Transfer learning based variable-fidelity surrogate model for shell buckling prediction

Tian, Kuo; Li, Zengcong; Zhang, Jiaxin; Huang, Lei; Wang, Bo

doi:10.1016/j.compstruct.2021.114285

Cited by 61 publications

(14 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, the NN model will be trained using a combination of computational data and experimental data with variable fidelity. [31,32] In addition, the trained NN model will be implemented into the EST model for better computation efficiency. ORCID Anthony M. Waas https://orcid.org/0000-0002-4916-2102…”

Section: Discussionmentioning

confidence: 99%

Determining damage initiation of carbon fiber reinforced polymer composites using machine learning

et al. 2022

View full text Add to dashboard Cite

Computational progressive failure analysis (PFA) is vital for the analysis of carbon fiber reinforced polymer (CFRP) composites. The damage initiation criterion is one of the essential components of a PFA code to determine the transition of a material's state from pristine or microscopically damaged to macroscopically damaged. In this paper, data-driven models are developed to determine the matrix damage initiation with the objective to save computation time. For 2D plane stress states, the computational cost for determining damage initiation can be dramatically reduced by implementing a binary search (BS) algorithm and predictive machine learning models. Machine learning models are evaluated against a regression problem of predicting damage crack angle as well as against a classification problem for predicting damage initiation outright. It is found that regression models perform much better for plane stress and 3D stress states when generating failure envelopes. In both cases, a neural network is able to produce a failure envelope that is over 99% accurate while reducing computational cost by over 90%.

show abstract

Section: Discussionmentioning

confidence: 99%

Determining damage initiation of carbon fiber reinforced polymer composites using machine learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The results show that machine learning can accurately predict high-performance metal-organic frameworks and can improve the screening speed by 2-3 orders of magnitude. [13] Some researchers worked on machine learning methods or surrogate modeling methods for accelerating structure analysis, [14][15][16][17] Tian et al employed transfer learning to establish the variablefidelity surrogate model for shell buckling prediction, [15] demonstrating the potential of transfer-learning based variable-fidelity surrogate model in time-consuming prediction problems.…”

Section: Literature Reviewmentioning

confidence: 99%

Accelerating Analysis for Structure Design via Deep Learning Surrogate Models

Shao

Chen

Wang

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Using computer simulation tools such as finite element analysis (FEA) to perform material stress analysis is a common design method in engineering practice. In order to model more realistic real‐world systems, simulation models have become more complex, and calculation becomes more expensive as a result. The rise of artificial intelligence technologies has made it possible to integrate deep learning methods and material stress analysis. Herein, FEA software is employed to obtain a large number of analysis cases as training samples and uses a fully connected neural network and long‐short‐term memory neural network as surrogate models, which can predict the stress distribution and stress sequence in the process of the bullet impacting target plates with different materials. These models can give results similar to FEA with 92.19% and 92.41% accuracy, respectively. The experimental results show that the deep learning surrogate models have great potential in material stress analysis.

show abstract

“…It reduces the need for expensive data in the target domain by reusing models or data from similar domains. Existing models are usually completely updated [28], [29] or retrained in the last few layers [30], [31]. Their successful applications can be seen in many areas [32].…”

Section: Introductionmentioning

confidence: 99%

Multi-Objective Surrogate Modeling Through Transfer Learning for Telescopic Boom Forklift

Lin

Huang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Simulation and optimization methods have been widely used in forklift design due to their cost-effectiveness. However, this type of method involves challenges such as the accuracy of the simulation model and the simulation solution time. These challenges reduce the stability and precision of the surrogate model and hence generate further optimization errors. In this paper, a multi-objective surrogate modeling (MSM) method for telescopic boom forklifts based on closed-loop transfer learning is proposed in order to solve these challenges. The MSM consists of the following two steps: to pre-train an initial deep neural network model (deep model) with a large amount of existing simulation data from the same type of forklift and to transfer the model with a small amount of measurement data collected on the current forklift. A general framework for deep neural network (DNN) training is introduced to improve the approximation ability of the initial model. Moreover, a novel uncertainty-analysis-based sampling method is suggested for measurement data development, and combined with transfer learning to form a closed-loop mode to improve the stability of the final model. The superiority of MSM is demonstrated through comparative studies with the fine-tuning method on a telescopic boom forklift with two objectives. The experimental results show that the Correlation coefficient (R) of the deep model can reach 0.9971 by using only 80 sets of training data. In addition, it can also achieve an improvement of at least a 13.25% reduction in Root Mean Squared Error (RMSE) and a 9.19% reduction on average in Maximum Absolute Error (MAE), as well as stronger robustness compared to the benchmarks. Furthermore, it will provide a valuable reference for the simulation optimization of complex electromechanical products.INDEX TERMS Telescopic boom forklift, surrogate model, transfer learning, uncertainty analysis, hyperparameter optimization.

show abstract

Transfer learning based variable-fidelity surrogate model for shell buckling prediction

Cited by 61 publications

References 53 publications

Determining damage initiation of carbon fiber reinforced polymer composites using machine learning

Determining damage initiation of carbon fiber reinforced polymer composites using machine learning

Accelerating Analysis for Structure Design via Deep Learning Surrogate Models

Multi-Objective Surrogate Modeling Through Transfer Learning for Telescopic Boom Forklift

Contact Info

Product

Resources

About