Explainable 1-D convolutional neural network for damage detection using Lamb wave

Pandey, P. C.; Rai, Akshay

doi:10.1016/j.ymssp.2021.108220

Cited by 71 publications

(35 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Spectroscopic techniques have been widely used for different purposes in various domains such as petrochemical [41,42], medical, pharmaceutical, and biological [43,44,45], food and agricultural [46,47,48,49], engineering [50] and material and geologic [51,52] analysis to monitor reactions and conditions of a final product.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, model-agnostic methods have attracted a lot of attention for feature evaluation, such as Shapley Additive Explanation (SHAP) [34] and LIME [28]. Explainable AI techniques in general have been widely used to explain predictions in financial and chemical time-series data [77,78,79,80] vibrational-based Structural Health Monitoring signals [50], hyperspectral imaging [81] and electrocardiogram data [82]. However, to the best of our knowledge, only one recent work focused on using the model-agnostic method (LIME) to explain the non-linear predictions of spectroscopy data to characterize plasma solution conductivity [29].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Explainable Predictive Modeling for Limited Spectral Data

Akulich¹,

Anahideh²,

Sheyyab³

et al. 2022

Preprint

View full text Add to dashboard Cite

Feature selection of high-dimensional labeled data with limited observations is critical for making powerful predictive modeling accessible, scalable, and interpretable for domain experts. Spectroscopy data, which records the interaction between matter and electromagnetic radiation, particularly holds a lot of information in a single sample. Since acquiring such high-dimensional data is a complex task, it is crucial to exploit the best analytical tools to extract necessary information. In this paper, we investigate the most commonly used feature selection techniques and introduce applying recent explainable AI techniques to interpret the prediction outcomes of high-dimensional and limited spectral data. Interpretation of the prediction outcome is beneficial for the domain experts as it ensures the transparency and faithfulness of the ML models to the domain knowledge. Due to the instrument resolution limitations, pinpointing important regions of the spectroscopy data creates a pathway to optimize the data collection process through the miniaturization of the spectrometer device. Reducing the device size and power and therefore cost is a requirement for the real-world deployment of such a sensor-to-prediction system as a whole. Furthermore, we consider a wide range of machine learning models that have been proven to be successful for the prediction of the Cetane Number of fuels. We specifically design three different scenarios to ensure that the evaluation of ML models is robust for the real-time practice of the developed methodologies and to uncover the hidden effect of noise sources on the final outcome. The evaluation is performed for both the full model and reduced models using different feature selection techniques on a real dataset. Finally, we propose a correctness metric for the feature selection techniques to assess the conformance of the selected subset

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Explainable Predictive Modeling for Limited Spectral Data

Akulich¹,

Anahideh²,

Sheyyab³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Rotating machinery is a key element in the modern industry, in particular within the context of the fourth industrial revolution or Industry 4.0. Especially, gears and bearings are essential components of rotating machinery and any faults in gears or bearings can lead to machine failure, which can result in accidents, product unavailability, and financial losses [1]. Hence, it is necessary to develop an efficient method that could identify the fault as early as possible [2].…”

Section: Introductionmentioning

confidence: 99%

A Fuzzy Fusion Rotating Machinery Fault Diagnosis Framework Based on the Enhancement Deep Convolutional Neural Networks

Yang

Karimi

Gelman

2022

Sensors

View full text Add to dashboard Cite

Some artificial intelligence algorithms have gained much attention in the rotating machinery fault diagnosis due to their robust nonlinear regression properties. In addition, existing deep learning algorithms are usually dependent on single signal features, which would lead to the loss of some information or incomplete use of the information in the signal. To address this problem, three kinds of popular signal processing methods, including Fast Fourier Transform (FFT), Short-Time Fourier Transform (STFT) and directly slicing one-dimensional data into the two-dimensional matrix, are used to create four different datasets from raw vibration signal as the input data of four enhancement Convolutional Neural Networks (CNN) models. Then, a fuzzy fusion strategy is used to fuse the output of four CNN models that could analyze the importance of each classifier and explore the interaction index between each classifier, which is different from conventional fusion strategies. To show the performance of the proposed model, an artificial fault bearing dataset and a real-world bearing dataset are used to test the feature extraction capability of the model. The good anti-noise and interpretation characteristics of the proposed method are demonstrated as well.

show abstract

“…Meanwhile, the corresponding signal processing methods such as wavelet transform and empirical mode decomposition has also been substantially studied and applied [ 4 ]. Recently, the application of smartphones, high-resolution cameras, unmanned aerial vehicles, and other non-contact sensing technologies gained prominent growth in SHM due to their advantages of low labor cost, high applicative efficiency, and so forth [ 5 ]; in line with these advancements, a myriad of machine learning and deep learning-based algorithms, typified by support vector machine, Gaussian mixture, convolutional neural network, and long short-term memory network, have been studied and proposed to process sheer amount and various dimensions of data collected, as well as to provide intelligent solutions for conventional damage detection methods [ 6 , 7 ].…”

Section: Introductionmentioning

confidence: 99%

A Novel Baseline-Free Damage Detection Method Based on Path Scanning of Lamb Waves Using Mobile Transducers

Yuan

Zhou

et al. 2022

Sensors

View full text Add to dashboard Cite

The baseline-free damage detection method of Lamb waves has the potential to obtain damage information efficiently in plate structures through damage scattering signals. However, the missing detection of damage occurs occasionally due to the angular scattering characteristic of Lamb waves. To solve this problem, a novel baseline-free damage detection approach based on path scanning at the detection region edges using mobile piezoelectric transducers is proposed herein. Several sensing points carrying separated damage scattering signals were picked out from the scanning paths. By removing the direct and boundary reflected signals, the damage signals were extracted and exported to a delay-and-sum imaging method to locate the damage. Two experiments with and without mobile transducers were conducted to validate the proposed method on an aluminum plate with artificially fabricated crack-like damage. The results show that the proposed baseline-free approach can locate the crack-like damage with high accuracy and efficiency and avoid potential loss of damage information. The proposed baseline-free method provides a novel and practical damage detection approach when considering the angular-dependent scattering characteristic of Lamb waves and can enhance the credibility of results in damage detection.

show abstract

Explainable 1-D convolutional neural network for damage detection using Lamb wave

Cited by 71 publications

References 16 publications

Explainable Predictive Modeling for Limited Spectral Data

Explainable Predictive Modeling for Limited Spectral Data

A Fuzzy Fusion Rotating Machinery Fault Diagnosis Framework Based on the Enhancement Deep Convolutional Neural Networks

A Novel Baseline-Free Damage Detection Method Based on Path Scanning of Lamb Waves Using Mobile Transducers

Contact Info

Product

Resources

About