Adaptive process control for crystal growth using machine learning for high-speed prediction: application to SiC solution growth

CrystEngComm ◽  
2021 ◽  
Author(s):  
Yifan Dang ◽  
Can Zhu ◽  
Motoki Ikumi ◽  
Masaki Takaishi ◽  
Wancheng Yu ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Speed ◽  
Control Method ◽  
Optimal Growth ◽  
Growth Conditions ◽  
Time Dependent ◽  
Growth Environment ◽  
Adaptive Process ◽  
Adaptive Process Control ◽  
Speed Prediction

A time-dependent recipe designed by an adaptive control method can consistently maintain the optimal growth conditions despite the unsteady growth environment.

scholarly journals An interpretable flux-based machine learning model of drug interactions across metabolic space and time

2021 ◽  
Author(s):  
Carolina H Chung ◽  
Sriram Chandrasekaran
Keyword(s):  
Machine Learning ◽  
Combination Therapy ◽  
Drug Interactions ◽  
Growth Conditions ◽  
Drug Combinations ◽  
Time Interval ◽  
Therapy Outcomes ◽  
Data Types ◽  
Growth Environment ◽  
Therapy Design

Drug combinations are a promising strategy to counter antibiotic resistance. However, current experimental and computational approaches do not account for the entire complexity involved in combination therapy design, such as the effect of the growth environment, drug order, and time interval. To address these limitations, we present an approach that uses genome-scale metabolic modeling and machine learning to explain and guide combination therapy design. Our approach (a) accommodates diverse data types, (b) accurately predicts drug interactions in various growth conditions, (c) accounts for time- and order-specific interactions, and (d) identifies mechanistic factors driving drug interactions. The entropy in bacterial stress response, time between treatments, and gluconeogenesis activation were the most predictive features of combination therapy outcomes across time scales and growth conditions. Analysis of the vast landscape of condition-specific drug interactions revealed promising new drug combinations and a tradeoff in the efficacy between simultaneous and sequential combination therapies.

Metrology-based quality and process control in automated stem cell production

2015 ◽  
Vol 82 (6) ◽  
Author(s):  
Friedrich W. Schenk ◽  
Michael Kulik ◽  
Robert Schmitt
Keyword(s):  
Process Control ◽  
Pluripotent Stem Cells ◽  
High Speed ◽  
Cell Production ◽  
Automated Production ◽  
Adaptive Process ◽  
Production Platform ◽  
Adaptive Process Control ◽  
Induced Pluripotent ◽  
First Time

AbstractWe present a fully automated production platform for the generation, cultivation and differentiation of induced pluripotent stem cells. Cell culture, the process by which cells are grown outside of their natural environment, is a highly individual process. It can only be performed automatically by employing specialized metrology in combination with adaptive process control. A main motivation for automated versus manually assisted cell production is the increase in throughput and quality. Therefore all devices in the production platform have to be high-throughput capable and deliver reproducible results. Especially by combining high-speed microscopy with intelligent automation, a metrology-based quality and process control could be realized which allows the production of iPS cells on an industrial scale for the first time.

scholarly journals High-speed prediction of computational fluid dynamics simulation in crystal growth

CrystEngComm ◽  
2018 ◽  
Vol 20 (41) ◽  
pp. 6546-6550 ◽  
Author(s):  
Yosuke Tsunooka ◽  
Nobuhiko Kokubo ◽  
Goki Hatasa ◽  
Shunta Harada ◽  
Miho Tagawa ◽  
...  
Keyword(s):  
Machine Learning ◽  
Fluid Dynamics ◽  
Computational Fluid Dynamics ◽  
High Speed ◽  
Cfd Simulation ◽  
Large Diameter ◽  
Dynamics Simulation ◽  
Computational Fluid Dynamics Simulation ◽  
High Quality ◽  
Speed Prediction

The combination of the CFD simulation and machine learning thus makes it possible to determine optimized parameters for high-quality and large-diameter crystals.

4H-SiC Bulk Growth Using High-Temperature Gas Source Method

2014 ◽  
Vol 778-780 ◽  
pp. 51-54 ◽  
Author(s):  
Yuichiro Tokuda ◽  
Jun Kojima ◽  
Kazukuni Hara ◽  
Hidekazu Tsuchida ◽  
Shoichi Onda
Keyword(s):  
High Temperature ◽  
Temperature Gradient ◽  
High Speed ◽  
Optimal Growth ◽  
Growth Conditions ◽  
High Temperature Gradient ◽  
Bulk Growth ◽  
Source Method ◽  
Gas Source ◽  
High Temperature Gas

Our latest results of SiC bulk growth by High-Temperature Gas Source Method　are given in this paper. Based on Mullins-Sekerka instability, optimal growth conditions to preclude dendrite crystals, which are one of the pending issues for high-speed bulk growth, was studied. First, the simulation studies showed that high temperature gradient in a growing crystal is required for high-speed bulk growth without dendrite crystals. Second, high-speed bulk growth was demonstrated under high temperature gradient.

scholarly journals Local mortality estimates during the COVID-19 pandemic in Italy

2021 ◽  
Author(s):  
Augusto Cerqua ◽  
Roberta Di Stefano ◽  
Marco Letta ◽  
Sara Miccoli
Keyword(s):  
Machine Learning ◽  
Excess Mortality ◽  
Control Method ◽  
Local Level ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Mortality Data ◽  
Official Method ◽  
Learning Techniques ◽  
Mortality Estimates

AbstractEstimates of the real death toll of the COVID-19 pandemic have proven to be problematic in many countries, Italy being no exception. Mortality estimates at the local level are even more uncertain as they require stringent conditions, such as granularity and accuracy of the data at hand, which are rarely met. The “official” approach adopted by public institutions to estimate the “excess mortality” during the pandemic draws on a comparison between observed all-cause mortality data for 2020 and averages of mortality figures in the past years for the same period. In this paper, we apply the recently developed machine learning control method to build a more realistic counterfactual scenario of mortality in the absence of COVID-19. We demonstrate that supervised machine learning techniques outperform the official method by substantially improving the prediction accuracy of the local mortality in “ordinary” years, especially in small- and medium-sized municipalities. We then apply the best-performing algorithms to derive estimates of local excess mortality for the period between February and September 2020. Such estimates allow us to provide insights about the demographic evolution of the first wave of the pandemic throughout the country. To help improve diagnostic and monitoring efforts, our dataset is freely available to the research community.

scholarly journals A Critical Review of Supersonic Flow Control for High-Speed Applications

2021 ◽  
Vol 11 (15) ◽  
pp. 6899
Author(s):  
Abdul Aabid ◽  
Sher Afghan Khan ◽  
Muneer Baig
Keyword(s):  
Supersonic Flow ◽  
Flow Control ◽  
Active Control ◽  
Critical Review ◽  
High Speed ◽  
Passive Control ◽  
Control Method ◽  
Sudden Expansion ◽  
Control Approach ◽  
Cost Efficient

In high-speed fluid dynamics, base pressure controls find many engineering applications, such as in the automobile and defense industries. Several studies have been reported on flow control with sudden expansion duct. Passive control was found to be more beneficial in the last four decades and is used in devices such as cavities, ribs, aerospikes, etc., but these need additional control mechanics and objects to control the flow. Therefore, in the last two decades, the active control method has been used via a microjet controller at the base region of the suddenly expanded duct of the convergent–divergent (CD) nozzle to control the flow, which was found to be a cost-efficient and energy-saving method. Hence, in this paper, a systemic literature review is conducted to investigate the research gap by reviewing the exhaustive work on the active control of high-speed aerodynamic flows from the nozzle as the major focus. Additionally, a basic idea about the nozzle and its configuration is discussed, and the passive control method for the control of flow, jet and noise are represented in order to investigate the existing contributions in supersonic speed applications. A critical review of the last two decades considering the challenges and limitations in this field is expressed. As a contribution, some major and minor gaps are introduced, and we plot the research trends in this field. As a result, this review can serve as guidance and an opportunity for scholars who want to use an active control approach via microjets for supersonic flow problems.

scholarly journals High-Speed Video Analysis of the Process Stability in Plasma Spraying

2021 ◽  
Author(s):  
K. Bobzin ◽  
M. Öte ◽  
M. A. Knoch ◽  
I. Alkhasli ◽  
H. Heinemann
Keyword(s):  
Plasma Spraying ◽  
High Speed ◽  
Plasma Jet ◽  
Plasma Jets ◽  
Time Dependent ◽  
Acquisition Time ◽  
Fast Fourier Transformation ◽  
Frequency Spectra ◽  
Dependent Signal ◽  
The Stability

AbstractIn plasma spraying, instabilities and fluctuations of the plasma jet have a significant influence on the particle in-flight temperatures and velocities, thus affecting the coating properties. This work introduces a new method to analyze the stability of plasma jets using high-speed videography. An approach is presented, which digitally examines the images to determine the size of the plasma jet core. By correlating this jet size with the acquisition time, a time-dependent signal of the plasma jet size is generated. In order to evaluate the stability of the plasma jet, this signal is analyzed by calculating its coefficient of variation cv. The method is validated by measuring the known difference in stability between a single-cathode and a cascaded multi-cathode plasma generator. For this purpose, a design of experiment, covering a variety of parameters, is conducted. To identify the cause of the plasma jet fluctuations, the frequency spectra are obtained and subsequently interpreted by means of the fast Fourier transformation. To quantify the significance of the fluctuations on the particle in-flight properties, a new single numerical parameter is introduced. This parameter is based on the fraction of the time-dependent signal of the plasma jet in the relevant frequency range.

Sign in / Sign up

Export Citation Format

Share Document