An official website of the United States government
Machine learning (ML) has shown to be an effective alternative to physical models for quality prediction and process optimization of metal additive manufacturing (AM). However, the inherent “black box” nature of ML techniques such as those represented by artificial neural networks has often presented a challenge to interpret ML outcomes in the framework of the complex thermodynamics that govern AM. While the practical benefits of ML provide an adequate justification, its utility as a reliable modeling tool is ultimately reliant on assured consistency with physical principles and model transparency. To facilitate the fundamental needs, physics-informed machine learning (PIML) has emerged as a hybrid machine learning paradigm that imbues ML models with physical domain knowledge such as thermomechanical laws and constraints. The distinguishing feature of PIML is the synergistic integration of data-driven methods that reflect system dynamics in real-time with the governing physics underlying AM. In this paper, the current state-of-the-art in metal AM is reviewed and opportunities for a paradigm shift to PIML are discussed, thereby identifying relevant future research directions.
more »
« less
This content will become publicly available on January 1, 2027
Physics-Informed Data-Driven Modeling of HVAC Systems: A Systematic Analysis
Heating, ventilation, and air conditioning (HVAC) systems account for a significant portion of energy consumption in developed countries. Accurately identifying their dynamics is crucial for developing effective controllers. However, it is challenging due to the system’s nonlinearities and variations across building types. Data-driven approaches have shown great promise in modeling the dynamics of HVAC systems, replacing traditional ordinary differential equations. However, relying solely on data can lead to poor generalization, particularly when the training data is limited or when unknown disturbances, such as weather conditions and occupant behavior, are present. Physics-informed machine learning (PIML) techniques have been developed for integrating physical principles into machine learning methods to improve the accuracy and data efficiency of modeling of dynamical systems. This paper investigates PIML techniques that incorporate three different physical properties: monotonicity, boundedness, and system structure. These models are benchmarked against physics-agnostic machine learning (PAML) approaches and the gray-box modeling technique to further highlight the performance of PIML models in terms of accuracy, robustness, and data efficiency for modeling HVAC systems from real data. Experimental data collected from a real-world HVAC system are used for systematically studying and analyzing thirteen gray-box, PAML, and PIML modeling techniques in different scenarios. Our results demonstrate that PIML models outperform PAML models in predicting the temperature dynamics of HVAC systems, especially when the training data is limited, unreliable, or noisy, with accurate and robust performance. Furthermore, we identify which physical properties are the most beneficial for enhancing machine learning performance for HVAC system identification.
more »
« less
- PAR ID:
- 10670470
- Publisher / Repository:
- IEEE
- Date Published:
- Journal Name:
- IEEE Access
- Volume:
- 14
- ISSN:
- 2169-3536
- Page Range / eLocation ID:
- 6481-6500
- Subject(s) / Keyword(s):
- HVAC systems, physics-informed machine learning, Gaussian process, neural network, gray-box modeling, sparse identification of nonlinear dynamics, data-driven modeling
- Format(s):
- Medium: X
- Associated Dataset(s):
- View Associated Dataset(s) >>
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Physics-informed machine learning (PIML) is a set of methods and tools that systematically integrate machine learning (ML) algorithms with physical constraints and abstract mathematical models developed in scientific and engineering domains. As opposed to purely data-driven methods, PIML models can be trained from additional information obtained by enforcing physical laws such as energy and mass conservation. More broadly, PIML models can include abstract properties and conditions such as stability, convexity, or invariance. The basic premise of PIML is that the integration of ML and physics can yield more effective, physically consistent, and data-efficient models. This paper aims to provide a tutorial-like overview of the recent advances in PIML for dynamical system modeling and control. Specifically, the paper covers an overview of the theory, fundamental concepts and methods, tools, and applications on topics of: 1) physics-informed learning for system identification; 2) physics-informed learning for control; 3) analysis and verification of PIML models; and 4) physics-informed digital twins. The paper is concluded with a perspective on open challenges and future research opportunities.more » « less
-
Abstract Physics-informed machine learning (PIML), the combination of prior physics knowledge with data-driven machine learning models, has emerged as an effective means of mitigating a shortage of training data, increasing model generalizability, and ensuring physical plausibility of results. In this paper, we survey a wide variety of recent works in PIML and summarize them from three key aspects: 1) motivations of PIML, 2) physics knowledge in PIML, and 3) methods of physics knowledge integration in PIML. We additionally discuss current challenges and corresponding research opportunities in PIML.more » « less
-
Abstract Adhesive bonding of composite materials has become increasingly crucial for advanced engineering applications, offering unique advantages for lightweight and high-performance designs. This study presents a novel framework, physics-informed failure mode proportion prediction (PIFMP) model, for predicting failure mode proportions in composite adhesive joints, addressing critical gaps in understanding mixed-mode failure behaviors. In contrast to conventional approaches that focus solely on force or stress prediction, this research integrates important parameters from multistage manufacturing processes (MMPs) and simulation data into a physics-informed machine learning (PIML) framework, enabling proactive failure prediction and design optimization. The proposed framework unifies data-driven machine learning models with features derived from finite element analysis (FEA), incorporating cohesive zone modeling (CZM) to capture the physical dynamics of adhesive behavior under lap shearing. By embedding FEA-based physics features into the machine learning process and leveraging a time-series transformer model to analyze the temporal progression of interfacial damage and separation, the framework ensures predictive accuracy and physics-informed consistency, enabling precise analysis of failure mechanisms. The empirical study validates the effectiveness and the reliability of the framework, demonstrating enhanced predictive performance through cross-validation. The work establishes a foundational approach for failure analysis and provides a robust basis for future advancements.more » « less
-
Data-driven approaches are increasingly popular for identifying dynamical systems due to improved accuracy and availability of sensor data. However, relying solely on data for identification does not guarantee that the identified systems will maintain their physical properties or that the predicted models will generalize well. In this paper, we propose a novel method for data-driven system identification by integrating a neural network as the first-order derivative of the learned dynamics in a Taylor series instead of learning the dynamical function directly. In addition, for dynamical systems with known monotonic properties, our approach can ensure monotonicity by constraining the neural network derivative to be non-positive or non-negative to the respective inputs, resulting in Monotonic Taylor Neural Networks (MTNN). Such constraints are enforced by either a specialized neural network architecture or regularization in the loss function for training. The proposed method demonstrates better performance compared to methods without the physics-based monotonicity constraints when tested on experimental data from an HVAC system and a temperature control testbed. Furthermore, MTNN shows good performance in the control application of a model predictive controller for a practical nonlinear MIMO system.more » « less
