scholarly journals Using High-Speed Imaging and Machine Learning to Capture Ultrasonic Treatment Cavitation Area at Different Amplitudes

2021 ◽  
Author(s):  
Brandon Aguiar ◽  
Paul Bianco ◽  
Arvind Agarwal
Keyword(s):  
Machine Learning ◽  
Ultrasonic Treatment ◽  
Energy Efficient ◽  
High Speed ◽  
Treatment Process ◽  
Liquid Aluminum ◽  
High Speed Imaging ◽  
Machine Learning Model ◽  
Great Contrast ◽  
Research Endeavor

The ultrasonic treatment process strengthens metals by increasing nucleation and decreasing grain size in an energy efficient way, without having to add anything to the material. The goal of this research endeavor was to use machine learning to automatically measure cavitation area in the Ultrasonic Treatment process to understand how amplitude influences cavitation area. For this experiment, a probe was placed into a container filled with turpentine because it has a similar viscosity to liquid aluminum. The probe gyrates up and down tens of micrometers at a frequency of 20 kHz, which causes cavitations to form in the turpentine. Each experimental trial ran for 5 seconds. We took footage on a high-speed camera running the UST probe from 20% to 35% amplitude in increments of 1%. Our research examined how the amplitude of the probe changed the cavitation area per unit time. It was vital to get a great contrast between the cavitations and the turpentine so that we could train a machine learning model to measure the cavitation area in a software called Dragonfly. We observed that as amplitude increased, average cavitation area also increased. Plotting cavitation area versus time shows that the cavitation area for a given amplitude increases and decreases in a wave-like pattern as time passes.

scholarly journals High-Speed Imaging of Paw Withdrawal Reflex to Objectively Assess Pain State in Mice

2018 ◽  
Author(s):  
Ishmail Abdus-Saboor ◽  
Nathan T. Fried ◽  
Mark Lay ◽  
Peter Dong ◽  
Justin Burdge ◽  
...  
Keyword(s):  
Machine Learning ◽  
Chronic Pain ◽  
High Resolution ◽  
Statistical Modeling ◽  
High Speed ◽  
High Speed Imaging ◽  
Pain Mechanisms ◽  
Withdrawal Reflex ◽  
Withdrawal Behaviors ◽  
Pain State

AbstractRodents are often used for studying chronic pain mechanisms and developing new pain therapeutics, but objectively determining the animal’s pain state is a major challenge. To improve the precision of using reflexive withdrawal behaviors for interpreting the mouse pain state, we adopted high-speed videography to capture sub-second movement features of mice upon hind paw stimulation. We identified several parameters that are significantly different between behaviors evoked by innocuous and noxious stimuli, and combined them to map the mouse pain state through statistical modeling and machine learning. To test the utility of this approach, we determined the pain state triggered by von Frey hairs (VFHs) and optogenetic activation of two nociceptor populations. Our method reliably assesses the “pain-like” probability for each mouse paw withdrawal reflex under all scenarios, highlighting the improved precision of using this high resolution behavior-centered composite methodology to determine the mouse pain state from reflexive withdrawal assays.

Cfd - Machine Learning Prediction of Machinery Coupling Windage Heating and Power Loss

2021 ◽  
Author(s):  
Ahmad Dawahdeh ◽  
Joseph Oh ◽  
Tianbo Zhai ◽  
Alan Palazzolo
Keyword(s):  
Machine Learning ◽  
Empirical Formula ◽  
Power Loss ◽  
High Speed ◽  
Experimental Tests ◽  
Learning Model ◽  
American Petroleum Institute ◽  
Peak Temperature ◽  
Cfd Models ◽  
Machine Learning Model

Abstract Couplings connect the spinning shafts of driving and driven machines in the industry. A coupling guard encloses the coupling to protect personnel from the high-speed rotating coupling. The American Petroleum Institute API publishes standards that restrict the overheating of the coupling guards due to windage caused by the spinning shaft. Based on the most recent version of API 671, the peak temperature for the coupling guard should not exceed 60 °C. This paper proposes a machine learning model and an empirical formula to predict the maximum guard temperature and power loss. The machine learning models use a database obtained from simulated CFD cases for different coupling guards under various conditions. Also, the paper provides validation for the CFD models with experimental tests for different cases. The proposed machine learning model uses eight different input parameters to predict temperature and power loss. The model shows an accurate prediction for a varied number of CFD cases. The performance of the generated model has been verified with the experimental results. Also, an empirical formula has been created using the same database from CFD results. The results show that the ML model has better prediction accuracy than the empirical formula for predicting peak temperature and power loss for all cases.

scholarly journals Drowsiness Detection for Motorized Vehicles Using Machine Learning

2021 ◽  
Vol 9 (9) ◽  
pp. 1684-1689
Author(s):  
Ms. Twinkle P George
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
High Speed ◽  
Video Stream ◽  
Coffee Shop ◽  
Drowsy Driving ◽  
Camera System ◽  
Machine Learning Model ◽  
Motorized Vehicles ◽  
Coffee Shops

Abstract: Driver drowsiness is one of the major causes for most of the accidents in the world. Detecting the driver's eye tiredness is the easiest way for measuring the drowsiness of the driver. The advent of high-speed motorized vehicles drowsy driving accidents has claimed the lives of millions of people across the globe. To avoid such accidents, proposes a Machine Learning based system drowsiness system for motorized vehicles with alarm and Web Push Notifications to notify the driver before any accident occurs. The driver's face is captured by a real-time camera system, and the eye borders are detected by a pre-trained machine learning model from the real-time video stream. Then each eye is represented by 6 – coordinates (x, y) starting from the left corner of the eye and then working clockwise around the eye. The EAR (Ear Aspect Ratio) is calculated across 20 consecutive frames, and if it falls below a certain threshold, it sounds an alarm and sends the details of the nearest coffee shop to your mobile device via a Web Push Notification. When the alarm is activated, it also displays a list of nearby coffee shops to help the driver stay awake. Keywords: Machine Learning, SVM, MOR, EAR

Experimental Measurement of In-Plane Rolling Nonpneumatic Tire Vibrations Using High-Speed Imaging

2019 ◽  
Vol 47 (3) ◽  
pp. 196-210
Author(s):  
Meghashyam Panyam ◽  
Beshah Ayalew ◽  
Timothy Rhyne ◽  
Steve Cron ◽  
John Adcox
Keyword(s):  
High Speed ◽  
Image Correlation ◽  
Dynamic Mode Decomposition ◽  
Dynamic Mode ◽  
High Speed Imaging ◽  
Correlation Algorithm ◽  
Mode Decomposition ◽  
Series Of Experiments ◽  
Plane Deformations ◽  
Dominant Frequencies

ABSTRACT This article presents a novel experimental technique for measuring in-plane deformations and vibration modes of a rotating nonpneumatic tire subjected to obstacle impacts. The tire was mounted on a modified quarter-car test rig, which was built around one of the drums of a 500-horse power chassis dynamometer at Clemson University's International Center for Automotive Research. A series of experiments were conducted using a high-speed camera to capture the event of the rotating tire coming into contact with a cleat attached to the surface of the drum. The resulting video was processed using a two-dimensional digital image correlation algorithm to obtain in-plane radial and tangential deformation fields of the tire. The dynamic mode decomposition algorithm was implemented on the deformation fields to extract the dominant frequencies that were excited in the tire upon contact with the cleat. It was observed that the deformations and the modal frequencies estimated using this method were within a reasonable range of expected values. In general, the results indicate that the method used in this study can be a useful tool in measuring in-plane deformations of rolling tires without the need for additional sensors and wiring.

Machine Learning Accelerated Genetic Algorithms for Computational Materials Search

2018 ◽  
Author(s):  
Steen Lysgaard ◽  
Paul C. Jennings ◽  
Jens Strabo Hummelshøj ◽  
Thomas Bligaard ◽  
Tejs Vegge
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Genetic Algorithms ◽  
Au Nanoparticles ◽  
Learning Model ◽  
Energy Calculations ◽  
Atomic Distribution ◽  
Machine Learning Model ◽  
Fold Reduction ◽  
Computational Materials

A machine learning model is used as a surrogate fitness evaluator in a genetic algorithm (GA) optimization of the atomic distribution of Pt-Au nanoparticles. The machine learning accelerated genetic algorithm (MLaGA) yields a 50-fold reduction of required energy calculations compared to a traditional GA.

BAND NN: A Deep Learning Framework For Energy Prediction and Geometry Optimization of Organic Small Molecules

2019 ◽  
Author(s):  
Siddhartha Laghuvarapu ◽  
Yashaswi Pathak ◽  
U. Deva Priyakumar
Keyword(s):  
Machine Learning ◽  
Density Functional ◽  
Computational Cost ◽  
Geometry Optimization ◽  
Dft Methods ◽  
Energy Prediction ◽  
Machine Learning Model ◽  
Equilibrium Structures ◽  
High Level ◽  
Non Equilibrium

Recent advances in artificial intelligence along with development of large datasets of energies calculated using quantum mechanical (QM)/density functional theory (DFT) methods have enabled prediction of accurate molecular energies at reasonably low computational cost. However, machine learning models that have been reported so far requires the atomic positions obtained from geometry optimizations using high level QM/DFT methods as input in order to predict the energies, and do not allow for geometry optimization. In this paper, a transferable and molecule-size independent machine learning model (BAND NN) based on a chemically intuitive representation inspired by molecular mechanics force fields is presented. The model predicts the atomization energies of equilibrium and non-equilibrium structures as sum of energy contributions from bonds (B), angles (A), nonbonds (N) and dihedrals (D) at remarkable accuracy. The robustness of the proposed model is further validated by calculations that span over the conformational, configurational and reaction space. The transferability of this model on systems larger than the ones in the dataset is demonstrated by performing calculations on select large molecules. Importantly, employing the BAND NN model, it is possible to perform geometry optimizations starting from non-equilibrium structures along with predicting their energies.

Sign in / Sign up

Export Citation Format

Share Document