Chevron has patented a system for reservoir modeling using neural networks to solve differential equations defining reservoir physics. The system utilizes measured data to create a neural ordinary differential equation network that accurately models reservoir characteristics. GlobalData’s report on Chevron gives a 360-degree view of the company including its patenting strategy. Buy the report here.

Smarter leaders trust GlobalData

Report-cover

Premium Insights Chevron Corp - Company Profile

Buy the Report

Premium Insights

The gold standard of business intelligence.

Find out more

According to GlobalData’s company profile on Chevron, Anti-wear lubricants was a key innovation area identified from patents. Chevron's grant share as of February 2024 was 70%. Grant share is based on the ratio of number of grants to total number of patents.

Reservoir modeling system using neural network with physics constraints

Source: United States Patent and Trademark Office (USPTO). Credit: Chevron Corp

A recently granted patent (Publication Number: US11921256B2) discloses a system and method for reservoir modeling using neural networks. The system includes physical processors configured to obtain reservoir equation information and measurement data for a reservoir with multiple wells. The physical equations defining the reservoir's physics are modeled as a neural network, with individual nodes representing each well. By preparing the neural network based on measured characteristics, the system can model reservoir characteristics constrained by the physics of the reservoir. The neural network includes nodes for injection and production wells, with capacitance-resistance modeling differential equations used to determine coefficients based on measured data.

Furthermore, the system and method involve modeling dynamic changes in inter-well connectivities and response times based on varying injection and production rates over time. The single-layer neural network outputs a solution constrained by the reservoir's physics, providing valuable insights for reservoir management. The method also includes steps for reservoir modeling using the prepared neural network, with input parameters such as well locations, injection rates, and production rates influencing the output of inter-well connectivities and response times. Overall, the patent presents an innovative approach to reservoir modeling using neural networks, offering a more efficient and accurate method for understanding and managing reservoir characteristics.

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

Premium 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

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

GlobalData’s Patent Analytics tracks patent filings and grants from official offices around the world. 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.