首页|New Findings on Machine Learning Described by Investigators at Machine Learning Group (Scaling Up Machine Learning-based Chemical Plant Simulation: a Method for Fine-tuning a Model To Induce Stable Fixed Points)
New Findings on Machine Learning Described by Investigators at Machine Learning Group (Scaling Up Machine Learning-based Chemical Plant Simulation: a Method for Fine-tuning a Model To Induce Stable Fixed Points)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Elsevier
Investigators publish new report on Machine Learning. According to news reporting originating in Berlin, Germany, by NewsRx journalists, research stated, "Idealized first-principles models of chemical plants can be inaccurate. An alternative is to fit a Machine Learning (ML) model directly to plant sensor data." Financial supporters for this research include TU Berlin, Germany, BASF. The news reporters obtained a quote from the research from Machine Learning Group, "We use a structured approach: Each unit within the plant gets represented by one ML model. After fitting the models to the data, the models are connected into a flowsheet-like directed graph. We find that for smaller plants, this approach works well, but for larger plants, the complex dynamics arising from large and nested cycles in the flowsheet lead to instabilities in the solver during model initialization. We show that a high accuracy of the single -unit models is not enough: The gradient can point in unexpected directions, which prevents the solver from converging to the correct stationary state." According to the news reporters, the research concluded: "To address this problem, we present a way to fine -tune ML models such that initialization, even with very simple solvers, becomes robust." This research has been peer-reviewed.
BerlinGermanyEuropeCyborgsEmerging TechnologiesMachine LearningMachine Learning Group
NETL
NSTL
Elsevier
