scispace - formally typeset
Open accessJournal ArticleDOI: 10.1016/J.ISCI.2021.102262

Using simulation to accelerate autonomous experimentation: A case study using mechanics.

02 Mar 2021-iScience (Elsevier)-Vol. 24, Iss: 4, pp 102262-102262
Abstract: Summary Autonomous experimentation (AE) accelerates research by combining automation and machine learning to perform experiments intelligently and rapidly in a sequential fashion. While AE systems are most needed to study properties that cannot be predicted analytically or computationally, even imperfect predictions can in principle be useful. Here, we investigate whether imperfect data from simulation can accelerate AE using a case study on the mechanics of additively manufactured structures. Initially, we study resilience, a property that is well-predicted by finite element analysis (FEA), and find that FEA can be used to build a Bayesian prior and experimental data can be integrated using discrepancy modeling to reduce the number of needed experiments ten-fold. Next, we study toughness, a property not well-predicted by FEA and find that FEA can still improve learning by transforming experimental data and guiding experiment selection. These results highlight multiple ways that simulation can improve AE through transfer learning.

... read more


7 results found

Open accessJournal ArticleDOI: 10.1016/J.MATT.2021.06.036
Eric A. Stach1, Brian L. DeCost2, A. Gilad Kusne3, A. Gilad Kusne2  +20 moreInstitutions (18)
01 Sep 2021-
Abstract: Summary Solutions to many of the world's problems depend upon materials research and development. However, advanced materials can take decades to discover and decades more to fully deploy. Humans and robots have begun to partner to advance science and technology orders of magnitude faster than humans do today through the development and exploitation of closed-loop, autonomous experimentation systems. This review discusses the specific challenges and opportunities related to materials discovery and development that will emerge from this new paradigm. Our perspective incorporates input from stakeholders in academia, industry, government laboratories, and funding agencies. We outline the current status, barriers, and needed investments, culminating with a vision for the path forward. We intend the article to spark interest in this emerging research area and to motivate potential practitioners by illustrating early successes. We also aspire to encourage a creative reimagining of the next generation of materials science infrastructure. To this end, we frame future investments in materials science and technology, hardware and software infrastructure, artificial intelligence and autonomy methods, and critical workforce development for autonomous research.

... read more

Topics: Workforce development (53%)

7 Citations

Journal ArticleDOI: 10.1115/1.4050177
Abstract: Additive manufacturing (AM) techniques, such as fused deposition modeling (FDM), are able to fabricate physical components from three-dimensional (3D) digital models through the sequential deposition of material onto a print bed in a layer-by-layer fashion. In FDM and many other AM techniques, it is critical that the part adheres to the bed during printing. After printing, however, excessive bed adhesion can lead to part damage or prevent automated part removal. In this work, we validate a novel testing method that quickly and cheaply evaluates bed adhesion without constraints on part geometry. Using this method, we study the effect of bed temperature on the peak removal force for polylactic acid (PLA) parts printed on bare borosilicate glass and polyimide (PI)-coated beds. In addition to validating conventional wisdom that bed adhesion is maximized between 60 and 70 °C (140 and 158 °F), we observe that cooling the bed below 40 °C (104 °F), as is commonly done to facilitate part removal, has minimal additional benefit. Counterintuitively, we find that heating the bed after printing is often a more efficient process for facile part removal. In addition to introducing a general method for measuring and optimizing bed adhesion via bed temperature modulation, these results can be used to accelerate the production and testing of AM components in printer farms and autonomous research systems.

... read more

Topics: Throughput (business) (54%), Adhesion (51%)

1 Citations

Open accessProceedings ArticleDOI: 10.1145/3485114.3485123
Aldair E. Gongora1, Siddharth Mysore1, Beichen Li2, Wan Shou2  +4 moreInstitutions (2)
28 Oct 2021-
Abstract: Advancements in additive manufacturing have enabled design and fabrication of materials and structures not previously realizable. In particular, the design space of composite materials and structures has vastly expanded, and the resulting size and complexity has challenged traditional design methodologies, such as brute force exploration and one factor at a time (OFAT) exploration, to find optimum or tailored designs. To address this challenge, supervised machine learning approaches have emerged to model the design space using curated training data; however, the selection of the training data is often determined by the user. In this work, we develop and utilize a Reinforcement learning (RL)-based framework for the design of composite structures which avoids the need for user-selected training data. For a 5 × 5 composite design space comprised of soft and compliant blocks of constituent material, we find that using this approach, the model can be trained using 2.78% of the total design space consists of 225 design possibilities. Additionally, the developed RL-based framework is capable of finding designs at a success rate exceeding 90%. The success of this approach motivates future learning frameworks to utilize RL for the design of composites and other material systems.

... read more

Topics: Reinforcement learning (55%)

Journal ArticleDOI: 10.1016/J.CEP.2021.108671
Abstract: This paper reviews system-level transformations converging into the next generation of Process Intensification strategies defined as PI4.0. Process Intensification 4.0 uses data-driven algorithms to understand other physical and chemical processes that improve equipment design, predictive control, and optimization. Following this, an overview of the use of Artificial Intelligence techniques, particularly Machine Learning for the acceleration of equipment design, process optimization, and streamlining, is presented. This work will highlight and discuss the emerging framework of the integration between Circular Chemistry, Industry 4.0, and Process Intensification and how the data obtained from this integration is at the core of the next generation of Process Intensification strategies. This is supported by a discussion of different cases that apply data-driven models enabled by Machine Learning as a mean to enhance an intensified system (product synthesis, equipment or methods).

... read more

Topics: Process (engineering) (52%)

Journal ArticleDOI: 10.1016/J.JOULE.2021.10.001
Mahshid Ahmadi1, Maxim Ziatdinov2, Yuanyuan Zhou3, Eric A. Lass1  +1 moreInstitutions (3)
17 Nov 2021-Joule
Abstract: Summary Metal halide perovskites (MHPs) have catapulted to the forefront of energy research due to the unique combination of high device performance, low materials cost, and facile solution processability. A remarkable merit of these materials is their compositional flexibility allowing for multiple substitutions at all crystallographic sites, and hence thousands of possible pure compounds and virtually a near-infinite number of multicomponent solid solutions. Harnessing the full potential of MHPs necessitates rapid exploration of multidimensional chemical space toward desired functionalities. Recent advances in laboratory automation, ranging from bespoke fully automated robotic labs to microfluidic systems and to pipetting robots, have enabled high-throughput experimental workflows for synthesizing MHPs. Here, we provide an overview of the state of the art in the automated MHP synthesis and existing methods for navigating multicomponent compositional space. We highlight the limitations and pitfalls of the existing strategies and formulate the requirements for necessary machine learning tools including causal and Bayesian methods, as well as strategies based on co-navigation of theoritical and experimental spaces. We argue that ultimately the goal of automated experiments is to simultaneously optimize the materials synthesis and refine the theoretical models that underpin target functionalities. Furthermore, the near-term development of automated experimentation will not lead to the full exclusion of human operator but rather automatization of repetitive operations, deferring human role to high-level slow decisions. We also discuss the emerging opportunities leveraging machine learning-guided automated synthesis to the development of high-performance perovskite optoelectronics.

... read more


38 results found

Journal ArticleDOI: 10.1109/TKDE.2009.191
Sinno Jialin Pan1, Qiang Yang1Institutions (1)
Abstract: A major assumption in many machine learning and data mining algorithms is that the training and future data must be in the same feature space and have the same distribution. However, in many real-world applications, this assumption may not hold. For example, we sometimes have a classification task in one domain of interest, but we only have sufficient training data in another domain of interest, where the latter data may be in a different feature space or follow a different data distribution. In such cases, knowledge transfer, if done successfully, would greatly improve the performance of learning by avoiding much expensive data-labeling efforts. In recent years, transfer learning has emerged as a new learning framework to address this problem. This survey focuses on categorizing and reviewing the current progress on transfer learning for classification, regression, and clustering problems. In this survey, we discuss the relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift. We also explore some potential future issues in transfer learning research.

... read more

Topics: Semi-supervised learning (69%), Inductive transfer (68%), Multi-task learning (67%) ... show more

13,267 Citations

Journal ArticleDOI: 10.1038/NMAT4089
Ulrike G. K. Wegst1, Hao Bai2, Eduardo Saiz3, Antoni P. Tomsia2  +1 moreInstitutions (3)
01 Jan 2015-Nature Materials
Abstract: Natural structural materials are built at ambient temperature from a fairly limited selection of components. They usually comprise hard and soft phases arranged in complex hierarchical architectures, with characteristic dimensions spanning from the nanoscale to the macroscale. The resulting materials are lightweight and often display unique combinations of strength and toughness, but have proven difficult to mimic synthetically. Here, we review the common design motifs of a range of natural structural materials, and discuss the difficulties associated with the design and fabrication of synthetic structures that mimic the structural and mechanical characteristics of their natural counterparts.

... read more

2,288 Citations

Open accessJournal ArticleDOI: 10.1073/PNAS.0631609100
Huajian Gao1, Baohua Ji1, Ingomar L. Jäger, Eduard Arzt2  +2 moreInstitutions (2)
Abstract: Natural materials such as bone, tooth, and nacre are nanocomposites of proteins and minerals with superior strength. Why is the nanometer scale so important to such materials? Can we learn from this to produce superior nanomaterials in the laboratory? These questions motivate the present study where we show that the nanocomposites in nature exhibit a generic mechanical structure in which the nanometer size of mineral particles is selected to ensure optimum strength and maximum tolerance of flaws (robustness). We further show that the widely used engineering concept of stress concentration at flaws is no longer valid for nanomaterial design.

... read more

1,530 Citations

Journal ArticleDOI: 10.1007/S00158-013-0978-6
Ole Sigmund1, Kurt Maute2Institutions (2)
Abstract: Topology optimization has undergone a tremendous development since its introduction in the seminal paper by Bendsoe and Kikuchi in 1988. By now, the concept is developing in many different directions, including “density”, “level set”, “topological derivative”, “phase field”, “evolutionary” and several others. The paper gives an overview, comparison and critical review of the different approaches, their strengths, weaknesses, similarities and dissimilarities and suggests guidelines for future research.

... read more

1,307 Citations

Journal ArticleDOI: 10.1038/NATURE02236
15 Jan 2004-Nature
Abstract: The question of whether it is possible to automate the scientific process is of both great theoretical interest and increasing practical importance because, in many scientific areas, data are being generated much faster than they can be effectively analysed. We describe a physically implemented robotic system that applies techniques from artificial intelligence to carry out cycles of scientific experimentation. The system automatically originates hypotheses to explain observations, devises experiments to test these hypotheses, physically runs the experiments using a laboratory robot, interprets the results to falsify hypotheses inconsistent with the data, and then repeats the cycle. Here we apply the system to the determination of gene function using deletion mutants of yeast (Saccharomyces cerevisiae) and auxotrophic growth experiments. We built and tested a detailed logical model (involving genes, proteins and metabolites) of the aromatic amino acid synthesis pathway. In biological experiments that automatically reconstruct parts of this model, we show that an intelligent experiment selection strategy is competitive with human performance and significantly outperforms, with a cost decrease of 3-fold and 100-fold (respectively), both cheapest and random-experiment selection.

... read more

515 Citations

No. of citations received by the Paper in previous years