The development of artificial intelligence (AI)-based industrial data-driven models is the driving force behind the digital transformation of manufacturing processes and the application of smart manufacturing. However, in real-world industrial applications, the intricate interplay among data quality, model accuracy, and generalizability poses significant challenges, hindering the effective deployment and scalability of data-driven models in complex manufacturing environments. To address this challenge, this paper proposes a universal Physics-informed Hybrid Optimization framework for Efficient Neural Intelligence (PHOENIX) in manufacturing, demonstrating its applicability in robotic welding scenarios. This framework systematically integrates physical principles into its input, model structure, and dynamic optimization processes, enabling proactive, real-time detection and predictive of welding instability. It achieves an accuracy of up to 98% for predictions within the next 50 ms and maintains an accuracy of 86% even for forecasts up to 1 s in advance. Through physics-informed data-driven modeling, the framework significantly reduces the dependence on high-cost data while maintaining the performance of the original model. By leveraging cloud-based optimization modules that integrate new data with historical experience, the framework enables autonomous model parameter optimization, ensuring its continuous adaptation to the complex and dynamic demands of industrial scenarios.

Functionally graded materials (FGMs), which constitute a new type of composite material, have received considerable attention in industry because of the spatial gradient of their composition and the microstructure-induced gradient in their material performance, which make them better suited for high-performance multifunctional applications. Additive manufacturing (AM) has become one of the most promising techniques for the manufacture of materials and structures because of its high flexibility. The combination of advanced materials (FGMs) and advanced manufacturing methods (AM) is expected to facilitate the further development of such engineering materials. In this paper, the definition, historical development and material gradient types of FGMs are introduced. The classification, process principle and typical research results of the AM of metal FGMs are summarized and discussed. In particular, the research status of wire and arc additive manufacture (WAAM), which is more suitable for the preparation of large-scale metal FGMs, is reviewed in detail according to the types of FGMs, and a double-wire bypass plasma arc additive manufacturing technique, which is suitable for inducing a gradient along the direction of single-pass cladding, is proposed. On the basis of this summary of the important achievements made to date, future research is proposed.