The process engineering domain widely uses Process Flow Diagrams (PFDs) and Process and Instrumentation Diagrams (P&IDs) to represent process flows and equipment configurations. However, the P&IDs and PFDs, hereafter called flowsheets, can contain errors causing safety hazards, inefficient operation, and unnecessary expenses. Correcting and verifying flowsheets is a tedious, manual process. We propose a novel generative AI methodology for automatically identifying errors in flowsheets and suggesting corrections to the user, i.e., autocorrecting flowsheets. Inspired by the breakthrough of Large Language Models (LLMs) for grammatical autocorrection of human language, we investigate LLMs for the autocorrection of flowsheets. The input to the model is a potentially erroneous flowsheet and the output of the model are suggestions for a corrected flowsheet. We train our autocorrection model on a synthetic dataset in a supervised manner. The model achieves a top-1 accuracy of 80% and a top-5 accuracy of 84% on an independent test dataset of synthetically generated flowsheets. The results suggest that the model can learn to autocorrect the synthetic flowsheets. We envision that flowsheet autocorrection will become a useful tool for chemical engineers.@en

ChatGPT is a powerful language model from OpenAI that is arguably able to comprehend and generate text. ChatGPT is expected to greatly impact society, research, and education. An essential step to understand ChatGPT’s expected impact is to study its domain-specific answering capabilities. Here, we perform a systematic empirical assessment of its abilities to answer questions across the natural science and engineering domains. We collected 594 questions on natural science and engineering topics from 198 faculty members across five faculties at Delft University of Technology. After collecting the answers from ChatGPT, the participants assessed the quality of the answers using a systematic scheme. Our results show that the answers from ChatGPT are, on average, perceived as “mostly correct”. Two major trends are that the rating of the ChatGPT answers significantly decreases (i) as the educational level of the question increases and (ii) as we evaluate skills beyond scientific knowledge, e.g., critical attitude.

@en

We propose a novel method enabling autocompletion of chemical flowsheets. This idea is inspired by the autocompletion of text. We represent flowsheets as strings using the text-based SFILES 2.0 notation and learn the grammatical structure of the SFILES 2.0 language and common patterns in flowsheets using a transformer-based language model. We pre-train our model on synthetically generated flowsheet topologies to learn the flowsheet language grammar. Then, we fine-tune our model in a transfer learning step on real flowsheet topologies. Finally, we use the trained model for causal language modeling to autocomplete flowsheets. Eventually, the proposed method can provide chemical engineers with recommendations during interactive flowsheet synthesis. The results demonstrate a high potential of this approach for future AI-assisted process synthesis but also reveal the limitations at the present state and the next steps that need to be taken to deploy this technique in realistic flowsheet synthesis scenarios.

@en

Artificial intelligence has great potential for accelerating the design and engineering of chemical processes. Recently, we have shown that transformer-based language models can learn to auto-complete chemical process flowsheets using the SFILES 2.0 string notation. Also, we showed that language translation models can be used to translate Process Flow Diagrams (PFDs) into Process and Instrumentation Diagrams (P&IDs). However, artificial intelligence methods require big data and flowsheet data is currently limited. To mitigate this challenge of limited data, we propose a new data augmentation methodology for flowsheet data that is represented in the SFILES 2.0 notation. We show that the proposed data augmentation improves the performance of artificial intelligence-based process design models. In our case study flowsheet data augmentation improved the prediction uncertainty of the flowsheet autocompletion model by 14.7%. In the future, our flowsheet data augmentation can be used for other machine learning algorithms on chemical process flowsheets that are based on SFILES notation.

@en

SFILES are a text-based notation for chemical process flowsheets. They were originally proposed by d’Anterroches (Process flow sheet generation & design through a group contribution approach) who was inspired by the text-based SMILES notation for molecules. The text-based format has several advantages compared to flowsheet images regarding the storage format, computational accessibility, and eventually for data analysis and processing. However, the original SFILES version cannot describe essential flowsheet configurations unambiguously, such as the distinction between top and bottom products. Neither is it capable of describing the control structure required for the safe and reliable operation of chemical processes. Also, there is no publicly available software for decoding or encoding chemical process topologies to SFILES. We propose the SFILES 2.0 with a complete description of the extended notation and naming conventions. Additionally, we provide open-source software for the automated conversion between flowsheet graphs and SFILES 2.0 strings. This way, we hope to encourage researchers and engineers to publish their flowsheet topologies as SFILES 2.0 strings. The ultimate goal is to set the standards for creating a FAIR database of chemical process flowsheets, which would be of great value for future data analysis and processing.

@en

Advances in deep convolutional neural networks led to breakthroughs in many computer vision applications. In chemical engineering, a number of tools have been developed for the digitization of Process and Instrumentation Diagrams. However, there is no framework for the digitization of process flow diagrams (PFDs). PFDs are difficult to digitize because of the large variability in the data, e.g., there are multiple ways to depict unit operations in PFDs. We propose a two-step framework for digitizing PFDs: (i) unit operations are detected using a deep learning powered object detection model, (ii) the connectivities between unit operations are detected using a pixel-based search algorithm. To ensure robustness, we collect and label over 1000 PFDs from diversified sources including various scientific journals and books. To cope with the high intra-class variability in the data, we define 47 distinct classes that account for different drawing styles of unit operations. Our algorithm delivers accurate and robust results on an independent test set. We report promising results for line and unit operation detection with an Average Precision at 50 percent (AP50) of 88% and an Average Precision (AP) of 68% for the detection of unit operations.

@en

Developing Piping and Instrumentation Diagrams (P&IDs) is a crucial step during process development. We propose a data-driven method for the prediction of control structures. Our methodology is inspired by end-to-end transformer-based human language translation models. We cast the control structure prediction as a translation task where Process Flow Diagrams (PFDs) without control structures are translated to PFDs with control structures. We represent the topology of PFDs as strings using the SFILES 2.0 notation. We pretrain our model using generated PFDs to learn the grammatical structure. Thereafter, the model is fine-tuned leveraging transfer learning on real PFDs. The model achieved a top-5 accuracy of 74.8% on 10,000 generated PFDs and 89.2% on 100,000 generated PFDs. These promising results show great potential for AI-assisted process engineering. The tests on a dataset of 312 real PFDs indicate the need for a larger PFD dataset for industry applications and hybrid artificial intelligence solutions.

@en

Flowsheets are the most important building blocks to define and communicate the structure of chemical processes. Gaining access to large data sets of machine-readable chemical flowsheets could significantly enhance process synthesis through artificial intelligence. A large number of these flowsheets are publicly available in the scientific literature and patents but hidden among innumerable other figures. Therefore, an automatic program is needed to recognize flowsheets. In this paper, we present a deep convolutional neural network (CNN) that can identify flowsheets within images from literature. We use a transfer learning approach to initialize the CNN's parameter. The CNN reaches an accuracy of 97.9% on an independent test set. The presented algorithm can be combined with publication mining algorithms to enable an autonomous flowsheet mining. This will eventually result in big chemical process databases.

@en

The design and techno-economic performance of a compact additively manufactured (AM) molten salt (MS)-to-supercritical carbon di-oxide (sCO ₂) primary heat exchanger (PHE) for solar thermal application is described. The PHE design consists of sCO ₂ flow through an array of microscale pin fins while the MS flows through mm-scale rectangular channels. Constraints imposed by AM using laser powder bed fusion method are considered in the design. Structural and fluid flow simulations are performed to arrive at a viable design of the core and headers. A simplified one-dimensional steady state model for the PHE is developed including the impact of surface roughness from the AM process. A process-based cost model is used to determine the tradeoff between thermofluidic design and manufacturing cost. A parametric study is performed using the thermo-fluidic and cost models to determine the set of geometrical and flow variables that result in high power density and low cost, while restricting the pressure drop on the sCO ₂ side to less than 2% of line pressure. Flow rates of MS and sCO ₂ were varied over heat capacity rate ratios ranging from 0.2 to 1. Results indicate that it is possible to design a low-pressure drop AM PHE with an effectiveness of 90% and a power density in excess of 10 MW/m ³ (including headers). Fabrication of representative nickel superalloy specimens are shown to demonstrate that low-porosity parts with the requisite dimensional tolerance of PHE core can be generated.

@en