11-19 更新 实时
首页/ 算力/ 正文

新 AI「副驾驶」让工程师在算法生成设计时予以引导

算力 来源:TechXplore 2026-11-14 01:00 0 阅读 机器翻译
新 AI「副驾驶」让工程师在算法生成设计时予以引导

编辑:Lisa Lock,审校:Robert Egan

本文已按照 Science X 的编辑流程与政策完成审阅。编辑在确保内容可信度的同时,特别强调了以下属性:

同行评审出版物

添加到首选来源

传统、人工介入与 AI 辅助拓扑优化工作流程的对比。图片来源:Communications Engineering (2026)。DOI: 10.1038/s44172-026-00818-x

利用算法设计结构,催生了针对超轻型飞机、高带宽天线和 F1 赛车优化的新型零件。但最优秀的算法设计技术仍然需要大量计算和时间:用户只有在设计完成后才能看到最终方案,此后若要做出修改,往往不得不从头重新开始整个设计流程。这一过程也让人更难相信最终设计在结构上是可靠的。

MIT 的研究人员正通过一套类似 AI 副驾驶的系统,让算法设计变得更具协作性。在算法生成结构的过程中,它会把各个区域呈现给人类设计师以征求反馈。

在一篇发表于开放获取期刊 Communications Engineering、介绍该系统的论文中,研究人员表明,与全算法方案相比,该系统能得出更易制造、屈曲载荷更高的结构,而总设计时间仅增加 15 秒。

研究人员认为,这种方法采用了一种名为拓扑优化的设计技术,有望让算法设计对更广泛的设计工程师群体而言更易上手、更易落地制造。

“目前,在设计过程推进的过程中,人类没有任何自主权或控制权,”论文第一作者、2026届博士Dat Ha解释道。他不久前刚从MIT土木与环境工程系博士毕业,如今是LeMessurier的结构设计师。“对于这些极其复杂的设计,我们也希望借助我们的大脑——这是世上最复杂的机器——以更贴合产业实际的方式解决这些设计问题。”

与Ha共同撰写这篇论文的还有:前MIT博士后、现佐治亚理工学院助理教授Ferdous Alam;MIT Jerry McAfee(1940)工程学教授Markus Buehler;MIT机械工程副教授Faez Ahmed;以及资深作者、MIT土木与环境工程副教授Josephine Carstensen。

将人类引入设计回路

拓扑优化是最先进、最有前景的算法设计技术之一。它利用形式化优化方法,以最大程度实现既定目标的方式,迭代地填充为设计所给定的空间。对大多数应用而言,这一过程需要大量计算和时间。等到最终完成时,设计可能难以实际建造,或者存在工程师未曾考虑到的其他问题。例如,有些设计可能在单个节点上有八个甚至更多的梁连接,这在现实世界中很难制造。

“工程师对计算机程序总是持非常怀疑的态度,尤其是当它们给出看起来很奇怪或出人意料的设计时,”Ha 说。“从理论上讲,拓扑优化确实非常强大,能够实现出色的高性能设计,但它的黑箱性质使其在工业界并未得到广泛采用。”

拓扑优化已在汽车和航空航天行业获得一定关注,但在建筑或桥梁设计中的应用较少,部分原因是设计工程师需要确认自己能够信任其输出结果。

“一个重大的限制因素在于,设计工程师对设计如何演变几乎没有影响力,因此无法控制那些不理想的特性,”Carstensen 解释道。“缺乏控制权和归属感也阻碍了它的应用。”

为解决这些问题,研究人员让拓扑优化变得更具协作性,Carstensen 将这种方法比作拥有一位设计副驾驶。

此前加入人类判断的尝试会大幅拖慢进度。研究人员的新系统利用机器学习,快速识别出算法设计中人类最有可能想要修改的区域。为训练该机器学习模型,研究人员构建了一个合成数据集,其中包含针对数千个设计的可能人类反馈,这些反馈从美学、性能标准和可制造性等方面对设计提出批评。

“我们当时想,如果能够记录下人类在这些程序中所做的修改,那么这些选择或许存在某种模式,这与其他类型的机器学习方法并没有太大区别,”Ha 说。

Carstensen 认为,该系统将算法设计与人类设计方法的优势结合在了一起。

“这个思路是挖掘设计师的智慧,让他们在设计演进的过程中注入自己的领域知识,”Carstensen 说。

在演示中,研究人员展示了他们这种“人在回路”的方法将可制造性和线性屈曲载荷提升了 39%,而总设计时间仅略有增加。

目前,该方法只允许用户将识别出的区域内的结构加厚或减薄,但他们希望在未来版本中加入其他修改选项。

“我们希望,通过解决这些障碍,能让拓扑优化面向更广泛的受众,不仅是产业界,也包括学术界的研究人员和学生,”Carstensen 说。

从设计到结构

研究人员认为,他们的方法可以与纯 AI 的设计方法形成互补。

“我们认为两者都有存在的空间,”Carstensen 说。“如果你所在的学科拥有大量计算资源,你可以用另一种方法。但如果你确实需要人的输入,就可以用这种协作式方法。”

加入人的输入也有助于提升信任。

“在某些情形下,人类需要在推进最终设计之前做出最终决定,”Carstensen 说。“通过让人类参与其中,我们能把性能更高的设计带入现实世界,从而造出性能更高的结构。因为这不仅仅关乎设计出好的作品,更关乎创造出人类真正愿意接受并实际制造出来的好作品。”

Dat Quoc Ha 等,《AI 引导的人在回路高性能工程结构逆向设计》,Communications Engineering(2026)。DOI: 10.1038/s44172-026-00818-x

期刊信息:Communications Engineering

这篇报道的作者是谁?

艺术史学士,物质文化硕士。曾任博物馆编辑、急救员和移植协调员。自2021年起为 Science X 从事编辑工作。完整简介 →

数学生物学学士,创意写作硕士。游历广泛,对科学与语言有独到见解。完整简介 →

本报道由 MIT News(web.mit.edu/newsoffice/)授权转载,该网站报道 MIT 的研究、创新与教学相关新闻。

引用:新型 AI“副驾驶”让工程师在算法生成结构设计的过程中加以引导(2026年11月13日),2026年11月13日取自 https://techxplore.com/news/2026-11-ai-copilot-algorithms.html

本文受版权保护。除为私人学习或研究目的进行的合理使用外,未经书面许可,不得复制本文任何部分。内容仅供参考。

团队开发新算法,为未来产品计算最佳形状

更快的拓扑优化:一种新兴工业设计技术获得速度提升

工程师提出一套可改进任何自主机器人系统的方法

借助新的建模技术,3D 打印部件如今与数字设计的匹配度更高

更智能的优化模型可将桥梁和建筑用材减少多达 90%

AI 帮助数字人在说话时动作更自然

受物理学启发的 AI 通过分析色彩与亮度模式来检测伪造人脸

AI 模型在被提示正受到监视时,回答可能会有所不同

隐藏的守门人:微小岩石孔隙中的水如何塑造地下储能

高分辨率仿生眼将彩色成像与更高效的运动检测相结合

虚拟模型助力 Wi-Fi 7 在拥挤网络中做出更优决策

获取即时摘要文本(Gist)

一种机器学习辅助的拓扑优化系统可识别结构设计过程中供工程师修改的区域。在演示中,与全自动优化相比,人工反馈提高了可制造性,并将线性屈曲载荷提高了 39%,但设计时间增加了 15 秒。

本摘要由 LLM 自动生成。完整免责声明

译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。

查看英文原文(New AI 'copilot' lets engineers guide structural designs as algorithms create them)

edited by Lisa Lock, reviewed by Robert Egan

This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

peer-reviewed publication

Add to Preferred Sources

New AI 'copilot' helps engineers design better structures Comparison of classic, human-informed, and AI-assisted topology optimization workflows. Credit: Communications Engineering (2026). DOI: 10.1038/s44172-026-00818-x

The use of algorithms to design structures has led to new parts optimized for ultralight aircraft, high-bandwidth antennas and F1 racing cars. But the best algorithmic design techniques still require lots of computation and time: Users only see the final design after it's complete, after which they often must start the design process all over again to make changes. That process also makes it harder to trust that the final designs are structurally sound.

MIT researchers are making algorithmic designs more collaborative with a system that acts like an AI copilot. As the algorithm is generating the structure, it presents regions to the human designer for feedback.

In an open-access Communications Engineeringpaper describing the system, the researchers showed it led to more easily manufacturable structures with higher buckling loads while adding only 15 seconds to the total design time compared to all-algorithmic approaches.

The researchers believe the approach, which uses a design technique known as topology optimization, could make algorithmic design more accessible and manufacturable for a broader class of design engineers.

"Right now, the human doesn't have any agency or control over the design process as it's playing out," explains lead author Dat Ha, Ph.D. '26, a recent MIT civil and environmental engineering doctoral student who is now a structural designer at LeMessurier. "For these really complex designs, we wanted to also tap into our brain, which is the most complex machine there is, to solve these design problems in a way that's more practical to industry."

Joining Ha on the paper are Ferdous Alam, a former MIT postdoc who is now an assistant professor at Georgia Tech; Markus Buehler, the MIT Jerry McAfee (1940) Professor of Engineering; Faez Ahmed, MIT associate professor of mechanical engineering; and senior author Josephine Carstensen, MIT associate professor of civil and environmental engineering.

Bringing a human in the loop

Topology optimization is one of the most advanced and promising algorithmic design techniques. It uses formal optimization techniques to iteratively fill in the space given for a design in a way that maximally achieves the stated goals. For most applications, the process requires a lot of computation and time. When it's finally done, the designs can be impractical to build or have other issues the engineer didn't consider. For instance, some designs might have eight or more beam connections at a single point, which would be difficult to make in the real world.

"Engineers are always very skeptical of computer programs, especially if they give you very weird-looking or unexpected designs," Ha says. "On paper, topology optimization is really powerful and can achieve great, high-performing designs, but its black-box nature has made it less widely adopted in industry."

Topology optimization has gotten traction in the automotive and aerospace industries, but it's been used less to design buildings or bridges, partly because design engineers need to know they can trust the output.

"A big limiting factor has been that the design engineer has very little influence over how the design evolves and therefore can't control undesirable features," Carstensen explains. "The lack of control and lack of ownership also inhibits its use."

To address those problems, the researchers made topology optimization more collaborative in an approach that Carstensen compares to having a design copilot.

Prior attempts at adding human judgment slowed things down dramatically. The researchers' new system uses machine learning to quickly identify the most likely regions of an algorithmic design that a human would want to change. To train the machine-learning model, the researchers created a synthetic data set of probable human feedback to thousands of designs that critiqued things like aesthetics, performance criteria and manufacturability.

"We thought if we could create a record of where humans have made changes to these programs, then perhaps there's a pattern to those choices, which is not very different from other types of machine-learning approaches," Ha says.

Carstensen sees the system as bringing together the best of algorithmic and human design approaches.

"The idea is to tap into the brains of the designers and get them to infuse their domain knowledge as the design evolves," Carstensen says.

In demonstrations, the researchers showed their human-in-the-loop approach improved manufacturability and linear buckling load by 39% while only modestly increasing the total design time.

Right now, the approach only allows users to make structures within identified regions thicker or thinner, but they hope to add other options for modification in future versions.

"The hope is that by addressing these hurdles, we open up topology optimization to a much wider audience, not only in industry but also to researchers and students in academia," Carstensen says.

From designs to structures

The researchers see their approach complementing AI-only approaches to design.

"We are arguing there's room for both," Carstensen says. "If you are in a discipline that has a lot of computational resources, you can use the other approach. But if you really need the human input, you can use this collaborative approach."

Adding human input also serves to increase trust.

"In some settings, the humans need to make the final decisions before advancing the final design," Carstensen says. "By involving humans, we can get higher-performing designs to the real world to create higher-performing structures. Because it's not just about designing good artifacts; it's about creating good artifacts that humans will actually accept and make."

Dat Quoc Ha et al., AI-guided human-in-the-loop inverse design of high performance engineering structures, Communications Engineering (2026). DOI: 10.1038/s44172-026-00818-x

Journal information:Communications Engineering

Who's behind this story?

Lisa Lock

BA art history, MA material culture. Former museum editor, paramedic, and transplant coordinator. Editing for Science X since 2021. Full profile →

Bachelor's in mathematical biology, Master's in creative writing. Well-traveled with unique perspectives on science and language. Full profile →

This story is republished courtesy of MIT News (web.mit.edu/newsoffice/), a popular site that covers news about MIT research, innovation and teaching.

Citation: New AI 'copilot' lets engineers guide structural designs as algorithms create them (2026, November 13) retrieved 13 November 2026 from https://techxplore.com/news/2026-11-ai-copilot-algorithms.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Team develops new algorithm to calculate the best shapes for things to come

Faster topology optimization: An emerging industrial design technique gets a speed boost

Engineers devise a recipe for improving any autonomous robotic system

3D printed parts now match digital designs more closely with new modeling technique

Smarter optimization model could cut bridge and building materials by up to 90%

AI helps digital humans move more naturally as they speak

Physics-inspired AI detects fake faces by analyzing color and brightness patterns

AI models can answer differently when told they are being watched

The hidden gatekeeper: How water in tiny rock pores shapes underground energy storage

High-resolution bionic eye combines color imaging with more efficient motion detection

Virtual model assists Wi-Fi 7 in making improved decisions within crowded networks

Get Instant Summarized Text (Gist)

A machine-learning-assisted topology optimization system identifies regions for engineers to modify during structural design. In demonstrations, human feedback improved manufacturability and increased linear buckling load by 39%, adding 15 seconds to design time compared with fully automated optimization.

This summary was automatically generated using LLM. Full disclaimer

This site uses cookies to assist with navigation, analyse your use of our services, collect data for ads personalisation and provide content from third parties. By using our site, you acknowledge that you have read and understand our Privacy Policy and Terms of Use.

原文为英文,正文由自动抓取并保留原文。

本文由采集器自动同步

原文发布于 TechXplore(New AI 'copilot' lets engineers guide structural designs as algorithms create them),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。

阅读原文 ↗