Controlling the in-service welding parameters for T-shape steel pipes using neural network

Vakili‐Tahami, Farid; Majnoun, Peyman; Ziaei-Asl, Ali

doi:10.1016/j.ijpvp.2019.103937

Cited by 18 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The appropriate structure of the neural network to predict mechanical properties was chosen by trial and error. In this study, the design of the neural network was composed of six (6) neurons in the input layer, ten (10) neurons in the first occult layer, nine (9) neurons in the second hidden layer and four (4) neurons for the output layer.…”

Section: Artificial Neural Network For Predicting Mechanical Propertiesmentioning

confidence: 99%

“…A mathematical model developed using second-order regression equations could be used satisfactorily to predict the tensile properties of AISI 1018 mild steel welds using the MIG welding process [9].The effect of different parameters on the welding condition and the burn-through risk for a T-shape steel joint during the in-service welding are analyzed using experimental tests and numerical analyses. The experimental data, together with a large set of results produced by the numerical simulation, are used to compose a user-friendly computer code based on the neural network algorithms to predict the temperature levels in the critical points for different welding conditions [10]. The welding strength of mild steel weld predicted by the developed ANN model was accurate from multiple regression analysis using a pulsed metal inert gas welding process [11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Mechanical Properties as a Function of Welding Variables in Robotic Gas Metal Arc Welding of Duplex Stainless Steels SAF 2205 Welds Through Artificial Neural Networks

Payares-Asprino

2021

Advances in Materials Science

View full text Add to dashboard Cite

Dual-phase duplex stainless steel (DSS) has shown outstanding strength. Joining DSS alloy is challenging due to the formation of embrittling precipitates and metallurgical changes during the welding process. Generally, the quality of a weld joint is strongly influenced by the welding conditions. Mathematical models were developed to achieve high-quality welds and predict the ideal bead geometry to achieve optimal mechanical properties. Artificial neural networks are computational models used to address complex nonlinear relationships between input and output variables. It is one of the powerful modeling techniques, based on a statistical approach, presently practiced in engineering for complex relationships that are difficult to explain with physical models. For this study robotic GMAW welding process manufactured the duplex stainless steel welds at different welding conditions. Two tensile specimens were manufactured from each welded plate, resulting in 14 tensile specimens. This research focuses on predicting the yield strength, tensile stress, elongation, and fracture location of duplex stainless steel SAF 2205 welds using back-propagation neural networks. The predicted values of tensile strength were later on compared with experimental values obtained through the tensile test. The results indicate <2% of error between observed and predicted values of mechanical properties when using the neural network model. In addition, it was observed that the tensile strength values of the welds were higher than the base metal and that this increased when increasing the arc current. The welds’ yield strength and elongation values are lower than the base metal by 6%, ~ 9.75%, respectively. The yield strength and elongation decrease might be due to microstructural changes when arc energy increases during the welding.

show abstract

Section: Artificial Neural Network For Predicting Mechanical Propertiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Prediction of Mechanical Properties as a Function of Welding Variables in Robotic Gas Metal Arc Welding of Duplex Stainless Steels SAF 2205 Welds Through Artificial Neural Networks

Payares-Asprino

2021

Advances in Materials Science

View full text Add to dashboard Cite

show abstract

“…The inter-critical temperature range, between A1 and A3, plays a significant role in maintaining temperature control during the last TMCP processes [4]. In-service welding repair is important to ensure the safe and reliable operation of natural gas pipelines [5][6][7][8]. During the welding process of the reinforced pipe, the natural gas in the pipe keeps flowing, and the high gas pressure is maintained, resulting in the completion of the welding process under a strong cooling condition.…”

Section: Introductionmentioning

confidence: 99%

Study on Distribution of Heat Treatment Temperature Field of Long distance Oil and Gas Pipeline with High Steel Grade

Liu

Yang

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In-service welding repair is important to ensure natural gas pipelines’ safe and reliable operation. The temperature distribution in the welding heat treatment process directly affects the pipeline’s bearing capacity and local stress distribution. This study studied the temperature distribution of a high steel pipeline generated by the heat treatment process for the long-term transportation of oil and gas was studied experimentally. The medium frequency induction heating method is applied to heat the tube body by winding a heating belt on the outer wall of the steel pipe to simulate pre-welding and post-welding heat treatment. At the same time, a thermocouple is used to record the temperature change of each position during the whole heating process to obtain data. Through numerical analysis and fitting, the distribution law of the temperature field in the heat treatment process of steel pipe is established to guide the field heating temperature control.

show abstract

“…The traditional T-shaped tube formed by the welding process significantly damages the mechanical performance of the tube, and the welding process can increase the weight of the Tshaped tube [4]. With the development of lightweight manufacturing technology, thin-walled hollow structural parts formed by the integrated forming method have been used extensively in the aerospace and automobile industries [5].…”

Section: Introductionmentioning

confidence: 99%

Investigation on a new compound-forming method of flanging and bulging with rubber flexible die

Wei¹,

Han

Liu³

et al. 2023

Preprint

View full text Add to dashboard Cite

The T-shaped tube is a common component in aviation pipeline systems and has broad application prospects. However, the severe wall thickness thinning has been the bottleneck problem restricting the application of T-shaped tubes. In order to avoid rupture due to excessive thinning and improve the forming quality, a new rubber compound-forming method combined with the flanging and bulging of the T-shaped tube using a prefabricated hole is proposed. The optimization model of the prefabricated hole is established based on the geometric analysis method and the incremental finite element method. The optimal prefabricated hole is achieved through two iteration optimizations. The experiments for the compound-forming method are carried out to reveal the forming height and the wall thickness distribution mechanism. Both the simulation and experiment results are in good agreement, and the experimental results with the optimal prefabricated are that the maximum thickening rate is 38% and the maximum thinning rate is 14.67% which are satisfied with the requirements of practical production. Compared with the traditional rubber compound bulging forming with the same process parameters, the rupture occurs before the axial feed reaches the ideal feed. The new compound forming method using the prefabricated hole could effectively avoid fracture on the branch’s top. The comparison results are further verified to be the correctness of the prefabricated hole optimization model and the effectiveness of the new compound forming method.

show abstract

Controlling the in-service welding parameters for T-shape steel pipes using neural network

Cited by 18 publications

References 22 publications

Prediction of Mechanical Properties as a Function of Welding Variables in Robotic Gas Metal Arc Welding of Duplex Stainless Steels SAF 2205 Welds Through Artificial Neural Networks

Prediction of Mechanical Properties as a Function of Welding Variables in Robotic Gas Metal Arc Welding of Duplex Stainless Steels SAF 2205 Welds Through Artificial Neural Networks

Study on Distribution of Heat Treatment Temperature Field of Long distance Oil and Gas Pipeline with High Steel Grade

Investigation on a new compound-forming method of flanging and bulging with rubber flexible die

Contact Info

Product

Resources

About