Digital twin
of your factory:
from monitoring to forecast
Procesia Industrial Cloud is a cloud platform that creates a digital twin of your shop floor. It captures every event, detects anomalies, and predicts downtime risks before they occur. Connects to your existing MES (SIMATIC IT / Opcenter) without changes on the factory side.
Procesia Industrial Cloud
A digital twin of your factory: real-time monitoring of shops and equipment, MES events, ML downtime forecast. Connects to SIMATIC IT / Opcenter with no changes on the plant side.
EXPLORE THE PLATFORM ↓ TRANSPORTProcesia Fleet — fleet monitoring
Live GPS positions on the map, trip history and bulk-cargo unload control: an in-body level sensor shows the tonnage of every trip online.
MORE ABOUT FLEET MONITORING →Everything you need for a transparent factory
Connect to your existing MES with no changes, web dashboards, downtime log with acknowledgement, Grafana analytics, and ML-based downtime forecasting once labeled history is collected.
Equipment monitoring
Shop floor diagram with real-time status indicators. Click any element to see details and events.
Downtime log
CRUD log with acknowledgement. Operator selects shift, reason, comment. XLSX export by period.
Grafana analytics
Ready-made dashboards: downtime dynamics by period, top reasons, OEE and line activity, event stream.
Multi-plant architecture
Each plant has its own agent and access token. Data isolation — owners see only their own plants and shops.
QR codes for tablets
QR code on a shop floor tablet → instant access, no login required. Mobile-friendly.
Auto-update for agents
Centralized version management. Agents auto-update; per-plant version pinning.
Predictive AI analytics
Trained on labeled history, predicts downtime and anomalies before they occur. Starts after 50–100 labeled events.
Live preview of the running system
These previews load directly from the production server — what you see here is exactly what your operator sees.
Delivered automation and optimization projects
MES integration, reconfiguration of existing production setups, integrations with weighing and laboratory systems. Below are examples of completed projects.
Connecting a new plant to MES
Integrated SIMATIC IT with cloud monitoring, configured agent, migrated equipment and operator registries. 4 weeks from start to first production dashboard.
Plant configuration optimization
Audit of existing recipes, reconfiguration of production routes and nodes, reduced batch transition times. Before/after measurement on real data via the built dashboard.
MES reconfiguration for production scaling
Added a new line to a live MES, configured registries, integrated new sensors and operators. Zero downtime for the running shop, phased migration.
From sensor to dashboard in seconds
A Windows agent at the factory pulls data from MSSQL and pushes it to the cloud over an encrypted channel. No changes to your MES, no VPN, no inbound open ports.
SIMATIC IT / Opcenter
HTTPS · JWT · API-key
Docker Compose
dashboards · filters
Downtime forecast
downtime history
7 steps from audit to forecast
A typical implementation cycle is about 4–6 weeks to launch the base system. AI forecasting is added as a separate stage as labeled history is collected.
Audit
MES analysis, SQL Server version, network availability, list of tables to poll.
Agent
Install the Windows agent, configure table polling, NSSM service, auto-update.
Cloud
Deploy API + DB + Grafana on a VPS or your cloud. Docker Compose, SSL.
Dashboards
Configure shop floor diagram, QR tokens for tablets, registries of operators and reasons.
Pilot
Testing with real data, training operators to acknowledge downtime.
Scaling
Connect additional plants and shops, data isolation, role-based access.
AI analytics
Launch the predictive model once enough labeled downtime history is collected.
MES ↔ 1C — production and accounting work as one
In addition to cloud monitoring, our team builds MES ↔ 1C integrations and customizations within AutomationX projects, tailored to each production site.
- Manual data transfer between MES and 1C
- Input errors, delays in accounting
- Production and finance out of sync
- Decisions made too late
- Direct MES ↔ 1C exchange, no operator needed
- Automatic transfer of output and consumption
- Reconciliation of item registries
- Exchange log and error monitoring
- SIMATIC IT (axpdb) as data source
- 1C UPP / ERP as receiver
- XML / web service exchange bus
- Scheduled jobs and monitoring
- Human error eliminated
- Faster response time
- Decision-making speed increased
- Production and accounting work as one
- SCADA/MES tuning for site-specific needs
- New operator screens, reports, and logs
- Customization of alarm logic
- Integrations with weighing systems, ERP, lab
- Incident resolution and bottleneck removal
- Regular performance audits
- Component updates and migrations
- Operator and engineer training
Frequently asked questions
What customers usually ask about connection, security, supported MES, implementation timeline and ML forecasting.
Do we need to modify our existing MES to connect Procesia?
No. The Windows agent works read-only via ODBC: it periodically polls MSSQL tables by datetime fields. No changes to SIMATIC IT / Opcenter are required, no CDC or triggers needed. Zero load on the existing system.
Do we need a VPN or open inbound ports on the factory side?
No. The Windows agent only initiates outbound HTTPS connections on port 443. No inbound firewall openings required on the factory side. Authorization is via API key, transport encrypted with TLS 1.3.
Which MES systems are supported?
Initially optimized for Siemens SIMATIC IT and Opcenter. Also connects to any MES that stores data in MSSQL: AutomationX, custom systems with MSSQL backends. Table polling is configured per concrete MES without any code changes.
How long does implementation take?
Standard cycle is 4-6 weeks from first technical call to a working production dashboard. Includes MSSQL audit, cloud deployment, agent configuration, registry migration, operator training. See case studies for details.
When does ML downtime forecasting start working?
After accumulating 50-100 labeled downtime events — usually 2-3 months of shop operation. Until then, base Grafana analytics work (trends, OEE, top reasons). The forecast is trained on the history of operator acknowledgments and added as a separate stage.
Can the platform be used for multiple factories?
Yes. The architecture is multi-plant by design: each factory connects via its own agent with its own API key. Data is isolated — owners only see their own factories. ML forecasts are trained per-plant (separate models for each factory).
Ready to discuss implementation at your factory
The first 30 days of the pilot are free. Reach out any way that works for you — we’ll discuss your MES infrastructure and put together an implementation plan.