Falkonry

Falkonry is US Navy’s First Choice for Signal-Aware AI

Falkonry Adopted by Naval Surface Warfare Center

For

Power Systems Monitoring

Read about the use case
Benefit 1

Capture correct data through early identification of data generation problems

Benefit 2

Analyze data in real-time and at scale without the need for data engineering

The only machine learning tool to analyze trillions of sensor data points

A single week of non-intrusive load monitoring data at one station produces nearly half a Trillion sensor data points.
  • Skip months of coding and debugging in Matlab and Python
  • Faster time to information for warfighter decision makers
  • Better data sharing across analytics team
Watch a demo Download factsheet

Falkonry Aligned with Navy 2025 Technology Priorities

Level 1

AI/Autonomy

Falkonry detects operational degradations and mission-threatening anomalies in ashore and afloat platforms, ensuring Navy fleet resilience, readiness, and efficiency.
Level 2

Edge AI

Run predictive models on remote platforms with low/no code AI/ML at the tactical edge, even for legacy equipment.
Level 3

Time Series Learning

Specialized machine learning to minimize prep, labeling and model engineering effort, while enabling data ontologies for curation.
Level 3

Assurance & Governance

Output explained with simple interfaces. Models traceable to data choices and outputs traceable to inputs.

Use Cases

Power Use Case

Power System Performance

Problem:

Non-intrusive load monitoring of facilities and platforms for improving availability and efficiency requires real-time power system performance analysis from HBM Genesis point-on-wave and proprietary phasor sensor data

Scale:

Dozens of sensors per site, 10KHz sampling rate, tens of billions of data points per day

Solution:

Time Series Intelligence analyzes power waveforms for non-conformities and anomalies across phases and power quality measurements and generates real-time alerts for issues

Sustainment Use Case

Sustainment Engineering

Problem:

Diagnosis of dark ship event on leading Naval destroyer causing extreme danger for crew and ship requires industrial automation data from native instruments and ship-board sensors

Scale:

Tens of thousands of sensors per ship at rates varying from 1 Hz to many KHz per sensor, results in tens of billions of data points per day

Solution:

Time Series Intelligence analyzes test-data-as-a-service data from the destroyer combined with ship design metadata, identified anomalies and correlations relevant to the dark ship event.

Sensor Fusion Use Case

Digital Engineering

Problem:

Validation and verification delayed by late discovery of design problems and component selection mismatches in new autonomous and manned Naval platforms

Scale:

30-day reliability tests executed across several duty cycles performed against real Naval engines used for ascertaining unmanned operation.

Solution:

Reconciliation of manual logs with machine discovered anomalies to identify non-conformance from sensor data collected during testing

Customer Fire-side Chat

Real-time AI in the Field with US Navy

Scalable tools

Scalable tools for modern data volumes

Teams face unprecedented challenges due to the sheer volume and complexity of data generated by an ever-growing array of sensors and systems. Falkonry’s scalable tools are capable of handling these massive data volumes efficiently and effectively

Scalable tools

Rapidly complete analysis projects

Automate much of the machine learning process, allowing users to quickly build and deploy models from sensor data. This significantly reduces the time and effort typically associated with developing AI/ML solutions.

Scalable tools

Intuitive, no-code tools for engineers

We democratize the benefits of advanced analytics through intuitive, no-code analysis tools. Unlocking insights from complex data shouldn't be limited to a few specialists but rather be possible for all mechanical and electrical engineers

Specialized AI for large volumes of sensor data

Highly automated

No programming or machine learning knowledge needed

Domain and sensor-independent

Analyze any combination of electrical, mechanical or ambient data

Supports high sampling rates

Work with data sampled thousands of times per second over long periods

Portable and hardware independent

Create, iterate and apply machine learning models on general-purpose hardware

Transparent and trustworthy

Explanations, confidence scores, and version tracking provide full provenance and deeper understanding of results

Explosion in time series data from complex systems

Go beyond traditional learning to discover behaviors

Unsupervised learning

Discover every distinct operating state without providing any labels or supervision

Self-supervised learning

Learn the normal range of behaviors from prior history to clearly identify unusual and rare behaviors

Semi-supervised learning

Learn desired mapping between labels and data patterns with as few as 2 examples

Custom models

Apply custom transformations and inference generation based on domain-knowledge

From data to embeddings to inferences

Working with Falkonry

Falkonry is an established Federal contractor with a proven track record of innovation and program success.

Sole-source
justified
Falkonry is Air Force SBIR Phase II awardee and sole-source justified for all DoD and Federal agencies

Rapid
procurement
Multiple ready pathways through a variety of contract vehicles: DLA, NASA SEWP, Amazon C2E and SBIR Phase III

High-side
availability
Air-gapped, C2E and on-prem deployment available along with IL4 and IL5 Cloud options

National
Security-vetted
DoD and In-Q-Tel vetted entity

User
certifications
In-person and virtual bootcamps available leading up to formal certification

Dedicated
Government support
Trained and vetted personnel for architecture, design and support activities
Contact Sales

Client Testimonials

Trusted across the military for digital transformation

Helpful Resources

Docs

Architecture of Time Series Intelligence

Blog post

Use AI to differentiate between earthquakes and underground explosions

Blog post

Interview with Ian Hersey: DoD’s push for digitalization and CBM+

Video

AI in Defense Operations

Video

Predictive Digital Twins

Paper

Collection and Analysis of LUSV Test Data

Take control of your mission.

Take away drudgery and toil from exploiting real-time data from sensors and telemetry. Rapidly figure out what's going on.

Start a trial