KDN: A class-added continual learning framework for cross-machine fault diagnosis with limited samples

Mechanical Systems and Signal Processing, Год журнала: 2025, Номер 227, С. 112379 - 112379

Опубликована: Янв. 28, 2025

Язык: Английский

---

Fault diagnosis for ion mill etching machine cooling system based on omni-dimensional dynamic convolution and dynamic spatial pyramid pooling

Nondestructive Testing And Evaluation, Год журнала: 2025, Номер unknown, С. 1 - 32

Опубликована: Янв. 29, 2025

Язык: Английский

---

Rolling Bearing Dynamics Simulation Information-Assisted Fault Diagnosis with Multi-Adversarial Domain Transfer Learning

Lubricants, Год журнала: 2025, Номер 13(3), С. 116 - 116

Опубликована: Март 7, 2025

To address the issues of negative transfer and reduced stability in learning models for rolling bearing fault diagnosis under variable working conditions, an unsupervised multi-adversarial algorithm based on dynamics simulation data is proposed. Firstly, constructs both a global domain classifier subdomain classifier. In classifier, simulated vibration signal, which contains rich label information, generated by constructing dynamic equations to replace prediction target data, thereby achieving alignment marginal conditional distributions. Simultaneously, improved loss function with embedded maximum mean discrepancy designed reduce feature distribution gap between source data. Finally, weight allocation mechanism samples developed promote positive suppress transfer. Experiments were conducted using Paderborn University dataset Huazhong Science Technology dataset, accuracy rates 89.457% 96.436%, respectively. The results show that, comparison existing cross-domain methods, proposed method demonstrates significant improvements diagnostic stability, demonstrating its superiority operational conditions.

Язык: Английский

---

The PSQSgram: A new adaptive multi-channel periodic pulse extraction method for bearing fault diagnosis

Expert Systems with Applications, Год журнала: 2025, Номер 277, С. 127162 - 127162

Опубликована: Март 5, 2025

Язык: Английский

---

Digital twin-inspired methods for rotating machinery intelligent fault diagnosis and remain useful life prediction: A state-of-the-art review and future challenges

Mechanical Systems and Signal Processing, Год журнала: 2025, Номер 232, С. 112770 - 112770

Опубликована: Апрель 21, 2025

Язык: Английский

---

A novel edge intelligence application model with lightweight network and antinoise ability for bearing fault diagnosis

Structural Health Monitoring, Год журнала: 2025, Номер unknown

Опубликована: Апрель 27, 2025

With the rapid development of deep learning, edge intelligence applications (EIA) have achieved numerous results. However, redundant parameters model and strong noise pollution pose challenges to EIA for bearing fault diagnosis. To solve these challenges, a with lightweight network antinoise ability was proposed First, novel pluggable channel slimming module designed make lightweight, which can effectively reduce computation model. Second, an learning is proposed, has discriminator enhance network’s feature extraction capability through supervised learning. Finally, adaptive input generalization model, adaptively adjust information under different application environments improve stability accuracy The performance verified test rig experiments on two types train axle box bearings datasets, indicated achieves more than 89% diagnostic at −10 dB.

Язык: Английский

---

Integration of multi-relational graph oriented fault diagnosis method for nuclear power circulating water pumps

Measurement, Год журнала: 2024, Номер unknown, С. 115811 - 115811

Опубликована: Сен. 1, 2024

Язык: Английский

---

A state of the art in digital twin for intelligent fault diagnosis

Advanced Engineering Informatics, Год журнала: 2024, Номер 63, С. 102963 - 102963

Опубликована: Ноя. 29, 2024

Язык: Английский

---

Bi-level binary coded fully connected classifier based on residual network 50 with bottom and deep level features for bearing fault diagnosis

Engineering Applications of Artificial Intelligence, Год журнала: 2024, Номер 133, С. 108342 - 108342

Опубликована: Март 29, 2024

Язык: Английский

---

Bearing fault detection system based on a deep diffusion model

Structural Health Monitoring, Год журнала: 2024, Номер unknown

Опубликована: Сен. 9, 2024

Bearings are crucial components of modern high-precision machinery and rotating machines. Excellent bearing failure detection systems vital for ensuring that machines operate precisely. Advances in artificial neural networks (ANNs) increases computer processing speed have led to the application many ANN models various fields, including detection, with excellent outcomes being achieved. However, construct an model can precisely detect failures, large quantities data must be collected on types failures. Thus, considerable time spent collection before operated production line, which costs manufacturers. To overcome this problem, present study used a diffusion augmentation improve accuracy trained small quantity sound data. This performed time-delay mapping preprocess convert them into two-dimensional diagram reduce dimensionality features, novel approach field detection. Finally, convolutional network model, exhibited optimal classification performance diagrams, By comparing results obtained from augmented raw data, confirmed using augment generalization ability

Язык: Английский

---