Milling of Graphene Reinforced Ti6Al4V Nanocomposites: An Artificial Intelligence Based Industry 4.0 Approach

Abstract

The studies about the effect of the graphene reinforcement ratio and machining parameters to improve the machining performance of Ti6Al4V alloy are still rare and incomplete to meet the Industry 4.0 manufacturing criteria. In this study, a hybrid adaptive neuro-fuzzy inference system (ANFIS) with a multi-objective particle swarm optimization method is developed to obtain the optimal combination of milling parameters and reinforcement ratio that lead to minimize the feed force, depth force, and surface roughness. For achieving this, Ti6Al4V matrix nanocomposites reinforced with 0 wt.%, 0.6 wt.%, and 1.2 wt.% graphene nanoplatelets (GNPs) are produced. Afterward, a full factorial approach was used to design experiments to investigate the effect of cutting speed, feed rate, and graphene nanoplatelets ratio on machining behaviour. After that, artificial intelligence based on ANFIS is used to develop prediction models as the fitness function of the multi-objective particle swarm optimization method. The experimental results showed that the developed models can obtain an accurate estimation of depth force, feed force, and surface roughness with a mean absolute percentage error of 3.87%, 8.56%, and 2.21%, respectively, as compared with experimentally measured outputs. In addition, the developed artificial intelligence models showed 361.24%, 35.05%, and 276.47% less errors for depth force, feed force, and surface roughness, respectively, as compared with the traditional mathematical models. The multi-objective optimization results from the new approach indicated that a cutting speed of 62 m/min, feed rate of 139 mm/min, and GNPs reinforcement ratio of 1.145 wt.% lead to the improved machining characteristics of GNPs reinforced Ti6Al4V matrix nanocomposites. Henceforth, the hybrid method as a novel artificial intelligent method can be used for optimizing the machining processes with complex relationships between the output responses.

A systematic literature review and taxonomy proposition of machine learning techniques in smart manufacturing

“…Machining processes were notoriously studied in the Machinery subsector, as demonstra-ted by Nasr et al (2020) -by means of a system developed to obtain the optimal combination of machining parameters and the reinforcement ratio that led to minimising the feed force, depth force, and surface roughness in a machining process of graphene nanoplatelets.…”

Prediction of Mechanical Properties for Carbon fiber/PLA Composite Lattice Structures Using Mathematical and ANFIS Models

“…Figure 4 shows an illustration of the ANFIS structure with two inputs, three membership functions (MFs), and one output. The layer explanation is described as follows [ 38 , 39 , 40 ]:…”

“…Figure 4 shows an illustration of the ANFIS structure with two inputs, three membership functions (MFs), and one output. The layer explanation is described as follows [38][39][40]: Training Data Layer 1: input membership functions (MFs). In this layer, also called the fuzzification layer, the fuzzy membership value of each input, i.e., µA i (x) and µB i (y) is calculated by a proper membership function, e.g., trapezoidal, Gaussian, and triangular.…”

Effect of ZrB2 Particles on Machining Parameters of AA7475 Alloy-Based Composites by Optimization Technique

“…Aeronautics and other industries have greatly benefted from particle-reinforced metal matrix composites (PRMMC), a new family of materials with improved features such as a greater ratio of mass to strength, a greater elastic modulus, and better resistance to wear and tear [1][2][3]. Tere are two ways to make PRMMCs, ex situ and in situ.…”