alternatives or if a part is out of stock due to a chip shortage.

“It’s like a library update in software design,” Celus CEO Markus Pohl told VentureBeat.

Improving a complex process

Engineers such as Markus Klausner, CTO at Celsus customer Viessmann Climate Solutions, used to spend countless hours matching design specifications with parts to design the control systems for heat pumps, refrigerators and air conditioners. He said that while electronics catalogs are getting better at organizing information, he still spends a lot of time aligning new design requirements with part specifications.

“Celus automates this process by linking up with the distributor so you don’t have to do the work manually,” Klausner told VentureBeat.

Because Celus also automates the design process, Klausner finds that his tools can currently create a design at the same level as an inexperienced engineer, but still help save time. Celus’s tools, he noted, are also getting better and better, and he expects them to overtake senior designers in the future.

Erick Brethenoux, VP analyst at Gartner, told VentureBeat that new techniques for automating PCB design like this one exemplify recent advances in how generative AI helps design chips, buildings, security systems and other types of products and systems. This involves a combination of AI and traditional engineering techniques to optimize various aspects of the design process.

“Generative AI is a collaborative process between humans and machines to create better designs,” says Brethenoux. These tools help increase efficiency as they can come up with new ideas and also help optimize for different requirements such as cost, size or performance.

Connecting between chips

Pohl said he hopes Celus’ tools will deliver efficiencies for the $273 billion enterprises will spend on electronic component sales by 2021. according to by Grand View Research estimates. It could also streamline some of the $1.3 trillion Grand View estimates In 2021, companies spent on engineering outsourcing, including some electronics engineering. A more efficient electronics design process also allows physical industries such as automotive companies to design new product variants to take advantage of new chips or avoid supply chain shortages.

Electronic design is an old idea, but has traditionally focused on improving the way engineers lay circuits in silicon chips. Leaders in electronic design automation include companies such as Cadence Design, Synopsis and Siemens EDA (formerly Mentor Graphics). These tools focused on digital logic early on and gradually added support for analog circuits. While these tools have improved in automating various aspects of the process, they tend to focus on the circuitry within each chip rather than the circuitry that connects them.

Pohl said the idea came to him while he was working on an electronic vehicle prototype, after spending countless hours perusing data sheets to find a suitable part. It felt like the opposite of the kind of automation he was used to selecting and customizing software components for the same design.

“I was shocked by how electronics engineers worked and was pretty sure I was doing it wrong,” he said.

He surveyed electronics engineers from across the industry and found that they all source components in the same way. In 2016, he worked with a small team to see if they could automate some of this process. Then, in 2018, they got the prototype working and launched the company.

Pohl argues that designing multi-chip circuit boards is a much more complex engineering problem than designing the chips themselves. Designing the logic on silicon chips is relatively homogeneous and is a more repeatable process. Chip designers also had a greater need for design automation as they scaled up individual chips to support billions of transistors.

“They reached a level of complexity where it was unfeasible to do it any other way,” Pohl said. “Board-level design will soon reach that level as complexity increases.

Building an ecosystem

Celus tools complement existing electronic design automation (EDA) tools. The company – fresh off a $25.6 million Series A round – is also partnering with several leading electronic computer-aided design (ECAD) design tools to manage circuit design data. It hopes to do this with vendors such as Altium, Autodesk and Siemens EDA to help automate the design of these tools and make them ready for production.

Other startups have also sprung up to help automate various aspects of the PCB design process, including companies like CircuitMind, JITX, and InstaDeep. Altium recently acquired Gumstix, another PCB design startup. In addition, Zuken, an established Japanese ECAD supplier, has also been working on a machine learning PCB design tool.

Earlybird Venture Capital led the financing, with participation from DI Capital and existing investors Speedinvest and Plug and Play.