Synchrotron X-ray microdiffraction ( μ XRD) services are conducted for industrial minerals to identify their crystal impurities in terms of crystallinity and potential impurities. μ XRD services generate huge loads of images that have to be screened before further processing and storage. However, there are insufficient effective labeled samples to train a screening model since service consumers are unwilling to share their original experimental images. In this article, we propose a physics law-informed federated learning (FL) based μ XRD image screening method to improve the screening while protecting data privacy. In our method, we handle the unbalanced data distribution challenge incurred by service consumers with different categories and amounts of samples with novel client sampling algorithms. We also propose hybrid training schemes to handle asynchronous data communications between FL clients and servers. The experiments show that our method can ensure effective screening for industrial users conducting industrial material testing while keeping commercially confidential information.

中文翻译：

---

基于联合学习的工业材料同步加速器 X 射线微衍射图像筛选

同步加速器 X 射线微衍射 ( μ XRD) 服务是针对工业矿物进行的，以从结晶度和潜在杂质的角度识别其晶体杂质。μ XRD 服务生成大量图像，在进一步处理和存储之前必须对其进行筛选。然而，由于服务消费者不愿意分享他们的原始实验图像，因此没有足够的有效标记样本来训练筛选模型。在这篇文章中，我们提出了一种基于物理定律的联邦学习（FL）μ XRD 图像筛选方法在提高筛选的同时保护数据隐私。在我们的方法中，我们使用新颖的客户端采样算法来处理具有不同类别和样本数量的服务消费者所带来的不平衡数据分布挑战。我们还提出了混合训练方案来处理 FL 客户端和服务器之间的异步数据通信。实验表明，我们的方法可以确保对进行工业材料测试的工业用户进行有效筛选，同时保留商业机密信息。