Building simulations and/or digital twins with AI
Plugboard is a Python-based event-driven framework designed for building and scaling simulations and digital twins of complex, interconnected systems. It supports integration with AI models, machine learning, and physics-based simulations, enabling flexible model composition and reconfiguration. The framework can run locally or be scaled across cloud infrastructure using Ray, with support for various simulation paradigms and data sources.
- ▪Plugboard allows users to create digital twin models of industrial processes, including those with material recirculation and AI integration.
- ▪It supports both discrete-time and event-based simulations and can scale from a laptop to cloud compute clusters using the Ray framework.
- ▪Models can be defined using a Python API or YAML files, with built-in support for LLMs, cloud storage, SQL databases, and logging for monitoring or process mining.
- ▪Users can initialize projects with an AI assistant via the 'plugboard ai init' command, which provides context for generating custom simulation code.
- ▪Optional installation extras include support for AWS, Azure, GCP, Redis, WebSockets, and hyperparameter optimization through Ray.
Opening excerpt (first ~120 words) tap to expand
Plugboard is an event-driven modelling and orchestration framework in Python for simulating and driving complex processes with many interconnected stateful components. You can use it to define models in Python and connect them together easily so that data automatically moves between them. After running your model on a laptop, you can then scale out on multiple processors or go to a compute cluster in the cloud thanks to the integration with the Ray framework. Some examples of what you can build with Plugboard include: Digital twin models of complex processes: It can easily handle common problems in industrial process simulation like material recirculation; Models can be composed from different underlying components, e.g.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.