Threefold versus fivefold cross-validation and individual versus average data in predictive regression modelling of machining experimental data

Feng, Cheng; Yu, Zhi-Guang; Emanuel, Joseph T.; Li, P. G.; Shao, Xinyu; Wang, Z. H.

doi:10.1080/09511920701530943

Cited by 8 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3 The strategy for determining the optimum conditions To achieve our objective, it is necessary to build an artificial neural network-based model of turning based on experimental data [32][33][34] and solve the optimization problem in a multi-criteria environment using the Edgeworth and Pareto method [28][29][30][31][35][36][37][38].…”

Section: Methodsmentioning

confidence: 99%

Minimization of turning time for high-strength steel with a given surface roughness using the Edgeworth–Pareto optimization method

Abbas

Pimenov

Ердаков

et al. 2017

Int J Adv Manuf Technol

View full text Add to dashboard Cite

High-strength steels are used in various civilian and military products. The initial cost of the raw materials for these products is very high. The surface roughness of these products is extremely important during the finishing pass to be accepted during the final inspection. The surface roughness should conform to the required values stated on the design drawing. The paper presents the results of experiments in turning of highstrength steel featuring three factors-cutting speed V, feed rate f, and depth of cut t-on five levels (125 specimens). These were divided into 25 groups. Each of the five groups was subjected to one common machining speed. Each group was machined using five levels of cutting depth. Each depth was processed using five levels of feed rate. Tessa was used for examination of surface roughness. There is little modern research on machining high-strength steel. The high cost of this material compels us to look for the optimum turning conditions to provide for the specified roughness of surface Ra and the minimum machining time of unit volume T m . As a result of our study, an artificial neural network was designed in Matlab on the basis of the MLP 3-10-1 multilayer perceptron that allows us to predict Ra of the workpiece with ±2.14% accuracy within the range of the experimental cutting speed, depth of cut, and feed rate values. For the first time, a Pareto frontier was obtained for Ra and T m of the finished workpiece from high-strength steel using the artificial neural network model that was later used to determine the optimum cutting conditions. It is possible to integrate the suggested optimization algorithms into computer-aided manufacturing using Matlab.

show abstract

Section: Methodsmentioning

confidence: 99%

Minimization of turning time for high-strength steel with a given surface roughness using the Edgeworth–Pareto optimization method

Abbas

Pimenov

Ердаков

et al. 2017

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

“…ANN milling model based on experimental data [34][35][36] was built to achieve our objective of solving the optimization problem in a multi-objective setting using both Edgeworth and the Pareto frontiers [31][32][33][37][38][39].…”

Section: Strategy For Determining the Optimal Conditionsmentioning

confidence: 99%

Optimization of cutting conditions using artificial neural networks and the Edgeworth-Pareto method for CNC face-milling operations on high-strength grade-H steel

Abbas

Pimenov

Ердаков

et al. 2019

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Computer Numerical Control (CNC) face milling is commonly used to manufacture products from high-strength grade-H steel in both the automotive and the construction industry. The various milling operations for these components have key performance indicators: accuracy, surface roughness (Ra), and machining time for removal of a unit volume min/cm 3 (T m). The specified surface roughness values for machining each component is achieved based on the prototype specifications. However, poor adherence to specifications can result in the rejection of the machined parts, implying extra production costs and raw material wastage. An algorithm using an artificial neural network (ANN) with the Edgeworth-Pareto method is presented in this paper to optimize the cutting parameter in CNC face-milling operations. The set of parameters are adjusted to improve surface roughness and minimal unit-volume material removal rates, thereby reducing production costs and improving accuracy. An ANN algorithm is designed in Matlab, based on a 3-10-1 Multi-Layer Perceptron (MLP), which predicts the Ra of the workpiece surface to an accuracy of ± 5.78% within the range of the experimental angular spindle speed, feed rate, and cutting depth. An unprecedented Pareto frontier for Ra and T m was obtained for the finished grade-H steel workpiece using an ANN algorithm that was then used to determine optimized cutting conditions. Depending on the production objective, one or the other of two sets of optimum machining conditions can be used: the first one sets a minimum cutting power, while the other sets a maximum T m with a slight increase (under 5%) in milling costs.

show abstract

“…There are five iterations, and each section is used as the testing set once. We chose 5-fold validation to reduce the computation time of our results as compared to 10-fold validation; recent studies have shown no statistical difference in the results from reduced iterations in validation [8].…”

Section: B Research Questionsmentioning

confidence: 99%

“…For the SourceForge repository, we built a tool based on PMD 8 to extract the API packages and classes directly from the applications' source code. PMD also allowed us to extract project terms from the source code.…”

Section: ) Selection Of Attributesmentioning

confidence: 99%

Categorizing software applications for maintenance

McMillan

Linares‐Vásquez

Poshyvanyk

et al. 2011

2011 27th IEEE International Conference on Software Maintenance (ICSM)

View full text Add to dashboard Cite

Threefold versus fivefold cross-validation and individual versus average data in predictive regression modelling of machining experimental data

Cited by 8 publications

References 21 publications

Minimization of turning time for high-strength steel with a given surface roughness using the Edgeworth–Pareto optimization method

Minimization of turning time for high-strength steel with a given surface roughness using the Edgeworth–Pareto optimization method

Optimization of cutting conditions using artificial neural networks and the Edgeworth-Pareto method for CNC face-milling operations on high-strength grade-H steel

Categorizing software applications for maintenance

Contact Info

Product

Resources

About