Low-Frequency Adaptation-Deep Neural Network-Based Domain Adaptation Approach for Shaft Imbalance Fault Diagnosis

Arora, Jatin Kumar; Rajagopalan, Sudhar; Singh, Jaskaran; Purohit, Ashish

doi:10.1007/s42417-022-00848-7

Cited by 2 publications

(2 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Maximum mean discrepancy (MMD) [32] is often used by statistics matching-based DA methods to calculate the distribution distance in different domains, which can measure the distribution discrepancies of different datasets [33,34]. Given X {x i |x i ∼ p, i = 1, 2, .…”

Section: Maximum Mean Discrepancymentioning

confidence: 99%

Non-Uniformly Weighted Multisource Domain Adaptation Network For Fault Diagnosis Under Varying Working Conditions

Zhang,

Wang

et al. 2024

Neural Process Lett

View full text Add to dashboard Cite

Most transfer learning-based fault diagnosis methods learn diagnostic information from the source domain to enhance performance in the target domain. However, in practical applications, usually there are multiple available source domains, and relying on diagnostic information from only a single source domain limits the transfer performance. To this end, a non-uniformly weighted multisource domain adaptation network is proposed to address the above challenge. In the proposed method, an intra-domain distribution alignment strategy is designed to eliminate multi-domain shifts and align each pair of source and target domains. Furthermore, a non-uniform weighting scheme is proposed for measuring the importance of different sources based on the similarity between the source and target domains. On this basis, a weighted multisource domain adversarial framework is designed to enhance multisource domain adaptation performance. Numerous experimental results on three datasets validate the effectiveness and superiority of the proposed method.

show abstract

Section: Maximum Mean Discrepancymentioning

confidence: 99%

Non-Uniformly Weighted Multisource Domain Adaptation Network For Fault Diagnosis Under Varying Working Conditions

Zhang,

Wang

et al. 2024

Neural Process Lett

View full text Add to dashboard Cite

show abstract

“…Further, Xie et al [39] developed sparse auto-encoder based rotor mass imbalance identification with mean squared error loss function. In 2023, Arora et al [40] explored domain adaptation tasks for rotor mass imbalance prediction using maximum mean discrepancy using CNN. Identifying and diagnosing mass imbalance in a rotor system is challenging because Industrial machinery runs at varying speeds according to process demands, and the magnitude of mass imbalance is dependent on the square root of the rotor system's speed, which causes the domain shift issue.…”

Section: Introductionmentioning

confidence: 99%

Genetically optimised SMOTE-based adversarial discriminative domain adaptation for rotor fault diagnosis at variable operating conditions

Rajagopalan,

Purohit,

Singh

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

For safety, reliability, and uninterrupted output of gas turbines, aviation engines, power-generating equipment, pumps, gears, compressors etc., rotor mass imbalance must be detected and diagnosed to avoid catastrophic failure. Industry 4.0 relies on predictive digital maintenance and deep learning-based convolutional neural network (CNN), which predicts defects but fails if the operating conditions change. Research studies in various fields indicate that the domain shift issue occurs due to source and target samples being from different domains, which reduces prediction capability. Moreover, research studies are scarce in examining prediction capability under varying operating speeds for rotor mass imbalance. Hence, this research proposes the adversarial discriminative domain adaptation (ADDA) technique which predicts machine failures under various operational conditions. The efficacy of ADDA has been explored by introducing 1D-CNN as a source and a target encoder inside ADDA's architecture to take advantage of CNN's feature extraction capability. Further, this research effectively tackles CNN's inherent issues of overfitting and hyperparameters value selection. Furthermore, The real-world scenario has more healthy samples than fault condition samples, causing a multiclass imbalance in sample data, which affects the classification decision boundary and causes biased prediction. Hence, the proposed methodology first addresses the class imbalance through synthetic minority oversampling (SMOTE), then genetic algorithm optimizes 1D-CNN's hyperparameters, and the effective dropout layer positioning solves the overfitting. Finally, the deep learning-based SMOTE_ADDA_GO-1D-CNN decreases domain discrepancy with adversarial discriminative domain adaptation. The proposed methodology's efficacy has been explored through F1-Score, which is used as multiclass evaluation metrics, and it has been benchmarked against standard machine learning and deep learning algorithms. The test results of the proposed methodology surpassed all of them with maximum prediction accuracy. Thus, this study contributes to rotor mass imbalance detection and diagnosis for multiclass imbalanced data under varying operational conditions by successfully overcoming potential challenges during fault prediction.

show abstract

Low-Frequency Adaptation-Deep Neural Network-Based Domain Adaptation Approach for Shaft Imbalance Fault Diagnosis

Cited by 2 publications

References 73 publications

Non-Uniformly Weighted Multisource Domain Adaptation Network For Fault Diagnosis Under Varying Working Conditions

Non-Uniformly Weighted Multisource Domain Adaptation Network For Fault Diagnosis Under Varying Working Conditions

Genetically optimised SMOTE-based adversarial discriminative domain adaptation for rotor fault diagnosis at variable operating conditions

Contact Info

Product

Resources

About