Engineering topics
Publications and source records attributed to Zeng, Yan.
AlabOS is a workflow orchestration framework designed to address the increased complexity in autonomous laboratories, featuring a reconfigurable experiment workflow model and a resource reservation mechanism.
Not Available
The success of solid-state synthesis often hinges on the first intermediate phase that forms, which determines the remaining driving force to produce the desired target material. Recent work suggests that when reaction energies are large, thermodynamics primarily dictates the initial product formed, regardless of reactant stoichiometry. Here, we validate this principle and quantify its constraints by performing in situ characterization on 37 pairs of reactants. These experiments reveal a threshold for thermodynamic control in solid-state reactions, whereby initial product formation can be predicted when its driving force exceeds that of all other competing phases by ≥60 milli–electron volt per atom. In contrast, when multiple phases have a comparable driving force to form, the initial product is more often determined by kinetic factors. Analysis of the Materials Project data shows that 15% of possible reactions fall within the regime of thermodynamic control, highlighting the opportunity to predict synthesis pathways from first principles.
Electron microscopy is indispensable for examining the morphology and composition of solid materials at the sub-micron scale. To study the powder samples that are widely used in materials development, scanning electron microscopes (SEMs) are increasingly used at the laboratory scale to generate large datasets with hundreds of images. Parsing these images to identify distinct particles and determine their morphology requires careful analysis, and automating this process remains challenging. In this work, we enhance the Mask R-CNN architecture to develop a method for automated segmentation of particles in SEM images. We address several challenges inherent to measurements, such as image blur and particle agglomeration. Moreover, our method accounts for prediction uncertainty when such issues prevent accurate segmentation of a particle. Recognizing that disparate length scales are often present in large datasets, we use this framework to create two models that are separately trained to handle images obtained at low or high magnification. By testing these models on a variety of inorganic samples, our approach to particle segmentation surpasses an established automated segmentation method and yields comparable results to the predictions of three domain experts, revealing comparable accuracy while requiring a fraction of the time. These findings highlight the potential of deep learning in advancing autonomous workflows for materials characterization.
The emergence of high-entropy materials has inspired the exploration of novel materials in diverse technologies. In electrochemical energy storage, high-entropy design has shown advantageous impacts on battery materials such as suppressing undesired short-range order, frustrating energy landscape, decreasing volumetric change and reducing the reliance on critical metals. This comment addresses the definition and potential improper use of the term “high entropy” in the context of battery materials design, highlights the unique properties of high-entropy materials in battery applications, and outlines the remaining challenges in the synthesis, characterization, and computational modeling of high-entropy battery materials.
Metastable polymorphs often result from the interplay between thermodynamics and kinetics. Despite advances in predictive synthesis for solution-based techniques, there remains a lack of methods to design solid-state reactions targeting metastable materials. Here, we introduce a theoretical framework to predict and control polymorph selectivity in solid-state reactions. This framework presents reaction energy as a rarely used handle for polymorph selection, which influences the role of surface energy in promoting the nucleation of metastable phases. Through in situ characterization and density functional theory calculations on two distinct synthesis pathways targeting LiTiOPO 4 , we demonstrate how precursor selection and its effect on reaction energy can effectively be used to control which polymorph is obtained from solid-state synthesis. A general approach is outlined to quantify the conditions under which metastable polymorphs are experimentally accessible. With comparison to historical data, this approach suggests that using appropriate precursors could enable targeted materials synthesis across diverse chemistries through selective polymorph nucleation.
To close the gap between the rates of computational screening and experimental realization of novel materials, we introduce the A-Lab, an autonomous laboratory for the solid-state synthesis of inorganic powders. This platform uses computations, historical data from the literature, machine learning (ML) and active learning to plan and interpret the outcomes of experiments performed using robotics. Over 17 days of continuous operation, the A-Lab realized 41 novel compounds from a set of 58 targets including a variety of oxides and phosphates that were identified using large-scale ab initio phase-stability data from the Materials Project and Google DeepMind. Synthesis recipes were proposed by natural-language models trained on the literature and optimized using an active-learning approach grounded in thermodynamics. Analysis of the failed syntheses provides direct and actionable suggestions to improve current techniques for materials screening and synthesis design. The high success rate demonstrates the effectiveness of artificial-intelligence-driven platforms for autonomous materials discovery and motivates further integration of computations, historical knowledge and robotics.
Machine learning (ML) has become a valuable tool to assist and improve materials characterization, enabling automated interpretation of experimental results with techniques such as X-ray diffraction (XRD) and electron microscopy. Because ML models are fast once trained, there is a key opportunity to bring interpretation in-line with experiments and make on-the-fly decisions to achieve optimal measurement effectiveness, which creates broad opportunities for rapid learning and information extraction from experiments. Here, we demonstrate such a capability with the development of autonomous and adaptive XRD. By coupling an ML algorithm with a physical diffractometer, this method integrates diffraction and analysis such that early experimental information is leveraged to steer measurements toward features that improve the confidence of a model trained to identify crystalline phases. We validate the effectiveness of an adaptive approach by showing that ML-driven XRD can accurately detect trace amounts of materials in multi-phase mixtures with short measurement times. The improved speed of phase detection also enables in situ identification of short-lived intermediate phases formed during solid-state reactions using a standard in-house diffractometer. Our findings showcase the advantages of in-line ML for materials characterization and point to the possibility of more general approaches for adaptive experimentation.
Here, we have designed and tested several synthesis routes targeting a highly fluorinated disordered rocksalt (DRX) cathode, Li 1.2 Mn 0.4 Ti 0.4 O 1.6 F 0.4 , with each route rationalized by thermochemical analysis. Precursor combinations were screened to raise the F chemical potential and avoid the formation of LiF, which inhibits fluorination of the targeted DRX phase. MnF 2 was used as a reactive source of F, and Li 6 MnO 4 , LiMnO 2 , and Li 2 Mn 0.33 Ti 0.66 O 3 were tested as alternative Li sources. Each synthesis procedure was monitored using a multi-modal suite of characterization techniques including X-ray diffraction, nuclear magnetic resonance, thermogravimetric analysis, and differential scanning calorimetry. From the resulting data, we advance the understanding of oxyfluoride synthesis by outlining the key factors limiting F solubility. At low temperatures, MnF 2 consistently reacts with the Li source to form LiF as an intermediate phase, thereby trapping F in strong Li-F bonds. LiF can react with Li 2 TiO 3 to form a highly lithiated and fluorinated DRX (Li 3 TiO 3 F); however, MnO is not easily incorporated into this DRX phase. Although higher temperatures typically increase solubility, the volatility of LiF above its melting point (848 °C) inhibits fluorination of the DRX phase. Based on these findings, metastable synthesis techniques are suggested for future work on DRX fluorination.
There are some limitations of traditional influenza vaccines concerning novel mutant strains. Therefore, it is particularly important to develop preventive means for antigen-unrelated types of influenza viruses. Recent studies have shown that probiotics can modulate the immune system and reduce the severity of viral infections. In this study, we investigated the potential of Lactiplantibacillus plantarum 0111 against influenza virus H9N2. Challenge experiments showed that L. plantarum 0111 pretreatments could effectively improve mice’s survival rate and weight loss and reduce the inflammatory cytokines IL-6 and TNF-α in the lungs and bronchoalveolar lavage fluid (BALF) along with the degree of lung and intestinal injury. FMT experiment demonstrates that the protective effect produced by L. plantarum 0111 is associated with gut microorganisms. In addition, 16S high-throughput sequencing of the mouse intestinal microbiota showed that L. plantarum 0111 remodeled the intestinal microbiota after H9N2 infection and maintained the gut microbiota balance. In a mouse model, the oral administration of L. plantarum 0111 increased IFN-β expression in the serum and BALF. At the same time, the transcript levels of IFN-β and related ISGs in the intestine and lungs of mice were also increased. In addition, the activation and polarization of T cells in mesenteric lymph nodes (MLNs) and the spleen were detected by flow cytometry, and the results showed that L. plantarum 0111 modulated cytokines in T cells and increased IgA expression in B cells in the MLNs and spleen. Thus, L. plantarum 0111 may improve gut microbiota-mediated immune responses and thus, resist infection by the influenza virus, and it could be used as an effective preventive measure against the influenza virus.
A Unified Language of Synthesis Actions (ULSA) for describing inorganic synthesis is developed to help create a synthesis ontology and a solid foundation for autonomous robotic synthesis.
The development of a materials synthesis route is usually based on heuristics and experience. A possible new approach would be to apply data-driven approaches to learn the patterns of synthesis from past experience and use them to predict the syntheses of novel materials. However, this route is impeded by the lack of a large-scale database of synthesis formulations. In this work, we applied advanced machine learning and natural language processing techniques to construct a dataset of 35,675 solution-based synthesis procedures extracted from the scientific literature. Each procedure contains essential synthesis information including the precursors and target materials, their quantities, and the synthesis actions and corresponding attributes. Every procedure is also augmented with the reaction formula. Through this work, we are making freely available the first large dataset of solution-based inorganic materials synthesis procedures.
Autonomous synthesis and characterization of inorganic materials requires the automatic and accurate analysis of X-ray diffraction spectra. For this task, we designed a probabilistic deep learning algorithm to identify complex multi-phase mixtures. At the core of this algorithm lies an ensemble convolutional neural network trained on simulated diffraction spectra, which are systematically augmented with physics-informed perturbations to account for artifacts that can arise during experimental sample preparation and synthesis. In this work, larger perturbations associated with off-stoichiometry are also captured by supplementing the training set with hypothetical solid solutions. Spectra containing mixtures of materials are analyzed with a newly developed branching algorithm that utilizes the probabilistic nature of the neural network to explore suspected mixtures and identify the set of phases that maximize confidence in the prediction. Our model is benchmarked on simulated and experimentally measured diffraction spectra, showing exceptional performance with accuracies exceeding those given by previously reported methods based on profile matching and deep learning. We envision that the algorithm presented here may be integrated in experimental workflows to facilitate the high-throughput and autonomous discovery of inorganic materials.
Autonomous experimentation driven by artificial intelligence (AI) provides an exciting opportunity to revolutionize inorganic materials discovery and development. Herein, we review recent progress in the design of self-driving laboratories, including robotics to automate materials synthesis and characterization, in conjunction with AI to interpret experimental outcomes and propose new experimental procedures. We focus on efforts to automate inorganic synthesis through solution-based routes, solid-state reactions, and thin film deposition. In each case, connections are made to relevant work in organic chemistry, where automation is more common. Characterization techniques are primarily discussed in the context of phase identification, as this task is critical to understand what products have formed during synthesis. The application of deep learning to analyze multivariate characterization data and perform phase identification is examined. To achieve “closed-loop” materials synthesis and design, we further provide a detailed overview of optimization algorithms that use active learning to rationally guide experimental iterations. Lastly, we highlight several key opportunities and challenges for the future development of self-driving inorganic materials synthesis platforms.
Abstract not provided