Model trees and sequential minimal optimization based support vector machine models for estimating minimum surface roughness value

Hashmi, Sarosh; Halawani, Sami M.; Barukab, Omar; Ahmad, Amir

doi:10.1016/j.apm.2014.07.026

Cited by 20 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e impact of dry machining [17][18][19][20][21][22] studied by various researchers also provides a positive platform toward ecofriendly machining, involving studies on cutting forces, chip formations, heat dissipation, etc. Various simulation models [23][24][25][26] are developed for estimating the minimum energy consumption, minimum R a , and maximum productivity. e study involved a minimum energy formulation by looking at the tactics and constraints for lowering the machine tool energy consumption, while maintaining the tool's life and parts' quality.…”

Section: Introductionmentioning

confidence: 99%

[Retracted] Green Machining Characteristics Study of Al‐6063 in CNC Milling Using Taguchi Method and Grey Relational Analysis

Kumar¹,

Kumar²,

Murugan³

et al. 2021

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

Green machining strategies in the manufacturing sector help to maintain the product value by considering the environmental impacts. Also, improvisation in the quality contribution of the parts can minimize the environmental consequences by improving resource efficiency, specifically in terms of coolants used in machining. Certain hazardous impacts have been witnessed because of longer exposure to such a machining environment. To address it, many researchers have concentrated on providing a healthy machining environment either by introducing dry machining or by minimum quantity lubrication (MQL). The proposed study addresses this context. The influence of these tactics on the attained surface quality of Al-6063 is quantified in this paper in terms of surface integrity (Ra) and removal rate of material (MRR). The study involves single-response optimization using the Taguchi design and multiresponse optimization using grey relational analysis (GRA). The results reveal that the depth of cut (Dc) and spindle speed (Ss) have the greatest impact on Ra and MRR. The machinability of Al-6063 is examined by considering the key machinability parameters, such as the spindle speed (Ss), feed rate (Fr), and the depth of cut (Dc), to arrive at the best possible surface roughness and removal rate of the material. As a typical Taguchi approach cannot perform multiresponse optimization, grey relational analysis is used. The grey relational analysis combined with Taguchi gives a novel methodology for multioptimization. The entire study is performed in dry condition and under minimum quantity lubrication. The results suggest that the responses are highly influenced by the depth of cut and spindle speed.

show abstract

Section: Introductionmentioning

confidence: 99%

[Retracted] Green Machining Characteristics Study of Al‐6063 in CNC Milling Using Taguchi Method and Grey Relational Analysis

Kumar¹,

Kumar²,

Murugan³

et al. 2021

Advances in Materials Science and Engineering

View full text Add to dashboard Cite

show abstract

“…The standard deviation of a Gaussian radial basis function is often utilized since it can handle higher‐dimensional input space. [ 32 ]

K ({normalx}_{normali} x) = \exp (- {(‖‖, x_{i} goodbreak- normalx)}^{2} / 2 {normalσ}^{2})

The final model for a better option

C, ξ and σ

can be written as

f (normalx) = \sum_{i = 1}^{normaln} ({normalα}_{normali} - {normalα}_{normali}^{*}) K (x_{i}, normalx) + b

…”

Section: Methodsmentioning

confidence: 99%

A novel and prediction approach of sheep wool reinforced polyester composites: Surface qualities and hybrid modeling

et al. 2022

View full text Add to dashboard Cite

This research aims to describe the hybrid algorithm's effectiveness in predicting and optimizing the abrasive water jet machining (AWJM) parameter on flexible sheep wool reinforced polyester composites. Selected five parameters are transverse speed (TS), water jet pressure (WJP), nozzle stand-off distance (NSoD), reinforcement weight percentage (wt%) and abrasive size (AS). In contrast, Surface Roughness (R a ) and Kerf Angle (K a ) are output performances. Multi objective optimization by ratio analysis (MOORA) is a tool is used for selecting and optimizing control variables. The most influential control variables are AS, WJP, TS, wt%, and NSoD, according to MOORA-Entropy feature selection results. The support vector machine algorithm (SVM) represents the AWJM process, and the model's performance is compared to SVM hybrid models. The differential evolutionary (DE) algorithm and the Entropy idea create a hybrid model. An SVM model is compared with the Hybrid SVM-Entropy model; hybrid improves prediction performance by 21.6%. When the MOORA-SVM-Entropy hybrid model is compared to the SVM model, it is revealed that the MOORA-SVM-Entropy hybrid model's prediction performance improves by 38.7%. According to the MOORA-Entropy approach, the optimal control variables are A

show abstract

“…Now for each branch, the procedure may be repeated recursively, utilising just the samples that actually reach the branch. If all samples at a node have the same categorization at any moment, the tree's growth is halted [26][27]. Splitting criteria are used to determine which attribute is picked to be used for a split for a given set of samples.…”

Section: M5 Model Treementioning

confidence: 99%

Modelling dissolved oxygen and biochemical oxygen demand using data-driven techniques

Sahu¹,

Londhe²,

Kulkarni³

2022

Environmental Engineering Research

View full text Add to dashboard Cite

Precise quantification of Biochemical oxygen demand (BOD) and Dissolved oxygen (DO) are critically important for water quality assessment as well as for development of various management policies. To calculate BOD and DO for any water sample, standard technique Winkler-Azide method is used which is cumbersome and prone to measurement error. Therefore, there is a need to device alternate Data Driven Technique (DDT). In the present study, three different DDT: Artificial Neural Network (ANN), Multi Gene Genetic Programming (MG-GP) and M5 Model Tree (M5T) have been used for DO as well as BOD prediction for 3 separate stretches of Mula-Mutha River situated in Pune, India. Additionally, attempt has been made to predict BOD using modelled DO; which shows possibility of using modelled parameter in development of another model. Performance of the models was assessed through, root mean square error (RMSE); mean absolute relative error (MARE) and coefficient of correlation (R). Results based on 3 stations indicate that ANN and MGGP both outperformed with R above 0.85 and RMSE below 1 mg/L for 2 stations out of 3. MGGP and M5T can grasp the influence parameter which can be seen from the input frequency distribution in MGGP and coefficient of input parameters in M5T.

show abstract

Model trees and sequential minimal optimization based support vector machine models for estimating minimum surface roughness value

Cited by 20 publications

References 15 publications

[Retracted] Green Machining Characteristics Study of Al‐6063 in CNC Milling Using Taguchi Method and Grey Relational Analysis

[Retracted] Green Machining Characteristics Study of Al‐6063 in CNC Milling Using Taguchi Method and Grey Relational Analysis

A novel and prediction approach of sheep wool reinforced polyester composites: Surface qualities and hybrid modeling

Modelling dissolved oxygen and biochemical oxygen demand using data-driven techniques

Contact Info

Product

Resources

About