Modelling and analysis of delta ferrite content in claddings deposited by flux cored arc welding using a neural network

2009 ◽  
Vol 223 (4) ◽  
pp. 779-787 ◽  
Author(s):  
P K Palani ◽  
N Murugan
Keyword(s):  
Neural Network ◽  
Arc Welding ◽  
Welding Process ◽  
Welding Current ◽  
Ferrite Content ◽  
Delta Ferrite ◽  
Novel Approach ◽  
Flux Cored Arc Welding ◽  
Minimum Number ◽  
Arc Welding Process

Measurement of delta ferrite in cladding gives important insight into the future mechanical and corrosion resistant behaviour of the cladded structures. The amount of delta ferrite formed during cladding is influenced by process parameters such as welding speed, welding current, and nozzle-to-plate distance. Therefore, it is essential to predict the effect of these parameters on the formation of delta ferrite. This article discusses the development of an artificial neural network model to predict the delta ferrite content in austenitic stainless-steel claddings deposited by the flux cored arc welding process. A novel approach of using the design of experiments to collect data to train the network has been adopted in this investigation. The study revealed that the delta ferrite content can be predicted more accurately using the neural networks with a minimum number of experiments. The results also indicated that welding current and speed have a significant influence on the amount of ferrite and the interaction effects of these parameters play a major role in determining ferrite in the claddings.

scholarly journals Real-Time Weld Gap Monitoring and Quality Control Algorithm during Weaving Flux-Cored Arc Welding Using Deep Learning

Metals ◽  
2021 ◽  
Vol 11 (7) ◽  
pp. 1135
Author(s):  
Chengnan Jin ◽  
Sehun Rhee
Keyword(s):  
Arc Welding ◽  
Control Algorithm ◽  
Weld Seam ◽  
Welding Process ◽  
Welding Current ◽  
Forming Process ◽  
Flux Cored Arc Welding ◽  
Arc Welding Process ◽  
Shell Forming ◽  
The Time Domain

In the flux-cored arc welding process, which is most widely used in shipbuilding, a constant external weld bead shape is an important factor in determining proper weld quality; however, the size of the weld gap is generally not constant, owing to errors generated during the shell forming process; moreover, a constant external bead shape for the welding joint is difficult to obtain when the weld gap changes. Therefore, this paper presents a method for monitoring the weld gap and controlling the weld deposition rate based on a deep neural network (DNN) for the automation of the hull block welding process. Welding experiments were performed with a welding robot synchronized with the welding machine, and the welding quality was classified according to the experimental results. Welding current and voltage signals, as the robot passed through the weld seam, were measured using a trigger device and analyzed in the time domain and frequency domain, respectively. From the analyzed data, 24 feature variables were extracted and used as input for the proposed DNN model. Consequently, the offline and online performance verification results for new experimental data using the proposed DNN model were 93% and 85%, respectively.

scholarly journals Multivariate Stochastic Optimization Approach Applied in a Flux-Cored Arc Welding Process

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 61267-61276 ◽  
Author(s):  
Alexandre F. Torres ◽  
Franco B. Rocha ◽  
Fabricio A. Almeida ◽  
Jose H. F. Gomes ◽  
Anderson P. Paiva ◽  
...  
Keyword(s):  
Stochastic Optimization ◽  
Arc Welding ◽  
Welding Process ◽  
Optimization Approach ◽  
Flux Cored Arc Welding ◽  
Arc Welding Process

A study on quality of weld in flux cored arc welding process

2014 ◽  
Vol 4 (1/2) ◽  
pp. 81
Author(s):  
Binoy K. Biswas ◽  
Asish Bandyopadhyay ◽  
Pradip K. Pal
Keyword(s):  
Arc Welding ◽  
Welding Process ◽  
Flux Cored Arc Welding ◽  
Arc Welding Process

A Neural Network Model for Predicting Two Observable Parameters of the Welded Cross Section in Case of Robotic Gas Tungsten Arc Welding Process

2012 ◽  
Vol 162 ◽  
pp. 531-536
Author(s):  
Gabriel Gorghiu ◽  
Paul Ciprian Patic ◽  
Dorin Cârstoiu
Keyword(s):  
Neural Network ◽  
Arc Welding ◽  
Welding Process ◽  
Gas Tungsten Arc Welding ◽  
Gas Tungsten Arc ◽  
Proposed Model ◽  
Input Layer ◽  
Gas Tungsten ◽  
Arc Welding Process ◽  
Observable Parameter

The paper presents a model of using the artificial neural networks when determining the relations of dependency between the observable parameters and the controllable ones in the case of RoboticGas Tungsten Arc Welding. The proposed model is based on the direct observation of welded joints, emphasizing on the process variables which have been arranged in the nodes of a neural network. The design of the network intended to achieve an architecture that contains four nodes in the input layer (all of them being controllable parameters) and two nodes in the output layer (one for each observable parameter).

Optimization of Flux Cored Arc Welding Process Parameter Using Genetic and Memetic Algorithms

2013 ◽  
Vol 13 (4) ◽  
pp. 239-250 ◽  
Author(s):  
T. Kannan ◽  
N. Murugan ◽  
B. N. Sreeharan
Keyword(s):  
Arc Welding ◽  
Welding Process ◽  
Memetic Algorithms ◽  
Optimization Techniques ◽  
Low Carbon ◽  
Robotic Welding ◽  
Bead Width ◽  
Flux Cored Arc Welding ◽  
Arc Welding Process ◽  
Welding Processes

AbstractMost of the manufacturing enterprises indulge in the bonding of metals during the production process. This makes welding one of the most important processes in industries. Subsequently, due to the high usage of welding process, industrial engineers desire to optimize the parameters concerned to achieve the desired weld bead characteristics. This paper focuses on optimization of flux cored arc welding process parameters, which are used for deposition of duplex stainless steel on low carbon structural steel plates. Experiments were conducted based on central composite rotatable design and mathematical models were developed using multiple regression method. Further, optimization with objectives as minimizing percentage dilution, maximizing height of reinforcement and bead width was carried out using genetic algorithm and memetic algorithm. This problem was formulated as a multi objective, multivariable and non-linear programming problem. The algorithms were implemented using basic functions of C language making it highly reliable, adoptable, very user friendly and extendable to other welding processes such as GMAW, GTAW, robotic welding, etc. The adopted optimization techniques were further compared based on various computational factors.

Sign in / Sign up

Export Citation Format

Share Document