与AVEVA合作
对等工业AI自主和人力控制
活生生的数码双胞胎正在帮助工厂运行更像活的系统，并为同步运行的产业奠定基础。
大多数人将工业环境与冷钢和钟表工作机械联系起来。 不过，在功能上，工厂或工厂更像是活生生的东西：它有脉搏，甚至有新陈代谢随着时间的流逝，它不断磨损，健康恶化的迹象往往显示为难以察觉的不正常现象。
长期以来，数字双子技术一直旨在反映这种活力和模式异常，这些异常可能是较大问题的表现。 但是，早期的实施是几起在物理现实背后的跳动；它们无法进行实时分析，也无法主动地解决所发现的任何问题。 他们更侧重于模拟、观察和假设情况规划，而不是闭关执行。 活生生的数码双胞胎不是作为能够发现异常或建议优化的现实的数字镜像，而是将复杂业务的动态高真实度数字化代表与通过操作和控制系统干预物理世界的能力结合起来。
大赦国际是这一变化的中心。 Rob McGreevy),AVEVA的首席产品官，将较新的，AI-注入了数码双胞胎到生长和进化的生物身上。 这些 " 有生 " 版本是植物资产和工艺的适应性常绿模式。 因为它们跟得上生活状况，连接曾经孤立运行的系统，它们提供了之前缺失的一层能见度和管弦乐，更好地反映设施本身的有机节奏。
现在，代理AI也使得工业系统能够超越诊断或建议，自行行动。 随着技术向更大的自主发展，它开始形成一种工业的回放，在这种回放中，小而恒定的调整使工厂或工厂保持健康并鸣叫。
称、人类判断和操作者监督仍然起推动作用，活生生的数码双胞胎为人类工程师提供了手段来监测AI正在做什么并确保行刑在正轨上。
保持数码双胞胎同步的技术
活生生的数码双胞胎通过一款数字线程将工程和设计信息与实时操作数据相接，或连接到一个资产在其生命周期中跟踪的纪录。 几起显著的技术变化帮助将这条线串在一起：传感器(近年来它更负担得起)现在从IOT设备和工业控制设备中流出遥测，软件平台将这些信息带入方便用户的界面。 预测模型和以物理为基础的模型还可以提供对机器或过程如何行事的AI-丰富的见解。
操作者通过这些镜头观看数码双胞胎，它们依次演变而来。 “你可以从可持续性的视角来看待数字双胞胎：我的排放量是多少？” “或通过维修的视角：这种资产表现得健康吗？或者通过业绩计量：它是否产生我所需要的部件数量？”
为半自动系统设定界限
下一阶段是让AI根据这些透镜的精髓采取行动。 就制造商而言，他们渴望这一章：在2026年制造业领导理事会对制造商的调查中(在新标签中打开),66%的称公司在其业务中使用或计划使用代理AI,40%的厂商预计到2030年会有一定程度的工厂自主权。 同时，他们也警惕潜在风险：在德勤2025年的智能制造调查(在新标签中开放)中，65%的主管将业务风险，包括业务中断的可能性列为他们最关心的问题。
制造商正在加速向代理AI和更大的工厂自主权发展
资料来源：麻省理工学院技术评论透视，数据来自制造业领导委员会(新页开口),2026年。
“还需要做更多的改进，需要更多的证明点、测试和验证。” 近期内，McGreevy期望代理AI遵循SCADA系统等其它工业技术所看到的路径。 “在SCADA中，`S ' 是指监督，而监督意味着中间有一个人，” 他认为，大赦国际在可预见的将来主要以这种咨询方式开展工作，完全自治仅限于狭隘的、高度重复的任务。
至于人类操作者的作用，日常正在演变。 曾经专门从事单一工艺线或维修任务的工人现在可以从事多个学科。 它们可以花更少的时间和精力逐一批准例行行动，而更多时间和精力用于确定可接受的业务限制。 由于AI可以强化其接收到的数据中的规律，早期抓错是工作的核心部分。 人类在解释AI所见所为方面的知识和经验是有用的。
公司和整个行业的治理也需要适应时代。 各组织必须建立明确的监管机制，以便大赦国际能够自行作出决定，以及如何监督和审计其行动。 然而，许多人尚未制定全面保障措施：在AVEVA和IMD最近的一项研究(在新标签中开放)中，43%的组织称 AI只略微或根本没有改变整个生态系统伙伴的决策和问责制，只有23%的组织报告发生了重大或根本性的变化。 (只有27%报告与合作伙伴实质性或广泛分享数据。 )
与此同时，监管机构开始界定一些规则。 《欧盟AI法》将关键基础设施中使用的某些AI安全组件归类为高风险部分并规定了对人的监督要求。 公司也正在建立自己的结构；AVEVA有一个负责的AI治理委员会，以及一套关于AI如何发展和部署的已公布的原则。
代理AI和活生生的数字双胞胎：真实世界案例研究
在已经运行的半自主系统中，这种监督在部署上有所不同。 在某些情况下，经营者批准每一项行动；在另一些情况下，大赦国际自行行事，而人们则监督和界定其可以在其中运作的界限。 Maggreevy列举了一些机器自主性以及人-加机器协作在AVEVA 客户中的样子的例子：
在沙特石油公司的Yanbu炼油厂，优化算法以闭环方式调整生产，必要时由运营商监督。 在其Ras Tanura炼油厂，算法建议修改，运营商决定是否实施。
- 雀巢公司利用内斯奎克工厂的人工智能优化来调制用来生产粉状饮料成分的工业干燥器。 在一次具有里程碑意义的试验中，这种调试将能源使用减少了16%，同时提高了质量和产量。
- 在泰国的SCG化工公司，AI支持的跨工程、操作和维护的数码双胞胎监测资产健康和可能的故障。 公司报告工厂可靠性为99%，投资收益为6个月内的9倍。
- 美国落基山脉国家实验室为电网控制室建立了一个基因化AI模型，以提供规模的监督。 该模型支持运营商进行可再生能源预测并估算电网条件。
展望未来
个别工厂的技术系统曾经缺失同样的同步性，但这种同步性在更大程度上也是缺失的。 “制造业和关键基础设施在过去50年中一直作为集成系统运作”，称 McGreevy。 但是，他建议，某些新兴技术正在创造机会来进行更加全面的协调。
在企业一级，这可能涉及实体AI的整合：将机器人和感知技术与AI驱动的决策相结合的系统。 例如，飞越管道和输电线的无人机可以将视觉检查数据输入能发现气体泄漏和其他危险的算法。 这不仅创造了更准确和相互关联的信息流动，而且使人类不必进入潜在的危险环境。 McGreevy预测，“机器人-元器件-软件的聚合将意味着事件减少、停机次数减少
一个更大的图片版本超越了任何一个工厂或过程，扩展到整个工业网络，麦格雷维将“综合价值链”称为“综合价值链”。 “活着的数码双胞胎使得整个价值链的数字表现成为可能”，他称。 “这使公司能够迅速进入react，以便进行供应链变化、需求变化、关税和物资供应。”
在当今动荡的地缘政治和不断变化的监管需求的现实中，这种复原力将是“绝对必要 ”，新增 McGreevy。 “没有它，就很难经营一个有效的企业。”
本文由 AI宝库自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
In partnership withAVEVA
Pairing industrial AI autonomy and human control
Living digital twins are helping industrial plants run more like living systems, and setting the stage for industries that work in sync.
Most people associate industrial environments with cold steel and clockwork machinery. Functionally, though, a plant or factory is more like a living thing: It has a pulse, even a metabolism. It goes through wear and tear as it ages, and signs of deteriorating health often show up as barely perceptible irregularities.
Digital twin technology has long aimed to mirror that dynamism and model anomalies that may be symptomatic of larger problems. But earlier implementations were a few beats behind physical reality; they were incapable of real-time analysis and unable to proactively address any issues detected. They focused more on simulation, observation and what-if scenario planning, rather than closed-loop execution. Rather than serving as a digital mirror of reality that can spot anomalies or suggest optimizations, a living digital twin combines a dynamic, high-fidelity digital representation of complex operations with the capacity to intervene in the physical world through operations and control systems.
AI is at the center of this change. Rob McGreevy, chief product officer at AVEVA, likens newer, AI-infused digital twins to organisms that grow and evolve. These “living” versions are adaptive, evergreen models of a plant’s assets and processes. Because they keep pace with live conditions and connect systems that once ran in isolation, they provide a previously missing layer of visibility and orchestration that better reflects the organic rhythms of the facility itself.
Now, agentic AI is also enabling industrial systems to move beyond diagnostics or suggestions and act of their own accord. As the technology progresses toward greater autonomy, it’s starting to develop the reflexes for a kind of industrial homeostasis, in which small, constant adjustments keep a plant or factory healthy and humming.
All that said, human judgment and operator oversight still play an instrumental role by defining what healthy looks like to begin with—and flagging when AI systems are falling out of alignment. Living digital twins provide the means for human engineers to monitor what AI is doing and ensure execution is on track.
The technologies that keep digital twins in sync
Living digital twins link engineering and design information with real-time operational data through a digital thread, or a connected record of an asset that follows it through its lifecycle. A couple of notable technological shifts have helped string this thread together: Sensors (which have gotten more affordable in recent years) now stream telemetry from IoT devices and industrial control equipment, and software platforms bring that information into user-friendly interfaces. Predictive and physics-based models can also provide AI-enriched insights into how a machine or process might behave.
The lenses through which operators view digital twins have evolved in turn. “You can look at the digital twin through the lens of sustainability: What are my emissions?” says McGreevy. “Or, through the lens of maintenance: Is this asset performing in a healthy way? Or, through a performance metric: Is it producing the number of widgets I need?”
Setting boundaries for semi-autonomous systems
The next phase is letting AI act on select insights those lenses illuminate. For their part, manufacturers are eager for this chapter: In a 2026 Manufacturing Leadership Council survey of manufacturers (opens in new tab), 66% said they are using or plan to use agentic AI in their operations, and 40% expect some degree of factory autonomy by 2030. At the same time, they’re wary of the potential risks: In Deloitte’s 2025 smart manufacturing survey (opens in new tab), 65% of executives ranked operational risk, including the potential for business disruption, among their top concerns.
Manufacturers are accelerating toward agentic AI and greater factory autonomy
Source: MIT Technology Review Insights with data from Manufacturing Leadership Council (opens in new tab), 2026
“There is a lot more refinement to be done, a lot more proof points, testing, and validation needed,” McGreevy says about the ongoing process of making AI autonomous. In the near term, McGreevy expects agentic AI to follow the path seen in other industrial technologies like SCADA systems. “The ‘S’ in SCADA means supervisory, and supervisory means there’s a human in the middle,” he says. He sees AI working mostly in that advisory mode for the foreseeable future, with full autonomy limited to narrow, highly repetitive tasks.
As for the role human operators play, the day-to-day is evolving. Workers who once specialized in a single process line or maintenance task can now take on multiple disciplines. They can spend less time and effort approving routine actions one by one, and more on defining acceptable operating limits. Because AI can reinforce patterns in the data it receives, catching missteps early is a core part of the job. Human knowledge and experience in interpreting what AI is seeing and doing is instrumental.
Governance on a company- and industry-wide scale, too, needs to adapt to the times. Organizations must establish clear guardrails for which decisions AI can make on its own and how its actions are monitored and audited. Still, many have yet to set up comprehensive safeguards: In a recent study from AVEVA and IMD (opens in new tab), 43% of organizations said AI has changed decision-making and accountability across ecosystem partners only slightly or not at all, while just 23% reported a significant or fundamental change. (Only 27% reported sharing data substantially or extensively with partners.)
In the meantime, regulators are starting to define some of the rules. The EU AI Act classifies certain AI safety components used in critical infrastructure as high-risk and imposes requirements for human oversight. Companies are setting up their own structures as well; AVEVA, for one, has a responsible AI governance board and a published set of principles for how AI is developed and deployed.
Agentic AI and living digital twins: Real-world case studies
Inside the semi-autonomous systems already running, that oversight looks different from one deployment to another. In some cases, an operator approves every action; in others, AI acts on its own while people oversee and define the boundaries it can operate within. McGreevy cites several examples of what machine autonomy and human-plus-machine collaboration looks like among AVEVA customers:
- At Saudi Aramco’s Yanbu refinery, optimization algorithms adjust production in a closed loop, with operators overseeing as needed. At its Ras Tanura refinery, the algorithms recommend changes and operators decide whether to implement them.
- Nestlé uses AI optimization at Nesquik plants to tune the industrial dryers used to produce powdered beverage ingredients. In a landmark test, this tuning reduced energy use by 16%, while improving quality and yield.
- At Thailand’s SCG Chemicals, an AI-supported digital twin spanning engineering, operations, and maintenance monitors asset health and flags potential failures. The company reports 99% plant reliability and a ninefold return on investment within six months.
- The National Laboratory of the Rockies in the U.S. has built a generative AI model for grid control rooms to provide oversight at scale. The model supports operators with renewable energy forecasting and estimates of grid conditions.
Looking to the future
The same synchronization that was once missing from individual plants’ technology systems has also been lacking on a larger scale. “Manufacturing and critical infrastructure have operated as siloed systems for the last 50 years,” says McGreevy. But certain emerging technologies, he suggests, are creating opportunities for more holistic coordination.
On an enterprise level, this might involve the integration of physical AI: systems that pair robotics and sensing technologies with AI-powered decision-making. Drones that fly over pipelines and power lines, for instance, can feed visual inspection data to algorithms that spot gas leaks and other hazards. Not only does this create a more accurate and interconnected flow of information, but it spares humans from needing to physically enter potentially dangerous environments. “The robotics-meets-software convergence will mean fewer incidents, fewer outages, and a more sustainable way of operating,” McGreevy predicts.
A bigger-picture version extends beyond any one plant or process to entire industrial networks, something McGreevy dubs the “integrated value chain.” “Living digital twins make digital manifestations of the entire value chain possible,” he says. “This allows companies to react quickly to supply chain changes, demand changes, tariffs, and material availability.”
Amid today’s realities of turbulent geopolitics and shifting regulatory demands, such resilience will be “an absolute necessity,” adds McGreevy. “Without it, it will be very hard to run an effective business.”
Auto-fetched and translated by AI Gem Box. All rights belong to the original author.