Deep Autoencoder Thermography for Defect Detection of Carbon Fiber Composites

Liu, Kaixin; Zheng, Mingkai; Liu, Yi; Yang, Junxiao; Yao, Yuan

doi:10.1109/tii.2022.3172902

Cited by 51 publications

(29 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature selection technique is necessary to remove the redundant or irrelevant features or features correlated in the data. Some studies proposed deep autoencoder or deep belief network to extract the nonlinear features 42,43 . However, the predictions of the base models didn't show any complex patterns but high correlation in this study.…”

Section: Selection Of Sequence Lengthmentioning

confidence: 99%

Neural network ensemble model for prediction of erythrocyte sedimentation rate (ESR) using partial least squares regression

Lee

Hong

Song

et al. 2022

Sci Rep

View full text Add to dashboard Cite

The erythrocyte sedimentation rate (ESR) is a non-specific blood test for determining inflammatory conditions. However, the long measurement time (60 min) to obtain ESR is an obstacle for a prompt evaluation. In this study, to reduce the measurement time of ESR, deep neural networks (DNNs) were applied to the sedimentation tendency of blood samples. DNNs using multilayer perceptron (MLP), long short-term memory (LSTM), and gated recurrent unit (GRU) were assessed and compared to determine a suitable length of time for the input sequence. To avoid overfitting, a stacking ensemble learning was adopted, which combines multiple models by using a meta model. Four meta models were compared: mean, median, least absolute shrinkage and selection operator, and partial least squares regression (PLSR) schemes. From the empirical results, LSTM and GRU models have better prediction than MLP over sequence lengths of 5 to 20 min. The decrease in $$\overline{\mathrm{MAPE} }$$ MAPE ¯ and $$\overline{\mathrm{RMSE} }$$ RMSE ¯ of GRU and LSTM was attenuated after a sequence length of 15 min, so the input sequence length is determined as 15 min. In terms of the meta model, the statistical comparison suggests that GRU combined with PLSR (GRU–PLSR) is the best case. Then, the GRU–PLSR was tested for prediction of ESR data obtained from periodontitis patients to check its applicability to a specific disease. The Bland–Altman plot shows acceptable agreement between measured and predicted ESR values. Based on the results, the GRU–PLSR can predict ESR with improved performance within 15 min and has potential applicability to ESR data with inflammatory and non-inflammatory conditions.

show abstract

Section: Selection Of Sequence Lengthmentioning

confidence: 99%

Neural network ensemble model for prediction of erythrocyte sedimentation rate (ESR) using partial least squares regression

Lee

Hong

Song

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…By comparing the correlation information from the previous samples and previous batches, the status of a measurement can be examined. In addition, the related methods of neural networks have also been applied to deal with data with nonlinear and dynamic properties; in a deep autoencoder thermography method, the layer-by-layer feature visualization reveals how the model extracts defect features . However, the following deflects require further discussion.…”

Section: Introductionmentioning

confidence: 99%

“…In addition, the related methods of neural networks have also been applied to deal with data with nonlinear and dynamic properties; in a deep autoencoder thermography method, the layer-by-layer feature visualization reveals how the model extracts defect features. 29 However, the following deflects require further discussion. First, high collinearity may exist in the variable-wise data, which may cause inefficiency of conventional CCA methods.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Batch Process Monitoring Based on Time-Slice Latent Variable Correlation Analysis

et al. 2022

View full text Add to dashboard Cite

Batch processes are generally characterized by complex dynamics and remarkable data collinearity, thereby rendering the monitoring of such processes necessary but challenging. This paper proposes a data-driven time-slice latent variable correlation analysis-based model predictive fault detection framework to ensure accurate fault detection in dynamic batch processes. The three-way batch process data are first unfolded into the two-way time slice. For each single time slice, process data are mapped to both major latent variables and residual subspaces to deal with the variable-wise data collinearity and extract dominant data information. A measurement status is then determined with a canonical correlation analysis of the major latent variables and correlated variables, using both the time and batch perspectives. Prediction-based residuals are generated, which provide the basis for identifying the property of faults detected, namely, static or dynamic. Based on experiments using a simulated penicillin production and an industrial inject molding process, the proposed monitoring scheme has been proven feasible and effective.

show abstract

“…In recent years, deep learning-based VSG methods have also been adopted in the process industry [ 35 ]. The generative adversarial network (GAN) [ 36 , 37 , 38 , 39 ], as one promising generative model, has been well studied and is valued for its generative properties. By generating virtual data that resemble actual data, the GAN enlarges the sample capacity to enhance the prediction performance.…”

Section: Introductionmentioning

confidence: 99%

Enhanced Soft Sensor with Qualified Augmented Samples for Quality Prediction of the Polyethylene Process

Dai

Liu

Meng³

et al. 2022

Polymers

Self Cite

View full text Add to dashboard Cite

Data-driven soft sensors have increasingly been applied for the quality measurement of industrial polymerization processes in recent years. However, owing to the costly assay process, the limited labeled data available still pose significant obstacles to the construction of accurate models. In this study, a novel soft sensor named the selective Wasserstein generative adversarial network, with gradient penalty-based support vector regression (SWGAN-SVR), is proposed to enhance quality prediction with limited training samples. Specifically, the Wasserstein generative adversarial network with gradient penalty (WGAN-GP) is employed to capture the distribution of the available limited labeled data and to generate virtual candidates. Subsequently, an effective data-selection strategy is developed to alleviate the problem of varied-quality samples caused by the unstable training of the WGAN-GP. The selection strategy includes two parts: the centroid metric criterion and the statistical characteristic criterion. An SVR model is constructed based on the qualified augmented training data to evaluate the prediction performance. The superiority of SWGAN-SVR is demonstrated, using a numerical example and an industrial polyethylene process.

show abstract

Deep Autoencoder Thermography for Defect Detection of Carbon Fiber Composites

Cited by 51 publications

References 28 publications

Neural network ensemble model for prediction of erythrocyte sedimentation rate (ESR) using partial least squares regression

Neural network ensemble model for prediction of erythrocyte sedimentation rate (ESR) using partial least squares regression

Dynamic Batch Process Monitoring Based on Time-Slice Latent Variable Correlation Analysis

Enhanced Soft Sensor with Qualified Augmented Samples for Quality Prediction of the Polyethylene Process

Contact Info

Product

Resources

About