Passive-sonar AI services for underwater domain awareness
Passive-sonar AI services: systems that detect, classify and re-identify vessels from the sound they radiate, and turn recordings into evidence an analyst can act on. The UDA track →
01Detection and classification pipelines
End-to-end systems that take raw hydrophone recordings and return detected, classified acoustic events: detection that adapts to the local ambient conditions of each recording, calibrated per-class probabilities, and evidence aggregated within a recording before anything is reported. Details →
02Vessel re-identification against a gallery
Acoustic fingerprints that match a new contact to a known hull or flag it as new. Enrolling a vessel is a single forward pass, with no retraining, and every comparison returns a score that can be ranked and thresholded. Details →
03DEMON analysis of vessel recordings
Shaft-rate and blade-rate estimation from cavitation noise, with the open-source DEMON-Analysis toolkit: interpretable, briefing-ready propulsion features that run alongside learned models and show the physical reason behind a match. Details →
04Offline, in-house deployment
Systems built to run entirely on the user organisation's own infrastructure and data: a frozen model with a growing gallery, no data egress, no retraining, GPU acceleration with CPU fallback, and open-source dependencies. Details →
Deep-learning services: models, training data and evaluation
Deep-learning services for underwater acoustics, and the models behind Oravont's UDA systems: networks that learn directly from raw hydrophone waveforms, the data to train them where labelled recordings run out, and evaluation that says what the results do and do not support. The deep-learning track →
01Raw-waveform models for underwater acoustics
Classifiers and embedding models built on SKANN, which learns its filterbank from the raw hydrophone waveform instead of a hand-set spectrogram, for closed-set classification or open-set retrieval of hulls. Details →
02Physics-grounded synthetic training data
Synthetic underwater acoustic data for pretraining where labelled recordings run out, generated from first-principle models of ship and ambient noise, kept in physical units and verified against classical references. Details →
03Robustness to ocean and recording conditions
Augmentation regimes that randomise recording-chain colouration, ambient noise and multipath while preserving the narrowband line structure that carries a vessel's identity. Details →
04Evaluation that is hard to flatter
Hull-disjoint, cross-passage evaluation protocols with transit deduplication and source-pure galleries, and reporting that states what the results do and do not support. Details →
Acoustic stealth engineering services
Underwater acoustic stealth engineering services for submarines and surface ships, from feasibility studies to delivered tools: acoustic modelling and radiated noise, target strength, own-sonar interference, airborne noise, shock and vibration, and mast design. Four in-house engineering tools, SSR-Sim, Dhvanyakalan, ABNContour and SMS-Suite, are available on enquiry. The stealth track →
01Acoustic modelling and underwater radiated noise (UWRN) estimation
A platform-level acoustic model of noise generation and propagation, and the total radiated noise it predicts under each operating condition. Details →
02Sonar signal reflection and target strength
How a hull returns active sonar, and how to return less of it. A vessel's reflection signature is governed by geometry, materials, coatings and structure. Details →
03Acoustic interference to own sonar
The noise a platform makes is also the noise its own sonar has to listen through. Interference is estimated at the sketch-design stage, so that mitigation is designed in rather than bolted on. Details →
04Airborne noise and habitability
Compartment noise levels during design, so that resting quarters and watchkeeping stations meet the staff requirements before the platform is built. Details →
05Shock, noise and vibration control
A safe, durable onboard environment for equipment and crew: the shock, vibration and noise limits that equipment must meet, and the mounting schemes that let it meet them. Details →
06Mast vibration and design
Masts carry periscopes, sensors, antennas and electronic-warfare systems, and they sit in the flow. Vibration control keeps the sensors accurate, the signature down and the structure sound. Details →
How engagements work
- Collaborative R&D with defence organisations and research laboratories, from feasibility study to working system.
- Consultancy in platform acoustics and passive-sonar AI, scoped to a specific design or data problem.
- Analysis of recordings you already hold, with a report that says what the results support, or delivered as a system that runs entirely on the user organisation's own infrastructure and data, with no data egress.
- Delivered tools and software: the stealth engineering tools on enquiry, and the open-source DEMON-Analysis toolkit and datasets listed under Tools & Data.
- Academic collaboration on underwater acoustics and machine learning.
Public materials on this site describe methods at an unclassified, headline level; programme specifics, customer data and evaluation results from sponsored work are not disclosed.
Start a conversation
Write to info@oravontsystems.com with the problem, the platform or data involved, and the timeframe. Enquiries reach a person, not a form.
Contact page