Artificial Intelligence Enabled Predictive Maintenance Digital Twins for Nuclear Power Plant Assets

人工智能支持核电厂资产的预测性维护数字孪生

• 批准号: 571661-2021
• 负责人: Hassan, MarwanM
• 金额: $ 2.91万
• 依托单位: University of Guelph
• 依托单位国家: 加拿大
• 项目类别: Alliance Grants
• 财政年份: 2022
• 资助国家: 加拿大
• 起止时间: 2022-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=753143
• 关键词: Artificial; Intelligence; Enabled; Predictive; Maintenance

The nuclear industry is capital-intensive, heavily regulated, and expected by the public to achieve a perfect safety record. This requires greater safe operations of crucial assets with greater availability. As such the creation of a digital environment to support the design and operation of nuclear facilities is becoming the next logical step. This will provide benefits in terms of reducing the requirements for expensive physical mock-ups and test. In addition, it will provide increasing return on investment through more efficient operation and improving public perception.This purpose of this project is to develop an effective asset management framework. This will enable data-driven decision making at all levels of planning, maintenance, and operations. The integrated models will be leveraged to inform operators of current operational system health and performance metrics. The digital twin (DT) has been identified as a promising approach for deploying these models to operating assets. In this project high performance computing, sensors' data and mathematical modelling will be integrated in a digital model (digital twin). The digital twin will be a computational representation of the asset (nuclear steam generators, valve, pumps). The digital twin consists of a computer-aided engineering (CAE) model of the asset onto which is superimposed data acquired from structural health monitoring during operation and from maintenance periods. Digital twins powered by AI will be exploited to predict impending asset failure and the contributory factors. The system will be able to Digital prescribe operational and/or maintenance actions to preserve equipment health so that can plant downtime can be minimized.

核工业是资本密集型的，受到严格的监管，公众期望它能达到完美的安全记录。这就要求关键资产在更大的可用性下更安全地运行。 因此，创建一个数字环境来支持核设施的设计和运营正成为下一个合乎逻辑的步骤。 这将在减少对昂贵的物理模型和测试的要求方面提供好处。 此外，它将通过更有效的运作和改善公众的看法来增加投资回报，本项目的目的是建立一个有效的资产管理框架。这将在规划、维护和运营的各个层面实现数据驱动的决策。 集成模型将被用来通知操作员当前的操作系统健康和性能指标。数字孪生模型（DT）被认为是将这些模型部署到运营资产的一种有前途的方法。 在这个项目中，高性能计算、传感器数据和数学建模将被集成到一个数字模型（数字孪生模型）中。 数字孪生将是资产（核蒸汽发生器，阀门，泵）的计算表示。数字孪生模型由资产的计算机辅助工程（CAE）模型组成，其上叠加了从运行期间和维护期间的结构健康监测中获取的数据。由人工智能驱动的数字双胞胎将被用来预测即将发生的资产故障和促成因素。该系统将能够数字化规定操作和/或维护措施，以保持设备健康，从而最大限度地减少工厂停机时间。