A Digital twin for Diesel Engines: Operator-infused PINNs with Transfer Learning for Engine Health Monitoring

2024-12-16

arXiv.org

AI Summary

Conventional neural network-based modeling for diesel engines suffers from poor generalizability, limited physical interpretability, and inadequate support for component-level health monitoring. Method: This paper proposes a digital twin framework integrating physics-informed neural networks (PINNs) with deep neural operators (DeepONet). We design an operator-injected PINN architecture to construct a differentiable, physically interpretable surrogate model for airflow dynamics; introduce a two-stage transfer learning strategy to drastically reduce online retraining overhead; and jointly employ Dropout and Gaussian noise to quantify epistemic and aleatoric uncertainties. Contribution/Results: Experiments demonstrate high-accuracy identification of unknown parameters and dynamic prediction under low computational resource constraints. The framework enables real-time, robust, physics-driven health monitoring and maintenance预警, establishing a novel paradigm for intelligent engine operation and maintenance.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

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

Abstract

Improving diesel engine efficiency and emission reduction have been critical research topics. Recent government regulations have shifted this focus to another important area related to engine health and performance monitoring. Although the advancements in the use of deep learning methods for system monitoring have shown promising results in this direction, designing efficient methods suitable for field systems remains an open research challenge. The objective of this study is to develop a computationally efficient neural network-based approach for identifying unknown parameters of a mean value diesel engine model to facilitate physics-based health monitoring and maintenance forecasting. We propose a hybrid method combining physics informed neural networks, PINNs, and a deep neural operator, DeepONet to predict unknown parameters and gas flow dynamics in a diesel engine. The operator network predicts independent actuator dynamics learnt through offline training, thereby reducing the PINNs online computational cost. To address PINNs need for retraining with changing input scenarios, we propose two transfer learning (TL) strategies. The first strategy involves multi-stage transfer learning for parameter identification. While this method is computationally efficient as compared to online PINN training, improvements are required to meet field requirements. The second TL strategy focuses solely on training the output weights and biases of a subset of multi-head networks pretrained on a larger dataset, substantially reducing computation time during online prediction. We also evaluate our model for epistemic and aleatoric uncertainty by incorporating dropout in pretrained networks and Gaussian noise in the training dataset. This strategy offers a tailored, computationally inexpensive, and physics-based approach for parameter identification in diesel engine sub systems.

Problem

• Develops a hybrid framework combining physics-informed neural networks with DeepONet
• Reduces computational costs and retraining burden through transfer learning strategies
• Enhances diesel engine health monitoring with improved accuracy and interpretability

Innovation

• Combining physics-informed neural networks with deep operator networks
• Using transfer learning to reduce retraining burden
• Leveraging physics-based knowledge with data-driven training