An Efficient and High-Quality Circuit Schematic Generation Method based on Action Mask and Graph Neural Network
Preprint
- 13 August 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
Deep reinforcement learning-based methods for PCB schematic reverse generation have demonstrated substantial potential, successfully producing schematics that rival the designs of human experts in prior research. However, current methods face challenges due to limitations in exploration space stemming from a fixed layout order, as well as inefficiencies inherent in the deep reinforcement learning process. To address these challenges, for the first time, this paper proposes an component placement order prediction method based on graph neural networks, aimed at overcoming the constraints imposed by a fixed layout order. Furthermore, an invalid action masking mechanism is incorporated into the output stage of the model to reduce the invalid exploration of reinforcement learning and improve the learning efficiency. Experimental results indicate that the proposed method improves the average performance of generated schematics by approximately 12%, while also accelerating training convergence speed by around 25%. These findings validate the effectiveness and practicality of the proposed approach, offering a novel perspective and solution towards the automated design of PCB schematics.Keywords
All Related Versions
- Version 1, 2025-08-13, Research Square
- Published version: Discover Artificial Intelligence, 6 (1).
This publication has 29 references indexed in Scilit:
- MTBoM: Metal Trace to Bill of Materials Generation for PCB Reverse Engineering2022
- Wire segmentation for printed circuit board using deep convolutional neural network and graph cut modelIET Image Processing, 2018
- Partitioning, floor planning, detailed placement and routing techniques for schematic generation of analog netlist2008
- Reverse engineering for obsolete single layer printed circuit board (PCB)2006
- Predictable routing2002
- RightTopologizer: an efficient schematic generator for multi-level optimization2002
- SPAR: a schematic place and route systemIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 1993
- An automatic netlist-to-schematic generatorIEEE Design & Test of Computers, 1993
- ASG: Automatic schematic generatorIntegration, 1991
- Schematic generation with an expert systemIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 1990