Siemens Energy has filed a patent for a method and system to model industrial processes, incorporating closed-loop feedback. The system uses a hybrid neural network model and first-principle dynamic model to predict outputs based on measured inputs. The model includes memoryless nonlinear blocks and a control block for controller parameters. GlobalData’s report on Siemens Energy gives a 360-degree view of the company including its patenting strategy. Buy the report here.

Smarter leaders trust GlobalData


Data Insights Siemens Energy AG - Company Profile

Buy the Report

Data Insights

The gold standard of business intelligence.

Find out more

According to GlobalData’s company profile on Siemens Energy, Ceramic composite hollow blades was a key innovation area identified from patents. Siemens Energy's grant share as of January 2024 was 54%. Grant share is based on the ratio of number of grants to total number of patents.

Method and system for modelling industrial processes using neural networks

Source: United States Patent and Trademark Office (USPTO). Credit: Siemens Energy AG

The patent application (Publication Number: US20240036532A1) describes a computer-implemented method for modeling an industrial process, specifically a closed-loop process involving a controller. The method involves measuring at least one input for the industrial process at a given time and predicting the output at a subsequent time using a hybrid neural network model. This model incorporates both neural network and first-principle models, including ordinary differential equations to define the rate of change over time. The method also includes a control block to integrate controller parameters into the model, allowing for accurate predictions based on training input and output observations.

Furthermore, the patent application includes additional claims such as incorporating setpoints and disturbances into the modeling process, utilizing a Hammerstein-Wiener model structure for memoryless nonlinear blocks, and repeating the measuring and predicting steps for multiple iterations. The method is adaptable for various industrial processes, such as gravity separation processes for oil, water, and gas, or controlling robotic arms. Additionally, the application covers a non-transitory computer-readable medium with processor control code for implementing the method and a data processing system with sensors, a controller, and a processor to carry out the modeling process efficiently. Overall, the patent application outlines a comprehensive approach to modeling industrial processes using a hybrid neural network model, combining neural network and first-principle models for accurate predictions and control.

To know more about GlobalData’s detailed insights on Siemens Energy, buy the report here.

Data Insights


The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.


GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.