公开(公告)号：US11860617B2

公开(公告)日：2024-01-02

申请号：US17779737

申请日：2020-11-25

Applicant: BASF SE

Inventor： Nataliya Yakut ,  Simeon Sauer ,  Mihail Bogojeski ,  Franziska Horn ,  Klaus-Robert Mueller

IPC: G05B23/02

CPC classification number: G05B23/0283 ,  G05B23/0254

Abstract: By accurately predicting industrial aging processes (IAP), such as the slow deactivation of a catalyst in a chemical plant, it is possible to schedule maintenance events further in advance, thereby ensuring a cost-efficient and reliable operation of the plant. So far, these degradation processes were usually described by mechanistic models or simple empirical prediction models. In order to accurately predict IAP, data-driven models are proposed, comparing some traditional stateless models (linear and kernel ridge regression, as well as feed-forward neural networks) to more complex stateful recurrent neural networks (echo state networks and long short-term memory networks). Additionally, variations of the stateful models are discussed. In particular, stateful models using mechanistical pre-knowledge about the degradation dynamics (hybrid models). Stateful models and their variations may be more suitable for generating near perfect predictions when they are trained on a large enough dataset, while hybrid models may be more suitable for generalizing better given smaller datasets with changing conditions.

公开(公告)号：US20230045548A1

公开(公告)日：2023-02-09

申请号：US17793728

申请日：2021-01-19

Applicant: BASF SE ,  TECHNISCHE UNIVERSITÄT BERLIN

Inventor： Nataliya Yakut ,  Mihail Bogojeski ,  Klaus-Robert Mueller

IPC: G06N3/04 ,  G06N3/08 ,  G06N3/063 ,  G05B13/04

Abstract: The present invention relates to training predictive data-driven model for predicting an industrial time dependent process. A data driven generative model is introduced for modelling and generating complex sequential data comprising multiple modalities, by learning a joint time-dependent representation of the different modalities. The model may be configured to handle any combination of missing modalities, which enables conditional generation based on known modalities, providing a high degree of control over the properties of the generated sequences.

公开(公告)号：US20230028276A1

公开(公告)日：2023-01-26

申请号：US17779737

申请日：2020-11-25

Applicant: BASF SE

Inventor： Nataliya Yakut ,  Simeon Sauer ,  Mihail Bogojeski ,  Franziska Horn ,  Klaus-Robert Mueller

IPC: G05B23/02

Abstract: By accurately predicting industrial aging processes (IAP), such as the slow deactivation of a catalyst in a chemical plant, it is possible to schedule maintenance events further in advance, thereby ensuring a cost-efficient and reliable operation of the plant. So far, these degradation processes were usually described by mechanistic models or simple empirical prediction models. In order to accurately predict IAP, data-driven models are proposed, comparing some traditional stateless models (linear and kernel ridge regression, as well as feed-forward neural networks) to more complex stateful recurrent neural networks (echo state networks and long short-term memory networks). Additionally, variations of the stateful models are discussed. In particular, stateful models using mechanistical pre-knowledge about the degradation dynamics (hybrid models). Stateful models and their variations may be more suitable for generating near perfect predictions when they are trained on a large enough dataset, while hybrid models may be more suitable for generalizing better given smaller datasets with changing conditions.