Aexion Synthesis
PROPULSION TEST ANALYTICS & PARAMETRIC SIMULATION

From telemetry to design insight.

Raw test-stand data becomes ready-to-use engineering analytics — in minutes. Built and validated on real hot fire tests, on live telemetry.

POST-TEST CYCLE
Minutes, not days

From the acquisition export to a complete descriptive and diagnostic report — with no manual preparation in between.

EVERY FIRING RETURNS
16 · 10 · 8

Sixteen tabs of descriptive analysis, ten of diagnostics, eight campaign sections — per test, every time.

DERIVED FROM YOUR DATA
c* · CF · Isp · O/F

Performance computed from your own measurements, with geometry and assumptions stated beside every result.

VALIDATED ON
Real hot fire

Built and proven alongside live hot-fire campaigns on a working test stand — never on synthetic data.

AI ANALYST ANSWERS IN
EN · RU · KK

It explains the computed result in plain language — and never produces the number itself.

WHO WE ARE

Engineers who test engines — not just a software vendor.

Aexion Synthesis builds the data analytics infrastructure for liquid rocket engine hot fire testing. We turn raw test-stand telemetry into structured, engineering-grade analytics — performance, diagnostics, anomaly detection — within minutes of a test, with an AI assistant that answers questions in plain language and always traces back to the source data.

The platform was built and proven on real hot fire campaigns, on live telemetry from a working test stand — not synthetic data. Our team does propulsion engineering itself, which is why the analytics speak the language of the people who run the tests. Founded in 2024 — and already validated on live hot fire campaigns, backed by NVIDIA Inception and the AWS and Anthropic startup programs. Remote-first, based in Almaty, Kazakhstan.

FOUNDED 2024 · REMOTE-FIRST · BUILT ON REAL HOT FIRE DATA · EVERY RESULT TRACEABLE TO SOURCE
PARTNERS & ECOSYSTEM

Backed by technology leaders

BACKED BY
Amazon Web Services

The cloud foundation of the platform. Ingest, computation, storage, and the portal all run on AWS infrastructure. AWS supports the project with credits and hands-on architecture guidance — helping us build a platform that scales from a single test to full campaigns without compromising data security.

aws.amazon.com ↗
NVIDIA Inception

Member of the global NVIDIA program for AI companies: access to NVIDIA technology and engineering expertise, training resources, and an ecosystem that includes leading aerospace startups — a direct line to the tooling and practices behind modern AI-driven engineering analytics.

nvidia.com ↗
Anthropic

Member of the Claude for Startups global program. Claude is the foundation of the platform's AI analyst — the layer that explains computed results in plain language, in English, Russian, and Kazakh, while every number stays with the deterministic computation core.

claude.com/startups ↗
PARTNERS
Thrust
FIRST PRIVATE SPACE COMPANY IN KAZAKHSTAN · STATE-LICENSED

Our test-stand partner. Thrust designs and fires its own liquid rocket engines and holds a state licence for space activity — the first private company in Kazakhstan to do so. The platform was built alongside their hot fire campaigns and proven on their telemetry: real hardware, real stand, not synthetic data.

thrust.kz ↗
MUK
IT & CLOUD DISTRIBUTION · KAZAKHSTAN & CENTRAL ASIA

One of the region's largest distributors of IT solutions and cloud services, including AWS and Azure. MUK is our procurement channel for the region: cloud infrastructure and vendor licensing behind platform deployments across Kazakhstan and Central Asia.

muk.group ↗
qCloudy
FIRST LOCAL AWS ADVANCED TIER PARTNER IN CENTRAL ASIA

Our cloud engineering partner — an AWS Advanced Tier partner with the AWS AI competency and a member of the AWS Well-Architected Framework program, with a certified engineering team building and operating AWS solutions since 2021, backed by 24/7 managed services. qCloudy supports the platform's cloud infrastructure, architecture reviews, and operations.

qcloudy.io ↗
BUILT FOR

For the people who run the tests.

Wherever liquid rocket engines are fired, someone has to turn the data into an answer — usually before the next test is scheduled. That is the job Aexion is built for.

Propulsion test teams

Turn every hot-fire test into a finished engineering record — the same day.

A single firing leaves gigabytes across dozens of channels, and the read usually waits days for someone to have time. Performance, ignition classification and flagged deviations are computed before the stand is cold.

Aerospace startups

Engineering-grade analytics without standing up a data team.

You need engines qualified, not a data pipeline maintained. Derived performance, stability metrics and deviation review from the first test — without hiring for it or writing throwaway analysis scripts.

Research institutions

Reproducible, traceable results across an entire campaign.

Work has to hold up years later, reviewed by people who were not on the stand. Every test in a campaign runs through the same deterministic core, and every number stays traceable to the channel and time window it came from.

University teams

Special terms: one hot fire analysed in full, at no cost.

The academic offer ↗
Request demo One past firing's data — a full report back.
HANABI 1.1 — THE PLATFORM TODAY

From raw data to engineering insight. In minutes.

Hanabi is the analytics core behind every Aexion report. It takes the raw output of your acquisition system — thrust, chamber and feed pressures, propellant temperatures, mass flow, valve states, stand video — and returns a complete engineering read of the firing: what the engine did, how well it did it, and what needs a closer look before the next test.

1
Upload

Export from your acquisition system as it was written. Channel names are mapped once per stand, then reused for every test after that.

2
Compute

Derived parameters, phase statistics, ignition classification and deviation flags — produced by a deterministic core, not estimated.

3
Review

An interactive report per test, plus exportable documents for design reviews and programme records.

01Full test picture
Every acquired channel on one time base, statistics computed per phase, and stand video locked to the same clock.
02Engine performance
Characteristic velocity and its efficiency against a thermochemical baseline, thrust coefficient, specific impulse and mixture ratio — from your own measurements.
03Ignition and chill-down
Start classification, delay and chamber-pressure overshoot — with the chill-down gradients that precede a hard start.
04Combustion stability
Thrust variation inside the steady-state window, its spectrum, and its coherence with feed pressure.
05Data quality
What was measured reliably, where samples are missing, and which parameters that leaves unavailable rather than estimated.
06Campaign and comparison
Trends and repeatability across the series, and two runs or configurations compared over matched windows.
FULL TEST PICTURERUN 04 · CAMPAIGN 001
IGNITION TRANSIENTt+0…2.1 speak thrust 428 kgf
STEADY-STATE WINDOWt+2.1…9.6 smean 352 kgf · CV 3.1%
SHUTDOWNt+9.6…10.4 stail-off measured, not trimmed off
CHANNELSTHRUST-01, PC-01, PF-02, MF-01/02one time base, one clock
STAND VIDEOCAM 01locked to the same clock

Statistics are computed inside each phase and never averaged across them: a transient and a steady burn are different measurements of different things.

ENGINE PERFORMANCERUN 04 · WINDOW t+2.1…9.6 s
CHARACTERISTIC VELOCITY1471 m/sc* = Pc · A* / ṁ
EFFICIENCYη_c* 0.90measured against a thermochemical baseline
THRUST COEFFICIENTCF 1.42CF = F / (Pc · A*)
SPECIFIC IMPULSE213 sIsp = c* · CF / g₀
MIXTURE RATIOO/F 1.35from MF-01/02 through the burn

The baseline is computed for your propellant pair and chamber conditions, and its assumptions are printed beside the result — the efficiency is checkable, not asserted.

IGNITION AND CHILL-DOWNRUN 04 · t+0…3 s
IGNITION DELAY0.52 sfrom the valve command
Pc PEAK / STEADY2.32 / 1.84 MPaovershoot +26%
FLAG RAISEDt+0.42 sPC-01, automatically
CHILL-DOWN∇T before valve openingprecursor checked ahead of t+0

Start behaviour is classified from the chamber-pressure trace against fixed thresholds, and the gradients in the oxidizer line before the command are read as the precursor they are.

COMBUSTION STABILITYRUN 04 · WINDOW t+2.1…9.6 s
THRUST VARIATIONCV 3.1%CV = σ_F / F̄
DOMINANT PEAK38 Hz4.1% of mean thrust
PF-02 COHERENCE0.71at the same peak — feed-coupled
RESOLVED BAND≤ 200 Hzbounded by your acquisition rate

A peak that appears in both thrust and feed pressure is feed-coupled rather than combustion-driven. Above the resolved band the report states no coverage instead of implying it.

DATA QUALITYRUN 04 · CAMPAIGN 001
CHANNELS RECORDED18present through the burn window
CALIBRATIONconfirmedTHRUST-01, PC-01, PF-02, MF-01/02
UNAVAILABLE PARAMETERSnoneevery input present for this run
ABOVE 200 Hzno coveragestated, not implied

Where a channel is missing samples or a calibration cannot be confirmed, every parameter depending on it is marked unavailable — not estimated, and not averaged over the gap.

CAMPAIGN AND COMPARISONCAMPAIGN 001 · RUN 04 vs RUN 03
RUNS IN SERIES10same computation core throughout
CHARACTERISTIC VELOCITY1454 → 1471 m/s+1.2%
THRUST COEFFICIENT1.40 → 1.42+1.4%
SPECIFIC IMPULSE208 → 213 s+2.4%
MIXTURE RATIO1.41 → 1.35−4.3%
THRUST VARIATION3.6% → 3.1%−0.5 pt

Differences are computed over matched steady-state windows. Where a window differs in length, the comparison says so rather than quietly comparing unequal things.

AI ANALYST

Ask your data in plain language.

Instead of digging through reports, ask a question. The analyst reads the run's own telemetry, computes the answer, and shows the chart behind it.

WHAT YOU CAN ASK
“Why did this run behave this way?”Plain-language explanation of anomalies — hard starts, pressure oscillation, thermal events — grounded in the run's data.
“How does this compare?”Cross-run and cross-campaign comparison of performance, ignition, and stability.
“What are the numbers?”Computed metrics — c*, Isp, O/F, CV%, burn duration — straight from the verified computation core.
“Where does this come from?”Every answer cites the exact report section or sensor channel behind it.
“…in English, Russian, or Kazakh”The same analyst, three languages (EN · RU · KK).
HOW WE KEEP IT HONEST
The model explains; it never computes. How the split works →
AI ANALYST · GUIDED DEMO
DETERMINISTIC CORE18 CHANNELSRUN 04 · CAMPAIGN 001
Try a question
DEMOThis is a guided demo — the live assistant runs inside the platform.
WHAT'S NEXT — HANABI 2.0

Hanabi 1.1 runs today, on real campaigns. Hanabi 2.0 is the next generation — new architecture, built for programmes and teams rather than a single stand.

SUMMER 2026 — UNDERWAY

One workspace per organisation on the new architecture, with stand data processed automatically as it arrives — a firing becomes a finished report without manual steps in between.

AUTUMN 2026

Every figure in the workspace opens down to its source data in one click, and the analyst reads your own programme documentation — your engines, your configurations, your previous runs.

END OF 2026

Parametric what-if runs and performance prediction across operating points: a proposed change weighed against your own test data before it is committed to a firing, with higher-fidelity flow simulation after that.

Let's talk about your test program.

From your stand's raw data to a complete analytics package.

Request demo
Copied to clipboard