scispace - formally typeset
Open AccessJournal ArticleDOI

Modelling and monitoring of abrasive finishing processes using artificial intelligence techniques: A review

Reads0
Chats0
TLDR
It is reported that most of the Artificial Intelligence algorithms available are not fully exploited for monitoring and modelling in abrasive finishing and emphasizes on bridging this gap.
About
This article is published in Journal of Manufacturing Processes.The article was published on 2020-09-01 and is currently open access. It has received 58 citations till now. The article focuses on the topics: Polishing & Lapping.

read more

Citations
More filters
Book

Principles of precision engineering

弘 中沢
TL;DR: In this article, the axiom of minimum information is used to define the principle of functional independence, which is also known as the functional independence principle of zero play, and it is used in the case of precision engineering.
Journal ArticleDOI

Manufacturing process monitoring using time-frequency representation and transfer learning of deep neural networks

TL;DR: The study finds that the multi-resolution capability of the CWT technique allows it to render more accurate and richer details of the signals, and shows that the classification accuracy can be improved by using shallower networks modified from the VGG-16 network to mitigate the overfitting issue.
Journal ArticleDOI

Differentiation of materials and laser powder bed fusion processing regimes from airborne acoustic emission combined with machine learning

TL;DR: In this article , the use of a low-cost microphone combined with state-of-the-art machine learning (ML) algorithms as online process monitoring to differentiate various materials and process regimes of Laser-Powder Bed Fusion (LPBF) was investigated.
Journal ArticleDOI

Acoustic emission and machine learning based classification of wear generated using a pin-on-disc tribometer equipped with a digital holographic microscope

TL;DR: In this article, the authors used an acoustic emission sensor and machine learning (ML) frameworks to classify different wear categories simulated with a customized pin-on-disc tribometer, and the results showed that the classifier was trained to differentiate the acoustic emission features of the different wear rates.
References
More filters
Journal ArticleDOI

Random Forests

TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Journal ArticleDOI

Deep learning

TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Book

The Nature of Statistical Learning Theory

TL;DR: Setting of the learning problem consistency of learning processes bounds on the rate of convergence ofLearning processes controlling the generalization ability of learning process constructing learning algorithms what is important in learning theory?
Book

Deep Learning

TL;DR: Deep learning as mentioned in this paper is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts, and it is used in many applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames.
Related Papers (5)
Frequently Asked Questions (14)
Q1. What are the main reasons why ML and DL are increasingly used to model process behavior?

Artificial intelligence techniques, such as ANN and expert systems, have been increasingly used to statistical model process behavior in areas where analytical models are unavailable. 

Quality output and increased productivity have been two of the biggest reasons for the integration of machine intelligence in the production line [1]. 

In case of deburring edges, compliant tools in the form of flap discs/wheel, as well as three-body abrasive tooling such as media finishing, are suitable options. 

The stochastic nature of material non-homogeneity, machine/ tool vibration, abrasive tool degradation, chip formation and undefined contacts makes it difficult to model the abrasive processes theoretically. 

Finishing of three-dimensional (3D) surfaces such as grooves, projections, or complex, indepth profiles is a trivial task for many abrasive finishing processes. 

For establishing a generalized data-driven model, is it critical to establish the parameter level using Design of Experiments (DoE’s). 

Inappropriate grinding of metals will cause undesirable and irreversible change in the microstructure of a surface layer resulting in the workpiece "burn". 

With manufacturing industries evolving and new materials been introduced rapidly, modelling process analytically, especially for abrasive finishing, will be a challenging task. 

The compound material, percentage mixture volume, abrasive particle micron size and applied pressure determine the resulting stock removal rate and surface roughness[79]. 

Out of the various events occurring in the interaction zone, only three events namely rubbing, ploughing and cutting are significantly responsible for the modification of the surface, i.e., material removal or surface wear in abrasive finishing process [49-52]. 

In abrasive processes, each abrasive grain particle removes a tiny bit of material when it forces onto the surface of the workpiece. 

A potential way of taking maximum advantage of the abrasive finishing is to model and monitor the characteristic features of the process. 

The authors have also explored other regression modelling techniques such as ANFIS, RF apart from ANN to estimate material removal based on parameters in the belt grinding process [74]. 

the likelihood for the traditional machining tools to encounter a void or micro level defect is very high as metals are non-homogenous at the micro level.