Trust-Aware Domain Adaptation Using Physics-Guided Reliability Learning for Cross-Condition Fault Diagnosis of
Saif Ullah1, Soonhyun Lim1, Jong-Myon Kim1
1Department of Electrical, Electronics and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of Korea.
Sensors (Basel, Switzerland)
|July 28, 2026
Summary
This study introduces a trust-aware domain adaptation network for reliable milling machine fault diagnosis. It improves accuracy by prioritizing physically consistent signals, enhancing cross-domain transfer learning.
Area of Science:
- Mechanical Engineering
- Artificial Intelligence
- Signal Processing
Background:
- Milling machine fault diagnosis faces challenges from varying operating conditions and limited labeled data.
- Conventional domain adaptation methods fail to account for varying signal reliability across different conditions.
Purpose of the Study:
- To develop a novel trust-aware domain adaptation network for robust cross-domain fault diagnosis in milling machines.
- To enhance deep representation learning by integrating physics-guided reliability estimation.
Main Methods:
- Extracting physically interpretable features (energy, spectral, nonlinear, impulsiveness) from vibration signals.
- Introducing a Physics Trust Network to estimate per-sample physical reliability scores.
- Employing a trust-weighted feature encoder and covariance alignment for domain adaptation.
Main Results:
- The proposed framework achieved an average accuracy of 98.07% on a real milling machine dataset.
- Demonstrated superior performance compared to state-of-the-art domain adaptation approaches.
- Ablation studies confirmed the independent contributions of reliability estimation and trust-guided learning.
Conclusions:
- The trust-aware domain adaptation network effectively addresses distribution shifts in cross-domain fault diagnosis.
- Physics-guided reliability estimation significantly improves the robustness and accuracy of fault diagnosis models.
- The framework enables effective knowledge transfer under varying operational conditions, particularly cross-speed scenarios.
Related Concept Videos
01:25Multimachine Stability
Multimachine stability analysis is crucial for understanding the dynamics and stability of power systems with multiple synchronous machines. The objective is to solve the swing equations for a network of M machines connected to an N-bus power system.
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
01:21Distributed Loads: Problem Solving
Beams are structural elements commonly employed in engineering applications requiring different load-carrying capacities. The first step in analyzing a beam under a distributed load is to simplify the problem by dividing the load into smaller regions, which allows one to consider each region separately and calculate the magnitude of the equivalent resultant load acting on each portion of the beam. The magnitude of the equivalent resultant load for each region can be determined by calculating...