Skip to main content

PlantPulse AI Platform

If you're getting started, follow this order
  1. Make the chatbot answer from our docs — includes a public demo and video
  2. Example questions — what you can ask
  3. One-line installationChange initial password
  4. Work process — how to keep it useful after deployment

"All factory data, for everyone, one natural language question away"

PlantPulse AI Platform is an industrial AI copilot platform that integrates real-time field data, AI analytics, and knowledge management for manufacturing operations.

When factory operators ask questions in natural language, the AI automatically performs real-time sensor data queries, anomaly detection, predictive analytics, and technical document search — enabling immediate and accurate decision-making.


Key figures

ItemValue
Integrated MCP data tools116 (read-only)
TimeSeries-Insight analytics tools27
Knowledge graph (ontology) tools5
RAG search tools3
Ontology node types14

Platform architecture

ComponentRole
AI Chat WebUser interface — natural language conversational AI copilot (built-in agent)
Integrated MCPReal-time factory data gateway (Platform server-web /api/v5/mcp, includes ontology)
OntologyFactory knowledge graph — equipment relationship/structure analysis (included in Integrated MCP)
TimeSeries-InsightAI anomaly detection + forecasting + feature store (27 analytics tools)
RAGLightRAG-based technical document search — manuals, SOPs, regulations at your fingertips
AURAManufacturing-specialized LLM — domain-fine-tuned model for industry

Adoption impact

AreaBefore (Legacy)After (PlantPulse AI)
Status overviewSCADA + spreadsheets + manuals 30 min–1 hourNatural language question 10 seconds
Anomaly detectionRule-based alarms (reactive)AI early warning + root cause estimate
Maintenance approachPreventive (calendar-based)Predictive maintenance (condition-based)
Document searchManual file server explorationAI hybrid search instant
AI costCloud API pay-per-useOn-premises fixed cost unlimited
Data securityExternal cloud transmissionOn-premises kept complete

Technology stack

LayerTechnology
AI modelsAURA LLM, IBM Granite TSPulse, TinyTimeMixer TTM
AI frameworkMCP (Model Context Protocol), LiteLLM, LightRAG
BackendJava 21 / Spring Boot 3.4, Python / FastAPI
Graph DBNeo4j
Vector DBQdrant
Relational DBPostgreSQL 18
Time series DBApache Cassandra
CacheValkey (Redis compatible)
Object storageMinIO (S3 compatible)
GPUNVIDIA DGX Spark compatible (low-spec operation)
DeploymentOn-premises / Edge / Cloud

Target industries

IndustryKey use cases
Food & beverage manufacturingProduction line OEE management, quality monitoring, energy optimization
Chemical & petrochemicalEarly process anomaly detection, safety compliance, equipment health management
Automotive partsPredictive maintenance, work instruction quality tracking, line balancing
Semiconductor & electronicsFine-grain anomaly detection, yield forecasting, cleanroom environment monitoring
Steel & metalsHigh-temperature equipment monitoring, energy management, maintenance cycle optimization