scholarly journals Predicting the Tensile Behaviour of Cast Alloys by a Pattern Recognition Analysis on Experimental Data

Metals ◽  
2019 ◽  
Vol 9 (5) ◽  
pp. 557 ◽  
Author(s):  
Cristiano Fragassa ◽  
Matej Babic ◽  
Carlos Perez Bergmann ◽  
Giangiacomo Minak
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Mechanical Properties ◽  
Pattern Recognition ◽  
Cast Iron ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Tensile Behaviour ◽  
Cast Alloys ◽  
Pattern Recognition Analysis

The ability to accurately predict the mechanical properties of metals is essential for their correct use in the design of structures and components. This is even more important in the presence of materials, such as metal cast alloys, whose properties can vary significantly in relation to their constituent elements, microstructures, process parameters or treatments. This study shows how a machine learning approach, based on pattern recognition analysis on experimental data, is able to offer acceptable precision predictions with respect to the main mechanical properties of metals, as in the case of ductile cast iron and compact graphite cast iron. The metallographic properties, such as graphite, ferrite and perlite content, extrapolated through macro indicators from micrographs by image analysis, are used as inputs for the machine learning algorithms, while the mechanical properties, such as yield strength, ultimate strength, ultimate strain and Young’s modulus, are derived as output. In particular, 3 different machine learning algorithms are trained starting from a dataset of 20–30 data for each material and the results offer high accuracy, often better than other predictive techniques. Concerns regarding the applicability of these predictive techniques in material design and product/process quality control are also discussed.

Finger Movement Pattern Recognition from Surface EMG Signals Using Machine Learning Algorithms

ICTMI 2017 ◽  
2019 ◽  
pp. 75-89 ◽  
Author(s):  
Shravan Krishnan ◽  
Ravi Akash ◽  
Dilip Kumar ◽  
Rishab Jain ◽  
Karthik Murali Madhavan Rathai ◽  
...  
Keyword(s):  
Machine Learning ◽  
Pattern Recognition ◽  
Learning Algorithms ◽  
Movement Pattern ◽  
Surface Emg ◽  
Machine Learning Algorithms ◽  
Finger Movement

A Simulation-Based Monitoring of a Composite Plate Using an Integrated Vibration Measurement System

2013 ◽  
Vol 569-570 ◽  
pp. 64-71 ◽  
Author(s):  
Pawel Kostka ◽  
Angelos Filippatos ◽  
Robin Höhne ◽  
Werner Hufenbach
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Composite Plate ◽  
Learning Algorithms ◽  
Diagnostic System ◽  
Machine Learning Algorithms ◽  
Vibration Measurement ◽  
Structural Dynamic ◽  
Baseline Phase ◽  
Moulding Process

The unique potential to integrate functional elements into fibre-reinforced components combined with the recent progress in the simulation models of composite materials provides new perspectives for reliability improvement of the next generation components. Such combination is presented on the example of a carbon-fibre reinforced composite plate with integrated vibration measurement and excitation systems. The investigated structure was consolidated in an adapted resin transfer moulding process using additional layers for positioning, contacting and isolating of the active elements. The integrated elements enable an online estimation of the structural dynamic behaviour and its damage-dependent changes.The article considers the identification problem of diagnostic models enabling a precise interpretation of the measured vibration responses. An approach based on the generation of classifiers by means of inductive machine learning algorithms is applied. At the baseline phase, modal properties are measured that correspond to the undamaged state of the structure. Using these experimental data, a simulation model of the structure was fitted by means of a mixed numerical experimental technique and used for the generation of multiple vibration patterns resulting from different mass distributions. The unique combination of experimental and numerical results enables a generation of high resolved learning datasets for machine learning algorithms using a minimum amount of experimental data. The verification of the estimated classifiers by means of the achievable diagnostic performance is firstly conducted theoretically using standardised validation techniques and a high performance is identified. Then, at the inspection phase, the performance of the whole diagnostic system is additionally experimentally confirmed based on the dynamic response resulting from different unseen structural disturbances.

scholarly journals Machine learning algorithms for the prediction of the mechanical properties of railways’ rail pads

2021 ◽  
Vol 1765 ◽  
pp. 012008
Author(s):  
D Ferreño ◽  
J A Sainz-Aja ◽  
I A Carrascal ◽  
M Cuartas ◽  
J Pombo ◽  
...  
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
Learning Algorithms ◽  
Machine Learning Algorithms

scholarly journals A Survey of kNN Algorithm

2018 ◽  
Vol 1 (1) ◽  
Author(s):  
Jingwen Sun ◽  
Weixing Du ◽  
Niancai Shi
Keyword(s):  
Machine Learning ◽  
Pattern Recognition ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Pattern Recognition Method ◽  
Recognition Method ◽  
Related Literature ◽  
Machine Learning Classification ◽  
Advantages And Disadvantages ◽  
Implementation Steps

The kNN algorithm is a well-known pattern recognition method, which is one of the best text classifi cation algorithms. It is one of the simplest machine learning algorithms in machine learning classification algorithm. In this paper, we summarize the kNN algorithm and related literature, introduce the idea, principle, implementation steps and implementation code of kNN algorithm in detail, and analyze the advantages and disadvantages of the algorithm and its various improvement schemes. This paper also introduces the development of kNN algorithm, the important published papers. At the end of this paper, the application of kNN algorithm is introduced, and its implementation in text classifi cation is emphasized.

scholarly journals Towards ergonomics working - machine learning algorithms and musculoskeletal modeling

2021 ◽  
Vol 1208 (1) ◽  
pp. 012001
Author(s):  
Franz Suess ◽  
Maximilian Melzner ◽  
Sebastian Dendorfer
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Psychological Stress ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Feedback Systems ◽  
Work Related ◽  
Biomechanical Loading ◽  
Musculoskeletal Models ◽  
Workplace Environments

Abstract Ergonomic workplaces lead to fewer work-related musculoskeletal disorders and thus fewer sick days. There are various guidelines to help avoid harmful situations. However, these recommendations are often rather crude and often neglect the complex interaction of biomechanical loading and psychological stress. This study investigates whether machine learning algorithms can be used to predict mechanical and stress-related muscle activity for a standardized motion. For this purpose, experimental data were collected for trunk movement with and without additional psychological stress. Two different algorithms (XGBoost and TensorFlow) were used to model the experimental data. XGBoost in particular predicted the results very well. By combining it with musculoskeletal models, the method shown here can be used for workplace analysis but also for the development of real-time feedback systems in real workplace environments.

Sign in / Sign up

Export Citation Format

Share Document