An interpretable LSTM deep learning model predicts the time-dependent swelling behavior in CERCER composite fuels

Zhao, Yunmei; Chen, Zhenyue; Dong, Yiqun; Tu, Jingqi

doi:10.1016/j.mtcomm.2023.106998

Cited by 4 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To accurately predict the temporal evolution of the COF for open-cell AlSn6Cu-Al 2 O 3 composites and the corresponding unreinforced materials, a LSTM network, which is a specific form of recurrent neural network (RNN) that is capable of capturing long-term dependencies in time series data, was employed. This approach is particularly suitable due to the temporal nature of wear processes, where the history of wear significantly influences future wear behavior [32,33]. The LSTM model is engineered to identify patterns in the COF values over time across different materials, analyzing three samples per material, with the objective of predicting the COF from historical data collected over a span of 420 s. This data was acquired from the experimental methods detailed in Section 2.2, consisting of time series data of COF measured at regular intervals during dry wear friction tests performed using a pin-on-disk apparatus.…”

Section: Machine Learning Modelmentioning

confidence: 99%

Fabrication and Dry-Sliding Wear Characterization of Open-Cell AlSn6Cu–Al2O3 Composites with LSTM-Based Coefficient of Friction Prediction

Kolev,

Drenchev,

Petkov

et al. 2024

Metals

View full text Add to dashboard Cite

This study investigates the fabrication, wear characterization, and coefficient of friction (COF) prediction of open-cell AlSn6Cu–Al2O3 composites obtained by a liquid-state processing technique. Focusing on wear behavior under varying loads using the pin-on-disk method, this research characterizes microstructure and phase composition via SEM, EDS, and XRD analyses. A novel aspect of this research is the application of an LSTM recurrent neural network model for the fast and accurate prediction of the COF of the composites, eliminating the need for extensive experimental work. Additionally, feature importance analysis using Random Forest regressors is conducted to ascertain the relative contribution of each input variable to the output variable, enhancing our understanding of the wear mechanisms in these materials. The results demonstrate the effectiveness of the composite’s reinforcement in improving wear resistance, highlighting the critical role of mechanical stress and the reinforcement’s hardness in the wear process. The quantitative findings related to the wear behavior include a mass-wear reduction in the open-cell AlSn6Cu–Al2O3 composite from 8.05 mg to 1.90 mg at 50 N and a decrease from 17.55 mg to 8.10 mg at 100 N, demonstrating the Al2O3 particles’ effectiveness in improving wear resistance under different loads.

show abstract

Section: Machine Learning Modelmentioning

confidence: 99%

Fabrication and Dry-Sliding Wear Characterization of Open-Cell AlSn6Cu–Al2O3 Composites with LSTM-Based Coefficient of Friction Prediction

Kolev,

Drenchev,

Petkov

et al. 2024

Metals

View full text Add to dashboard Cite

show abstract

“…The recurrent neural network (RNN) represents a neural network architecture designed to handle sequential data, including text, time series, and speech. The foundational concept of an RNN involves its ability to maintain connections to prior states, thereby enabling the model to preserve information about preceding sequence elements [10,30,31].…”

Section: Applying Recurrent Neural Network (Rnn) For Gene Expression ...mentioning

confidence: 99%

Applying a Recurrent Neural Network-Based Deep Learning Model for Gene Expression Data Classification

Babichev,

Liakh,

Kalinina

2023

Applied Sciences

View full text Add to dashboard Cite

The importance of gene expression data processing in solving the classification task is determined by its ability to discern intricate patterns and relationships within genetic information, enabling the precise categorization and understanding of various gene expression profiles and their consequential impacts on biological processes and traits. In this study, we investigated various architectures and types of recurrent neural networks focusing on gene expression data. The effectiveness of the appropriate model was evaluated using various classification quality criteria based on type 1 and type 2 errors. Moreover, we calculated the integrated F1-score index using the Harrington desirability method, the value of which allowed us to improve the objectivity of the decision making when model effectiveness was evaluated. The final decision regarding model effectiveness was made based on a comprehensive classification quality criterion, which was calculated as the weighted sum of classification accuracy, integrated F1-score index, and loss function values. The simulation results show higher appeal of a single-layer GRU recurrent network with 75 neurons in the recurrent layer. We also compared convolutional and recurrent neural networks on gene expression data classification. Although convolutional neural networks showcase benefits in terms of loss function value and training time, a comparative analysis revealed that in terms of classification accuracy calculated on the test data subset, the GRU neural network model is slightly better than the CNN and LSTM models. The classification accuracy when using the GRU network was 97.2%; in other cases, it was 97.1%. In the first case, 954 out of 981 objects were correctly identified. In other cases, 952 objects were correctly identified.

show abstract

Section: Introductionmentioning

confidence: 99%

“…In recent years, machine learning (ML) techniques have been widely adopted in relevant fields of biochemistry [15], material science [16,17], and mechanical performance analysis [18,19]. with an end-to-end prediction paradigm, using a simulated dataset is commonly reported [19,20]. As suggested in [21], by providing enormous amounts of relevant data, numerical modeling naturally complements the ML technique and aids in creating reliable data-driven models.…”

Section: Introductionmentioning

confidence: 99%

“…Regarding the model interpretability methods, the SHapley Additive exPlanations (SHAP) method has gained increasing popularity, which explains how each feature influences the model and allows local and global analysis [41]. SHAP analysis has offered valuable insights into the disciplinary fields of composite performance analysis [19,37,42,43] and sensor fault detection [44], as well as manufacturing processes [45].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A High-Generalizability Machine Learning Framework for Analyzing the Homogenized Properties of Short Fiber-Reinforced Polymer Composites

Zhao,

Chen,

Jian

2023

Polymers

Self Cite

View full text Add to dashboard Cite

This study aims to develop a high-generalizability machine learning framework for predicting the homogenized mechanical properties of short fiber-reinforced polymer composites. The ensemble machine learning model (EML) employs a stacking algorithm using three base models of Extra Trees (ET), eXtreme Gradient Boosting machine (XGBoost), and Light Gradient Boosting machine (LGBM). A micromechanical model of a two-step homogenization algorithm is adopted and verified as an effective approach to composite modeling with randomly distributed fibers, which is integrated with finite element simulations for providing a high-quality ground-truth dataset. The model performance is thoroughly assessed for its accuracy, efficiency, interpretability, and generalizability. The results suggest that: (1) the EML model outperforms the base members on prediction accuracy, achieving R2 values of 0.988 and 0.952 on the train and test datasets, respectively; (2) the SHapley Additive exPlanations (SHAP) analysis identifies the Young’s modulus of matrix, fiber, and fiber content as the top three factors influencing the homogenized properties, whereas the anisotropy is predominantly determined by the fiber orientations; (3) the EML model showcases good generalization capability on experimental data, and it has been shown to be more effective than high-fidelity computational models by significantly lowering computational costs while maintaining high accuracy.

show abstract

An interpretable LSTM deep learning model predicts the time-dependent swelling behavior in CERCER composite fuels

Cited by 4 publications

References 37 publications

Fabrication and Dry-Sliding Wear Characterization of Open-Cell AlSn6Cu–Al2O3 Composites with LSTM-Based Coefficient of Friction Prediction

Fabrication and Dry-Sliding Wear Characterization of Open-Cell AlSn6Cu–Al2O3 Composites with LSTM-Based Coefficient of Friction Prediction

Applying a Recurrent Neural Network-Based Deep Learning Model for Gene Expression Data Classification

A High-Generalizability Machine Learning Framework for Analyzing the Homogenized Properties of Short Fiber-Reinforced Polymer Composites

Contact Info

Product

Resources

About