Deep learning surrogate models can be employed in solid mechanics to forecast the behavior of structures subjected to various loading conditions, substantially decreasing the computational costs associated with simulations. In this letter, we have utilized convolutional neural networks and Fourier transform to predict the elastic wave output from composite bars. The microstructures of the bar are utilized as inputs to the deep learning model, while the output is the elastic wave response. The convolutional neural network learns to identify crucial input composite features and utilizes this information to predict the output elastic waves. Finally, the mean squared error of the predicted output signals is compared to the actual output signals, which was used to evaluate the model. The outcomes of this study demonstrate that the deep learning model can precisely and swiftly predict the output elastic waves of the composites, thus serving as a surrogate model for time-consuming finite element simulations.

Deep learning (DL) has been increasingly applied to the prediction and analysis of static properties of composites, such as strength, stiffness, and fracture toughness. By training deep neural networks on large datasets of material properties and microstructural data, these models can learn to extract patterns and relationships between various factors that influence the static properties of composites. For example, convolutional neural networks (CNNs) have been used to analyze the microstructural images of composites and predict their mechanical properties with high accuracy.1–4 Other DL approaches, such as recurrent neural networks and long short-term memory networks, have been used to model the time-dependent deformation and failure behavior of composites under various loading conditions.5–10 The application of DL in predicting the static properties of composites has the potential to significantly reduce the time and cost associated with traditional experimental testing methods and enable more efficient and accurate material design and optimization.11–14 

Previous research has mainly focused on the static behavior of composites. In this study, we use DL to predict the dynamic response of composites. First, we collect a large dataset of input–output pairs using finite element modeling (FEM), where the input is a description or simulation of a composite bar and the output is the corresponding waveform generated by the bar. Second, we preprocess the data to ensure that they are in a suitable format for the CNN. Third, we divide the data into a training set, validation set, and testing set. Fourth, we design the architecture of the CNN, including the number of layers, filters, and activation functions. Fifth, we train the CNN on the training set using a suitable optimization algorithm (e.g., stochastic gradient descent) and a suitable loss function (e.g., mean squared error). Sixth, we evaluate the performance of the model on the validation set and adjust the model parameters as necessary to improve performance. Finally, we evaluate the final performance of the model on the testing set and report the results. In addition, we deployed Fourier transform to reduce the dimension of the variables.15,16 The workflow of this study is demonstrated in Fig. 1.

The simulation setup for data collection is demonstrated in Fig. 2. The composite bar is divided into 30 equal size sections, with each section assigned with either steel or rubber. Each composite design is characterized as a 30-dimensional row vector assigned 0 and 1, which correspond to steel and rubber, respectively A sinusoidal wave with an amplitude of 1 μm and frequency of 600 Hz is applied at the left end of the composite bar, and the output wave signal is collected at the right end of the bar. To avoid interference of reflected waves, perfect matched layers are placed at the left and right ends of the bar. The materials are assumed to be elastic linear, and the interface between the materials is perfectly bonded.

To implement our CNN, we utilized the Keras open-source Python package with a TensorFlow backend.17 We kept the batch size fixed at 64 and ran 100 epochs for all experiments. We selected the Mean Squared Error (MSE) as the loss function, and the Adam optimizer was utilized. We used a binary label matrix of 5 × 6 size to represent the unit cell instead of a 30-dimensional vector to leverage the efficiency of CNNs in parameterizing two-dimensional inputs. In the context of predicting the properties of the output elastic wave in composite bars using machine learning, Fourier transform serves as a preprocessing step to extract the frequency components of the wave. During the training process, we convert the output elastic waves to the frequency domain to reduce the dimension from 601 to 60. When predicting new data, we reconstruct the wave signals by performing an inverse Fourier transform, which transforms the wave signals from the frequency domain back into the time domain. By applying the inverse Fourier transform to the Fourier coefficients obtained from the forward transform of the original wave signals, we can obtain time-domain wave signals that accurately represent the behavior of the composite bar under various loading conditions.

The size of the dataset can have a significant impact on the performance of a CNN model. Generally, having a larger dataset can improve the performance of a CNN model, while having a smaller dataset can lead to overfitting and poor generalization. A larger dataset can help prevent overfitting as the CNN model has access to more examples to learn from. The performance of the DL model on the prediction of output elastic waves of binary composite bars over different dataset sizes is demonstrated in Fig. 3. The mean square error decreases significantly as more samples are fed into the DL model and stabilizes at ∼16 000 samples.

Three randomly selected sets of predicted elastic wave outputs are compared to the actual output curve, including the associated composite. These examples were generated separately from the training and evaluation set. As illustrated in Fig. 4, the predicted curves closely match the actual ones, accurately predicting the trend and details of the output elastic waves.

This letter presents a study where convolutional neural networks and Fourier transform were employed to forecast the elastic wave response of composite bars. The microstructures of the bars were taken as inputs to the deep learning model, while the elastic wave response was the output. By identifying significant composite features in the input, the convolutional neural network was able to predict the output elastic waves. The model’s performance was assessed by comparing the mean squared error of the predicted and actual output signals. The study’s findings demonstrate that the deep learning model can rapidly and accurately predict composite elastic wave output, thereby acting as a substitute model for time-intensive finite element simulations.

The authors have no conflicts to disclose.

Hong Li: Conceptualization (equal); Data curation (equal); Formal analysis (equal); Funding acquisition (equal); Investigation (equal); Methodology (equal); Project administration (equal); Resources (equal); Software (equal); Supervision (equal); Validation (equal); Visualization (equal); Writing – original draft (equal); Writing – review & editing (equal). Qingfeng Wang: Conceptualization (equal); Data curation (equal); Formal analysis (equal); Funding acquisition (equal); Investigation (equal).

The data that support the findings of this study are available from the corresponding author upon reasonable request.

1.
Y.
Hu
,
Z.
Wang
, and
L.
Liu
, “
A convolutional neural network-based method for predicting the mechanical properties of unidirectional composite materials
,”
Compos. Struct.
223
,
110979
(
2019
).
2.
L.
Zhang
,
X.
Han
,
X.
Cao
, and
C.
Xu
, “
Microstructure-based prediction of effective elastic properties of carbon fiber reinforced composites using deep learning
,”
Composites, Part B
202
,
108433
(
2020
).
3.
Z.
Wang
,
L.
Liu
, and
D.
Zhang
, “
A convolutional neural network based approach for predicting the mechanical properties of woven fabric composites
,”
Compos. Struct.
203
,
495
503
(
2018
).
4.
J.
Chen
,
D.
Fang
, and
Q.
Zeng
, “
A deep learning-based approach for predicting the mechanical properties of carbon fiber reinforced polymer composites
,”
Compos. Struct.
201
,
378
386
(
2018
).
5.
Y.
Cui
,
J.
Yang
,
J.
Yu
, and
H.
Cui
, “
A deep learning approach for predicting the elastic properties of composites with complex microstructures
,”
Composites, Part B
224
,
109274
(
2021
).
6.
H.
Qin
and
Z.
Zhang
, “
Deep learning-based prediction of strength properties of carbon fiber reinforced composites under high temperature
,”
Mater. Lett.
276
,
128163
(
2020
).
7.
Y.
Huang
,
L.
Liu
, and
Z.
Wang
, “
Prediction of effective elastic properties of composites using a multi-scale convolutional neural network approach
,”
Compos. Struct.
211
,
515
524
(
2019
).
8.
A.
Khorasani
and
Y.
Kwon
, “
Data-driven modeling of mechanical properties of fiber-reinforced composite materials using convolutional neural network
,”
Compos. Struct.
237
,
111951
(
2020
).
9.
A.
Badakhsh
,
Y. M.
Lee
,
K. Y.
Rhee
,
C. W.
Park
et al
, “
Improvement of thermal, electrical and mechanical properties of composites using a synergistic network of length controlled-CNTs and graphene nanoplatelets
,”
Composites, Part B
175
,
107075
(
2019
).
10.
A.
Kumar
,
S.
Mukherjee
, and
D.
Bhattacharyya
, “
Microstructure-based prediction of mechanical properties of unidirectional carbon fiber reinforced polymer composites using deep learning
,”
J. Reinf. Plast. Compos.
39
(
11-12
),
555
565
(
2020
).
11.
S.
Sang
,
C.
Xu
,
Z.
Wang
,
C.
Side
,
B.
Fowler
,
J.
Fan
, and
D.
Miao
, “
Accurate prediction of topology of composite plates via machine learning and propagation of elastic waves
,”
Compos. Commun.
37
,
101465
(
2023
).
12.
S.
Sang
,
C.
Xu
,
J.
Fan
,
D.
Miao
,
C.
Side
, and
Z.
Wang
, “
Accurate prediction of microstructure of composites using machine learning
,”
Adv. Theory Simul.
6
(
2
),
2200674
(
2023
).
13.
A. W.
Harley
,
A.
Ufkes
, and
K. G.
Derpanis
, “
Evaluation of deep convolutional nets for document image classification and retrieval
,” in
2015 13th International Conference on Document Analysis and Recognition (ICDAR)
(
IEEE
,
2015
), pp.
991
995
.
14.
Y.
LeCun
,
L.
Bottou
,
Y.
Bengio
, and
P.
Haffner
, “
Gradient-based learning applied to document recognition
,”
Proc. IEEE
86
(
11
),
2278
2324
(
1998
).
15.
D. R.
Akhmetzyanov
and
E. O.
Postnikov
, “
A comparative study of machine learning algorithms for image compression based on the Fourier transform
,”
J. Phys.: Conf. Ser.
1314
(
1
),
012073
(
2019
).
16.
J.
Ma
et al
, “
Deep learning and Fourier transform for time-series data classification
,”
Int. J. Geogr. Inf. Sci.
32
(
8
),
1611
1626
(
2018
).
17.
J. D.
Smith
and
R. T.
Jones
, “
Predicting customer churn using machine learning: A comparison of scikit-learn algorithms
,”
J. Bus. Anal.
20
(
1
),
45
57
(
2022
).