Munich Re has patented a method involving machine learning models to predict future well drilling performance based on training data and bias criteria. The process includes refining model parameters iteratively until a termination criterion is met, resulting in a production-ready model for improved drilling efficiency. GlobalData’s report on Munchener Ruckversicherungs-Gesellschaft Aktiengesellschaft (Munich Re) gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Munchener Ruckversicherungs-Gesellschaft Aktiengesellschaft (Munich Re), was a key innovation area identified from patents. Munchener Ruckversicherungs-Gesellschaft Aktiengesellschaft (Munich Re)'s grant share as of April 2024 was 40%. Grant share is based on the ratio of number of grants to total number of patents.
Machine learning model for well drilling performance prediction
A recently granted patent (Publication Number: US11914680B2) outlines a method for improving well drilling performance through machine learning models. The method involves receiving a well drilling performance model request with training data sets, selecting bias criteria, choosing machine learning models, and refining model parameters iteratively until a termination criterion is met. The process includes determining outlier data sets, training the models, and outputting a production-ready model for predicting non-productive time (NPT) performance based on planned drilling parameters. The system also includes outlier analytics and extreme well drilling condition models to predict outlier events and extreme conditions, respectively.
Furthermore, the method and system involve generating drilling goals based on predicted NPT performance, outputting them through a drilling planning interface, and utilizing convolutional neural networks for the machine learning models. The models consider various independent variables such as planned runs, distance drilled, hole size, pressure severity, dog leg, vibration severity, and curvature categories to predict non-productive time values. Additionally, the system includes outlier classifier models to classify outlier data elements and improve drilling performance predictions. Overall, the patent aims to enhance drilling efficiency and reduce non-productive time by leveraging advanced machine learning techniques tailored to the drilling industry's specific requirements.
To know more about GlobalData’s detailed insights on Munchener Ruckversicherungs-Gesellschaft Aktiengesellschaft (Munich Re), 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.
