Abstract
Machine learning (ML) has attracted growing interest in process systems engineering for its potential in process design, synthesis, and optimization. By learning complex patterns from data, ML methods complement traditional first-principles modelling and heuristic approaches, particularly for conceptual process design and the exploration of alternatives. Although current text-based representations capture unit-level connectivity, they lack a holistic view of process intent, equipment hierarchy, and contextual information to guide learning and inference. Consequently, models trained on such linear token sequences tend to reproduce syntactic structure rather than underlying process reasoning, thus limiting interpretability and user control. In this work, we introduce a contextual framework for representing process flowsheet information in ML models that embeds process engineering logic directly into the model inputs. The approach combines a structured, text-based representation of process topology with context descriptors that define the process type and synthesis task. The task context, such as simplified block flow design, enables engineers to steer learning and generation towards intended designs. This shifts control from post-training filtering to context-driven learning, allowing models to act as flexible, engineer-guided synthesis tools rather than passive pattern generators. Transformer models were trained on 100, 000 synthetic ethylene glycol process flowsheets, with and without context features. To emulate user-guided synthesis, the models were asked to generate different design configurations involving critical equipment (reactors and distillation columns). Models trained without contextual input achieved an average success rate of 24.6% on average (59.6% in the best case), whereas context-aware models achieved 98.8% on average.