Dynamic temperature measurement and real-time monitoring for characterising material formability during straining

预计到2027年，全球金属冲压市场规模将达到2780亿美元，其中汽车行业将占35.5%。热成形汽车部件越来越多地应用于汽车中，以实现轻量化车身/底盘结构并减少二氧化碳排放。在钣金成形中，准确预测和预防成形缺陷是确保成功成形高质量、轻量化结构件的关键。然而，由于缺乏材料在高温下的成形性数据来量化复杂的应变状态，阻碍了热成形过程模拟的准确性和效率，从而导致了原型和生产过程中的高能耗和高成本。Multi-X Solutions Limited是帝国理工学院的衍生公司，也是皇家工程院企业中心的终身成员，该公司使用发明的仪器、方法和开发的汽车应用AI（人工智能）模型，提供具有成本效益的材料测试设备和服务，能够在现实制造条件下对材料的可成形性特性和性能进行新颖的定量测量和评估。Multi-X旨在利用我们已建立的高保真数据集，进一步开发和培训基于人工智能的汽车零部件冲压工艺深度学习平台/软件。为了解决在应变过程中与温度分布测绘和监测相关的挑战，Multi-X将使用国家物理实验室（NPL）的成像荧光粉温度计技术实现非接触式温度测量。这将显著提升Multi-X的旗舰测试服务和用于热成型轻量化汽车零部件的人工智能工具的价值主张。成功的项目成果将进一步提高Multi-X领先的材料成形性测试技术的质量保证，并生成高保真度数据集，用于汽车、飞机和其他公共交通行业等广泛领域的人工智能工具培训。最终目标是使开发的测试方法标准化，以促进数据驱动的制造业的发展。该项目的成功将为基于计算机的模拟和人工智能模型提供真实数据，从而为热成形过程提供准确的成形性测量，从而推进产品设计和优化制造工艺。它还将显著减少开发时间、试错和从产品设计到原型制作的成本，同时提高热成型的生产率。此外，该项目的目标是充分利用材料的可成形性，以最大限度地提高部件的复杂性，减轻车辆重量，并直接有助于减少二氧化碳排放。

The global metal stamping market is projected to reach a size of $278Bn by 2027, with the automotive sector accounting for 35.5% of the total. Hot formed car components are increasingly utilised in vehicles to achieve lightweight car body/chassis structures and reduce CO2 emissions. In sheet metal forming, the accurate prediction and prevention of forming-induced defects are crucial to ensure successful forming of high-quality, lightweight structural components. However, the accuracy and efficiency of process simulation for hot forming are hindered by the lack of material formability data at elevated temperatures to quantify complex straining states, resulting in high energy consumption and costs in prototyping and production.Multi-X Solutions Limited, a spin-out of Imperial College and a lifetime member of the Enterprise Hub at the Royal Academy of Engineering, provides cost-effective material testing equipment and services using invented instrumentation, methods, and developed AI (Artificial Intelligence) models for automotive applications, enabling novel quantitative measurement and evaluation of material formability properties and performance under real-life manufacturing conditions. Multi-X aims to further develop and train the Al-based deep learning platform/software for car component stamping processes using our established high-fidelity datasets.To address the challenges related to temperature distribution mapping and monitoring during the straining process, Multi-X will implement contactless temperature measurement using imaging phosphor thermometer technology from the National Physical Laboratory (NPL). This implementation will significantly enhance the value propositions of Multi-X's flagship testing service and AI tools for hot forming lightweight car components.A successful project outcome will further improve the quality assurance of Multi-X's leading material formability testing technology and generate high-fidelity datasets used for training Al tools across a wide range of sectors, including automotive, aircraft, and other public transportation industries.The ultimately goal is to standardise the developed testing method for the advancement of the data-driven manufacturing industry. The success of this project will enable accurate formability measurement for hot forming processes by providing real-life data for computer-based simulation and Al models, thereby advancing product designs and optimising manufacture processes. It will also lead to a significant reduction in development time, trial and error, and costs from product design to prototyping, while increasing productivity in hot forming. Moreover, the project aims to fully exploit material formability properties to maximise component complexity, reduce vehicle weight, and directly contribute to CO2 emissions reduction.