The Role of AI in Transforming PCB Design

The first step is completing a Project Summary, which includes a description of your project, the selection of the functionalities it should contain, the intended application, which CAD tool the project should be handed over to, as well as the option to define preferred and/or excluded parts and manufacturers. The Project Settings stage has two particularly important functions. Firstly, it causes the user to pause and take a step back to think about what they want to do before launching blindly into the software.

Secondly, it informs the platform about the essential parameters of the project, allowing it to tailor its advice and responses to better align with the project goals. The CELUS Design Platform was developed with artificial intelligence in mind from the very beginning, acting in many ways like a senior design engineer—offering guidance and knowledge to the next generation of engineers who may be full of ideas but lack the experience gained over decades in the field.

It was this “companion” approach to project design and planning that attracted RECOM to partner with CELUS from the outset. We could immediately see the advantages of artificial intelligence when used as a time-saving tool—eliminating the drudgery of collating information, generating BoMs (Bills of Materials), creating netlists, and trawling through endless datasheets to extract essential details such as efficiency figures, dimensions, or tolerances. These are tasks that can be reliably assigned to a tireless AI assistant without leaving the design engineer feeling they’ve lost control of the process. However, in the intervening years, AI has advanced—and now it offers more than just assistance. It offers collaboration.

For example, with the CELUS platform, once past the Project Settings and into the design stage, the software uses a familiar drag-and-drop interface to create the system architecture block diagram. The lines linking the functional blocks could represent power, data, or both. It’s not necessary to specify the connection type, as the system understands how the functional blocks should be interconnected. However, if the circuit designer has a specific preference—say, for an I2C data connection because they already have an existing interface firmware for that protocol—they can simply instruct the system accordingly. The platform will then select the appropriate interface during schematic generation.

This integration of artificial intelligence into design platforms marks a paradigm shift in PCB design. Unlike conventional PCB software, which simply flags design rule violations, AI-powered platforms provide a truly transformative approach. AI enables the system to access and analyze vast databases with ease, using built-in intelligence to suggest informed, context-aware solutions that effectively translate project goals into functional electronic designs.

RECOM is currently integrating its product portfolio, which includes approximately 30,000 parts, into the CELUS knowledge database. By tapping into this extensive dataset, the AI can make nuanced component selections tailored to each project’s specific requirements, significantly improving design efficiency and overall performance.

Despite the clear potential of AI in PCB design, it's natural for engineers to have concerns about its implications. Questions about job security and accountability often arise: Will AI take my job? Will I be blamed if it makes a mistake? Rather than posing a threat, an AI assistant can act as a dependable partner, capable of explaining its decisions and offering valuable insights. This ability to justify choices creates a collaborative environment where less-experienced engineers can learn and grow without feeling intimidated. In addition, AI’s capacity for continual learning allows it to evolve alongside its users, constantly improving and adapting to new challenges.

Software platforms such as CELUS take the block diagram and find suitable solutions for circuit designers to evaluate and generate the schematic, BoM (bill of materials), a floorplan proposal, and footprints in a choice of different Electronic Design Automation (EDA) formats that are compatible with popular PCB layout software such as Altium Designer, Autodesk Eagle, and KiCad. Once in the chosen native EDA format, the user can further modify the given solution to optimize the design, such as changing component placement, adding polygons or copper pour to fill in the planes, setting component groups, or changing the stack-up, among other things.

These are the common design options that the layouter is familiar with and allow the user to take advantage of the head start provided by the platform-generated prototype, enabling a fast time-to-market solution using their own custom design rules and preferences instead of default settings. This handover process also optimizes the strengths of the different software platforms: AI is excellent for quickly turning an idea into a design, while the many specialized and advanced EDA platforms are ideal for generating the Gerber files containing the required CAM physical data such as copper layers, solder masks, NC drill data, and so on. Each to its own.

The boundary between AI-assisted design and layout software is not fixed. As machine learning algorithms become more powerful, more preparatory work can be completed before handover. For example, when laying out a power electronics PCB, designers often rely on online calculators to check the current capacity limits of tracks and vias. Existing EDA programs typically include modules that generate useful current density maps but can only make automatic layout adjustments if voltage levels and component power demands are known.

As a result, this part of the design process remains largely manual and depends heavily on the designer’s skill and experience to select appropriate track widths and via aspect ratios. However, if power consumption data could be made available to the artificial intelligence design assistant, it could be synchronized with the layout software. This would enable machine-to-machine communication to automatically optimize the layout design. Although such capabilities are not yet fully realized, ongoing advancements suggest they could become standard features in the near future.

Overall, AI-assisted PCB design offers a transformative approach that combines the power of automation, optimization, and decision support to streamline the design process, enhance design outcomes, and drive innovation in the field of electronic design.