FedIFL: A federated cross-domain diagnostic framework for motor-driven systems with inconsistent fault modes

TL;DR

FedIFL is a federated diagnostic framework that improves fault detection in motor-driven systems across diverse working conditions by handling inconsistent fault modes and label spaces through invariant feature learning.

Contribution

The paper introduces FedIFL, a novel federated learning approach that addresses label space inconsistency and domain shifts in cross-client fault diagnosis.

Findings

FedIFL achieves superior fault diagnosis accuracy across diverse clients.

The framework effectively mitigates domain shifts and label space variations.

Experiments demonstrate FedIFL's robustness in real-world motor-driven systems.

Abstract

Due to the scarcity of industrial data, individual equipment users, particularly start-ups, struggle to independently train a comprehensive fault diagnosis model; federated learning enables collaborative training while ensuring data privacy, making it an ideal solution. However, the diversity of working conditions leads to variations in fault modes, resulting in inconsistent label spaces across different clients. In federated diagnostic scenarios, label space inconsistency leads to local models focus on client-specific fault modes and causes local models from different clients to map different failure modes to similar feature representations, which weakens the aggregated global model's generalization. To tackle this issue, this article proposed a federated cross-domain diagnostic framework termed Federated Invariant Features Learning (FedIFL). In intra-client training, prototype contrastive learning mitigates intra-client domain shifts, subsequently, feature generating ensures local models can access distributions of other clients in a privacy-friendly manner. Besides, in cross-client training, a feature disentanglement mechanism is introduced to mitigate cross-client domain shifts, specifically, an instance-level federated instance consistency loss is designed to ensure the instance-level consistency of invariant features between different clients, furthermore, a federated instance personalization loss and an orthogonal loss are constructed to distinguish specific features that from the invariant features. Eventually, the aggregated model achieves promising generalization among global label spaces, enabling accurate fault diagnosis for target clients' Motor Driven Systems (MDSs) with inconsistent label spaces. Experiments on real-world MDSs validate the effectiveness and superiority of FedIFL in federated cross-domain diagnosis with inconsistent fault modes.