scholarly journals Accelerating the Design of Automotive Catalyst Products Using Machine Learning

2021 ◽  
Author(s):  
Thomas M. Whitehead ◽  
Flora Chen ◽  
Christopher Daly ◽  
Gareth J. Conduit
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Experimental Validation ◽  
Detailed Understanding ◽  
Automotive Catalyst ◽  
Performance Targets ◽  
Harmful Emissions

The design of catalyst products to reduce harmful emissions is currently an intensive process of expert-driven discovery, taking several years to develop a product. Machine learning can accelerate this timescale, leveraging historic experimental data from related products to guide which new formulations and experiments will enable a project to most directly reach its targets. We used machine learning to accurately model 16 key performance targets for catalyst products, enabling detailed understanding of the factors governing catalyst performance and realistic suggestions of future experiments to rapidly develop more effective products. The proposed formulations are currently undergoing experimental validation.

scholarly journals Experimental Validation of Falling Liquid Film Models: Velocity Assumption and Velocity Field Comparison

Polymers ◽  
2021 ◽  
Vol 13 (8) ◽  
pp. 1205
Author(s):  
Ruiqi Wang ◽  
Riqiang Duan ◽  
Haijun Jia
Keyword(s):  
Experimental Data ◽  
Particle Image Velocimetry ◽  
Velocity Field ◽  
Experimental Validation ◽  
Particle Image ◽  
Velocity Fields ◽  
Number Range ◽  
Comparison Results ◽  
Image Velocimetry ◽  
Experimental Particle

This publication focuses on the experimental validation of film models by comparing constructed and experimental velocity fields based on model and elementary experimental data. The film experiment covers Kapitza numbers Ka = 278.8 and Ka = 4538.6, a Reynolds number range of 1.6–52, and disturbance frequencies of 0, 2, 5, and 7 Hz. Compared to previous publications, the applied methodology has boundary identification procedures that are more refined and provide additional adaptive particle image velocimetry (PIV) method access to synthetic particle images. The experimental method was validated with a comparison with experimental particle image velocimetry and planar laser induced fluorescence (PIV/PLIF) results, Nusselt’s theoretical prediction, and experimental particle tracking velocimetry (PTV) results of flat steady cases, and a good continuity equation reproduction of transient cases proves the method’s fidelity. The velocity fields are reconstructed based on different film flow model velocity profile assumptions such as experimental film thickness, flow rates, and their derivatives, providing a validation method of film model by comparison between reconstructed velocity experimental data and experimental velocity data. The comparison results show that the first-order weighted residual model (WRM) and regularized model (RM) are very similar, although they may fail to predict the velocity field in rapidly changing zones such as the front of the main hump and the first capillary wave troughs.

scholarly journals Smart Design Nano-Hybrid Formulations by Machine Learning

Proceedings ◽  
2020 ◽  
Vol 78 (1) ◽  
pp. 5
Author(s):  
Raquel de Melo Barbosa ◽  
Fabio Fonseca de Oliveira ◽  
Gabriel Bezerra Motta Câmara ◽  
Tulio Flavio Accioly de Lima e Moura ◽  
Fernanda Nervo Raffin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Water Solubility ◽  
Inorganic Materials ◽  
Fine Tuning ◽  
Support Vector ◽  
Drug Solubility ◽  
Physical Behavior ◽  
Best Fit

Nano-hybrid formulations combine organic and inorganic materials in self-assembled platforms for drug delivery. Laponite is a synthetic clay, biocompatible, and a guest of compounds. Poloxamines are amphiphilic four-armed compounds and have pH-sensitive and thermosensitive properties. The association of Laponite and Poloxamine can be used to improve attachment to drugs and to increase the solubility of β-Lapachone (β-Lap). β-Lap has antiviral, antiparasitic, antitumor, and anti-inflammatory properties. However, the low water solubility of β-Lap limits its clinical and medical applications. All samples were prepared by mixing Tetronic 1304 and LAP in a range of 1–20% (w/w) and 0–3% (w/w), respectively. The β-Lap solubility was analyzed by UV-vis spectrophotometry, and physical behavior was evaluated across a range of temperatures. The analysis of data consisted of response surface methodology (RMS), and two kinds of machine learning (ML): multilayer perceptron (MLP) and support vector machine (SVM). The ML techniques, generated from a training process based on experimental data, obtained the best correlation coefficient adjustment for drug solubility and adequate physical classifications of the systems. The SVM method presented the best fit results of β-Lap solubilization. In silico tools promoted fine-tuning, and near-experimental data show β-Lap solubility and classification of physical behavior to be an excellent strategy for use in developing new nano-hybrid platforms.

Risk-Controlled Wellbore Stability Criterion Based on Machine Learning Assisted Finite Element Model

2021 ◽  
Author(s):  
Hussain AlBahrani ◽  
Nobuo Morita
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Finite Element ◽  
Finite Element Model ◽  
Stability Criterion ◽  
Element Model ◽  
Rock Failure ◽  
Wellbore Stability ◽  
Wellbore Instability ◽  
Conventional Methods

Abstract In many drilling scenarios that include deep wells and highly stressed environments, the mud weight required to completely prevent wellbore instability can be impractically high. In such cases, what is known as risk-controlled wellbore stability criterion is introduced. This criterion allows for a certain level of wellbore instability to take place. This means that the mud weight calculated using this criterion will only constrain wellbore instability to a certain manageable level, hence the name risk-controlled. Conventionally, the allowable level of wellbore instability in this type of models has always been based on the magnitude of the breakout angle. However, wellbore enlargements, as seen in calipers and image logs, can be highly irregular in terms of its distribution around the wellbore. This irregularity means that risk-controlling the wellbore instability through the breakout angle might not be always sufficient. Instead, the total volume of cavings is introduced as the risk control parameter for wellbore instability. Unlike the breakout angle, the total volume of cavings can be coupled with a suitable hydraulics model to determine the threshold of manageable instability. The expected total volume of cavings is determined using a machine learning (ML) assisted 3D elasto-plastic finite element model (FEM). The FEM works to model the interval of interest, which eventually provides a description of the stress distribution around the wellbore. The ML algorithm works to learn the patterns and limits of rock failure in a supervised training manner based on the wellbore enlargement seen in calipers and image logs from nearby offset wells. Combing the FEM output with the ML algorithm leads to an accurate prediction of shear failure zones. The model is able to predict both the radial and circumferential distribution of enlargements at any mud weight and stress regime, which leads to a determination of the expected total volume of cavings. The model implementation is first validated through experimental data. The experimental data is based on true-triaxial tests of bored core samples. Next, a full dataset from offset wells is used to populate and train the model. The trained model is then used to produce estimations of risk-controlled stability mud weights for different drilling scenarios. The model results are compared against those produced by conventional methods. Finally, both the FEM-ML model and the conventional methods results are compared against the drilling experience of the offset wells. This methodology provides a more comprehensive and new solution to risk controlling wellbore instability. It relies on a novel process which learns rock failure from calipers and image logs.

Software-in-the-Loop Combined Machine Learning for Dynamic Responses Analysis of Floating Offshore Wind Turbines

2021 ◽  
Author(s):  
Peng Chen ◽  
Changhong Hu ◽  
Zhiqiang Hu
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Wind Turbines ◽  
Dynamic Responses ◽  
Offshore Wind ◽  
Learning Technology ◽  
Mean Values ◽  
Offshore Wind Turbines ◽  
Floating Offshore Wind Turbines ◽  
Brute Force Method

Abstract Artificial intelligence (AI) brings a new solution to overcome the challenges of Floating offshore wind turbines (FOWTs) to better predict the dynamic responses with intelligent strategies. A new AI-based software-in-the-loop method, named SADA is introduced in this paper for the prediction of dynamic responses of FOWTs, which is proposed based on an in-house programme DARwind. DARwind is a coupled aero-hydro-servo-elastic in-house program for FOWTs, and a reinforcement learning method with exhaust algorithm and deep deterministic policy gradient (DDPG) are embedded in DARwind as an AI module. Firstly, the methodology is introduced with the selection of Key Disciplinary Parameters (KDPs). Secondly, Brute-force Method and DDPG algorithms are adopted to changes the KDPs’ values according to the feedback of 6DOF motions of Hywind Spar-type platform through comparing the DARwind simulation results and those of basin experimental data. Therefore, many other dynamic responses that cannot be measured in basin experiment can be predicted in good accuracy with SADA method. Finally, the case study of SADA method was conducted and the results demonstrated that the mean values of the platform’s motions can be predicted with higher accuracy. This proposed SADA method takes advantage of numerical-experimental method, basin experimental data and the machine learning technology, which brings a new and promising solution for overcoming the handicap impeding direct use of conventional basin experimental way to analyze FOWT’s dynamic responses during the design phase.

scholarly journals Exact Solution for Viscoelastic Flow in Pipe and Experimental Validation

Polymers ◽  
2022 ◽  
Vol 14 (2) ◽  
pp. 334
Author(s):  
Ekaterina Vachagina ◽  
Nikolay Dushin ◽  
Elvira Kutuzova ◽  
Aidar Kadyirov
Keyword(s):  
Experimental Data ◽  
Exact Solution ◽  
Analytical Methods ◽  
Experimental Validation ◽  
Parametric Method ◽  
Fluid Flows ◽  
Parametric Representation ◽  
Viscoelastic Flow ◽  
Exponential Form ◽  
Image Velocimetry

The development of analytical methods for viscoelastic fluid flows is challenging. Currently, this problem has been solved for particular cases of multimode differential rheological equations of media state (Giesekus, the exponential form of Phan-Tien-Tanner, eXtended Pom-Pom). We propose a parametric method that yields solutions without additional assumptions. The method is based on the parametric representation of the unknown velocity functions and the stress tensor components as a function of coordinate. Experimental flow visualization based on the SIV (smoke image velocimetry) method was carried out to confirm the obtained results. Compared to the Giesekus model, the experimental data are best predicted by the eXtended Pom-Pom model.

scholarly journals Adaptive Intelligent Welding Manufacturing

2021 ◽  
Vol 100 (01) ◽  
pp. 63-83
Author(s):  
YUMING ZHANG ◽  
◽  
QIYUE WANG ◽  
YUKANG LIU
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Deep Learning ◽  
Welding Process ◽  
Welding Parameters ◽  
Weld Quality ◽  
Robotic Welding ◽  
Process Variables ◽  
Physical Constraints ◽  
Needed Information

Optimal design of the welding procedure gives the desired welding results under nominal welding conditions. During manufacturing, where the actual welding manufacturing conditions often deviate from the nominal ones used in the design, applying the designed procedure will produce welding results that are different from the desired ones. Adaption is needed to make corrections and adjust some of the welding parameters from those specified in the design. This is adaptive welding. While human welders can be adaptive to make corrections and adjustments, their performance is limited by their physical constraints and skill level. To be adaptive, automated and robotic welding systems require abilities in sensing the welding process, extracting the needed information from signals from the sensors, predicting the responses of the welding process to the adjustments on welding parameters, and optimizing the adjustments. This results in the application of classical sensing, modeling of process dynamics, and control system design. In many cases, the needed information for the weld quality and process variables of our concern is not easy to extract from the sensor’s data. Studies are needed to propose the phenomena to sense and establish the scientific foundation to correlate them to the weld quality or process variables of our concern. Such studies can be labor intensive, and a more automated approach is needed. Analysis suggests that artificial intelligence and machine learning, especially deep learning, can help automate the learning such that the needed intelligence for robotic welding adaptation can be directly and automatically learned from experimental data after the physical phenomena being represented by the experimental data has been appropriately selected to make sure they are fundamentally correlated to that with which we are concerned. Some adaptation abilities may also be learned from skilled human welders. In addition, human-robot collaborative welding may incorporate adaptations from humans with the welding robots. This paper analyzes and identifies the challenges in adaptive robotic welding, reviews efforts devoted to solve these challenges, analyzes the principles and nature of the methods behind these efforts, and introduces modern approaches, including machine learning/deep learning, learning from humans, and human-robot collaboration, to solve these challenges.

scholarly journals EXPERIMENTAL VALIDATION OF A COMPUTATIONAL PROGRAM FOR SIMULATING HYBRID SOLAR AND GAS WATER HEATING SYSTEMS

2007 ◽  
Vol 6 (2) ◽  
pp. 19
Author(s):  
J. M. S. Lafay ◽  
A. Krenzinger
Keyword(s):  
Experimental Data ◽  
Solar Energy ◽  
Computer Program ◽  
Solar Collector ◽  
Experimental Validation ◽  
Simulation Program ◽  
Water Heating ◽  
Heating Systems ◽  
Experimental Systems ◽  
Computational Program

This work presents the methodology and results of the validation of a computer program for the simulation of water heating systems combining solar energy and gas. Two experimental systems, named series and parallel, were assembled. These systems have the same components, differing on how they are connected. All the components were individually characterized and their parameters determined. Simulations of the behavior of the thermal tank, gas heater and solar collector were performed and confronted to experimental data. The results show that the simulation program “AQUESOLGAS” can accurately describe the behavior of water heating systems with solar energy and gas.

scholarly journals Automatic phonetic classification of vocalic allophones in Tol

2021 ◽  
Vol 6 (1) ◽  
pp. 403
Author(s):  
Marie Bissell
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Indigenous Languages ◽  
Diverse Range ◽  
Detailed Understanding ◽  
Allophonic Variation ◽  
Phonetic Classification

The aim of the present study involving automatic phonetic classification of /e/ and /u/ tokens in Tol is two-fold: first, I test existing claims about allophonic variation within these vowel classes, and second, I investigate allophonic variation within these vowel classes that has yet to be documented. The acoustic phonetic classifications derived in the present study contribute to a more detailed understanding of the allophonic systems operating within the Tol language. Operationalizing machine learning algorithms to investigate under-resourced, indigenous languages has the potential to provide detailed insights into the acoustic phonetic dynamics of a diverse range of vocalic systems.

Determining Usefulness of Machine Learning in Materials Discovery Using Simulated Research Landscapes

2021 ◽  
Author(s):  
Marcos del Cueto ◽  
Alessandro Troisi
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Data Acquisition ◽  
Prediction Accuracy ◽  
New Materials

When existing experimental data are combined with machine learning (ML) to predict the performance of new materials, the data acquisition bias determines ML usefulness and the prediction accuracy. In this...

Experimental Study on the Avoidance and Suppression Criteria for the Vortex-Induced Vibration of a Cantilever Cylinder

2002 ◽  
Vol 124 (2) ◽  
pp. 187-195 ◽  
Author(s):  
Takaaki Sakai ◽  
Masaki Morishita ◽  
Koji Iwata ◽  
Seiji Kitamura
Keyword(s):  
Experimental Data ◽  
Experimental Study ◽  
Water Flow ◽  
Experimental Validation ◽  
Flow Direction ◽  
High Viscosity ◽  
Design Guideline ◽  
Vortex Induced Vibration ◽  
High Viscosity Oil ◽  
Effect Of Structure

Experimental validation of the design guideline to prevent the failure of a thermometer well by vortex-induced vibration is presented, clarifying the effect of structure damping on displacement amplitudes of a cantilever cylinder. The available experimental data in piping are limited to those with small damping in water flow, because of the difficulty in increasing structure damping of the cantilever cylinders in experiments. In the present experiment, high-viscosity oil within cylinders is used to control their structure damping. Resulting values of reduced damping Cn are 0.49, 0.96, 1.23, 1.98, and 2.22. The tip displacements of the cylinder induced by vortex vibration were measured in the range of reduced velocity Vr from 0.7 to 5 (Reynolds number is 7.8×104 at Vr=1). Cylinders with reduced damping 0.49 and 0.96 showed vortex-induced vibration in the flow direction in the Vr>1 region. However, in cases of reduced damping of 1.23, 1.98, and 2.22, the vibration was suppressed to less than 1 percent diameter. It is confirmed that the criteria of “Vr<3.3 and Cn>1.2” for the prevention of vortex-induced vibration is reasonably applicable to a cantilever cylinder in a water flow pipe.

Sign in / Sign up

Export Citation Format

Share Document