A Multi-head Attention Fusion Network for Industrial Prognostics under Discrete Operational Conditions

2026-04-11

AI Summary

This study addresses the challenge of remaining useful life (RUL) prediction in complex industrial systems operating under discrete operational conditions, where abrupt condition transitions significantly disrupt degradation patterns. To tackle this issue, the authors propose a multi-head attention fusion network that explicitly encodes discrete operational conditions as embedding vectors and models them separately from monotonic degradation trends and residual noise. A bidirectional long short-term memory (BiLSTM) network captures temporal dependencies, while a novel multi-branch fusion module integrates condition-aware representations through an attention mechanism. Evaluated on NASA datasets, the proposed method substantially improves RUL prediction accuracy under varying operational conditions, demonstrating the effectiveness of explicit condition embedding and attention-based fusion for degradation modeling.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Life-Long and Continual Learning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Complex systems such as aircraft engines, turbines, and industrial machinery often operate under dynamically changing conditions. These varying operating conditions can substantially influence degradation behavior and make prognostic modeling more challenging, as accurate prediction requires explicit consideration of operational effects. To address this issue, this paper proposes a novel multi-head attention-based fusion neural network. The proposed framework explicitly models and integrates three signal components: (1) the monotonic degradation trend, which reflects the underlying deterioration of the system; (2) discrete operating states, identified through clustering and encoded into dense embeddings; and (3) residual random noise, which captures unexplained variation in sensor measurements. The core strength of the framework lies in its architecture, which combines BiLSTM networks with attention mechanisms to better capture complex temporal dependencies. The attention mechanism allows the model to adaptively weight different time steps and sensor signals, improving its ability to extract prognostically relevant information. In addition, a fusion module is designed to integrate the outputs from the degradation-trend branch and the operating-state embeddings, enabling the model to capture their interactions more effectively. The proposed method is validated using a dataset from the NASA repository, and the results demonstrate its effectiveness.

Problem

• industrial prognostics
• operating conditions
• degradation modeling
• multi-head attention
• discrete states

Innovation

• multi-head attention
• operational condition
• degradation modeling
• BiLSTM
• sensor fusion