Abstract
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 high-strength 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.