General Electric had 37 patents in artificial intelligence during Q2 2024. General Electric Co filed a patent for a system to diagnose additive manufacturing devices by generating physics features for digital twins of components based on raw data and transfer functions, classifying components into different conditions, and determining component health. Another patent involves managing hydrogen storage systems by detecting elevated hydrogen concentrations, determining leak mass flow rates, and mitigating leaks by controlling system features based on the determined rates. GlobalData’s report on General Electric gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
General Electric had no grants in artificial intelligence as a theme in Q2 2024.
Recent Patents
Application: Systems, and methods for diagnosing an additive manufacturing device using a physics assisted machine learning model (Patent ID: US20240210930A1)
The patent filed by General Electric Co. describes a system for diagnosing an additive manufacturing device using a digital twin of a component. The system involves obtaining parameters and generating physics features for the digital twin, classifying the component based on physics features, and determining the health of the component using the generated physics features and classifiers. The apparatus includes memory and a processor to select classifiers, determine thresholds for physics features, evaluate data from the device's operation, classify the operation, and generate an output based on the classification. The output may include identifying errors or failures, determining root causes using machine learning or statistical models, and providing corrections for the root cause, such as adjusting the additive manufacturing device.
The system also involves updating classifiers based on wear and tear of the device, using physics-based models for extracting physics features, and incorporating data science models for classifiers. The classification process may involve a weighted average and transfer functions. Additionally, the patent includes a method for diagnosing an additive manufacturing device, which includes selecting classifiers based on physics features, determining thresholds, evaluating data, classifying operation, and generating an output. The method may also involve correcting errors based on the output. Overall, the patent outlines a comprehensive system and method for diagnosing and maintaining additive manufacturing devices using digital twins and physics-based models.
To know more about GlobalData’s detailed insights on General Electric, buy the report here.
Data Insights
From
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.
