Modeling and prediction of WEDM performance parameters for Al/SiCp MMC using dimensional analysis and artificial neural network

Phate, Mangesh; Toney, Shraddha

doi:10.1016/j.jestch.2018.12.002

Cited by 64 publications

(31 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the equations ( 13), ( 14) and ( 15), the independent variable (X 2 , X 3 ,X 4 ) derivatives are those in (7), (8), and ( 9) respectively.…”

Section: (2)mentioning

confidence: 99%

“…Thoseare the reasons why this research tries to present another more standardized approach but based on the previous well-develop tools. To that, the method of dimensional analysis, widely used in other disciplines, such as physics [as an example see 2, 3,4] and at a lesser degree in economics, statistics, artificial neural network [see 5,6,7], and production systems [8], is used as a paradigm to produce a standard framework; it also admits generalized [9,10,11] and alternative [12] forms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dimensional Analysis and Implicit Function: An Application to Textual Data

Juárez

2020

Wseas Transactions on Business and Economics

View full text Add to dashboard Cite

The purpose of the research is to test the viability and usefulness of the dimensional analysis based on the Vaschy-Buckingham Π theorem and implicit function applied to textual data. The method uses hermeneuticalanalysis that allows identifying most frequent words, phrases, and the colocations of words, defining words as categories, and then, as fundamental and derived variables; collocation textual analysis also provides the word links that create a conceptual structure to building the dimensional matrixes and equations by the Vaschy-Buckingham Π theorem. The Gauss-Jordan method gives a solution to the matrixes. Besides, the implicit function theorem allows creating relationships among the Π numbers and solving them by partial derivatives, gaining insights about the relevance of variables and their relationships. As an example, the model applies to the financial summary report about Isodiol International Inc. Reports Profitable Q4 Financial Statements, delivered by EMIS. Results showed the following relevant categories:1)Company Financial Performance,2)Company,3)Continued,4)Global,5)Expand,6)Footprint,7)Diversification,8)Costs,9)Bioactive,10 )Acquisitions,11)CBD,12)Anticipate,13)Traction,14).Additional. They were classified as fundamental and derived variables. All of them were considered derived variables, while the fundamental variables were:1)Expand, 2)Footprint,3)Diversification,4)Costs,5)Bioactive,6)Acquisitions,7)CBD,8)Anticipate,9)Traction,10). The application of the Vaschy-Buckingham Π theoremresulted in four Πnumbers, rearranged into an implicit function where the dependent variable was Company Financial Performance. The solution by partial derivatives resulted in identifying the category “Company Financial Performance” as well as “Traction” and “Additional” as core categories in the financial report; however, the other categories are also relevant. Conclusions point out the relevance of the analysis to textual data as an interphase between qualitative and quantitative data and also in helping to find relevant variables.

show abstract

“…In the equations ( 13), ( 14) and ( 15), the independent variable (X 2 , X 3 ,X 4 ) derivatives are those in (7), (8), and ( 9) respectively.…”

Section: (2)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Dimensional Analysis and Implicit Function: An Application to Textual Data

Juárez

2020

Wseas Transactions on Business and Economics

View full text Add to dashboard Cite

show abstract

“…The authors have considered the tool's wear rate, the quality of the finished product, and the chips' shape obtain during the machining. Phate and Toney (2019) have investigated the effect of W-EDM process parameters on the Al/SiC MMC. The approach of Buckingham's pi theorem (DA) and ANN has used for useful analysis.…”

Section: Introductionmentioning

confidence: 99%

Prediction and optimization of tool wear rate during electric discharge machining of Al/Cu/Ni alloy using adaptive neuro-fuzzy inference system

Phate¹,

Bendale²,

Toney³

et al. 2020

Heliyon

View full text Add to dashboard Cite

Aluminum (Al)-copper (Cu)-nickel (Ni) alloy is a versatile material with lightweight and excellent strength. It also possesses properties such as superior corrosion resistance, fatigue strength. These alloys are essential in sectors viz. automobile, aerospace, defense, aerospace, etc. In this research work, the authors have presented the prediction and analysis of tool wear rate (TWR). The impact of electrical discharge machining (EDM) on process parameters viz. input current (IP), pulse on time (TON), pulse off time (TOFF)/for Al/Cu/Ni alloy with the composition 91/4/5 and 87/8/5 (weight %) is analyzed. Taguchi's L 18 (2 1 *3 3) mixed plan is employed to plan the experimentation. A mathematical model develops to correlate these process parameters. A soft computing technique known as an adaptive neuro-fuzzy inference system (ANFIS) utilizes to predict TWR. Taguchi analysis reveals that input current is the most influencing parameter followed by pulse on time. TWR decreases with a decrease in the amount of Aluminium. It increases in the amount of copper in the alloy. TWR firstly decreases with an increase in pulse on time and then starts to grow after the median value of 25 micro-sec. The confirmation experiments have conducted using optimum process parameters to validate the obtained results. The experimental finding shows the superior capability of ANFIS to predict the TWR with acceptable accuracy. The optimized TWR obtained was 0.1238 mm 3 /min based on the optimal settings of input parameters.

show abstract

“…In [12], the authors propose an optimization model for the milling of aluminum hybrid MMC and the regression model helps to form the inputs of the MMC machinability. The authors of the study [13] propose a traditional artificial neural network (ANN) model to predict the performance parameters of an Al/SiCp MMC machining process and the prediction model exposes the efficient features of the process successfully. In [14], the authors present an ANN based prediction network to help the Al based MMC manufacturing process, analysis of the study cover the micro-hardness, tensile extension, yield strength, modulus, and tensile stress.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Predictive Model for Surface Roughness in Cylindrical Grinding of Al Based Metal Matrix Composite

Uçar¹,

Katı²

2020

European Journal of Technic

View full text Add to dashboard Cite

The Metal Matrix Composite (MMC) technology of today is a challenging topic with novel developments. MMC materials have a key role in space, automotive, naval, and aviation industries and supplies of the defense industry owing to their superior specifications. Hence, advancing the machining quality of these materials is an essential point. This work presents a machine learning based prediction model for the surface roughness of LM25/SiC/4p composite. The related dataset is linked to an MMC, which is machined with a cylindrical grinder, so the input parameters of the model are depth of cut, wheel velocity, feed, and velocity of the work piece. The proposed model is based on a state of the art machine-learning method called Gaussian Process Regression (GPR). Alongside its robust performance in the small datasets, GPR has the ability with its Bayesian approach basis in providing uncertainty evaluation on the predicted values. Parameter optimization is also applied to the proposed GPR model. For a better evaluation of the GPR, a support vector machine based prediction model is also tested. In addition to the data split test method, models are tested with a 5-fold cross-validation algorithm. The experimental results present that the proposed GPR model reaches an adequate accuracy in terms of R-square, root mean squared error, and mean absolute error criteria.

show abstract

Modeling and prediction of WEDM performance parameters for Al/SiCp MMC using dimensional analysis and artificial neural network

Cited by 64 publications

References 18 publications

Dimensional Analysis and Implicit Function: An Application to Textual Data

Dimensional Analysis and Implicit Function: An Application to Textual Data

Prediction and optimization of tool wear rate during electric discharge machining of Al/Cu/Ni alloy using adaptive neuro-fuzzy inference system

Machine Learning Based Predictive Model for Surface Roughness in Cylindrical Grinding of Al Based Metal Matrix Composite

Contact Info

Product

Resources

About