Defining inkjet printing conditions of superconducting cuprate films through machine learning
| Autor: | Albert Queraltó, Adrià Pacheco, Nerea Jiménez, Susagna Ricart, Xavier Obradors, Teresa Puig |
|---|---|
| Přispěvatelé: | European Research Council, Ministerio de Economía y Competitividad (España), Ministerio de Ciencia e Innovación (España), European Commission, Generalitat de Catalunya |
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | Digital.CSIC. Repositorio Institucional del CSIC instname |
| ISSN: | 2050-7526 |
| Popis: | The design and optimization of new processing approaches for the development of rare earth cuprate (REBCO) high temperature superconductors is required to increase their cost-effective fabrication and promote market implementation. The exploration of a broad range of parameters enabled by these methods is the ideal scenario for a new set of high-throughput experimentation (HTE) and data-driven tools based on machine learning (ML) algorithms that are envisaged to speed up this optimization in a low-cost and efficient manner compatible with industrialization. In this work, we developed a data-driven methodology that allows us to analyze and optimize the inkjet printing (IJP) deposition process of REBCO precursor solutions. A dataset containing 231 samples was used to build ML models. Linear and tree-based (Random Forest, AdaBoost and Gradient Boosting) regression algorithms were compared, reaching performances above 87%. Model interpretation using Shapley Additive Explanations (SHAP) revealed the most important variables for each study. We could determine that to ensure homogeneous CSD films of 1 micron thickness without cracks after the pyrolysis, we need average drop volumes of 190–210 pl, and no. of drops between 5000 and 6000, delivering a total volume deposited close to 1 μl. The present work has been carried out in the framework of an ERC Advanced Grant (ULTRASUPERTAPE (ERC-2014-ADG-669504) and IMPACT (ERC-2019-PoC-874964) projects) funded by the European Research Council. We also acknowledge funding from the Spanish Ministry of Economy and Competitiveness through the “Severo Ochoa” Programme for Centres of Excellence in R&D (SEV-2015-0496 and CEX2019-000917-S), and the SUMATE project (RTI2018-095853-B-C21, co-financed by the European Regional Development Fund). In addition, we thank the European Commission for the funding through the COST action CA16218 (NANOCOHYBRI) and the Catalan Government (2017-SGR-1519 and XRE4S). A. Queraltó received funding from the Spanish Ministry of Science, Innovation and Universities (“Juan de la Cierva” postdoctoral fellowship (Grant no. IJC2018-035034-I)) and the DATOPTICON project (Severo Ochoa call FUNFUTURE-FIP-2020). We would like to thank Jordi Aguilar for fruitful discussions regarding the implementation of machine learning. With funding from the Spanish government through the ‘Severo Ochoa Centre of Excellence’ accreditation (CEX2019-000917-S). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|