Lockheed Martin signs SIAT license agreement with NEC for use in space programs
As Lockheed Martin designs and tests spacecraft, massive amounts of data points are created and it is important to review this information to identify any anomalies. This process could be extremely time consuming without the right tools in place, such as artificial intelligence (IA).
For years, Lockheed Martin incorporated System Invariant Analysis Technology from NEC Corporation (SIAT) in its space programs to facilitate this process. This will now continue until 2024 thanks to a new multi-year license agreement recently signed.
NEC’s advanced SIAT analytics engine uses data collected by sensors to learn system behavior and proactively detect inconsistencies. SIAT can identify relationships that have not been discovered by experts and visualize them comprehensively, providing tremendous assistance to employees monitoring facilities and systems.
“It gives us a holistic view of a system and an understanding that we have not been able to analyze in this way in the past.,” noted Kevin WoodwardLockheed Martin Space Fellow Emeritus and Senior Executive for AI.
Without these advanced AI and machine learning tools, it would be impossible for a single engineer to manually analyze the massive amounts of data at the speed needed to analyze the information in its entirety.
“These are very complex systems we work with and SIAT allows us to quickly analyze how the subsystems work with each other. SIAT can analyze large amounts of data in just a few hours. If you were to ask a human to do the same task, it could take hundreds of years“Woodward said.
Lockheed Martin has integrated SIAT into its Telemetry Analysis Technology for Universal Artificial Intelligence (T-TAURI) Artificial Intelligence Service, a comprehensive framework for time series analysis. This enables the company to conduct proactive anomaly detection during spacecraft design, development, production and testing – even before applications in mission operations. By integrating SIAT into Lockheed Martin’s T-TAURI platform, teams can gain a comprehensive and holistic understanding of a system, creating a foundational framework for other advanced technologies such as system-level digital twins.
Lockheed Martin has already successfully applied this technology on several operations, notably during the Orion tests. In four hours, T-TAURI and SIAT built a model of the Orion normal vehicle operation from nearly 150,000 sensors to establish more than 22 billion logical relationships for analysis. The resulting models can be used to monitor all future testing of subsequent vehicles to compare expected and irregular behavior to analyze consistency and aid in regression analysis.
In addition to Orion, Lockheed Martin is deploying SIAT in satellite production. The company uses AI technology to assist with prognostics, data review, and anomaly detection/resolution and testing. Applying big data, AI and ML capabilities will result in significant system production savings while improving mission assurance.