scholarly journals MACHINE LEARNING FOR DECISION-MAKING IN THE REMANUFACTURING OF WORN-OUT GEARS AND BEARINGS

2021 ◽  
Vol 32 (2) ◽  
pp. 135-150
Author(s):  
Wayne Tsimba ◽  
Gibson Chirinda ◽  
Stephen Matope
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Mechanical Equipment ◽  
Spur Gears ◽  
Element Analysis ◽  
Wear And Tear ◽  
Decision Making System ◽  
Image Processing Algorithms ◽  
Processing Algorithms ◽  
Day To Day Operations

Mechanical industries use rotating mechanical equipment in their day to day operations. The equipment suffers from wear and tear, and is usually discarded as scrap. But is there a way to recover some of this equipment and reuse it? This paper uses machine learning to capture and analyse the wearing damage of bearings and gears to determine whether they can be redeemed. Finite element analysis is conducted on worn-out spur gears and pillow bearings in order to facilitate feature extraction in image processing algorithms. This converts the actual gears, bearings, and seals into CAD files. The decision-making system is designed, and it uses these CAD files to decide on the optimum manufacturing process to restore redeemable components. The mechanical components of the system are designed using SOLIDWORKS. MATLAB, Proteus software, and the Arduino micro-controller are used for the system application design and simulation. The results from tests conducted on a worn-out gear and bearing show that the gear is 4% non-redeemable, while the bearing is 60.2% non-redeemable. The decision taken by the system is to redeem the gear and to discard the bearing.

scholarly journals Intelligent Predicting Learning Disabilities in School Going Children using Fuzzy Logic K Mean Clustering in Machine Learning.

2019 ◽  
Vol 8 (4) ◽  
pp. 1694-1698
Keyword(s):  
Social Sciences ◽  
Machine Learning ◽  
Decision Making ◽  
Learning Disabilities ◽  
Fuzzy Logic ◽  
Side Effects ◽  
Early Analysis ◽  
Comprehensive Investigation ◽  
Engineering Statistics ◽  
Decision Making System

Learning disabilities (LD) is turning into a major issue in various nations around the globe which can even contrarily influence human common advancement. The undertaking of this work is to help the specialized programme network in their task to be with the standard. The underlying section of the paper gives a comprehensive investigation of the distinctive components of diagnosing learning disabilities. Despite the fact that LD can be analysed early - before 5 years of age, most youngsters were not determined to have LD until the age of nine on account of its unpredictable side effects and unclear indication in children disorder issue. Fuzzy logic K-means clustering has inspired a tremendous transformation in Machine learning and can take and able to resolve a variation of problems. This paper is the elaboration on the strategy for utilizing this mix to encourage the early analysis of LD. Since Fuzzy Logic clustering in Machine Learning is generally considered and connected in different areas of science, we invite all the related analysts from the fields of computer science, engineering, statistics, social sciences, healthcare, and so on, etc. The result of the paper demonstrates that the previously mentioned methodology can possibly be the potential of the supporting decision-making system in LD investigating and diagnosing.

scholarly journals Web Service for Point Cloud Supported Robot Programming Using Machine Learning

2022 ◽  
pp. 253-262
Author(s):  
Kristina Enes
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Web Service ◽  
Production System ◽  
Production Line ◽  
Robot Programming ◽  
Programming Skills ◽  
Image Processing Algorithms ◽  
Processing Algorithms

AbstractIn industrial automation, the use of robots is already standard. But there is still a lot of room for further automation. One such place where improvements can be made is in the adjustment of a production system to new and unknown products. Currently, this task includes the reprogramming of the robot and a readjustment of the image processing algorithms if sensors are involved. This takes time, effort, and a specialist, something especially small and middle-sized companies shy away from. We propose to represent a physical production line with a digital twin, using the simulated production system to generate labeled data to be used for training in a deep learning component. An artificial neural network will be trained to both recognize and localize the observed products. This allows the production line to handle both known and unknown products more flexible. The deep learning component itself is located in a cloud and can be accessed through a web service, allowing any member of the staff to initiate the training, regardless of their programming skills. In summary, our approach addresses not only further automation in manufacturing but also the use of synthesized data for deep learning.

scholarly journals Comparative analysis of image processing techniques for obstacle avoidance and path deduction

2021 ◽  
Vol 2070 (1) ◽  
pp. 012121
Author(s):  
R Rajavarshini ◽  
S Shruthi ◽  
P Mahanth ◽  
Boddu Chaitanya Kumar ◽  
A Suyampulingam
Keyword(s):  
Machine Learning ◽  
Image Processing ◽  
Obstacle Avoidance ◽  
Transportation System ◽  
Image Processing Algorithm ◽  
Image Processing Techniques ◽  
Haar Cascade ◽  
Image Processing Algorithms ◽  
Processing Algorithms ◽  
Processing Techniques

Abstract The growing need for automation has a significant impact on our daily lives. Automating the essentials of our society like transportation system has plenty of applications like unmanned ground vehicles in military, wheel chair for disabled, domestic robots, etc., There are driving, braking, obstacle tackling etc., to a transportation system that can be automated. This paper particularly focuses on automating the obstacle avoidance which provides intelligence to the vehicle and ensures a high degree of safety and is performed using image processing algorithms. Edge based detection, image segmentation, and Machine Learning based method are the three image processing techniques used to detect and avoid obstacles. Haar cascade classifier is the machine learning method where Haar cascade analysis is performed for better accurate results with justifying graphs and parametric values obtained. A comparison of the three image processing algorithms is also tabulated considering obstacle size, colour, familiarities and environmental lightings and the best image processing algorithm is inferred.

Sign in / Sign up

Export Citation Format

Share Document