Indentation Reverse Algorithm of Mechanical Response for Elastoplastic Coatings Based on LSTM Deep Learning

Long, Xu; Ding, Xiaoyue; Li, Jiao; Dong, Ruipeng; Su, Yuezeng; Chang, Chao

doi:10.3390/ma16072617

Cited by 14 publications

(6 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang et al [48] employed a hyperparametric tunable artificial neural network model to establish a positive relationship between the material elastoplastic parameters and the indentation P-h curve. Meanwhile, Long et al [49] proposed a long short-term memory neural network to deeply learn the time series of P-h curves to predict the relationship between P-h curves of metal-coated materials and their stress-strain response. This network established the mapping relation from the P-h curves to the corresponding elastoplastic material stress-strain response.…”

Section: Machine Learningmentioning

confidence: 99%

Critical Review of Nanoindentation-Based Numerical Methods for Evaluating Elastoplastic Material Properties

Long,

Dong,

et al. 2023

Coatings

Self Cite

View full text Add to dashboard Cite

It is well known that the elastoplastic properties of materials are important indicators to characterize their mechanical behaviors and are of guiding significance in the field of materials science and engineering. In recent years, the rapidly developing nanoindentation technique has been widely used to evaluate various intrinsic information regarding the elastoplastic properties and hardness of various materials such as metals, ceramics, and composites due to its high resolution, versatility, and applicability. However, the nanoindentation process of indenting materials on the nanoscale provides the measurement results, such as load-displacement curves and contact stiffness, which is challenging to analyze and interpret, especially if contained in a large amount of data. Many numerical methods, such as dimensionless analysis, machine learning, and the finite element model, have been recently proposed with the indentation techniques to further reveal the mechanical behavior of materials during nanoindentation and provide important information for material design, property optimization, and engineering applications. In addition, with the continuous development of science and technology, automation and high-throughput processing of nanoindentation experiments have become a future trend, further improving testing efficiency and data accuracy. This paper critically reviewed various numerical methods for evaluating elastoplastic constitutive properties of materials based on nanoindentation technology, which aims to provide a comprehensive understanding of the application and development trend of the nanoindentation technique and to provide guidance and reference for further research and applications.

show abstract

Section: Machine Learningmentioning

confidence: 99%

Critical Review of Nanoindentation-Based Numerical Methods for Evaluating Elastoplastic Material Properties

Long,

Dong,

et al. 2023

Coatings

Self Cite

View full text Add to dashboard Cite

show abstract

“…For these very reasons, the computing speed a computational efficiency of an LSTM model are greatly enhanced. Furthermore, a dropout layer can also be added after each LSTM hidden layer, and its value is usually between 0.2 and 0.5, effectively avoiding the occurrence of overfitting during model training [34,36]. Overfitting is a common problem in deep learning fields [37].…”

Section: Multi-hidden-layer Lstm Structurementioning

confidence: 99%

Long Short-Term Memory Network for Predicting Wind-Induced Vibration Response of Lightning Rod Structures

et al. 2023

View full text Add to dashboard Cite

Lightning rod structures are susceptible to wind loads due to their high slenderness ratio, high flexibility, and light weight. The wind-induced dynamic response of a lightning rod is critical for structural safety and reliability. The traditional methods for this response, including observation and simulation, focus on structural health monitoring (SHM), wind tunnel tests (WTTs), or fluid–structure interaction (FSI) simulations. However, all these approaches require considerable financial or computational investment. Additionally, problems such as data loss or data anomalies in the sensor monitoring process often occur during SHM or WTTs. This paper proposes an algorithm based on a long short-term memory (LSTM) network to predict the wind-induced dynamic response and to solve the problem of data link fracture caused by abnormal sensor data transmission or wind-induced damage to lightning rod structures under different wind speeds. The effectiveness and applicability of the proposed framework are demonstrated using actual monitoring data. Root-mean-squared error (RMSE), determination of coefficient (R2), variance accounted for (VAF), and the refined Willmott index (RWI) are employed as performance assessment indices for the proposed network model. At the same time, the random forest algorithm is adopted to analyze the correlation between the data of the different measurement points on the lightning rod structure. The results show that the LSTM method proposed in this paper has a high accuracy for the prediction of “missing” strain data during lightning rod strain monitoring under wind speeds of 15.81~31.62 m/s. Even under the extreme wind speed of 31.62 m/s, the values of RMSE, MAE, R2, RWI and VAF are 0.24053, 0.18213, 0.94539, 0.88172 and 0.94444, respectively, which are within the acceptable range. Using the data feature importance analysis function, it is found that the predicted strain data of the measurement point on the top part of the lightning rod structure are closely related to the test strain data of the two adjacent sections of the structure, and the effect of the test strain data of the measurement points that are far from the predicted measurement point can be ignored.

show abstract

“…Long short-term memory (LSTM) machine learning algorithms, which can effectively handle sequential data and can learn the long-term dependence of the data [37], have been used to consider time-series features of F-δ curves. However, Long's study [38] revealed that when LSTM networks were used alone for prediction, the results were only acceptable and did not yield the expected excellent results. To solve the above problems, in this paper, a CNN-LSTM architecture combining a convolutional neural network (CNN) and LSTM [39] is used for the first time to estimate TSLs at the bonded interface of IGBT modules.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Using Machine Learning and Finite Element Analysis to Extract Traction-Separation Relations at Bonding Wire Interfaces of Insulated Gate Bipolar Transistor Modules

Zhao,

An,

Wang

et al. 2024

Materials

View full text Add to dashboard Cite

For insulated gate bipolar transistor (IGBT) modules using wire bonding as the interconnection method, the main failure mechanism is cracking of the bonded interface. Studying the mechanical properties of the bonded interface is crucial for assessing the reliability of IGBT modules. In this paper, first, shear tests are conducted on the bonded interface to test the bonded interface’s strength. Then, finite element–cohesive zone modeling (FE-CZM) is established to describe the mechanical behavior of the bonded interface. A novel machine learning (ML) architecture integrating a convolutional neural network (CNN) and a long short-term memory (LSTM) network is used to identify the shape and parameters of the traction separation law (TSL) of the FE-CZM model accurately and efficiently. The CNN-LSTM architecture not only has excellent feature extraction and sequence-data-processing abilities but can also effectively address the long-term dependency problem. A total of 1800 sets of datasets are obtained based on numerical computations, and the CNN-LSTM architecture is trained with load–displacement (F–δ) curves as input parameters and TSL shapes and parameters as output parameters. The results show that the error rate of the model for TSL shape prediction is only 0.186%. The performance metric’s mean absolute percentage error (MAPE) is less than 3.5044% for all the predictions of the TSL parameters. Compared with separate CNN and LSTM architectures, the proposed CNN-LSTM-architecture approach exhibits obvious advantages in recognizing TSL shapes and parameters. A combination of the FE-CZM and ML methods in this paper provides a promising and effective solution for identifying the mechanical parameters of the bonded interfaces of IGBT modules.

show abstract

Indentation Reverse Algorithm of Mechanical Response for Elastoplastic Coatings Based on LSTM Deep Learning

Cited by 14 publications

References 54 publications

Critical Review of Nanoindentation-Based Numerical Methods for Evaluating Elastoplastic Material Properties

Critical Review of Nanoindentation-Based Numerical Methods for Evaluating Elastoplastic Material Properties

Long Short-Term Memory Network for Predicting Wind-Induced Vibration Response of Lightning Rod Structures

Using Machine Learning and Finite Element Analysis to Extract Traction-Separation Relations at Bonding Wire Interfaces of Insulated Gate Bipolar Transistor Modules

Contact Info

Product

Resources

About