Synthetic Data Augmentation and Deep Learning for the Fault Diagnosis of Rotating Machines

Khan, Asif; Hwang, Hyunho; Kim, Heung-Soo

doi:10.3390/math9182336

Cited by 29 publications

(13 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of neurons will determine the degree of complexity of a model [45]. Although overfitting can be solved by dropping some neurons [46], dropping out too many neurons will induce underfitting, like those results when trained with Set_2 augmented data with dropout value 0.5 shown in Table 5.…”

Section: Prediction Performancementioning

confidence: 99%

Exploration of hybrid deep learning algorithms for covid-19 mrna vaccine degradation prediction system

Ing

Abdullah²,

Mashor³

et al. 2022

Int. J. Adv. Intell. Informatics

View full text Add to dashboard Cite

Coronavirus causes a global pandemic that has adversely affected public health, the economy, including every life aspect. To manage the spread, innumerable measurements are gathered. Administering vaccines is considered to be among the precautionary steps under the blueprint. Among all vaccines, the messenger ribonucleic acid (mRNA) vaccines provide notable effectiveness with minimal side effects. However, it is easily degraded and limits its application. Therefore, considering the cruciality of predicting the degradation rate of the mRNA vaccine, this prediction study is proposed. In addition, this study compared the hybridizing sequence of the hybrid model to identify its influence on prediction performance. Five models are created for exploration and prediction on the COVID-19 mRNA vaccine dataset provided by Stanford University and made accessible on the Kaggle community platform employing the two deep learning algorithms, Long Short-Term Memory (LSTM) as well as Gated Recurrent Unit (GRU). The Mean Columnwise Root Mean Square Error (MCRMSE) performance metric was utilized to assess each model’s performance. Results demonstrated that both GRU and LSTM are befitting for predicting the degradation rate of COVID-19 mRNA vaccines. Moreover, performance improvement could be achieved by performing the hybridization approach. Among Hybrid_1, Hybrid_2, and Hybrid_3, when trained with Set_1 augmented data, Hybrid_3 with the lowest training error (0.1257) and validation error (0.1324) surpassed the other two models; the same for model training with Set_2 augmented data, scoring 0.0164 and 0.0175 MCRMSE for training error and validation error, respectively. The variance in results obtained by hybrid models from experimenting claimed hybridizing sequence of algorithms in hybrid modeling should be concerned.

show abstract

Section: Prediction Performancementioning

confidence: 99%

Exploration of hybrid deep learning algorithms for covid-19 mrna vaccine degradation prediction system

Ing

Abdullah²,

Mashor³

et al. 2022

Int. J. Adv. Intell. Informatics

View full text Add to dashboard Cite

show abstract

“…In addition, transfer learning also has been used in various fields. It was applied to sarcasm detection [40] in language processing and applied to damage detection and fault diagnosis of rotating machines [41,42].…”

Section: Transfer Learningmentioning

confidence: 99%

Wavelet and Neural Network-Based Multipath Detection for Precise Positioning Systems

Kim

Kee

2023

Mathematics

View full text Add to dashboard Cite

Multipath errors are significantly challenging in radio navigation systems. In particular, multipath errors in indoor environments cause significant errors in the position domain because not only the building materials that surround the environment but also all objects inside the building can reflect the navigation signals. Multipath errors in outdoor environments, such as in global navigation satellite system (GNSS) signal applications, have been widely studied for precise positioning. However, multipath studies for indoor applications have rarely been conducted because of the complicated environment and the many objects made of various materials in small areas. In this study, multipath mitigation methods using a shallow neural network and a transfer learning-based deep neural network were respectively considered to overcome the complexity caused by the reflected signals in indoor environments. These methods classify each measurement according to whether the measurement exhibits a severe multipath error. Carrier-phase measurements broadcasted from the transmitter were used for the wavelet transform, and the magnitude values after the transform were used for neural network-based learning. Shallow and deep networks attain approximately 87.1% and 85.6% detection accuracies, respectively, and the positioning error can be reduced by 10.4% and 9.4%, respectively, after multipath mitigation.

show abstract

“…Data augmentation is a widely used practice in ML when it is desired to increase the relevance of the dataset under study, mainly for image classification, natural language understanding, semantic segmentation and also in fault diagnosis [18,58,59,60]. In addition to increasing the amount of data for training, it is possible to insert small variations that, do not change the general context of the sample (although they exist).…”

Section: Data Augmentationmentioning

confidence: 99%

Fault Diagnosis using eXplainable AI: a Transfer Learning-based Approach for Rotating Machinery exploiting Augmented Synthetic Data

Brito¹,

Brito²,

Duarte³

2022

Preprint

View full text Add to dashboard Cite

Due to the growing interest for increasing productivity and cost reduction in industrial environment, new techniques for monitoring rotating machinery are emerging. Artificial Intelligence (AI) is one of the approaches that has been proposed to analyze the collected data (e.g., vibration signals) providing a diagnosis of the asset's operating condition. It is known that models trained with labeled data (supervised) achieve excellent results, but two main problems make their application in production processes difficult: (i) impossibility or long time to obtain a sample of all operational conditions (since faults seldom happen) and (ii) high cost of experts to label all acquired data. Another limitating factor for the applicability of AI approaches in this context is the lack of interpretability of the models (black-boxes), which reduces the confidence of the diagnosis and trust/adoption from users. To overcome these problems, a new generic and interpretable approach for classifying faults in rotating machinery based on transfer learning from augmented synthetic data to real rotating machinery is here proposed, namelly FaultD-XAI (Fault Diagnosis using eXplainable AI). To provide scalability using transfer learning, synthetic vibration signals are created mimicking the characteristic behavior of failures in operation. The application of Gradient-weighted Class Activation Mapping (Grad-CAM) with 1D Convolutional Neural Network (1D CNN) allows the interpretation of results, supporting the user in decision making and increasing diagnostic confidence. The proposed approach not only obtained promising diagnostic performance, but was also able to learn characteristics used by experts to identify conditions in a source domain and apply them in another target domain. The experimental results obtained on three datasets containing different mechanical faults suggest the method offers a promising approach on exploiting transfer learning, synthetic data and explainable artificial intelligence for fault diagnosis. Lastly, to guarantee reproducibility and foster research in the field, the developed dataset is made publicly available.

show abstract

Synthetic Data Augmentation and Deep Learning for the Fault Diagnosis of Rotating Machines

Cited by 29 publications

References 61 publications

Exploration of hybrid deep learning algorithms for covid-19 mrna vaccine degradation prediction system

Exploration of hybrid deep learning algorithms for covid-19 mrna vaccine degradation prediction system

Wavelet and Neural Network-Based Multipath Detection for Precise Positioning Systems

Fault Diagnosis using eXplainable AI: a Transfer Learning-based Approach for Rotating Machinery exploiting Augmented Synthetic Data

Contact Info

Product

Resources

About