The ISA-95 Standard (ANSI/ISA-95) is an international standard developed by the International Society of Automation that defines a hierarchical model and abstract interface architecture for integrating enterprise-level business planning systems with shop-floor manufacturing control systems. It establishes a canonical ontology of manufacturing operations, specifying standardized terminology, data models, and information exchange protocols that enable semantic interoperability between ERP, MES, and SCADA layers without requiring custom point-to-point integrations.
Glossary
ISA-95 Standard

What is ISA-95 Standard?
The international standard defining the hierarchical interface architecture between enterprise business systems and manufacturing control systems.
The standard partitions the manufacturing enterprise into five functional levels—from physical process (Level 0) to business logistics (Level 4)—and formally defines the data objects exchanged at the critical Level 3/Level 4 boundary, including production schedules, resource definitions, and performance metrics. By serving as a foundational manufacturing knowledge graph schema, ISA-95 enables the construction of a digital thread that links business objectives directly to production execution, making it the backbone ontology for modern software-defined manufacturing automation architectures.
Core Components of ISA-95
The ISA-95 standard defines a hierarchical model that partitions manufacturing operations into distinct functional layers, creating a canonical framework for integrating business logistics with real-time production control.
Level 4: Business Planning & Logistics
Establishes the enterprise domain responsible for long-range strategic planning and financial orchestration.
- Scope: Plant production scheduling, inventory management, order processing, and procurement.
- Key Systems: Enterprise Resource Planning (ERP) platforms.
- Timeframe: Operates on shifts, days, weeks, or months.
- Function: Defines the what and why of production based on market demand, not the how.
Level 3: Manufacturing Operations Management
The critical bridge layer that translates business objectives into actionable production workflows and analyzes execution results.
- Core Activities: Detailed scheduling, dispatching, quality assurance, and performance analysis.
- Key Systems: Manufacturing Execution Systems (MES) and Laboratory Information Management Systems (LIMS).
- Timeframe: Operates on hours, shifts, and days.
- Function: Manages the how of production by coordinating resources, defining work instructions, and recording genealogical data.
Level 2: Supervisory Control
Oversees the automated execution of physical processes by monitoring and directing multiple localized controllers.
- Mechanism: Supervisory Control and Data Acquisition (SCADA) systems and Distributed Control Systems (DCS).
- Interaction: Reads data from PLCs and adjusts setpoints to optimize stability.
- Timeframe: Operates on seconds and minutes.
- Function: Provides the human-machine interface (HMI) for operators to visualize and supervise automated sequences.
Level 1: Sensing & Manipulation
The physical interface layer where digital logic meets mechanical actuation and analog measurement.
- Actuators: Programmable Logic Controllers (PLCs) executing ladder logic to open valves, start motors, or position robotic arms.
- Sensors: Devices measuring physical properties like pressure, flow, temperature, and proximity.
- Timeframe: Operates in real-time, often in milliseconds or microseconds.
- Function: Executes the closed-loop control algorithms that maintain physical process equilibrium.
Level 0: Physical Production Process
Represents the actual physical, chemical, or mechanical transformation of raw materials into finished goods.
- Elements: Conveyors, reactors, cutting tools, and packaging lines.
- Data Origin: The source of all raw telemetry and the destination for all control commands.
- Timeframe: Continuous or batch physical processes.
- Function: The ground truth of manufacturing reality that all higher levels seek to model and optimize.
B2MML: Business To Manufacturing Markup Language
An XML implementation of the ISA-95 data models that standardizes the electronic exchange of information between Level 4 and Level 3 systems.
- Purpose: Provides a vendor-neutral transaction format for production schedules, performance metrics, and material definitions.
- Benefit: Eliminates proprietary point-to-point interfaces by using a common schema.
- Structure: Defines schemas for Personnel, Equipment, Material, and Process Segment resources.
- Integration: Acts as the semantic bridge ensuring ERP and MES systems share a unified definition of capacity and capability.
Frequently Asked Questions
Clear, technical answers to the most common questions about the ISA-95 standard and its role as a canonical ontology for integrating enterprise and control systems in modern manufacturing.
The ISA-95 standard is an international framework (IEC/ISO 62264) that defines a hierarchical model of manufacturing operations and a standardized interface between enterprise-level business systems (Level 4) and plant-floor control systems (Levels 0-2). It works by establishing a formal object model that organizes production resources, process segments, and scheduling operations into a canonical ontology, enabling seamless data exchange between ERP, MES, and SCADA systems. The standard partitions the manufacturing enterprise into five functional levels—from physical process sensing to business logistics—and specifies the exact data structures and message formats required for each interface boundary, eliminating the need for custom, brittle point-to-point integrations.
ISA-95 vs. Related Standards
How the ISA-95 hierarchical model compares to other key industrial interoperability and data modeling standards across scope, semantic rigor, and application domain.
| Feature | ISA-95 | OPC UA | AutomationML | Asset Administration Shell |
|---|---|---|---|---|
Primary Scope | Enterprise-control system integration | Secure, real-time data exchange | Plant engineering data exchange | Digital representation of assets |
Standard Body | ISA / IEC (IEC 62264) | OPC Foundation (IEC 62541) | IEC (IEC 62714) | Platform Industrie 4.0 / IEC (IEC 63278) |
Semantic Model | Hierarchical equipment and activity models | Object-oriented address space with base types | CAEX object-oriented plant topology | Submodel templates with property definitions |
Formal Ontology Support | ||||
Real-Time Data Transport | ||||
Defines Manufacturing Operations Activities | ||||
Primary Use Case | ERP-MES integration, KPI definition | PLC-to-SCADA communication | Engineering tool data handoff | Digital twin interoperability |
Data Exchange Format | B2MML (XML schema) | OPC UA binary / JSON | AutomationML (XML-based) | AASX package (JSON / XML) |
Enabling Efficiency, Speed & Accuracy
Intelligent Analysis, Decision & Execution
We build AI systems for teams that need search across company data, workflow automation across tools, or AI features inside products and internal software.
Talk to Us
Search across company data
Give teams answers from docs, tickets, runbooks, and product data with sources and permissions.
Useful when people spend too long searching or get different answers from different systems.

Automate internal workflows
Use AI to route work, draft outputs, trigger actions, and keep approvals and logs in place.
Useful when repetitive work moves across multiple tools and teams.

Add AI to products and internal tools
Build assistants, guided actions, or decision support into the software your team or customers already use.
Useful when AI needs to be part of the product, not a separate tool.
Related Terms
The ISA-95 standard does not operate in isolation. It forms the backbone of a broader industrial data architecture, interfacing with execution protocols, engineering models, and modern semantic technologies to enable true interoperability.

About the author
Prasad Kumkar
CEO & MD, Inference Systems
Prasad Kumkar is the CEO & MD of Inference Systems and writes about AI systems architecture, LLM infrastructure, model serving, evaluation, and production deployment. Over 5+ years, he has worked across computer vision models, L5 autonomous vehicle systems, and LLM research, with a focus on taking complex AI ideas into real-world engineering systems.
His work and writing cover AI systems, large language models, AI agents, multimodal systems, autonomous systems, inference optimization, RAG, evaluation, and production AI engineering.
Partnered with leading AI, data, and software stack.
How We Work
Custom AI workflows for your Business
One-fit-all AI don't work for modern businesses. At Inferensys, we aim to understand your business & custom requirements; which we use to define most efficient agentic workflows, the data, and the tools for your business.
01
Review the use case
We understand the task, the users, and where AI can actually help.
Read more02
Pick the right approach
We define what needs search, automation, or product integration.
Read more03
Build the first useful version
We implement the part that proves the value first.
Read more04
Improve from there
We add the checks and visibility needed to keep it useful.
Read moreThe first call is a practical review of your use case and the right next step.
Talk to Us