Domain-Shift Aware Neural Networks for Unbalance Characterization in Rotating Systems
This paper investigates the use of a domain-shift aware neural network for estimating unbalance masses in rotating shafts under varying operating conditions.
This paper presents a novel approach to addressing domain shift in regression tasks, which is not fully known in the training conditions.
Before reading this…
Applications
- →Structural Health Monitoring
- →Machine learning for mechanical systems
To understand this paper, make sure you know these concepts first:
- Neural networksfind papers →
- Domain adaptationfind papers →
Abstract
More Like ThisThis work investigates the application of a domain-shift aware neural network for regression tasks aimed at estimating unbalance masses in rotating shafts under varying operating conditions. Experimental data were collected from a test rig in which a primary shaft, equipped with a flange carrying unbalanced masses, was driven at different rotational speeds, while a secondary shaft could be optionally activated to introduce domain discrepancy. The unbalance masses were positioned at a fixed radial distance, and the dynamic response of the system was recorded using triaxial accelerometers. The inverse problem of mass estimation is formulated within a domain adaptation framework, where the network is trained with a maximum mean discrepancy strategy to align feature representations across source and target distributions. The results demonstrate the effectiveness of explicitly addressing domain shift in improving prediction accuracy, especially when the system's physical behavior and sources of domain discrepancy are not fully known and fall outside the training conditions. These findings highlight the potential of domain-shift aware models for regression tasks in Structural Health Monitoring.