ML
Learn patterns and predict
- Input
- Consumption, sensor and equipment history
A model is trained on equipment data, then analyses future trends or unusual behaviour.
- Output
- Consumption forecasts, anomaly detection and health indicators
ARG Digital Twin
Digital TwinA live copy of the whole organisation, from device to decision
ARG Digital Twin is the live digital counterpart of a physical site: every real device has a digital twin carrying its live value, state, history, limits and behaviour — and every process of an organisation runs in one system behind one sign-in.
AI works in this environment too: a project-connected assistant, RAG knowledge retrieval and an ML backend for training, prediction and model evaluation.
230/63 kV substation — live 3D twin
44
industries in 10 sectors
22
enterprise modules · 311 screens
10
industrial and IT protocols
3,600+
device models in the catalog
167
3D library items
69,000+
updates per second, distribution layer
ML · RAG · LLM · AGENT
Explore AI in detailAI alongside the digital twin’s data and tools
The project-connected assistant and the independent ARG_AI backend serve complementary roles: one helps users understand the situation and work inside the software; the other provides model training, analysis, prediction and result monitoring.
ML
Learn from data and measure results
Prepare history → train models → predict and detect → evaluate and monitor
LLM + RAG + Tools
Understand the project, retrieve knowledge and act
User intent → relevant knowledge and project tools → analysis or proposed change → user confirmation
RAG
Retrieve project knowledge
- Input
- Project documents, catalogs and device templates
Knowledge retrieval finds passages relevant to the question and equipment and supplies them to the assistant.
- Output
- Answers grounded in documents and the project context
LLM
Explain the findings clearly
- Input
- User question, project data and tool results
The assistant explains findings, summarises information and uses system tools to investigate the question.
- Output
- Engineering dialogue, reports and reviewable recommendations
Agent
Work inside the system
- Input
- User intent and the current page or project context
Tools read equipment state, alarms and history; proposed creation or changes enter the user confirmation workflow.
- Output
- Multi-step investigation and proposed dashboards or logic
The LLM and RAG assistant: from project knowledge to system design
RAG supplies relevant knowledge, the LLM interprets the request and results, and agent tools move the work forward inside the system.
Understand equipment and project knowledge
The assistant draws on device catalogs, SNMP and Modbus templates, OIDs and uploaded project documents. RAG combines keyword and semantic retrieval to answer in the context of the relevant equipment.
Create structures, dashboards and 3D scenes
A user request can become a proposal for buildings, floors, spaces, devices and points, or for dashboard creation and cloning, 2D elements, scenes and 3D objects. System tools and user confirmation carry out the workflow.
Help design logic and scenarios
The assistant reads and checks existing logic and proposes creating or editing Rules, Limits, Scenarios, Scripts and State Machines. Command-producing logic starts disabled and requires a separate activation confirmation.
Maintain context as the work continues
Conversation history, summaries and user or project memory help continue the work. Equipment aliases, preferences and routines can be retained, pinned or forgotten.
IN THE PROJECT WORKSPACE
From an alarm question to equipment investigation
Ask the assistant to inspect active alarms, offline equipment or a point’s history. The request carries project context and tools read the required information from the system. Proposed changes are presented for user confirmation.
IN THE INDEPENDENT ARG_AI BACKEND
From equipment history to a model you can evaluate
For energy forecasting, historical data trains the model; results are checked against test data and recorded with error metrics. Anomaly detection learns normal behaviour to identify observations that need investigation.
Deploy against each site’s real data
For a refinery, petrochemical plant or other infrastructure, project engineering defines data sources, equipment mapping, history quality, permitted documents and acceptance criteria. The deployment guide describes OT/DMZ integration and local LLM or provider API options. In this industrial architecture, AI informs engineers and operators while process control remains in the existing control system.
Inside the Digital Twin
Eleven sections, 39 chapters — each with real screens of the software.
Dashboards & twins built
3D twins and dashboards built with the platform
Architecture & data path
Device-to-dashboard chain, point model, topologies
Enterprise modules
22 menu groups that digitise every mechanism of an organisation
Devices & protocols
Industrial protocols, the ARG Device Catalog, controllers
Dashboards & 3D scenes
Real-time monitoring, 2D designer, scene builder, Twin Designer
Logic, alarms & simulation
Limits and alarms, logic engine, scenarios, state machines, test lab
AI & offline maps
Persian AI assistant, the ARG AI backend, offline map server
Industries & applications
44 industries in 10 sectors, each with its own dashboard
Performance, scale & security
Measured capacity, HA and clustering, roles, layered security
Deployment & delivery
Multi-project, profiles, deployment, method, server console, support
Reference & roadmap
Integration and API, references, data model, how-tos, FAQ, roadmap
Digital Twin Academy
Step-by-step courses for operators, engineers, administrators and managers — real screens, live-demo exercises, checks and a certificate.
System Overview Diagram
A look at every component: from field devices and protocols at the bottom, up through the platform core, companion services, the presentation layer and users at the top. Each layer is described in detail, with a diagram, in its own chapter.
1
Introduction and Use Cases
ARG Digital Twin is a live digital version of a physical infrastructure: every real piece of equipment (chiller, UPS, server rack, pump, transformer, sensor…) has a digital counterpart in the system that carries its real-time values, status, history, allowed limits and behavioral rules. Users see these counterparts on 2D dashboards or 3D scenes, issue commands, receive alerts, and define automation logic without writing code. Every process in an organization — from energy and facilities to security, assets, ticketing and production — becomes digital in a single system with a single sign-on.
Which Environments
- Smart buildings and office/commercial complexes (HVAC, lighting, elevators, parking, safety)
- Data centers and server rooms (DCIM: racks, power, cooling, UPS, temperature/humidity)
- Substations and distribution networks (transmission substations, high-voltage, dispatching)
- Process and water facilities (treatment plants, pump houses, mechanical rooms, boilers)
- Fuel stations, warehouses, industrial sites, hotels, greenhouses
Who It Is For
- Facility and operations managers: overview, alerts, reports and control from one place
- Control room operators: live dashboard, commands with secure confirmation, ready-made scenarios
- Automation and network engineers: connecting equipment with 10 protocols, point mapping, rules and state machines
- Energy and asset managers: meters, tariffs, demand, cost, maintenance
- Integrators: standard API, WebSocket, equipment catalog, Windows/Linux/Docker deployment
System Workflow
1 · Connect Equipment connects using its own protocol (SNMP, Modbus, OPC UA, MQTT, PLC…)
2 · Model Each point gets a unique identifier and a control variable with a unit, scale and limits
3 · Monitor Real-time values reach the dashboards and history is stored
4 · Alert Crossing limits, loss of connection, or stale data generates an alert and notification
5 · Automate Rules, schedules, scenarios and state machines respond automatically
6 · Control The operator or logic issues a command; the command executes with secure confirmation and an equipment receipt
3
Capabilities at a Glance
10Industrial and IT protocols implemented
22Enterprise modules · 311 pages
4Dashboard types: 2D, 3D, list, map
24Element types in the 2D designer (10 categories)
153+144BMS and photoreal equipment animations
1673D library items in 29 categories
5No-code automation mechanisms
4Notification channels + escalation policy
3,600+Equipment models from 770+ brands in the catalog
33Machine learning models in ARG AI
6Interface languages · full right-to-left support
80+Smart assistant actions with user confirmation
Monitoring and Display
- Live dashboard with less than one second of latency from equipment to screen
- 2D designer with drag-and-drop, value-driven animation, charts, gauges, camera, web view
- 3D builder with an equipment library, pipe/duct/cable routing, and each object linked to a real point
- Online and offline maps of sites and assets; operational views with data-quality labels
- Full history for every point, with independent retention per project
Control and Automation
- Commands to equipment from the dashboard with password confirmation and an execution receipt
- Conditional rules with priority, scheduling, quiet periods and rate limits
- Four-level limits with hysteresis; multi-step scripts; persistent state machines; scenarios
- A logic test lab and data simulator for testing before go-live
Intelligence and Knowledge
- A Persian-language smart assistant with access to project data, long-term memory and a knowledge base
- The ARG AI backend with 33 models: anomaly detection, forecasting, predictive maintenance, compliance, smart reporting
- An equipment catalog with SNMP/Modbus templates and automatic point generation from the model
Enterprise
- Multi-project with complete data isolation and tiered access keys
- Roles and permissions across 12 domains × 7 actions; login/logout and event logging
- Energy, UPS/battery, assets and maintenance, ticketing, physical access, hotel, production, tracking
- REST API with OpenAPI documentation and WebSocket for integration
27
Differences from Traditional BMS and SCADA
| Aspect | Traditional BMS / SCADA | ARG Digital Twin |
|---|---|---|
| Equipment connectivity | Locked to a single protocol or brand; a gateway is needed to bridge to IT | 10 industrial and IT protocols in a single core; a catalog with ready-made points for 3,600+ models |
| Visualization | Static graphic screens; 3D versions are rare or purely decorative | 2D designer and 3D builder with every object live-linked to a point; offline maps |
| Automation | PLC programming / scripting by a specialist | No-code rules, scenarios, state machines + visual editor + test lab |
| Intelligence | Fixed reports | A smart assistant with data access and confirmed actions; ARG AI with 33 models |
| Enterprise scope | Facilities only | 22 modules: energy, security, assets, ticketing, production, hotel, tracking, agriculture |
| Multi-tenancy | A separate installation for each site | One installation, multiple projects with full isolation; product profiles |
| Integration | OPC or file-based | REST + OpenAPI, WebSocket, Webhook; companion services with their own APIs |
| Language and localization | English | 6 languages with genuine right-to-left support; local carrier SMS via SMPP |
| Deployment | Dedicated hardware / server | Windows, Linux, Docker, cloud — on enterprise PostgreSQL with replication and HA support |
See the Digital Twin live
The live ArgBMS demo with real 3D twins, dashboards and logic.