Russian software · Rospatent No. 2024612865

A digital twin
instead of a gas analyzer

Axioma is a predictive emission monitoring system (PEMS). Your environmental and chief engineers get continuous emission control without a gas analyzer at every stack: 98–99% accuracy vs CEMS, 99% data availability, deployment in 4–6 months instead of 12–18.

Axioma ensures compliance with Federal Law No. 98-FZ for Category I NVOS facilities and quota-regulated sites, replacing physical gas analyzers with a verified digital model. Data is suitable for submission to supervisory authorities. The first PEMS projects in Russia registered in the ARSHIN registry.

Russian software Rospatent No. 2024612865 Register of domestic software Projects in ARSHIN
01 · CEMS economics

The true cost of owning a gas analyzer

Tick what applies to your facility — we will estimate the total cost of ownership per source over 15 years.

Source outfitting

Sampling lines, gas analyzers, flow meters, cabinets, installation

≈ RUB 100 mn · one-off

Verification of every channel

Component-wise checks, 24-hour conditioning, environment control, metrology

≈ RUB 15 mn/yr × 15 yrs

Maintenance

Servicing, consumables, calibration gas mixtures, field visits

≈ RUB 15 mn/yr × 15 yrs

Equipment replacement

5–7 year service life: two to three full replacements over the ownership horizon

2–3 replacements in 15 yrs

Downtime on failure

Reporting to the regulator stops until post-repair verification

site-dependent

Import dependency

Instruments, components, service and supplies exposed to sanction risk

strategic risk
Total cost of ownership over 15 years, per source
550 RUB mn
Calculate for my site
Illustrative estimate based on typical industry costs (CEMS TCO ≈ RUB 400–430 mn over 15 years, downtime excluded). Exact figures come from a paid survey on your data.
02 · How it works

From process-control data to the regulator — four steps

PEMS has been used worldwide since 1993: USA (40 CFR 75), EU (CEN/TS 17198), China (HJ/T 76). In Russia the field is forming under the Ecology national project: the Mendeleev VNIIM institute is preparing a set of 6 GOST R standards for predictive systems, with DCT taking part.

STEP 1

We connect the sources

SCADA data is validated, interpolated and time-aligned — dirty series never enter the model.

SCADALaboratoryMet station
STEP 2

We build the digital twin

The process model is assembled from physicochemical blocks and industrial AI. No programming on the customer side.

BalancesGibbs reactorThermohydraulics
STEP 3

We validate by measurement

A mobile instrumental complex confirms 98–99% accuracy on real operating modes of the facility.

Mobile complexValidation
STEP 4

We report and optimize

Emission readings go to supervisory authorities. The optimizer suggests operating modes without output loss.

ARSHINGosreestrDSS
Scenarios

Six digital-ecology tasks on one platform

Details on each scenario — on the Solutions page.

Plant emission monitoring

Automated emission calculation for the industrial site from process-control data.

CEMS replacement on most sources
PlantPEMS

Mine and underground workings

Emission calculation for closed mine workings at mining enterprises.

Control where no analyzer can be installed
MineMining

Dispersion forecasting

Modelling of pollutant dispersion with local weather and production plans.

Planning without losses under weather limits
DSSMeteo

Mode optimization

Recommendations to operators on furnace modes within environmental limits.

Compliance without stopping production
OptimizerRTO

Greenhouse gases

Carbon footprint by process stage, carbon passports for ESG and export.

Readiness for carbon regulation
CO₂ESG

Validation and metrology

Periodic model quality checks by the mobile complex instead of component-wise verification.

Sustained status of a measuring system
ChecksumsIsolated runtime
03 · Economics

Axioma vs CEMS: two worlds of ownership

DimensionCEMSAxioma
CAPEX per sourceRUB 50–150 mn2× lower · guidance RUB 35–70 mn
Annual OPEXverification + service ≈ RUB 30 mn5× lower · support 15–20% of license
Accuracybaseline (instrumental)98–99% relative to CEMS
Data availability85–95%99%
Deployment12–18 months4–6 months
Service life5–7 years, then replacement15–20 years, software updates
Verificationcomponent-wise, 24 h conditioningmodel check by the mobile complex
First-year savings exceed the CAPEX difference. Total cost of ownership over 15 years is 3–5× lower. Full independence from imported instruments and service.
04 · Team

An engineering school proven by projects

Axioma was created by a team with a 20-year history. The core was formed through the restructuring of the Siemens Corporate Technology R&D center in Russia.

20 years of engineering school

2005: Siemens Corporate Technology R&D center founded in Russia, laboratories at SPbPU and ITMO. 2020: restructured into DCT with the team retained.

100+ delivered projects

Digital twins of equipment and processes, optimization of the Sapsan train, monitoring for CERN.

Siemens Energy and healthcare

Digital twins of steam generators, corrosion processes, high-voltage equipment, and the cryogenic system of an MR tomograph.

NEOM and computer vision

Landscape change detection from satellite imagery: 2,600 km² every 3 weeks; seven models from prototype to production in 7 months.

PEMS pioneer in Russia

The first predictive emission control projects registered in the ARSHIN registry. Participation in the GOST R standards for predictive systems.

Deployments at industry leaders

Commercial deployments of Axioma and iDStudio at anchor customers in metallurgy and petrochemistry (public descriptions anonymized).

Cases

Evidence instead of promises

Projects proven in industrial operation. More on the Cases page.

Digital twin of a flash smelting furnace

SO₂ emission control without gas analyzers at the sources: balances, Gibbs reactor, AI block. Exceedance forecasts and operator recommendations.

99% data availability; model replicated to several sites
MetallurgyAnonymized

Emission dispersion control

Production mode planning with local weather for a plant next to residential areas.

Lower losses under adverse weather conditions
DSSMeteo

iDStudio: predictive diagnostics

Residual-life assessment of terminal handling machines via strain gauges and a digital twin — DCT’s second product.

Line productivity +50%
PortsiDStudio
05 · Objections

Seven doubts of a chief engineer — and honest answers

The banner rotates every 6 seconds; hover to pause.

98-FZ requires physical measurements

The law requires continuous automated control of emissions but does not prescribe a specific instrument type. Axioma is registered in ARSHIN as an automated emission measuring system of an alternative type; DCT has already delivered such projects. Approval runs through the local office of Rosprirodnadzor.

A calculation method is inaccurate

Model accuracy is 98–99% relative to instrumental CEMS measurements. It is confirmed by the mobile instrumental complex at validation and by regular in-service checks — by protocol, not by promise.

Regulators will not accept it

Russia’s first PEMS projects are already registered in ARSHIN — the precedent exists. DCT supports the approval with Rosprirodnadzor: documentation package, metrological justification, validation results.

There is no GOST for PEMS yet

True — and normal for an emerging technology. Mendeleev VNIIM is developing a set of 6 GOST R standards for predictive systems with DCT involved. International practice is formalized: 40 CFR 75 Appendix E (USA), CEN/TS 17198:2019 (EU), HJ/T 76 (China).

It costs more than a gas analyzer

The opposite: Axioma CAPEX is 2× lower (guidance RUB 35–70 mn per source), OPEX 5× lower. A CEMS costs RUB 400–430 mn per source over 15 years of ownership, before downtime and import risks.

We don’t trust AI

There are no generative models in Axioma. The core is physicochemical blocks (material and heat balances, Gibbs reactor, thermohydraulics); AI only corrects. The model does not learn in production; retraining follows a protocol. Isolated runtime, checksums, invalid data flagged as unreliable.

Too few cases

PEMS in Russia is just beginning — and we are doing the first projects. Behind the team are 100+ digital-twin projects for Siemens Energy, CERN and NEOM. Full deployment details — in the 2027 casebook, sent on request.

1 / 7
Q&A

What else gets asked before kickoff

How accurate is the calculation method?

98–99% relative to instrumental measurements. Accuracy is confirmed by the mobile instrumental complex at validation and by regular in-service checks.

Do supervisory authorities accept calculated data?

DCT’s first projects are registered in ARSHIN as alternative-type measuring systems; Mendeleev VNIIM is preparing GOST R standards for predictive systems. DCT supports approval with Rosprirodnadzor at the facility location.

Which facilities are suitable for Axioma?

Sources with a stable process, stable feedstock and sufficient SCADA instrumentation: CHP plants, metallurgy, petrochemistry. Applicability is determined in a paid survey; a hybrid “PEMS + point CEMS” scheme is possible for some sources.

How much does it cost?

Guidance: RUB 35–70 mn per source depending on complexity. Packages: Start (1–3 sources), Production (4–8), Plant (8+). Support is 15–20% of the license fee per year.

How to justify the economics to management?

Through TCO: a CEMS per source over 15 years is about RUB 400–430 mn (outfitting ≈100 mn, verification ≈15 mn/yr, service ≈15 mn/yr, replacement every 5–7 years). Axioma cuts CAPEX 2× and OPEX 5×; first-year savings exceed the CAPEX difference.

Can we trust AI decisions?

This is not an LLM or a black box: the core is a physicochemical process model, AI only corrects it. The model does not learn in production; retraining follows a protocol with validation. All calculations are logged; data failing integrity checks is flagged as unreliable.

How long does deployment take?

4–6 months: survey (2–4 weeks), model build, validation by the mobile complex, reporting to the regulator. A typical CEMS project takes 12–18 months.

What infrastructure does it run on?

Axioma is Russian software (certificate No. 2024612865, register of domestic software) running on Astra Linux. Suitable for critical infrastructure and state-owned companies.

What if SCADA data is insufficient?

During the survey we audit instrumentation: if signals are missing, we propose minimal sensor upgrades (still an order of magnitude cheaper than a CEMS sampling system) or a hybrid scheme.

Public cases are few — how can we verify you?

Public descriptions are anonymized under NDA. We suggest a pilot on one source with mobile-complex validation: you pay for a measurable result, not a presentation. Full deployment details — in the 2027 casebook.

Contacts

Let’s discuss your facility

A demo on your own data, or a paid preliminary survey. We reply within one business day.

Company
Digital Corporate Technologies LLC
8 Aptekarskaya Emb., lit. A, Saint Petersburg, 197022, Russia

Phone / E-mail
+7 (812) 209-17-17
info@dct-ai.com
www.dct-ai.com

Registry
PSRN (OGRN) 1227800100021 · TIN (INN) 7813664900
The request creates a lead in our Bitrix24 CRM. If the CRM hook is offline, your mail client will open instead.
Request sent. We will contact you within one business day.