Piping and Instrumentation Diagrams (P&IDs) are used in the process industry to visualize the elements present in a process plant and the connections between them. In reality, P&IDs are often only available as image, PDF, or as hard-copy. Methods to digitize P &IDs exist, but there are only few publicly available P &IDs that can be utilized for the development of new, especially data-driven, methods. We address this lack by proposing an algorithm that is able to create a random structure of P&IDs. Different parameters, such as the number and type of components, inflows, and outflows, can be defined. Our goal is to create a large, labeled, random dataset for the training and validation of models for the digitization of P &IDs. The algorithm consists of the two parts: graph creation and visualization. In this work, we present the graph creation part.

The introduction of AI methods in production or production-related environments meets with resistance from operators due to their lack of relevant experience and their responsibility for plant safety. To overcome these inhibitions one requires prototypical implementations, which offer considerable benefits, meet the highest requirements for reliability, are accepted by the operating personnel, and get support from those in charge. As a result, AI technologies must be embedded into the complex IT/OT infrastructure of the companies. Traceability, maintainability and longevity must also be guaranteed. As a first step towards this, we present a concept of the demonstrator and its first results, which should make AI comprehensible by visualizing challenges and exploring possibilities in the process industry.