Laser transmission welding is a highly accurate method for joining plastics, but its diverse process parameters require effective modeling for optimal results. Traditional artificial neural networks (ANNs) typically establish predictive models between laser processing parameters and welding strength, neglecting the crucial role of welding morphology in feature extraction, thus diminishing accuracy. To address this, we developed a serial ANN model based on statistically evident correlations, which predicts joint morphology and strength sequentially, resulting in a 47% improvement in predictive accuracy and a mean error of just 7.13%. This two-layered approach effectively reduces the stepwise propagation of errors in ANNs, allowing the first layer to provide a refined data representation for the second layer to predict welding strength. Furthermore, finding the optimal laser parameter set is time-consuming and computationally demanding with traditional ANN-based optimization methods. To address this, we integrated the Markov decision process with the serial ANN for the first time and proposed a novel varying step strategy for the model, enabling a balance of swift convergence and avoidance of suboptimal solutions. Notably, the Markov-serial ANN model attained enhanced optimization results using only 15.5% of the computational resources required by a standard parameter interval optimization methodology. Welding experiments verified the reliability of the Markov-serial ANN, achieving a mean error of 4.54% for welding strength.
Skip Nav Destination
Prediction and optimization of joint quality in laser transmission welding using serial artificial neural networks and their integration with Markov decision process
Article navigation
August 2024
Research Article|
July 09 2024
Prediction and optimization of joint quality in laser transmission welding using serial artificial neural networks and their integration with Markov decision process
Yuxuan Liu
;
Yuxuan Liu
a)
(Conceptualization, Formal analysis, Investigation, Methodology, Software, Validation, Writing – original draft, Writing – review & editing)
1
Department of Mechanical Engineering, The University of Tokyo
, Tokyo 1138656, Japan
Search for other works by this author on:
Fei Liu
;
Fei Liu
a)
(Data curation, Resources, Visualization)
2
School of Mechanical Engineering and Automation, Beihang University
, Beijing 100191, China
3
Ningbo Institute of Technology, Beihang University
, Ningbo 315832, China
Search for other works by this author on:
Wuxiang Zhang;
Wuxiang Zhang
(Funding acquisition, Writing – review & editing)
2
School of Mechanical Engineering and Automation, Beihang University
, Beijing 100191, China
3
Ningbo Institute of Technology, Beihang University
, Ningbo 315832, China
Search for other works by this author on:
Xilun Ding;
Xilun Ding
(Project administration)
2
School of Mechanical Engineering and Automation, Beihang University
, Beijing 100191, China
3
Ningbo Institute of Technology, Beihang University
, Ningbo 315832, China
Search for other works by this author on:
Fumihito Arai
Fumihito Arai
(Supervision)
1
Department of Mechanical Engineering, The University of Tokyo
, Tokyo 1138656, Japan
Search for other works by this author on:
J. Laser Appl. 36, 032012 (2024)
Article history
Received:
March 28 2024
Accepted:
June 15 2024
Citation
Yuxuan Liu, Fei Liu, Wuxiang Zhang, Xilun Ding, Fumihito Arai; Prediction and optimization of joint quality in laser transmission welding using serial artificial neural networks and their integration with Markov decision process. J. Laser Appl. 1 August 2024; 36 (3): 032012. https://doi.org/10.2351/7.0001384
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Citing articles via
Smart-Alloying for tailored microstructures in laser-based metal additive manufacturing
Anastasiya Toenjes, Carolin Zinn, et al.
Tailored microstructure in laser-based powder bed fusion of IN718 through novel beam shaping technology
Narges Mirzabeigi, Peter Holfelder-Schwalme, et al.
Laser powder bed fusion of a nanocrystalline Finemet Fe-based alloy for soft magnetic applications
S. Sadanand, M. Rodríguez-Sánchez, et al.
Related Content
Study on microstructures and mechanical performance of laser transmission welding of poly-ether-ether-ketone (PEEK) and carbon fiber reinforced PEEK (CFR-PEEK)
J. Laser Appl. (November 2022)
Volume imaging NDE and serial sectioning of carbon fiber composites
AIP Conference Proceedings (April 2018)
An artificial neural network model for serial speech production and speech error simulation
J Acoust Soc Am (November 2013)
Locally weighted histogram analysis and stochastic solution for large-scale multi-state free energy estimation
J. Chem. Phys. (January 2016)
Acoustical multi-frequency filtering by a defective asymmetric phononic serial loop structure
AIP Advances (July 2020)