面向工艺流程图控制结构自动生成的大语言模型方法
Toward automatic generation of control structures for process flow diagrams with large language models
AI总结:
提出一种基于Transformer的端到端方法,将控制结构预测视为翻译任务,利用SFILES 2.0表示PFD拓扑,通过预训练和微调实现自动生成,在生成数据上达到74.8%-89.2%的Top-5准确率。
摘要:
开发管道和仪表图(P&IDs)是工艺开发中的关键步骤。我们提出了一种数据驱动的控制结构预测方法。我们的方法受基于Transformer的端到端人类语言翻译模型启发。我们将控制结构预测视为翻译任务,其中没有控制结构的工艺流程图(PFDs)被翻译为带有控制结构的PFDs。我们使用SFILES 2.0符号将PFDs的拓扑表示为字符串。我们使用生成的PFDs预训练模型以学习语法结构。之后,利用迁移学习在真实PFDs上对模型进行微调。该模型在10,000个生成的PFDs上达到了74.8%的Top-5准确率,在100,000个生成的PFDs上达到了89.2%的Top-5准确率。这些有希望的结果显示了人工智能辅助工艺工程的巨大潜力。在312个真实PFDs数据集上的测试表明,工业应用需要更大的PFD数据集和混合人工智能解决方案。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。