adityaanirudhk Goto Github PK

followers: 8.0 following: 12.0 repos: 11.0 gists: 0.0

Name: K. Aditya Anirudh

Type: User

Company: STUDENT

Bio: ROBOTICS AND AUTOMATION ENTHUSIAST! OCASSIONAL MACHINE LEARNING SCIENTIST. WELCOME TO MY PROFILE!

K. Aditya Anirudh's Projects

aditya-robotics-

Python sample codes for robotics algorithms.

design-of-axial-and-radial-active-magnetic-bearing-for-high-speed-epoxy-granite-micromilling-machine

This project addresses issues with current CNC micromilling machine bearings, limiting spindle speed to 20,000 rpm due to friction. Conventional bearings cause thermal complications and tool chatter, disrupting precision machining for tolerances under 5 micrometers. Axial and Radial Magnetic Bearings (AMB) aim to reduce friction.

driver-monitoring-system-for-automobile-using-machine-learning-and-opencv

The following project can be used to monitor the driver continuously for fatigue and the case of exhaustion and that of falling asleep. In such a case when the computer finds that the driver is sleeping the computer will trigger an alarm automatically, and the alarm will only stop on killing the process/stopping the car.

fault-diagnosis-for-mobile-robots

Fault diagnosis for mobile robot using ROS2 and Machine learning.

fault-diagnosis-in-stator-windings-of-a-three-phase-induction-motor-using-machine-learning-technique

First of all we have collected data and exported in data sheet.we have collected the data for healthy, unbalance, Faulty(stator winding) motor by doing an experiment and all of the data has been collected by YOKOGOWA power analyser. The collected data is stator current of three phases.For making the anaysis simplier we have converted the all 3 phase data into a single one by doing park's vector method. For ML Algorithms we need to select some of the feature We have done Feature extraction(33 feature) from PVM and PVAC . We have trained and tasted the model choosen classifier by giving 75% data for traning and we have used 25% data for testing out of180 sample. Then choose the best classifier and the best classifier that we get is K-Nearest Neighbour. After selecting the best model we have to tune the parameter of KNN model so that we get best accuracy. After fitting test data into the model we get accuracy of 91.1% and we can see the confusion matrix that shows how well the model classified the different fault (Healthy(0), Unbalance(1), Stator fault(2)) of motor . Out of 15 healthy test data all 15 are predicted in heathy class, out of 15 unbalance data 13 samples are classified in unbalance class and other 2 are misclassified in faulty case, out of 15 stator fault data 13 samples are classified in fault class and other 2 are misclassified in unbalance case.

iot-automotive-tuning-diagnostics-analytics

Introducing IoT Automotive Tuning, Diagnostics & Analytics, a cutting-edge GitHub repository that revolutionizes the way we interact with our vehicles in the connected world. Imagine the power to disable that pesky Check Engine Light, remotely install firmware updates, receive alerts for overdue maintenance, or even start your car from your alarm c

adityaanirudhk Goto Github PK

K. Aditya Anirudh's Projects

aditya-robotics-

design-of-axial-and-radial-active-magnetic-bearing-for-high-speed-epoxy-granite-micromilling-machine

driver-monitoring-system-for-automobile-using-machine-learning-and-opencv

fault-diagnosis-for-mobile-robots

fault-diagnosis-in-stator-windings-of-a-three-phase-induction-motor-using-machine-learning-technique

iot-automotive-tuning-diagnostics-analytics

matlab-robotics

pybotics

robotics-project

steel-plate-fault-diagnosis-using-classification-models

weed-management-rover

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent