Dual disentanglement domain generalization method for rotating Machinery fault diagnosis

Mechanical Systems and Signal Processing, Journal Year: 2025, Volume and Issue: 228, P. 112460 - 112460

Published: Feb. 14, 2025

Language: Английский

---

Residual angular speed analysis based on laser Doppler vibrometer and its application in planetary gearbox diagnosis

Measurement, Journal Year: 2025, Volume and Issue: unknown, P. 116987 - 116987

Published: Feb. 1, 2025

Language: Английский

---

Fault Diagnosis of Hydro-Turbine Based on CEEMDAN-MPE Preprocessing Combined with CPO-BILSTM Modelling

Energies, Journal Year: 2025, Volume and Issue: 18(6), P. 1342 - 1342

Published: March 9, 2025

The accuracy of hydro-turbine fault diagnosis directly impacts the safety and operational efficiency hydroelectric power generation systems. This paper addresses challenge low diagnostic in traditional methods under complex environments. is achieved by proposing a signal preprocessing method that combines complete ensemble empirical mode decomposition with adaptive noise multiscale permutation entropy (CEEMDAN-MPE) optimized crested porcupine optimizer algorithm for bidirectional long- short-term memory network (CPO-BILSTM) model diagnosis. performs denoising using CEEMDAN, while MPE extracts key features. Furthermore, hyperparameters CPO-optimized BILSTM are innovatively introduced. extracted features fed into CPO-BILSTM A total 150 sets acoustic vibrational signals collected validation test bench different operating conditions. experimental results demonstrate 96.67%, representing improvements 23.34%, 16.67%, 6.67% over models such as LSTM (73.33%), CNN (80%), (90%), respectively. In order to verify effectiveness method, this paper, original signal, processed CEEMDAN-PE, CEEMDAN-MPE input controlled experiments. effectively denoises preserving integrates deep learning and, help intelligent optimization algorithms, significantly enhances model’s ability, improves applicability conditions, provides valuable supplement

Language: Английский

---

Calibrated source-free adaptation for intelligent diagnosis

Mechanical Systems and Signal Processing, Journal Year: 2025, Volume and Issue: 229, P. 112582 - 112582

Published: March 14, 2025

Language: Английский

---