Wind tunnel having low latency data publishing
Inventors
Assignees
United States Department of the Air Force
Publication Number
US-11933694-B1
Publication Date
2024-03-19
Expiration Date
2041-08-18
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Abstract
An instrumented wind tunnel. The wind tunnel receives a test subject which can be a model of an object to be tested with dynamic airflow. The test subject is fitted with at least one sensor to deliver data to a chassis, which in turn uses a network having at least 10 Gb/s capability to deliver the data to a RAM cache. The RAM cache can push the data to multiple viewers for real time monitoring of wind tunnel tests. The operator can then make live adjustments of the test conditions.
Core Innovation
The invention is an instrumented wind tunnel equipped to test a test subject, which may be a model of an object exposed to dynamic airflow. The wind tunnel includes an inlet, a test stage to receive the test subject, and an exhaust, all in mutual fluid communication. The key innovation comprises an instrumentation system having at least 10 sensors attached to the test subject, which report data to an in-memory networked cache (IMNC). This IMNC communicates with at least one viewer via a network with a transmission rate of at least 10 Gb/s, facilitating real-time data monitoring and adjustments.
The problem addressed is the inadequacy of prior wind tunnel data collection systems in terms of speed, resolution, and latency. Existing systems suffer from insufficient sampling rates (typically about 10 to 20 kHz), which can lead to missed data or phenomena crucial for understanding aerodynamic forces and characteristics. Current computer data gathering systems lack the capacity for higher sampling rates and real-time data accessibility, resulting in data loss, coarse data, and high latency unsuitable for dynamic testing and live adjustments during the test run.
The invention remedies these disadvantages by enabling high-frequency data collection (sampling rates of 50 kHz to at least 200 kHz), low-latency data storage, and access through the IMNC and high-speed networks. It supports simultaneous access to the data by multiple viewers without adversely affecting data push operations, thereby allowing live monitoring and control of test conditions. The invention also employs distributed data storage, push-pull isolation, sharding, and high-performance software configurations to optimize real-time data handling, greatly improving upon previous data retention time, bandwidth, and faster visualization.
Claims Coverage
The patent includes two independent claims and describes a number of inventive features related to the architecture and operation of the instrumented wind tunnel's data acquisition and communication system.
Instrumentation system with high sensor counts and IMNC communication
The wind tunnel incorporates at least 10 sensors attached to the test subject, reporting data to an in-memory networked cache (IMNC) which is connected to at least one viewer via a network supporting at least 10 Gb/s transmission rates, enabling real-time data access and visualization.
Distributed IMNC system with multiple submasters and high-throughput networking
The instrumentation system uses multiple IMNC instances, each equipped with a quad-core (or higher) processor and large RAM configurations (e.g., at least 64 GB per submaster), connected via a common 10 Gb/s switch to respective Ethernet cards. Data are sharded across multiple submasters to allow high data rates and increased storage, with separate physical or virtual machines each running instances of data stores, enabling horizontal scaling and improved push-pull isolation.
The claims collectively cover an instrumentation system for a wind tunnel that supports high-frequency data sampling through multiple sensors communicating with distributed, high-performance IMNC data stores connected via high-speed networks, supporting live data visualization and extended data history, overcoming prior limitations in latency, sampling rates, and data availability.
Stated Advantages
Enables sampling rates of at least 200 kHz over durations sufficient to capture dynamic phenomena with high resolution.
Supports real-time monitoring and processing without adverse impact on data acquisition or system performance.
Provides low latency data access (less than 10 ms) to processing machines, allowing live adjustments during wind tunnel tests.
Allows simultaneous access by multiple viewer machines without reducing data push performance.
Supports horizontal scaling and sharding of data across multiple machines or instances for increased storage duration and throughput.
Utilizes open-source software and efficient data encoding techniques (e.g., Flatten to String command) for fast data serialization and processing.
Reduces command overhead in data posting by using Lua scripts to consolidate multiple commands into a single network transaction.
Significantly improves bandwidth, time history, and data viewing time compared to prior art systems, enabling operators to perform responsive adjustments during tests.
Documented Applications
Testing of aerodynamic models such as aircraft wings, missiles, automobiles, and buildings in a wind tunnel to capture detailed aerodynamic forces, moments, pressures, and velocities under static and dynamic conditions.
Real-time monitoring and adjustment of test conditions based on high-speed sensor data streams, improving the accuracy and responsiveness of wind tunnel experiments.
Post-processing and analysis of aerodynamic data using viewers capable of computing power spectrum distributions and key performance indicators from live data.
Use in simulations of data acquisition and viewer processing for code development and verification prior to deployment with actual hardware.
Interested in licensing this patent?