A study of wire tool surface topography and optimization of wire electro-spark machined UNS N06690 using the federated mode of RSM-ANN

Raj, Alex Noel Joseph; Misra, Joy Prakash; Khanduja, Dinesh; Upadhyay, Vikas

doi:10.1108/ijsi-09-2021-0101

Cited by 9 publications

(4 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The engineering example of high-pressure turbine rotor verifies that VSM can efficiently and accurately complete the multi-failure correlated probabilistic evaluation. Atul used response surface method and artificial neural network to optimize the process parameters in the nickel base superalloy processing and obtained the minimum wire wear value (Atul et al, 2022). Commonly used surrogate models include polynomial response surface models, neural network models and Kriging models (Zhu et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Robust optimization design method for structural reliability based on active-learning MPA-BP neural network

Dong

Sheng

Zhao

et al. 2023

IJSI

View full text Add to dashboard Cite

PurposeMechanical products usually require deterministic finite element analysis in the design phase to determine whether their structures meet the requirements. However, deterministic design ignores the influence of uncertainties in the design and manufacturing process of mechanical products, leading to the problem of a lack of design safety or excessive redundancy in the design. In order to improve the accuracy and rationality of the design results, a robust design method for structural reliability based on an active-learning marine predator algorithm (MPA)–backpropagation (BP) neural network is proposed.Design/methodology/approachThe MPA was used to obtain the optimal weights and thresholds of a BP neural network, and an active-learning function applicable to neural networks was proposed to efficiently improve the prediction performance of the BP neural network. On this basis, a robust optimization design method for mechanical product reliability based on the active-learning MPA-BP model was proposed. Random moving quadrilateral sampling was used to obtain the sample points required for training and testing of the neural network, and the reliability sensitivity corresponding to each sample point was calculated by subset simulated significant sampling (SSIS). The total mass of the mechanical product and the structural reliability sensitivity of the trained active-learning MPA-BP model output were taken as the optimization objectives, and a multi-objective reliability-robust optimization design model was constructed, which was solved by the second-generation non-dominated ranking genetic algorithm (NSGA-II). Then, the dominance function was used in the obtained Pareto solution set to make a dominance-seeking decision to obtain the final reliability-robust optimization design solution. The feasibility of the proposed method was verified by a reliability-robust optimization design example of the bogie frame.FindingsThe prediction error of the active-learning MPA-BP neural network was smaller than those of the particle swarm optimization (PSO)-BP, marine predator algorithm (MPA)-BP and genetic algorithm (GA)-BP neural networks under the same basic parameter settings of the algorithm, which indicated that the improvement strategy proposed in this paper improved the prediction accuracy of the BP neural network. To ensure the reliability of the bogie frame, the reliability sensitivity and total mass of the bogie frame were reduced, which not only realized the lightweight design of the bogie frame, but also improved the reliability and robustness of the bogie.Originality/valueThe MPA algorithm with a higher optimization efficiency was introduced to find the weights and thresholds of the BP neural network. A new active-learning function was proposed to improve the prediction accuracy of the MPA-BP neural network.

show abstract

Section: Introductionmentioning

confidence: 99%

Robust optimization design method for structural reliability based on active-learning MPA-BP neural network

Dong

Sheng

Zhao

et al. 2023

IJSI

View full text Add to dashboard Cite

show abstract

“…[8][9][10] A comparative graph of publications of different materials and superalloys processed by WESM is shown in Figure 1. Since the last decade, the application of the technique for processing superalloys was emerged to fulfill the industries' requirement of cost-effective and precise processing (11)(12)(13).…”

Section: Introductionmentioning

confidence: 99%

“…11 In 2016, Kumar et al concluded that trim cut generates smoother and fine surface texture as compared to rough cut irrespective of high discharge energy generated in rough-cut WEDM during the machining of Nimonic-90 using a metal powder mixed dielectric. 12 Ayesta et al also performed WESM of Inconel 718 and attempted to study the fatigue behavior of the processed part. 13 In 2017, Kumar et al used the desirability function to optimize multi-response variables during the machining of Nimonic 90.…”

Section: Introductionmentioning

confidence: 99%

Performance evaluation of electro-spark eroded high-volume fraction of Cr-Fe-Ni superalloy

Raj

Misra

Khanduja

2022

Proceedings of the Institution of Mechanical Engineers, Part C:

Self Cite

View full text Add to dashboard Cite

Current research aims to execute a viability study of electro-spark erosion technique to process Inconel 690, a high-volume fraction of Cr-Fe-Ni superalloy (∼32% Cr). The Box-Behnken design of response surface methodology with varying processing conditions is used to execute the experimental trails. Process performance is examined in terms of material removal rate and surface topography. The surface conditions of the processed surface are studied using scanning electron microscopy. The tool wear character and tribological behavior of the processed surface are also scrutinized to check the post-process consequences. The study explores the formation of oxide layers, craters, spherical droplets, and micro-cracks on the surface processed at Ton: 118 mu; Toff: 45 mu; Ip: 130 mu; Sv: 50 V ( parametrical settings for maximum material removal rate), and at Ton: 118 mu; Toff: 30 mu; Ip: 220 mu; Sv: 50 V ( parametrical settings for maximum surface roughness) attributing a deteriorating surface quality. The maximum material removal rate of 9.38 mm3/min and minimum surface roughness of 0.47 μm are achieved. A significant improvement of approximately 20 HV in micro-hardness is detected owing to the formation of a recast layer on the processed surface. Consequently, a noticeable improvement is observed in the wear resistance of the processed surface.

show abstract

“…The process can only be used to detect a single predefined or probable damage. Raj et al. (2022) groups' objective was to investigate the post processed wire tool surface using scanning electron microscopy and to determine the streamlined conditions of input process variables using multi-objective optimization approaches in order to obtain minimal wire wear values.…”

Section: Introductionmentioning

confidence: 99%

Surface roughness modeling using machine learning approaches for wire electro-spark machining of titanium alloy

Sharma

Misra

Singhal

2022

IJSI

Self Cite

View full text Add to dashboard Cite

PurposeIn the present study, wire electro-spark machining of Titanium alloy is performed with the machining parameter such as spark-on time, spark-off time, current and servo voltage. The purpose of this study is to model surface roughness using machine learning approach for input/controllable variable. Machined surface examined using scanning electron microscope (SEM) and XRD methods.Design/methodology/approachFull factorial approach has been used to design the experiments with varying machining parameters into three-level four factors. Obtained surface roughness was modeled using machine learning methods namely Gaussian process regression (GPR) and support vector machine (SVM) methods. These methods were compared for both training and testing data with a coefficient of correlation and root mean square error basis. Machined surface examined using scanned electron microscopy and XRD for surface quality produced and check migration of tool material to workpiece material.FindingsMachine learning algorithms has excellent scope for prediction quality response for the wire electric discharge machining (WEDM) process, resulting in saving of time and cost as it is difficult to find each time experimentally. It has been found that the proposed model with minimum computational time, provides better solution and avoids priority weightage calculation by decision-makers.Originality/valueThe proposed modeling provides better predication about surface produced while machining of Ti6Al7Nb using zinc-coated brass wire electrode during WEDM operation.

show abstract

A study of wire tool surface topography and optimization of wire electro-spark machined UNS N06690 using the federated mode of RSM-ANN

Cited by 9 publications

References 36 publications

Robust optimization design method for structural reliability based on active-learning MPA-BP neural network

Robust optimization design method for structural reliability based on active-learning MPA-BP neural network

Performance evaluation of electro-spark eroded high-volume fraction of Cr-Fe-Ni superalloy

Surface roughness modeling using machine learning approaches for wire electro-spark machining of titanium alloy

Contact Info

Product

Resources

About