Patents by Inventor Nataliya Yakut
Nataliya Yakut has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240061403Abstract: The present teachings relate to a method for improving a production process for manufacturing a chemical product using at least one input material at an industrial plant, the industrial plant comprising a plurality of physically separated equipment zones, the method comprising: providing, via an interface, an upstream object identifier comprising input material data; receiving, at a computing unit, real-time process data from one or more of the equipment zones; determining, via the computing unit, a subset of the real-time process data based on the upstream object identifier and a zone presence signal; computing, via the computing unit, at least one zone-specific performance parameter of the chemical product related to the upstream object identifier based on the subset of the real-time process data and historical data; determining, in response to at least one of the performance parameters, a target equipment zone where the input material and/or chemical product is to be sent.Type: ApplicationFiled: December 10, 2021Publication date: February 22, 2024Inventors: Christian Andreas Winkler, Hans Rudolph, Michael Hartmann, Markus Rautenstrauch, Yuan En Huang, Sebastian Wandernoth, Nataliya Yakut
-
Publication number: 20240024839Abstract: The present teachings relate to a method for monitoring a production process for manufacturing a chemical product at an industrial plant, the method comprising: providing an up-stream object identifier comprising input material data, receiving real-time process data from one or more of the equipment zones; determining a subset of the real-time process data based on the upstream object identifier and a zone presence signal; computing at least one zone-specific performance parameter of the chemical product related to the up-stream object identifier based on the subset of the real-time process data and historical data; appending, to the upstream object identifier, the at least one zone-specific performance parameter. The present teachings also relate to a system for monitoring a production process, a dataset, use, a method for generating the dataset and a software program for the same.Type: ApplicationFiled: September 16, 2021Publication date: January 25, 2024Inventors: Christian-Andreas Winkler, Hans Rudolph, Michael Hartmann, Markus Rautenstrauch, Yuan En Huang, Sebastian Wandernoth, Nataliya Yakut
-
Publication number: 20240012395Abstract: A method can be used for controlling a downstream production process for manufacturing an article at a downstream industrial plant, by processing at least one thermoplastic polyurethane (“TPU”) and/or expanded thermoplastic polyurethane (“ETPU”) material using the downstream production process. The method involves providing, at a downstream computing unit, a set of downstream control settings for controlling the production of the article. The downstream control settings are determined based on a downstream object identifier; at least one desired downstream performance parameter related to the article; and downstream historical data. The set of downstream control settings is usable for manufacturing the article at the downstream industrial plant. A corresponding system for downstream production, use, and software product are provided.Type: ApplicationFiled: September 16, 2021Publication date: January 11, 2024Applicant: BASE SEInventors: Christian-Andreas WINKLER, Hans Rudolph, Michael Hartmann, Markus Rautenstrauch, Yuan En Huang, Nataliya Yakut, Sebastian Wandermoth
-
Patent number: 11860617Abstract: 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).Type: GrantFiled: November 25, 2020Date of Patent: January 2, 2024Assignee: Technische Universitaet BerlinInventors: Nataliya Yakut, Simeon Sauer, Mihail Bogojeski, Franziska Horn, Klaus-Robert Mueller
-
Publication number: 20230409015Abstract: The present teachings relate to a method for improving a production process for manufacturing a chemical product at an industrial plant comprising at least one equipment and one or more computing units, and the product being manufactured by processing at least one input material, which method comprises: receiving real-time process data from the equipment; determining a subset of the real-time process data; computing at least one state related to the input material and/or the equipment. The present teachings also relate to a system for improving the production process, a use, and a software program.Type: ApplicationFiled: December 10, 2021Publication date: December 21, 2023Inventors: Christian Andreas Winkler, Hans Rudolph, Michael Hartmann, Markus Rautenstrauch, Yuan En Huang, Sebastian Wandernoth, Nataliya Yakut
-
Publication number: 20230390725Abstract: The present teachings relate to a method for monitoring and/or controlling a production process for manufacturing at least one industrial product at an industrial plant comprising at least one equipment by processing at least one input, the method comprising: receiving, via an input inter-face, real-time process data from the equipment; determining, via the computing unit, a subset of the real-time process data; providing as output data the subset of the real-time process data. The present teachings also relate to a system, a use, and a software product.Type: ApplicationFiled: December 10, 2021Publication date: December 7, 2023Inventors: Christian Andreas Winkler, Hans Rudolph, Michael Hartmann, Markus Rautenstrauch, Yuan En Huang, Sebastian Wandernoth, Nataliya Yakut
-
Publication number: 20230350395Abstract: The present teachings relate to a method for controlling a production process, for manufacturing a chemical product, comprising: providing an upstream object identifier comprising input material data and at least one desired performance parameter related to the chemical product; determining a set of process and/or operation parameters based on the upstream object identifier and the at least one desired performance parameter; determining zone-specific control settings for each of the equipment zones based on the determined set of process and/or operation parameters and historical data; providing the zone-specific control settings for controlling the production of the chemical product related to the upstream object identifier. The present teachings also relate to a system for controlling a production process, a use of the control settings, and a software product for implementing the method steps disclosed herein.Type: ApplicationFiled: September 16, 2021Publication date: November 2, 2023Inventors: Christian-Andreas Winkler, Hans Rudolph, Michael Hartmann, Markus Rautenstrauch, Yuan En Huang, Sebastian Wandernoth, Nataliya Yakut
-
Publication number: 20230341838Abstract: The present teachings relate to a method for controlling a downstream production process for manufacturing a chemical product using at least one precursor material, the method comprising: providing a set of downstream control settings for controlling the production of the chemical product, wherein the downstream control settings are determined based on: a downstream object identifier; the downstream object identifier comprising precursor data; at least one desired downstream performance parameter related to the chemical product; downstream historical data; and wherein the set of downstream control settings is usable for manufacturing the chemical product at the downstream industrial plant. The present teachings also relate to a system, a use and a software product.Type: ApplicationFiled: September 16, 2021Publication date: October 26, 2023Inventors: Christian-Andreas Winkler, Hans Rudolph, Michael Hartmann, Markus Rautenstrauch, Yuan En Huang, Sebastian Wandernoth, Nataliya Yakut
-
Publication number: 20230045548Abstract: 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.Type: ApplicationFiled: January 19, 2021Publication date: February 9, 2023Inventors: Nataliya Yakut, Mihail Bogojeski, Klaus-Robert Mueller
-
Publication number: 20230028276Abstract: 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).Type: ApplicationFiled: November 25, 2020Publication date: January 26, 2023Applicant: TECHNISCHE UNIVERSITÄT BERLINInventors: Nataliya Yakut, Simeon Sauer, Mihail Bogojeski, Franziska Horn, Klaus-Robert Mueller