Asset Details
Do you wish to reserve the book?
Thermal-fluid modeling and physics-informed machine learning for predicting molten pool depth in single-layer multi-track fiber laser cladding
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
Thermal-fluid modeling and physics-informed machine learning for predicting molten pool depth in single-layer multi-track fiber laser cladding
Do you wish to request the book?
Thermal-fluid modeling and physics-informed machine learning for predicting molten pool depth in single-layer multi-track fiber laser cladding
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
Thermal-fluid modeling and physics-informed machine learning for predicting molten pool depth in single-layer multi-track fiber laser cladding
2024
Overview
Understanding the molten pool dynamics and accurately predicting its geometry are critical aspects of laser cladding. The molten pool depth is crucial for the metallurgical bond between layers, yet it remains difficult to determine. To address this challenge, this study developed a high-fidelity thermal-fluid model and utilized physics-informed machine learning to predict the molten pool depth in single-layer multi-track fiber laser cladding of 316L stainless steel. Initially, the thermal-fluid model was established and validated through experiments, followed by an analysis of the molten pool’s temperature and flow field. Dimensionless numbers such as dimensionless heat input, Peclet number, and Marangoni number were calculated to assess the impact of molten pool flow on its geometry. A physics-informed temporal convolutional network (TCN) model was then developed based on the dataset generated from the thermal-fluid model, incorporating physical information like Marangoni convection. The performance of the proposed prediction model was compared with other time series machine learning approaches, showing mean absolute error (MAE) improvements of 82.7%, 38.9%, and 31.3% over models using the same dataset and physical information but based on recurrent neural networks (RNN), long short-term memory (LSTM), and gated recurrent units (GRU), respectively. These findings highlight the potential of integrating physical insights into predictive modeling to enhance the accuracy and efficiency of laser cladding processes.
Publisher
Springer London,Springer Nature B.V
