A hybrid particle swarm optimization and recurrent dynamic neural network for multi-performance optimization of hard turning operation

Abstract

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.

Designing of a PSO-Based Adaptive SMC With a Multilevel Inverter for MPPT of PV Systems Under Rapidly Changing Weather Conditions

“…Thereafter, each particle's fitness or objective function value is evaluated while taking into account its current position. The velocity and position of each particle are iteratively modified, considering the particle's own best position and the best position obtained by any particle in the population [16].…”

An improved particle swarm fuzzy PID for adaptive control of temperature in CFRP induction heating

“…On the whole, the formula show that the particle swarm optimization algorithm has strong global retrieval ability in the early stage and strong local retrieval ability in the later stage. 16,17 However, it is easy to fall into the local optimal solution, and the convergence speed is slow in the later stage. Algorithm fusion will improve the particle swarm optimization algorithm’s capacity for global searches and hasten later convergence rates.…”

Hybrid machine learning approach for accurate and expeditious 3D scanning to enhance rapid prototyping reliability in orthotics using RSM-RSMOGA-MOGANN

“…However, the correlations between predicted and actual values were further validated experimentally, and the results were presented as the reduction in ST and percentage reduction in WPE. The potential of various AHML tools is evident in multiple research sectors for data training, validation and optimization; however, the impact of these tools is not adequately utilized in the context of 3D-SA (Deshwal et al, 2020; Khangwal et al, 2021; Pourmostaghimi et al, 2022). The integration of AHML tools with 3D-SA for optimizing various process parameters will enable the collection of highly précised scans in a time-efficient manner and enhance RP’s reliability for the fabrication of customized utility.…”