AcoustR.
Diagnostics from sound.
AcoustR turns microphone signals into condition assessments for engines and machines. Where traditional condition-monitoring needs a vibration-sensor stack bolted onto every asset, AcoustR works from the sound the asset already makes — making diagnostics radically cheaper to deploy and easier to scale.
From signal to decision.
A pipeline that compresses days of expert listening and trial-and-error into a model-driven assessment. Built on the same sensor-optimisation and diagnostic-contribution thinking that powers the underlying research.
Capture
A microphone — fixed or hand-held — records the asset under operating conditions. No invasive instrumentation, no downtime to install.
Decompose
Signal-processing isolates the diagnostic features that distinguish a healthy machine from a degrading one — frequency bands, transients, harmonics.
Decide
A condition score with explicit uncertainty, not a black-box label. Operators get an action: keep running, schedule, or stop.
Diagnostic value, not more sensors.
Most condition-monitoring stacks are sold by sensor count. The research underneath AcoustR — the Multi-Objective Sensor Optimisation Framework (MOSOF) and the Normalised Diagnostic Contribution Index (NDCI) — proves that a smaller, smarter sensor set can match or beat a larger one when you actually score what each sensor contributes to a diagnosis.
AcoustR takes that insight to its limit: in many machines, a single well-placed microphone carries enough diagnostic information to act on. The product is what falls out when you treat sensor selection as an optimisation problem rather than a procurement decision.
Designed for
- Industrial assets where vibration sensors are too expensive or invasive to install at scale
- Fleets where consistency of assessment matters more than per-asset depth
- MRO workflows that need triage before tear-down
- Aerospace and automotive R&D needing fast acoustic baselines
Not a fit for
- Single bespoke assets where a full digital-twin already exists
- Environments dominated by uncontrolled background noise
- Failure modes with no acoustic signature
Where it goes next.
Research foundation
Sensor-optimisation methods (MOSOF · NDCI) developed and peer-reviewed across three first-author Sensors papers. Validated across four aircraft subsystems (Engine, Fuel, EPS, ECS) on Cranfield's SESAC platform.
Live product
Acoustic diagnostic pipeline running on first-generation hardware. Currently working with early customers and pilot partners across industrial machinery.
Vertical depth
Codified failure-mode libraries for the highest-value verticals (rotating machinery, fluid systems). Self-serve onboarding for fleet customers.
Multi-modal fusion
Combine acoustic with the minimum-viable additional sensor — selected by NDCI — to extend coverage to failure modes that are silent to the microphone.
From the founder
"I spent four years asking what makes a sensor network good — not just which sensors detect what, but which contribute the most diagnostic value per unit of cost, weight, and reliability burden. The answer turned out to be measurable. AcoustR is what happens when you take that answer to a single, low-cost, high-information sensor — a microphone — and build a real product around it."
— Dr Burak Suslu · Founder
Pilot, partner, or invest.
If you operate machines that fail expensively, fund early industrial-AI ventures, or work in MRO where triage cost is the bottleneck — I'd like to hear from you.
hello@buraksuslu.com →