Kamal Pal

Monitoring of Weld Penetration Using Arc Acoustics

The weld penetration monitoring is a challenging work in modern automated manufacturing industries. The weld quality can be improved with higher depth of penetration and less weld pool area. In this work, various pulse parameters have been varied to investigate their influence on weld penetration in pulsed metal inert gas (P-MIG) welding. The primary objective was to improve the depth of penetration adjusting the pulse parameters. The sound sensor and an infrared pyrometer were used along with arc sensors to properly monitor the depth of weld penetration. Finally, an attempt has also been made to correlate the time domain statistical features of each sensor with weld bead characteristics.

Soft computing methods used for the modelling and optimisation of Gas Metal Arc Welding: a review

The quality of a weld primarily depends on the process parameters in any welding process. The welding parameters influence the weld bead geometry and weld microstructure, which is related to mechanical properties. It indicates the necessity to establish the relationship between process variables and weld quality characteristics. The Gas Metal Arc Welding (GMAW) processes are highly non-linear and coupled multivariable systems. It suggests the need for an intelligent system to evaluate the process and to determine the best adjustment. The soft computing techniques provide an alternative method for learning, predictive modelling, optimisation and control of weld quality without any mathematical model. This review illustrates the importance of soft computing tools for prediction, optimisation and control of GMAW processes.

Multi-sensor based prediction of metal deposition in pulsed gas metal arc welding using various soft computing models

The deposition efficiency is an important economic factor in welding. A multitude of uncontrollable factors influence the metal deposition, which indicates the necessity of robust sensors with an intelligent system to monitor the process in real time. This paper attempts to develop artificial neural network (ANN) models to predict the weld deposition efficiency using the welding sound signal along with the welding current and the arc voltage signals in pulsed metal inert gas welding. Three different implementations of ANNs have been used: gradient descent error back-propagation, neuro-genetic algorithm and neuro-differential evolution. The results indicate that the sound signal kurtosis, used in conjunction with the current and the voltage signals, is a reliable indicator of deposition efficiency.

Multi-objective optimisation of EDM process using hybrid Taguchi-based methodologies for Ti-6Al-4V alloy

Advanced hard-to-machine materials are difficult to manufacture. This work explores the application of electrical discharge machining (EDM) of Ti-6Al-4V alloy for different pulse parameters. Machining performance is evaluated by material removal rate (MRR), tool wear rate (TWR) and surface roughness (SR). For the experiment, orthogonal array have been found using Taguchi methodology. The optimum parametric settings obtained by grey relational analysis (GRA)-based Taguchi method which was compared with hybrid grey relational-principal component analysis (PCA)-based Taguchi. It was found that GRA-based PCA optimisation methodology results more feasible parametric setting which has also been confirmed by the validation experiments. The rectangular pulse current shape and its duration have found to be significant. The optimum value of process variables were pulse duration of 5µs, duty factor of 11%, peak current of 30 A and gap voltage of 9 V to achieve maximum MRR and lower TWR with better surface finish. [Received 10 April 2015; Revised 16 May 2016; Accepted 17 May 2016]

Optimisation of weld deposition efficiency in pulsed MIG welding using hybrid neuro-based techniques

The weld quality depends primarily on the degree of arc stability and the bead characteristics in gas metal arc welding. The weld deposition has to be enhanced to make the process economically feasible. This article addresses modelling and optimisation of deposition efficiency in highly non-linear pulsed metal inert gas welding. The design of experiments was performed using central composite response surface methodology for the model development. The back propagation neural network technique was found to be better than the response surface regression model. Two global optimisation techniques, namely, genetic algorithm and differential evolution, were then applied to maximise the deposition efficiency. The capability to identify the hidden optimum solutions using differential evolution technique was found to be better than genetic algorithm.

Sensor based prediction of weld microstructure in pulsed MIG welding

Pulsed gas metal arc welding (P-GMAW) is often used to improve weld quality as well as productivity in todays manufacturing industries. Current pulsing is used in grain refinement of weld fusion zone and uniform microstructure with less heat input. In this work, weld microstructure and its hardness have been studied on low carbon steel in pulsed metal inert gas welding using bead on plate method. The primary objective was to compare the grain morphology and different phase percentage to hardness variation in various welding zones, especially in the interface of weld fusion zone and heat affected zone (HAZ), affected by pulse parameters. Various sensors have been used to monitor the weld microstructural features. The weld peak temperature along with arc heat input were found to be strongly correlated with weld ferrite content, grain size and its hardness. The arc sound is also an essential indicator of weld microstructure affected by arc stability.