Search for: All records

Chatter, a self-excited vibration phenomenon, is a critical challenge in high-speed machining operations, affecting tool life, product surface quality, and overall process efficiency. While machine learning models trained on simulated data have shown promise in detecting chatter, their real-world applicability remains uncertain due to discrepancies between simulated and actual machining environments. The primary goal of this study is to bridge the gap between simulation-based machine learning models and real-world applications by developing and validating a Random Forest-based chatter detection system. This research focuses on improving manufacturing efficiency through reliable chatter detection by integrating Operational Modal Analysis (OMA), Receptance Coupling Substructure Analysis (RCSA), and Transfer Learning (TL). The study applies a Random Forest classification model trained on over 140,000 simulated machining datasets, incorporating techniques like Operational Modal Analysis (OMA), Receptance Coupling Substructure Analysis (RCSA), and Transfer Learning (TL) to adapt the model for real-world operational data. The model is validated against 1600 real-world machining datasets, achieving an accuracy of 86.1%, with strong precision and recall scores. The results demonstrate the model’s robustness and potential for practical implementation in industrial settings, highlighting challenges such as sensor noise and variability in machining conditions. This work advances the use of predictive analytics in machining processes, offering a data-driven solution to improve manufacturing efficiency through more reliable chatter detection. 

Abstract The mass deployment of distributed energy resources (DERs) to achieve clean energy objectives has become a major goal across several states in the U.S. However, the viability and reality of achieving these goals in dense urban areas, such as New York City, are challenged by several ‘Techno‐Economic’ barriers associated with available land space and the number of AC/direct current (DC) conversion stages that requires multiple electrical balance of plant (BOP) equipment for pairing/interconnecting these resources to the grid. The fundamental issue of interconnection is addressed by assessing the use of a common DC bus in a one‐of‐a‐kind configuration (to pair grid‐connected energy storage, photovoltaic, and electric vehicle chargers (EVC) systems) and reduce the number of BOP equipment needed for deployment. Building on similar work that has touched on distribution‐level DC interconnection, this paper will also address the intricacies of interconnecting third‐party and Utility DERs to a DC‐based point of common coupling. It will examine the requisite site controller configuration (control architecture) and requirements to coordinate the energy storage system's use between managing Utility and Third‐Party EVC demand while prioritising dispatch. The result shows that the DC‐coupled system is technologically feasible and hierarchical control architecture is recommended to maintain stability during various use cases proposed. This will inform a lab demonstration of this system that aims to test DC integration of the DERs with recommendations for the microgrid (MG) controllers and reduction in the BOP equipment. These learnings will then be applied to practical grid‐scale deployment of the systems at Con Edison's Cedar Street Substation. This system, if proven successful, has the potential to change the way community distributed generation and MGs are interconnected to the Utility System.