Motivated by the ever-increasing wealth of data boosted by national strategies in terms of data-driven Integrated Computational Materials Engineering (ICME), Materials Genome Engineering, Materials Genome Infrastructures, Industry 4.0, Materials 4.0 and so on, materials informatics represents a unique strategy in revealing the fundamental relationships in the development and manufacturing of advanced materials. Materials developments are becoming ever more integrated with robust data-driven and data-intensive technologies. In the present review, big data-assisted digital twins (DTs) for the smart design and manufacturing of advanced materials are presented from the perspective of the digital thread. In the introduction of the DT design paradigm in the ICME era, the simulation aspects of DT and the data and design infrastructures are discussed. Referring to the simulation and theoretical factors of DTs, high-throughput simulation and automation and artificial intelligence-assisted multiscale atomistic modeling are detailed through several cases studies. With respect to data and data mining technologies, entropy and its application for attribute selection in decision trees are discussed to emphasize knowledge-based modeling, simulation and data analysis in machine learning coherently. Guided by the perspectives and case studies of the digital thread, we present our recent work on the design, manufacturing and product service via big data-assisted DTs for smart design and manufacturing by integrating some of these advanced concepts and technologies. It is believed that big data-assisted DTs for smart design and manufacturing effectively support better products with the application of novel materials by reducing the time and cost of materials design and deployment.

The discovery of novel metallic glasses (MGs) with high glass-forming ability (GFA) has been an important area of active research for years in materials science and engineering. Unfortunately, the traditional approach based on trial-and-error methods is inefficient, time consuming and costly. Therefore, machine learning (ML) has recently drawn significant research interest as an alternative approach for the development of MGs. In this review, we discuss the current progress regarding the ML guided design of MGs from a variety of perspectives, including the GFA database, data representation, ML algorithms and numerical evaluation. Furthermore, we consider the challenges facing this field, including the scarcity and quality of GFA data, the development of physics informed data descriptors, the selection of appropriate algorithms and the necessity for experimental validation. We also briefly discuss possible solutions to tackle these challenges.

The development of multicomponent alloys with target properties poses a significant challenge, owing to the enormous number of potential component combinations, high costs and the inefficiency of conventional empirical trial-and-error experimental approaches. To tackle this challenge, we develop a machine learning (ML)-guided high-throughput experimental (HTE) approach to accelerate the development of non-equimolar hard Co_xCr_yTi_zMo_uW_v high-entropy alloys (HEAs). We first develop a set of all-process HTE facilities ranging from multi-tube ingredient assignment to multi-station electrical arc smelting and specimen preparation for bulk alloy samples with discrete compositions. Instead of random or combinatorial composition searching, HEAs with only ~1/28 of all the potential compositions are synthesized in two stages guided by the ML prediction. The final ML models, trained using 138 experimental data, predict the alloy hardness with mean relative errors of 5.3%, 6.3% and 15.4% at high (HV > 800), medium (HV = 600-800) and low (HV < 600) hardness ranges, respectively. In total, 14 superhard HEAs with HV > 900 are discovered by our ML-guided HTE approach. Moreover, the multiple ML models predict the hardness of 3876 hypothetical alloys covering the whole composition range, thereby revealing the systematic component effects based on the complete composition-hardness and descriptor-hardness correlations. The hardening mechanisms are elaborated by analyzing the microstructures of CoCrTiMoW. Furthermore, physical insights can be gained by transitioning from “machine learning” to “learning from machine”. This work demonstrates that our ML-guided HTE approach provides an effective strategy for multicomponent alloy development with a potential hundred-fold overall increase in efficiency at a fraction of the cost compared to conventional methods.