In the present work, a new hybrid approach combining particle swarm optimization (PSO) algorithm with recurrent dynamic neural network (RDNN), which is described as PSO-RDNN algorithm, is proposed for multi-performance optimization of machining parameters in finish turning of hardened AISI D2. The suggested optimization problem is solved using the weighted sum technique. Process parameters including cutting speed and feed rate are optimized for minimizing operation cost, maximizing tool life, and producing parts with acceptable surface roughness. Based on experimental results, two neural network models were developed for predicting tool flank wear and surface roughness during the machining process. Based on trained neural networks and structured hybrid algorithm, optimum cutting parameters were obtained. The coefficient of determination for trained neural networks was calculated as R2 = 0.9893 and R2 = 0.9879 for predicted flank wear and surface roughness, respectively, which proves the efficiency of trained neural models in real industrial applications. Furthermore, the offered methodology returns a Pareto optimality graph, which represents optimized cutting variables for several various cutting conditions.

This paper proposes an intelligent model-based optimization methodology for optimizing the production cost and material removal rate subjected to surface quality constraint in turning operation of hardened AISI D2. Unlike traditional approaches, this paper deals with finding optimum cutting parameters considering the real condition of the cutting tool. Tool flank wear is predicted by the model obtained using genetic programming. On the basis of the predicted flank wear value, the surface roughness of work piece is estimated by neural networks. Applying the particle swarm optimization algorithm, the optimum machining parameters are determined. The simulation and experimental results show that machining with proposed intelligent optimization methodology has higher efficiency than conventional techniques with constant optimized cutting parameters.

The aim of the present investigation is to identify the wear mechanisms of multilayer coated carbide tool under different machining conditions during turning of hardened AISI 4340 steel. The chemical vapor deposited multilayer coated (TiN/MT TiC,N/Al2O3) carbide tool was used. The worn surfaces of the cutting tools were examined under digital optical microscope, scanning electron microscope, and elemental analysis. The investigation results showed a strong correlation between the cutting conditions and tool wear. The cutting speed and feed rate ensure the dominant effects on the tool wear followed by the depth of cut and also the progress of tool wear were verified under different intervals of time. The flank and rake faces of the cutting tool were severely gouged by the hard particles of workpiece material exhibited abrasive wear phenomenon. Intermittently, chipping at cutting edge, notching and catastrophic failure modes were observed in continuous machining.

Hard turning, i.e., turning hardened steels, may produce the unique “hook” shaped residual stress (RS) profile characterized by surface compressive RS and subsurface maximum compressive RS. However, the formation mechanism of the unique RS profile is not yet known. In this study, a novel hybrid finite element modeling approach based on thermal-mechanical coupling and internal state variable plasticity model has been developed to predict the unique RS profile patterns by hard turning AISI 52100 steel (62 HRc). The most important controlling factor for the unique characteristics of residual stress profiles has been identified. The transition of maximum residual stress at the surface to the subsurface has been recovered by controlling the plowed depth. The predicted characteristics of residual stress profiles favorably agree with the measured ones. In addition, friction coefficient only affects the magnitude of surface residual stress but not the basic shape of residual stress profiles.

Cette étude est concernée par le tournage dur de l'acier de roulement 100Cr6 en utilisant un outil en nitrure de bore cubique (CBN7020). Des essais de laboratoire ont été planifiés pour investiguer l'effet de la vitesse de coupe sur les différentes formes de l'usure de l'outil. Ensuite, une autre série d'expériences a été dédiée à l'étude de la rugosité obtenue en fonction des paramètres de coupe. La relation entre la rugosité de la surface usinée et l'usure en dépouille correspondante de l'outil a été mise sous la forme d'équations puissance pour décrire l'évolution de la rugosité à différentes vitesses de coupe allant jusqu'à 350 m.min-1. La comparaison des rugosités (Ra et Rt) en fonction de l'avance en tant que paramètre d'influence prépondérante a montré que le modèle à une variable (f) décrit d'une manière excellente les résultats expérimentaux alors que le modèle général à trois variables (Vc, f, ap) reste satisfaisant et très bien apprécié par le coefficient de détermination. Pour la rugosité moyenne, le modèle théorique surestime les valeurs de Ra avec une divergence notable à 0,2 mm.tr-1 alors que la rugosité totale est sous-estimée aux faibles valeurs de l'avance, ce qui donne lieu à des prédictions théoriques en deçà des attentes et conforte expérimentalement les modèles sous forme puissance proposés. Bien que la quantité de chaleur dégagée soit importante au vu des températures mesurées sur le copeau, la surface usinée n'a pas été thermiquement affectée.