Testing Generative AI in Circuit Board Design

BY Mark Howell 21 June 20245 MINS READ
article cover

Today in Edworking News we want to talk about Testing Generative AI for Circuit Board Design

TLDR:

We test LLMs to figure out how helpful they are for designing a circuit board. We focus on utility of frontier models (GPT4o, Claude 3 Opus, Gemini 1.5) across a set of design tasks, to find where they are and are not useful. They look pretty good for building skills, writing code, and getting useful data out of datasheets.

Introduction

Can an AI-powered chatbot help with a task as precise as circuit board design? These LLMs (Large Language Models) are famous for hallucinating details, and missing a single important detail can sink a design. Determinism is hard but super important for electronics design! Today, several shallow product offerings are making AI for electronics design look mostly like hype. But we believe there is real utility to be found here, if we can take a better approach.
In this article, we set LLMs to challenging tasks that expert human circuit board designers handle daily. We're not looking for basic help, rather pushing on what it takes to help an expert do their job better.

Models Tested

  • Gemini 1.5 Pro from Google

  • GPT-4o from OpenAI

  • Claude 3 Opus from Anthropic
    We explore prompting strategies to get the best performance out of each model and test their capabilities in building skills, writing code, and extracting useful data from datasheets.

Asking Stupid Questions

There's a lot to know in circuit board design, and nobody has mastered every domain. Asking an LLM stupid questions is a great way to learn. For example, an RF engineer might not know much about supply chain or power supply design. To simulate someone new to a domain, basic questions without expert vocabulary help evaluate the LLM’s utility.

Example Query

What is the delay per unit length of a trace on a circuit board?

  • Claude 3 Opus excelled by bringing in relevant concepts and got the answer right while pointing out critical nuances.

  • Google Gemini 1.5 performed poorly, likely due to incorporating low-quality internet sources.

Finding Parts

An experienced engineer often knows the approximate size and cost of components. We tested LLMs by asking them to suggest parts for a communications layer for a motor driver using 100M optical Ethernet.

Prompts and Responses

Despite using detailed specifications and prompt engineering, all models performed poorly here. They struggled to suggest the right parts and failed to account for necessary nuances.

Representative Conclusion from Gemini 1.5

  • Example Part Selection:
    - Optical Connectors: LC Duplex connectors (Amphenol or similar)
    - Optical Transceivers: 100Base-FX SFP transceivers with industrial temperature ratings
    - Ethernet Networking Device: Microchip LAN8742A or Texas Instruments DP83848
    Grading: All models missed the requirement for a three-port Ethernet switch and suggested inappropriate transceivers for a compact robot joint.

Parsing Datasheets

Critical design data is often stored in PDF datasheets. We tested three ways of pulling information:

  1. Copy/paste from PDF and prompt

  2. Capture an image and have the LLM interpret

  3. Upload entire PDF

Example Case

Using the Nordic nRF5340 WLCSP with an 820-page datasheet, our best method was loading the entire datasheet and querying interactively.

Image Description: An example of a circuit board designed using AI assistance

Designing Circuits

LLMs can understand schematics well enough to turn them into netlists. Can they design a circuit itself? We tested an analog circuit design task.

Task: Design a microphone pre-amplifier

The prompt included requirements for biasing an electret microphone and creating a single-ended signal to drive an ADC.

  • Claude 3 Opus provided the best layout proposals but made some fundamental errors.

  • LLMs tend to attach capacitors across positive and negative pins indiscriminately.

Higher-Level Code

In practical design, higher-level functions are used. LLMs did better at inventing and using higher-level functions.

Example

Gemini 1.5 invented reasonable APIs, but still, misses surfaced in netlist generation.

Conclusion

Circuit board design requires precision, and unsupervised AI techniques face data challenges. Design context and meaning aren't encapsulated purely in textual data. Our experiments show that LLMs are useful for specific tasks like extracting and transforming information, but struggle with generating accurate, complex designs.
Edworking is the best and smartest decision for SMEs and startups to be more productive. Edworking is a FREE superapp of productivity that includes all you need for work powered by AI in the same superapp, connecting Task Management, Docs, Chat, Videocall, and File Management. Save money today by not paying for Slack, Trello, Dropbox, Zoom, and Notion.

Remember these 3 key ideas for your startup:

  1. Learning New Domains: Utilizing chatbots like Claude 3 Opus can help quickly cover new areas in circuit board design, emphasizing critical details.

  2. Data Extraction: Gemini 1.5 large context window is very effective for pulling detailed component data from dense datasheets, simplifying otherwise tedious tasks.

  3. Higher-Level Code Generation: Employing LLMs to generate higher-level code rather than raw netlists can improve accuracy in complex designs, saving time and reducing errors.
    For more details, see the original source.

article cover
About the Author: Mark Howell Linkedin

Mark Howell is a talented content writer for Edworking's blog, consistently producing high-quality articles on a daily basis. As a Sales Representative, he brings a unique perspective to his writing, providing valuable insights and actionable advice for readers in the education industry. With a keen eye for detail and a passion for sharing knowledge, Mark is an indispensable member of the Edworking team. His expertise in task management ensures that he is always on top of his assignments and meets strict deadlines. Furthermore, Mark's skills in project management enable him to collaborate effectively with colleagues, contributing to the team's overall success and growth. As a reliable and diligent professional, Mark Howell continues to elevate Edworking's blog and brand with his well-researched and engaging content.

Trendy NewsSee All Articles
CoverDecoding R1: The Future of AI Reasoning ModelsR1 is an affordable, open-source AI model emphasizing reasoning, enabling innovation and efficiency, while influencing AI advancements and geopolitical dynamics.
BY Mark Howell 26 January 2025
CoverSteam Brick: A Minimalist Gaming Console Redefines PortabilitySteam Brick: A modified, screenless Steam Deck for travel, focusing on portability by using external displays and inputs. A creative yet impractical DIY project with potential risks.
BY Mark Howell 26 January 2025
CoverVisual Prompt Injections: Essential Guide for StartupsThe Beginner's Guide to Visual Prompt Injections explores vulnerabilities in AI models like GPT-4V, highlighting security risks for startups and offering strategies to mitigate potential data compromises.
BY Mark Howell 13 November 2024
CoverGraph-Based AI: Pioneering Future Innovation PathwaysGraph-based AI, developed by MIT's Markus J. Buehler, bridges unrelated fields, revealing shared complexity patterns, accelerating innovation by uncovering novel ideas and designs, fostering unprecedented growth opportunities.
BY Mark Howell 13 November 2024
CoverRevolutionary Image Protection: Watermark Anything with Localized MessagesWatermark Anything enables embedding multiple localized watermarks in images, balancing imperceptibility and robustness. It uses Python, PyTorch, and CUDA, with COCO dataset, under CC-BY-NC license.
BY Mark Howell 13 November 2024
CoverJungle Music's Role in Shaping 90s Video Game SoundtracksJungle music in the 90s revolutionized video game soundtracks, enhancing fast-paced gameplay on PlayStation and Nintendo 64, and fostering a cultural revolution through its energetic beats and immersive experiences.
BY Mark Howell 13 November 2024
CoverMastering Probability-Generating Functions: A Guide for EntrepreneursProbability-generating functions (pgfs) are mathematical tools used in probability theory for data analysis, risk management, and predictive modeling, crucial for startups and SMEs in strategic decision-making.
BY Mark Howell 31 October 2024
CoverMastering Tokenization: Key to Successful AI ApplicationsTokenization is crucial in NLP for AI apps, influencing data processing. Understanding tokenizers enhances AI performance, ensuring meaningful interactions and minimizing Garbage In, Garbage Out issues.
BY Mark Howell 23 October 2024
Try EdworkingA new way to work from  anywhere, for everyone for Free!
Sign up Now