A comparative study of basic and ensemble artificial intelligence models for surface roughness prediction during the AA7075 milling process

Gabsi, Abd El Hedi; Aissa, Chokri Ben; Mathlouthi, Safa

doi:10.1007/s00170-023-11026-8

Cited by 5 publications

(2 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The models tested in this study include SVM, k-NN, and RF. To enhance our analysis, we have introduced two additional potent models: eXtreme Gradient Boosting (XGBoost) and Binary deep neural network (BDNN) [39,40], for comparison with the stacking ensemble model proposed in this research. We will validate these models through a comprehensive process of parameter tuning, training, and validation to assess their performance while considering various combinations of selected features.…”

Section: Parameter Tuning Training and Validationmentioning

confidence: 99%

“…Additionally, a single model may only capture a specific aspect of the data, potentially missing out on other important patterns or insights. To address these limitations, three modeling techniques (DOE, SVM, and BNN) were compared in [28] to develop a predictive model for surface roughness, while [29] represents the study examining thirteen machine learning algorithms in the context of surface roughness, including seven basic models and six ensemble models. In [30], SVR and ANN integrated with GA were employed to optimize turning operations, showcasing their superiority over traditional models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of machine tool spindle assembly quality variation based on the stacking ensemble model

Liu,

Kuo,

Chen

2024

Int J Adv Manuf Technol

View full text Add to dashboard Cite

This paper presents a stacking ensemble model to predict the assembly quality variation of machine tool spindles. The model uses data from 925 single-spindle inspections and extracts evaluation metrics from multiple domains to extract valuable information. Feature selection is performed using a correlation model to identify important features, and various lightweight supervised learning algorithms are applied to analyze the data. To further enhance the model's performance, a stacking ensemble approach is proposed, which combines algorithms. The proposed ensemble model achieves an accuracy rate of 85.47%, a precision rate of 86.44 %, a recall rate of 85.64 %, and an F1 value of 86.04 %. The results demonstrate that the proposed stacking ensemble model is an effective approach for predicting the assembly quality variation of machine tool spindles, using the data available.

show abstract

Section: Parameter Tuning Training and Validationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Prediction of machine tool spindle assembly quality variation based on the stacking ensemble model

Liu,

Kuo,

Chen

2024

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

Effects of current intensities on material removal rate, electrode wear rate, and surface roughness of machining high carbon high chromium steel

Rakesh,

Gupta,

Mahto

et al. 2024

Materialwissenschaft Werkst

View full text Add to dashboard Cite

The electrical discharge machining is very successful and generally recognized for producing complicated shapes and small openings with exceptional precision. The objective of this study is to assess the impact of different electrical discharge machining parameters on the attributes of the machining process. The evaluation of the machining process was conducted based on the workpiece‘s material removal rate, the rate at which the electrodes wear, and the level of surface roughness. Simultaneously achieving a high material removal rate, low electrode wear rate, and high surface roughness is not possible with a specific combination of approaches due to their contradicting nature. Frequently, it is necessary to independently apply many measures instantaneously in order to assess their impact on various responses. This research investigates the machining of high carbon high chromium steel making use of electrical discharge machining with aluminum, copper, and graphite electrodes. The study focuses on the impact of different current intensities on the rate of material removal, electrode wear, and surface roughness. The experimental results demonstrate that the highest material removal rate (mmcubicmin−1) is achieved at a current density of 12 A when using a copper electrode (54.67), as opposed to aluminum electrode (22.91) and graphite electrode (29.43).

show abstract

Pre-control of grinding surface quality by data-driven: a review

Fu,

Lv,

Chen

et al. 2024

Int J Adv Manuf Technol

View full text Add to dashboard Cite

A comparative study of basic and ensemble artificial intelligence models for surface roughness prediction during the AA7075 milling process

Cited by 5 publications

References 59 publications

Prediction of machine tool spindle assembly quality variation based on the stacking ensemble model

Prediction of machine tool spindle assembly quality variation based on the stacking ensemble model

Effects of current intensities on material removal rate, electrode wear rate, and surface roughness of machining high carbon high chromium steel

Pre-control of grinding surface quality by data-driven: a review

Contact Info

Product

Resources

About