Nicholas Ng

Eduardo de Conto, Blaise Genest, Arvind Easwaran et al.

Digital twins (DTs) are increasingly utilized to monitor, manage, and optimize complex systems across various domains, including civil engineering. A core requirement for an effective DT is to act as a fast, accurate, and maintainable surrogate of its physical counterpart, the physical twin (PT). To this end, machine learning (ML) is frequently employed to (i) construct real-time DT prototypes using efficient reduced-order models (ROMs) derived from high-fidelity simulations of the PT's nominal behavior, and (ii) specialize these prototypes into DT instances by leveraging historical sensor data from the target PT. Despite the broad applicability of ML, its use in DT engineering remains largely ad hoc. Indeed, while conventional ML pipelines often train a single model for a specific task, DTs typically require multiple, task- and domain-dependent models. Thus, a more structured approach is required to design DTs. In this paper, we introduce DesCartes Builder, an open-source tool to enable the systematic engineering of ML-based pipelines for real-time DT prototypes and DT instances. The tool leverages an open and flexible visual data flow paradigm to facilitate the specification, composition, and reuse of ML models. It also integrates a library of parameterizable core operations and ML algorithms tailored for DT design. We demonstrate the effectiveness and usability of DesCartes Builder through a civil engineering use case involving the design of a real-time DT prototype to predict the plastic strain of a structure.

Jonathan King, Nicholas Ng, Nobuko Yoshida

Modern web applications can now offer desktop-like experiences from within the browser, thanks to technologies such as WebSockets, which enable low-latency duplex communication between the browser and the server. While these advances are great for the user experience, they represent a new responsibility for web developers who now need to manage and verify the correctness of more complex and potentially stateful interactions in their application. In this paper, we present a technique for developing interactive web applications that are statically guaranteed to communicate following a given protocol. First, the global interaction protocol is described in the Scribble protocol language -- based on multiparty session types. Scribble protocols are checked for well-formedness, and then each role is projected to a Finite State Machine representing the structure of communication from the perspective of the role. We use source code generation and a novel type-level encoding of FSMs using multi-parameter type classes to leverage the type system of the target language and guarantee only programs that communicate following the protocol will type check. Our work targets PureScript -- a functional language that compiles to JavaScript -- which crucially has an expressive enough type system to provide static linearity guarantees. We demonstrate the effectiveness of our approach through a web-based Battleship game where communication is performed through WebSocket connections.