The predicted surface roughness has been performed using artificial neural network code in MATLAB. Shows the predicted surface roughness using this method. The input data for three independent variables spindle speed, feed rate, and depth of cut while actual surface roughness acted as target. The network propagates the input pattern from layer to layer until the output is generated. Then the result output will be compared with the target which is actual surface roughness in this study. The error is calculated and propagated back through network. Then, the weight will be changed and the same process repeated until the smallest error is achieved. The plot of predicted surface roughness (output) against the actual surface roughness (target) in Figure 3 below shown that both are correlated. This is because the predicted surface roughness is approaching towards the actual surface roughness with the coefficient of termination, R is 0.77739

Fig4Data Mining Application_decrypted

Result Comparisons

Artificial neural network is a feasible technique and has been used quite often in recent researches in engineering field. The adaptation of this technique provides a brand new perspective in this field and in surface roughness prediction to be precise. Back-propagation neural network had been implemented to achieve the goal which is to minimize the error during surface roughness prediction with respect to decision trees technique as shown in figure. The decision tree and neural network are the methods to get the prediction of future data from present set of data. The difference in the two is in decision tree gives the prediction in the range of values but neural network give a specified value. If the range of output is of short type then to some extent the result is accurate but is the range of output is large then for much accuracy neural network method is adopted to get the prediction of future data. So it is totally based upon the user that the time restriction is there or accuracy is required. If accuracy is required then the user has to adopt neural network and if time restriction is there decision tree can be adopted.

Fig5Data Mining Application_decrypted

The result of the prediction is favorable with 6.42% average percentage of error, meaning that neural network is capable to predict the surface roughness up to 93.58% accurate. As a conclusion, artificial neural network provided better accuracy to predict surface roughness in CNC milling process.

Representative APR 391%

Let's say you want to borrow $100 for two week. Lender can charge you $15 for borrowing $100 for two weeks. You will need to return $115 to the lender at the end of 2 weeks. The cost of the $100 loan is a $15 finance charge and an annual percentage rate of 391 percent. If you decide to roll over the loan for another two weeks, lender can charge you another $15. If you roll-over the loan three times, the finance charge would climb to $60 to borrow the $100.

Implications of Non-payment: Some lenders in our network may automatically roll over your existing loan for another two weeks if you don't pay back the loan on time. Fees for renewing the loan range from lender to lender. Most of the time these fees equal the fees you paid to get the initial payday loan. We ask lenders in our network to follow legal and ethical collection practices set by industry associations and government agencies. Non-payment of a payday loan might negatively effect your credit history.

Calculate APR