Development of an Ontology-Based Knowledge Management System for the Secondary Battery Manufacturing Process

Learn the concepts of ontologies and how to apply them in practice, focusing on the manufacturing process for secondary battery cathode materials. You will learn how to transform fragmented process data into meaningful knowledge assets and build AI-based quality prediction and defect root-cause inference systems. You will develop practical ontology engineering skills to lead the digital and AI transformation of manufacturing operations.

(5.0) 1 reviews

28 learners

Level Intermediate

Course period Unlimited

Set theory
Set theory
crash
crash
dax
dax
modeling
modeling
LangGraph
LangGraph
Set theory
Set theory
crash
crash
dax
dax
modeling
modeling
LangGraph
LangGraph

What you will gain after the course

  • Modeling secondary battery manufacturing process data as an ontology and building a knowledge graph

  • Ontology-Based Quality Defect Root Cause Inference and Prediction System Design

  • Establishing an Intelligent Knowledge Management Architecture for DX/AX in Manufacturing Operations

Building an Ontology-Based Knowledge Management System for Secondary Battery Manufacturing Processes

This course provides an in-depth exploration of the concept of ‘ontology’—a core technology for successfully driving the digital transformation (DX) and artificial intelligence transformation (AX) of manufacturing processes amid the rapidly changing secondary battery industry environment—and its practical applications. In particular, focusing on the secondary battery cathode material manufacturing process, learners will study through concrete scenarios how ontologies assign meaning to data and contribute to the development of intelligent process control and quality prediction systems. Through this course, learners will develop the ability to transform fragmented data into knowledge assets, infer the root causes of quality defects, and build an ontology-based knowledge management system for implementing next-generation autonomous manufacturing plants.


Part 1. Overview of the Secondary Battery Industry and Ontology-Based DX/AX

In this module, you will explore the latest trends in the secondary battery industry and the need for digital transformation (DX) and AI transformation (AX). You will understand the basic concepts of ontologies and their importance in semantically linking manufacturing process data, and identify the strategic value of ontology-based DX/AX through real-world industry cases.

Trends in the Secondary Battery Industry and the Need for Digital Transformation

Understand the changes in the global electric vehicle market and the importance of secondary battery material technologies, and learn the need for digital transformation (DX) and AI transformation (AX) to manage manufacturing process data and identify causal relationships.

Importance of Ontology Concepts and Semantic Connections

Learn the basic concepts of ontologies and the principles of knowledge structuring, and understand the role of ontologies in enabling semantic connections between physical process assets and the chemical properties of materials.

Analysis of Successful Ontology-Based DX/AX Cases

Analyze the technology portfolios and research and development trends of EcoPro and POSCO Future M, and learn through real-world cases how ontology-based DX/AX can be applied in the secondary battery manufacturing industry.


Part 2. Core Ontology Standards and Battery Domain Ontology

In this module, you will learn the concepts of ISA-95 and B2MML, core standards in the manufacturing industry, and explore how to convert them into ontologies to ensure interoperability across the entire process. You will also delve into ways to integrate materials science knowledge through BattINFO and EMMO, ontologies specialized for the battery domain.

Understanding the ISA-95 Standard and Manufacturing Process Integration

Learn the hierarchical structure and roles of the ISA-95 standard, which defines interfaces among enterprise resource planning (ERP) systems, manufacturing execution systems (MES), and control systems, and understand how to transform it into an ontology to ensure interoperability across the entire process.

Hands-on practice in data standardization using B2MML

Learn the concept of B2MML (Business to Manufacturing Markup Language), an XML implementation of ISA-95, and practice standardizing data by using key B2MML elements such as MaterialInformation, EquipmentInformation, and ProcessSegment as an ontology schema.

BattINFO and EMMO: Battery Domain-Specific Ontologies

Learn about Europe’s EMMO (Elementary Multiperspective Materials Ontology) and its subdomain, BattINFO, to understand how to define batteries’ chemical structures, electrochemical performance metrics, and characterization methods using standardized terminology. Analyze the properties of the ActiveMaterial and CharacterizationMethod classes.


Part 3. In-Depth Analysis of the Manufacturing Processes for Secondary Battery Cathode Materials

In this module, we provide an in-depth analysis of the key processes involved in manufacturing secondary battery cathode materials: precursor synthesis, mixing, calcination, and post-treatment. You will understand the main variables in each process and their impact on quality, and explore the mechanisms behind and solutions to major quality defects such as cation mixing defects, particle cracking, and impurity contamination.

Precursor Manufacturing Process and Analysis of Key Variables

Learn in detail about the precursor synthesis process that serves as the “skeleton” of the cathode material. Analyze the mechanism of the coprecipitation reaction and the effects of key process variables, such as pH, temperature, and stirring speed, on particle size, tap density, and morphology.

Understanding Mixing and Calcination Processes and Their Impact on Quality

Learn the mixing process, which uniformly blends the precursor and lithium source, and the calcination/sintering process, which forms the crystal structure through high-temperature heating. Analyze the effects of each process variable—including lithium source selection, Li/Me ratio, calcination temperature, calcination time, and atmosphere control—on the quality of the final cathode material.

Hands-on Analysis of Cathode Post-Treatment Processes and Major Types of Quality Defects

We will conduct practical training to understand the post-treatment process for calcined cathode materials to meet final product specifications, and to analyze the mechanisms and diagnostic methods of major quality defects occurring in cathode material manufacturing, including cation mixing defects, particle cracking and gas generation, and impurity contamination.


Part 4. Building an Ontology-Based Process DX/AX Framework

In this module, you will design a framework for semantically integrating secondary battery process data and converting it into knowledge assets using ISA-95 and battery domain ontologies. You will implement semantic control scenarios for precursor processes, explore energy and quality optimization strategies for the calcination process, and carry out a project to build an ontology-based process framework.

Designing an ISA-95-Based Ontology Framework

Learn how to design an ontology structure that integrates the physical assets of a manufacturing site with the chemical knowledge of materials based on the ISA-95 standard. Understand the concept of building a framework that semantically integrates process data and transforms it into a knowledge asset.

Implementing a Semantic Control Scenario for Precursor Processes

Learn a scenario for semantically controlling the continuity of chemical reactions in the precursor process through an ontology. Practice defining classes such as PrecursorBatch, ReactionParameter, and ChemicalInput and establishing their relationships to infer the chemical state inside the reactor, and use inference rules to predict final particle quality.

Methods for optimizing energy and quality in the firing process

Learn how to optimize energy and quality in the calcination process, which takes the longest time and exhibits significant quality variation, by building an ontology-based digital twin. Analyze scenarios for tracing the causes of quality defects such as CationMixing through data mapping and quality linkage.

Ontology-Based Process Framework Design Project

Carry out a project to design a data integration and knowledge assetization framework using the ISA-95 and BattINFO ontologies by selecting a specific step in the manufacturing process for secondary-battery cathode materials (e.g., precursor production or calcination). Use ontology modeling tools to concretize the conceptual framework and define the key classes, attributes, and relationships.


Part 5. Intelligent Quality Anomaly Detection and AI Integration Strategies

In this module, you will learn contextual anomaly detection techniques that go beyond simple numerical comparisons by leveraging ontologies. You will explore strategies for integrating ontologies with AI models, propose ways to accelerate the AX (AI Transformation) of secondary battery manufacturing processes, and strengthen your practical application skills through hands-on design of ontology-based AI systems.

Intelligent Quality Anomaly Detection Using Ontologies

Learn the principles by which ontologies detect “contextual anomalies” beyond simple numerical comparisons. Analyze context-aware and complex anomaly detection scenarios to understand how to build ontology-based intelligent quality anomaly detection systems.

Ontology Integration Strategies with AI Models

Learn how to accelerate the AX (AI transformation) of secondary battery manufacturing processes by linking ontologies with AI models. Understand how semantic annotation through BattINFO enhances AI models’ understanding of materials data, and explore AI integration strategies using ontology-based graph databases.

Hands-on Practice in Designing Ontology-Based AI Systems

You will practice designing an intelligent quality anomaly detection or process control AI system using an ontology. You will build an ontology-based knowledge graph and develop specific scenarios for using it as training data for AI models or integrating it with an inference engine.


Part 6. Ontology-Based Knowledge Management and Future Strategy

In this module, we analyze the strategic value of accelerating research and development through the adoption of ontologies, responding to battery passports and global regulations, and improving process efficiency and reducing costs. We undertake a project to build an ontology-based knowledge management system and examine the pivotal role of ontologies in the transition to future autonomous manufacturing plants.

Accelerating research and development through ontology adoption

Learn how ontology-based knowledge structuring can accelerate research and development (R&D) processes, such as developing cathode materials with new compositions. Analyze cases in which the semantic structuring of past experimental data shortens the time required to find optimal process conditions.

Battery Passport and Global Regulatory Response Strategies

Understand global regulatory trends, including the U.S. IRA and European battery regulations, and learn strategies for addressing “battery passport” requirements—such as material origin information and carbon footprint tracking—using ontologies. Analyze ways to achieve complete traceability through a Digital Thread.

Ontology-Based Knowledge Management System Development Project

This project involves the conceptual design of an ontology-based knowledge management system for a specific domain within the secondary battery manufacturing process. It envisions an automated pipeline for transforming fragmented legacy data into an ontology-based graph database and proposes a plan for introducing a semantic query system that enables field engineers to easily leverage the ontology.

The Role of Ontologies in Future-Ready Autonomous Manufacturing Plants

Understand that ontology adoption will become a key driving force for securing knowledge competitiveness beyond competitiveness in secondary battery manufacturing, and examine the decisive foundational role of ontologies in the transition to future autonomous manufacturing plants. Comprehensively evaluate the strategic value of ontologies, including process efficiency, cost reduction, and predictive maintenance.

Recommended for
these people

Who is this course right for?

  • Engineers and data scientists responsible for the digital transformation of secondary battery manufacturing processes

  • Manufacturing IT managers and PMs carrying out smart factory implementation projects

  • A manufacturing decision-maker considering the adoption of an AI-powered quality management system

Need to know before starting?

  • Basic domain knowledge of manufacturing processes or quality control

  • Basic understanding of databases and data modeling

  • Experience processing data using programming languages such as Python

Hello
This is mj

Career Verified

스크린샷 2026-04-09 오후 6.42.23.pngimage.png

Curriculum

All

20 lectures ∙ (2hr 16min)

Course Materials:

Lecture resources
Published: 
Last updated: 

Reviews

All

1 reviews

5.0

1 reviews

  • positive09253898님의 프로필 이미지
    positive09253898

    Reviews 7

    ∙

    Average Rating 5.0

    5

    30% enrolled

    mj's other courses

    Check out other courses by the instructor!

    Similar courses

    Explore other courses in the same field!