基于生成對抗網(wǎng)絡(luò)的PCB布線生成方法
電子技術(shù)應(yīng)用
朱沛然1,2,朱開本1,2,劉威1,2,3,4
1.武漢大學 物理科學與技術(shù)學院;2.武漢大學 微電子學院; 3.武漢紡織大學 數(shù)理科學學院;4.武漢量子技術(shù)研究院
摘要: 為解決印制電路板(Printed Circuit Board, PCB)設(shè)計過程中傳統(tǒng)自動布線算法時間開銷愈發(fā)高昂的問題,提出了一種基于生成對抗網(wǎng)絡(luò)的布線生成方法。該方法將PCB布線問題轉(zhuǎn)換為圖像生成問題,通過舍棄生成器的噪聲輸入、引入多級殘差連接和添加自定義損失函數(shù)使網(wǎng)絡(luò)能夠?qū)W習布線問題的物理特征,提高預(yù)測結(jié)果準確度。網(wǎng)絡(luò)在自建的PCB布線數(shù)據(jù)集中進行訓(xùn)練和測試,實驗結(jié)果表明,與傳統(tǒng)自動布線算法A*搜索算法相比,所提出的生成式方法減少了約50%的布線時間。該方法為PCB布線問題提供了新的解決方案,有利于降低其復(fù)雜度及時間開銷。
中圖分類號:TN40 文獻標志碼:A DOI: 10.16157/j.issn.0258-7998.256572
中文引用格式: 朱沛然,朱開本,劉威. 基于生成對抗網(wǎng)絡(luò)的PCB布線生成方法[J]. 電子技術(shù)應(yīng)用,2025,51(11):30-34.
英文引用格式: Zhu Peiran,ZHU Kaiben,Liu Wei. A generation method for PCB routing based on generative adversarial networks[J]. Application of Electronic Technique,2025,51(11):30-34.
中文引用格式: 朱沛然,朱開本,劉威. 基于生成對抗網(wǎng)絡(luò)的PCB布線生成方法[J]. 電子技術(shù)應(yīng)用,2025,51(11):30-34.
英文引用格式: Zhu Peiran,ZHU Kaiben,Liu Wei. A generation method for PCB routing based on generative adversarial networks[J]. Application of Electronic Technique,2025,51(11):30-34.
A generation method for PCB routing based on generative adversarial networks
Zhu Peiran1,2,ZHU Kaiben1,2,Liu Wei1,2,3,4
1.School of Physical Science and Technology, Wuhan University;2.School of Microelectronics, Wuhan University;3.School of Mathematics and Physics, Wuhan Textile University; 4.Wuhan Institute of Quantum Technology
Abstract: To address the increasingly high time cost of traditional automatic routing algorithms in the design process of printed circuit boards (PCB), a routing generation method based on generative adversarial networks is proposed. This method transforms the PCB routing problem into an image generation problem. By discarding the noise input of the generator, introducing multi-level residual connections, and adding a custom loss function, the method can learn the physical features of the routing problem, and the accuracy of the prediction results is improved. The network is trained and tested on a self-built PCB routing dataset. Experimental results show that compared to the traditional A* search algorithm, the proposed generative method reduces routing time by 50%. This method provides a new solution for PCB routing problems, helping to reduce the complexity and time cost of routing tasks.
Key words : routing;printed circuit board;conditional generative adversarial network;electronic design automation
引言
印制電路板(Printed circuit board, PCB)是連接諸多電子元件的重要部件[1],布線是PCB設(shè)計的核心環(huán)節(jié)[2],需要在實現(xiàn)電路功能的同時滿足多種約束條件。隨著電路規(guī)模的增大,傳統(tǒng)的自動化布線算法時間開銷愈發(fā)高昂[3]。使用人工智能方法輔助布線已成為研究熱點[4-6],其通過提取布線特征[7-8]或訓(xùn)練智能體等方法[9-10]為傳統(tǒng)算法提供指導(dǎo),但直接生成布線的方法準確率較低。
為此,本文提出了一個改進的條件生成對抗網(wǎng)絡(luò),通過在自建的PCB布線數(shù)據(jù)集中訓(xùn)練,能夠生成高準確度的避障布線結(jié)果,并提高布線速度。
本文詳細內(nèi)容請下載:
http://ccf-cncc2011.cn/resource/share/2000006837
作者信息:
朱沛然1,2,朱開本1,2,劉威1,2,3,4
(1.武漢大學 物理科學與技術(shù)學院,湖北 武漢 430072;
2.武漢大學 微電子學院,湖北 武漢 430072;
3.武漢紡織大學 數(shù)理科學學院, 湖北 武漢 430200;
4.武漢量子技術(shù)研究院, 湖北 武漢 430072)

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。
