Journal Article
Machine learning based modelling and optimization in hard turning of AISI D6 steel with newly developed AlTiSiN coated carbide tool
4
TL;DR: In this paper , the authors used machine learning (ML) based surrogate models to test, evaluate and optimize various input machining parameters and output responses for the hard machining of AISI D6 steel.
read more
Abstract: In recent times Mechanical and Production industries are facing increasing challenges related to the shift toward sustainable manufacturing. In this article, machining was performed in dry cutting condition with a newly developed coated insert called AlTiSiN coated carbides coated through scalable pulsed power plasma technique in dry cutting condition and a dataset was generated for different machining parameters and output responses. The machining parameters are speed, feed, depth of cut and the output responses are surface roughness, cutting force, crater wear length, crater wear width, and flank wear. The data collected from the machining operation is used for the development of machine learning (ML) based surrogate models to test, evaluate and optimize various input machining parameters. Different ML approaches such as polynomial regression (PR), random forest (RF) regression, gradient boosted (GB) trees, and adaptive boosting (AB) based regression are used to model different output responses in the hard machining of AISI D6 steel. The surrogate models for different output responses are used to prepare a complex objective function for the germinal center algorithm-based optimization of the machining parameters of the hard turning operation.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Liquid nitrogen spraying in hard machining process of AISI H13 steel
Farshid Jafarian,E. Mohseni +1 more
TL;DR: In this article , the effect of liquid nitrogen cooling on thermal loads, micro-hardness, white layer thickness, and surface quality in hard machining of AISI H13 steel was investigated.
Explainable machine learning for enhancing predictive accuracy of cutting forces in hard turning processes
Abdelhakim Dorbane,Fouzi Harrou,Ying Sun,Souâd Makhfi,Malek Habak +4 more
Model prediksi temperatur pahat pada proses bubut melalui anova dan regresi
Lailatus Sa'diyah Yuniar Arifianti,Sudirman Rizki Ariyanto,Susi Tri Umaroh,Ferly Isnomo Abdi,Mohammad R. J +4 more
Abstract: Pada proses pembubutan, temperatur tinggi sering terjadi akibat gesekan antara pahat dan benda kerja, yang berdampak pada peningkatan keausan pahat dan penurunan kualitas hasil pemesinan. Penelitian ini bertujuan untuk menganalisis pengaruh parameter proses, yaitu kecepatan putar (spindle speed), kecepatan makan (feed rate), dan kedalaman potong (depth of cut), terhadap temperatur pahat menggunakan metode analisis variansi (ANOVA) dan regresi linier berganda. Percobaan dilakukan sebanyak 16 kali berdasarkan rancangan faktorial penuh 2³ dengan dua replikasi. Hasil analisis menunjukkan bahwa feed rate dan depth of cut berpengaruh signifikan terhadap temperatur pahat, sedangkan spindle speed tidak memberikan pengaruh yang signifikan secara individual. Namun, interaksi antara faktor-faktor tersebut terbukti memberikan pengaruh yang signifikan terhadap temperatur. Model regresi linier berganda yang dikembangkan memiliki nilai koefisien determinasi (R²) sebesar 93,99%, yang menunjukkan kecukupan model untuk prediksi. Temuan ini memberikan kontribusi dalam pengendalian parameter proses untuk meminimalkan temperatur pahat, memperpanjang umur pahat, serta meningkatkan efisiensi dan kualitas dalam proses pembubutan.
Parameter optimization of titanium-coated stainless steel inserts for turning operation
Karthick Muniyappan,Lenin Nagarajan +1 more
TL;DR: The surface roughness of a high-strength stainless steel tool coated with tungsten carbide and processed using cryogenic treatment is significantly increased after turning operation. The processed tool insert became brittle and resulted in an increase in surface roughness.
References
Random Forests
Leo Breiman
- 01 Oct 2001
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.
A comparison on neural net simulators
TL;DR: Five artificial neural net simulators that are free of charge, run on Sun Sparcstations under X windows, and are available by anonymous FTP over the Internet, have been tested and the number as well as the range of facilities they offer to generating and working with connectionist networks are considered.
564
A Comparative Study on Machine Learning Algorithms for Smart Manufacturing: Tool Wear Prediction Using Random Forests
TL;DR: Experimental results have shown that RFs can generate more accurate predictions than FFBP ANNs with a single hidden layer and SVR, and experimental results have also shown thatRFs can be more accurate than support vector regression (SVR) without a hidden layer.
Tool breakage detection using support vector machine learning in a milling process
TL;DR: In this article, an intelligent tool breakage detection system which uses a support vector machine (SVM) learning algorithm is proposed to provide the ability to recognize process abnormalities and initiate corrective action during a manufacturing process, specifically in a milling process.
197
Physics guided neural network for machining tool wear prediction
TL;DR: A novel physics guided neural network model is presented for tool wear prediction that explores sufficient information from both physics and data domains to eliminate the physical inconsistency existing in conventional data driven models.
184