Special Issue on Physics-Informed Machine Learning for Smarter Design and Manufacturing

Journal of Computing and Information Science in Engineering

Physics-Informed Machine Learning (PIML) is a transformative approach in machine learning that integrates physical laws, principles, and domain knowledge into the learning process. Unlike traditional machine learning models which depend solely on data, PIML models are specifically designed to respect the underlying physics in the problems of interest. This integration is achieved by embedding physical equations, conservation laws, and other relevant physical constraints directly into the model’s architecture or training process. As such, PIML offers several advantages including enhanced predictive accuracy, improved generalization, and greater data efficiency, while ensuring the developed models' robustness, reliability, and interpretability. 

PIML for smarter design and manufacturing represents a cutting-edge paradigm that combines physics principles with advanced machine learning techniques to revolutionize the design and manufacturing processes. This innovative methodology harnesses the strengths of both domains to address complex industry challenges, such as optimizing system performance, reducing resource consumption, and improving product quality.  

---

Topic Areas

THE SCOPE OF THIS ISSUE INCLUDES BUT IS NOT LIMITED TO: