Machine-learning-assisted fabrication: Bayesian optimization of laser-induced graphene patterning using in-situ Raman analysis

Wahab, Hud; Jain, Vivek; Tyrrell, Alexander Scott; Seas, Michael; Kotthoff, Lars; Johnson, Patrick A.

doi:10.1016/j.carbon.2020.05.087

Cited by 55 publications

(42 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…b) Sheet conductance of carbon trace on PI as a function of laser fabrication parameters [99] centered around 2700 cm -1 in the Raman spectrum of LIG ( Fig. 2e) [42,59,82] was identified to be the same as in singlelayer graphene, but with a larger width at half maximum of around 60 cm -1 [83]. Meanwhile, the sharp peak observed around 26° (002) in the XRD spectrum suggested the formation of a highly crystalline graphene structure ( Fig.2f) [84].…”

Section: A Transformation Processmentioning

confidence: 99%

Physical Sensors Based on Laser-Induced Graphene: A Review

Kaidarova

Kosel

2021

IEEE Sensors J.

View full text Add to dashboard Cite

Physical sensors form the fundamental building blocks of a multitude of advanced applications that detect and monitor the surroundings and communicate the acquired physical data. The everlasting need for more compliant, low-cost, and energy-efficient sensor solutions has led to considerable interest in enhancing their features and operation limits even further. While graphene has emerged as a promising candidate material, due to its outstanding electrical and mechanical properties, it is still not available in large volumes for practical applications. Meanwhile, Laser-Induced Graphene has opened new perspectives for a versatile, durable, printed physical sensing platform capable of detecting various physical parameters across a range of conditions and subjects. In this review, LIG physical sensors were categorized into four broad types based on their transduction mechanism: mechanical, thermal, magnetic, and electromagnetic. We summaries various design strategies established for preparing reliable physical sensors without the involvement of chemical treatments, synthesis, and multi-step fabrication processes. The review considers the effects of laser choice, lasing environment, and parameters on graphene properties. We also discuss a broad spectrum of applications of LIG physical sensors in fields ranging from healthcare, tactile sensing, environmental monitoring, energy harvesting, and soft robotics to desalination and THz modulation.

show abstract

Section: A Transformation Processmentioning

confidence: 99%

Physical Sensors Based on Laser-Induced Graphene: A Review

Kaidarova

Kosel

2021

IEEE Sensors J.

View full text Add to dashboard Cite

show abstract

“…To improve the crystallinity of the ZIF-67, we implemented a BO algorithm 51 for efficiently sampling the synthesis variables from the search space. Description of BO can be found in Supporting Information.…”

Section: ■ Results and Discussionmentioning

confidence: 99%

“…58 As for the surrogate model, RF was chosen instead of the Gaussian process, as the search space contains categorical and continuous variables. 51 BO-RF can maximize the objective function which is then evaluated by an acquisition function (expected improvement, EI) via quantifying the utility of candidates (Figure 3A). As shown in Figure 3B, FWHM of representative peaks in the XRD spectra of four ZIF-67 samples synthesized with the reaction parameters recommended by BO-RF decreased as the number of iterations increased, suggesting the improved crystallinity.…”

Section: ■ Results and Discussionmentioning

confidence: 99%

Accelerate Synthesis of Metal–Organic Frameworks by a Robotic Platform and Bayesian Optimization

Xie

Zhang

Deng

et al. 2021

ACS Appl. Mater. Interfaces

View full text Add to dashboard Cite

Synthesis of materials with desired structures, e.g., metal− organic frameworks (MOFs), involves optimization of highly complex chemical and reaction spaces due to multiple choices of chemical elements and reaction parameters/routes. Traditionally, realizing such an aim requires rapid screening of these nonlinear spaces by experimental conduction with human intuition, which is quite inefficient and may cause errors or bias. In this work, we report a platform that integrates a synthesis robot with the Bayesian optimization (BO) algorithm to accelerate the synthesis of MOFs. This robotic platform consists of a direct laser writing apparatus, precursor injecting and Joule-heating components. It can automate the MOFs synthesis upon fed reaction parameters that are recommended by the BO algorithm. Without any prior knowledge, this integrated platform continuously improves the crystallinity of ZIF-67, a demo MOF employed in this study, as the number of operation iterations increases. This work represents a methodology enabled by a data-driven synthesis robot, which achieves the goal of material synthesis with targeted structures, thus greatly shortening the reaction time and reducing energy consumption. It can be easily generalized to other material systems, thus paving a new route to the autonomous discovery of a variety of materials in a cost-effective way in the future.

show abstract

“…The maximum I G /I D (5.4) was shown to be four times higher than others that were performed without computer‐based optimization. [ 37 ] This indicates that optimization methods can yield materials with better properties than previous reports, therefore accelerating materials science development.…”

Section: Synthesis and Processingmentioning

confidence: 99%

Data Science Applied to Carbon Materials: Synthesis, Characterization, and Applications

Morelos-Gómez

Terrones

Endo

2021

Advcd Theory and Sims

View full text Add to dashboard Cite

Data science has been rapidly developed and implemented in diverse scientific and technological fields over the past decade, to accelerate new knowledge generation and develop high‐impact applications. Recently, different data science tools and techniques have been widely used, such as optimizations, regressions, and classifications of data (tabular, spectral, or visual). In this review, data science tools and techniques are discussed for their adoption for the synthesis, characterization, and applications of carbon‐based materials. Materials synthesis in conjunction with data science has resulted in optimal growth conditions with desired properties and processing techniques. Regarding characterization, molecular structures can be reconstructed using microscopy images, and a particular property can be predicted based on the other properties of the desired carbon material. Moreover, for the applications of carbon materials, data science has enabled prediction of the water treatment efficiency, classification of electronic signals, prediction of the biological activity, and virus classification. It is clear that by combining data science and carbon‐related materials, it is now possible to accelerate theory‐experimental research in the quest for novel materials and their emerging applications.

show abstract

Machine-learning-assisted fabrication: Bayesian optimization of laser-induced graphene patterning using in-situ Raman analysis

Cited by 55 publications

References 52 publications

Physical Sensors Based on Laser-Induced Graphene: A Review

Physical Sensors Based on Laser-Induced Graphene: A Review

Accelerate Synthesis of Metal–Organic Frameworks by a Robotic Platform and Bayesian Optimization

Data Science Applied to Carbon Materials: Synthesis, Characterization, and Applications

Contact Info

Product

Resources

About