This is Episode 38B of our review of the “The Coming Wave” and Numorpho Cybernetic Systems (NUMO) progression into Actionable Intelligence as a prelude to what we call Existential Intelligence.

At Numorpho, we are building a new wave platform called Mantra M5 which will serve as the end-to-end orchestrator for upstream, midstream and downstream activities in orchestrating innovation, automation, integration and enactment in process centric domains. Our goal with this platform is to facilitate outcome-based engineering based on objective functions and enable actionable intelligence to convert meaning to motion.

In this episode, we blueprint a Digital Twin use case that will be test replica of a real digital twin that will be manifested in a real industrial setting.

Let’s dive in….

The Cast of Characters (in order of appearance)

• G

DISCLAIMER: The statements made by the “real” characters in the course of this conversation are LLM AI generated!

Can you review and summarize the Platform Stack architecture attachment from the Digital Twin Consortium

Here is a summary of the key points from the Platform Stack Architectural Framework document from the Digital Twin Consortium:

The document provides an overview of a reference architecture for building digital twin systems. It aims to define common foundational building blocks and best practices.

The architecture has several main elements:

1. Security, trust and governance as a foundation. This covers concepts like privacy, resilience, reliability etc.
2. IT/OT platform layer for implementing the system using compute, storage, networking etc.
3. Virtual representation layer which includes stored (e.g. databases) and computational (simulations) representations of the real-world assets.
4. Service layer for integration, interoperability and synchronization between systems and with real-world data.
5. Application layer where analytics, visualization etc. create value from the digital twin system.

• The architecture can be used to build systems of digital twins in a composable, federated approach. Standards like DTDL provide common data formats.
• The document maps the architecture to several real-world use cases like buildings energy management, emergency response, manufacturing quality control etc.
• It also relates the architecture to other existing approaches like RAMI 4.0, asset administration shells, and cloud provider stacks from AWS, Microsoft etc.

In summary, it provides a framework focused on:

1. integration,
2. interoperability,
3. synchronization and
4. composability

to build robust and value-adding digital twin systems aligned with industry best practices.

Let’s talk about each of the focus areas: integration, interoperability, synchronization and composability.

INTEGRATION

Let’s start with integration. In the context of the Platform Stack Architectural Framework what are key requirements and condition, what protocols and standards should we follow and what tools should we be using? Also are there some good lessons in larger reference implementations in the document from an integration perspective?

Here are some key points on integration in the context of the Platform Stack Architectural Framework:

Requirements and Considerations:

Ability to integrate diverse data sources like sensors, enterprise systems, simulation models etc.
Managing different data formats, protocols, APIs.
Real-time and batch data integration.
Edge, cloud and on-premises integration.

Standards and Protocols:

MQTT, AMQP for messaging
OPC UA for industrial/OT integration
REST APIs
Data Distribution Service (DDS) for real-time data sharing

Tools:

Middleware like Kafka, RabbitMQ, Azure Service Bus etc.
Integration platforms like MuleSoft, Azure Logic Apps
SDKs for common protocols like OPC UA

Example Implementations:

The manufacturing quality control use case uses MQTT to integrate sensor data and results.
The carbon reporting use case leverages OPC UA for synchronizing industrial asset data.

In summary, the integration layer needs to bring together diverse systems efficiently leveraging common standards and patterns. A key focus is on IoT, OT and enterprise system integration.

INTEROPERABILITY

What is interoperability and can you do a similar summary for this focus area?

Here is a summary of key points on interoperability in the context of the Platform Stack Architectural Framework:

Interoperability refers to the ability of diverse systems and components to exchange data and work together seamlessly.

This requires:

Common data formats and schemas – The document references DTDL as an emerging standard for digital twin data exchange.
Shared semantics and meaning – Ontologies like schema.org provide common vocabularies and meaning across domains.
Open interfaces and APIs – Standards like REST APIs, GraphQL enable accessing data across components.
Loose coupling – Components interact through well-defined interfaces rather than tight dependencies.
Common protocols – Protocols like MQTT, AMQP enable standardized messaging between components.
Federated identity and access management – Standards like OAuth enable smooth access control across systems.

Example implementations:

The emergency response use case highlights the need for interoperability between diverse emergency teams and systems.
The FIWARE architecture provides NGSI APIs and data models as a standard for context data exchange.

Overall, interoperability requires applying standards, common semantics, and loose coupling when designing interfaces between the components of a digital twin system. This is critical for building robust, adaptable and reusable systems.

SYNCHRONIZATION

What about synchronization. What would go badly wrong if synchronization was not accounted for?

Synchronization is a critical requirement for digital twins to accurately mirror the real-world entities they represent. Without proper synchronization:

• The digital twin’s state may diverge from the real-world resulting in incorrect or misleading outputs. For example, an asset management twin that doesn’t sync maintenance records may recommend inappropriate maintenance.
• The digital twin may not reflect real-time operating conditions. This could impact diagnostics, predictive capabilities and control applications. For example, a manufacturing twin that doesn’t sync sensor data could miss detecting process deviations.
• Changes made to the real-world system may not be propagated to the twin. For example, a building twin that doesn’t sync occupant schedule changes won’t properly optimize energy usage.
• Lack of synchronization frequency and fidelity controls could result in performance issues on IT/OT systems as massive volumes of inconsequential data are copied.

Proper synchronization requires:

Standards like OPC UA Pub/Sub for efficient, real-time sync from industrial systems.
Bidirectional sync mechanisms to update twin and vice-versa.
Defined sync intervals and fidelity thresholds tailored to use case needs.
Handling sync latency across systems, especially when covering edge and cloud.

In summary, lack of robust and optimized synchronization mechanisms can severely impact the accuracy and performance of digital twins, undermining their value. Synchronization is a defining characteristic of effective digital twins.

COMPOSABILITY

Composable Architecture is the final focus area. Can you delve into this in the context of the paper?

Here are some key points about composable architecture from the Platform Stack Architectural Framework:

Composable architecture refers to building large systems by combining smaller modular components.
This allows creating sophisticated digital twin systems by composing simpler individual digital twins.
The architecture focuses on interfaces and synchronization to enable integrating digital twins from different vendors/systems.
Standards like DTDL provide common data schemas to build interoperable twins that can plug together.
Twins expose standard interfaces like REST APIs to interact with other twins and applications.
Loose coupling and high cohesion allows replacing individual twins easily without disrupting the entire system.
The federated approach allows combining twins across organizational boundaries to create digital supply chains.
The architecture enables building hierarchical systems-of-systems linking cross-domain twins.

Example implementations:

The buildings-as-batteries use case highlights composing building-level twins into community-level energy management systems.
FIWARE highlights composing smart solution twins like warehouse pick-and-place robots into larger logistics systems.

In summary, composable architectures allow assembling sophisticated digital twin systems from modular building blocks, enabling scalability, adaptability and rapid innovation.

Here is the definition of the project called Digital Twin for X:

The possibility of Digital Twins to impact the manufacturing industry is immense and spans the entire product lifecycle from design to sustainment. However, no two digital twins are exactly alike making them difficult to quantify in business terms. To provide value, a given DT must match the fidelity and scope of the model to the type of problem being solved. Building on the Digital Twin Consortium (DTC) framework, this project call will fund the creation of two framework-compliant DT’s—one at a manufacturer and one within MxD’s Future Factory.

The project has the following objectives:

Architect a Digital Twin System Using DTC Framework

Determine a manufacturing industry use case or identify a system/subsystem of interest within MxD’s Factory Floor. Demonstrate all major Digital Twin capability categories: Data Services, Integration, Intelligence, User Experience, Management, and Trustworthiness.

Implement the Digital Twin System

Document the problem to be solved or the system to be understood, including baseline levels of performance. Develop a structured methodology for deciding upon system boundaries, curating minimum-viable datasets, and matching fidelity to problem statement. Develop, integrate, and test the DT system to validate hypotheses.

Devise a Level of Effort Methodology

Using project results and prior expertise, develop a coarse methodology to provide manufacturers an estimate of the level of effort for their novel use. This methodology should align to the DTC framework of capabilities and maturity levels and incorporate decisions made about scope, fidelity, and frequency.

Develop a Case Study for Technology Showcase

Incorporate project learnings into a Case Study in existing DTC Tech Showcase format.

Based on this can you create an Executive summary for an Interoperable Digital Twin Framework that would be the basis for blueprinting the two digital twins with implementations at a live production site and one as a showcase in MxD’s Future Factory?

Here is a draft executive summary for an interoperable digital twin framework to guide the implementation of digital twins at a manufacturer’s production site and the MxD Future Factory:

Interoperable Digital Twin Framework – Executive Summary

Overview
This framework provides guidance for architecting interoperable digital twins that follow industry best practices, the Digital Twin Consortium (DTC) Platform Stack framework model and Numorpho’s Digital Twine World Model (DTWM) Reference Architecture. It will be used to develop digital twins for a manufacturing use case across two environments – a live production site and the MxD Future Factory testbed.

The objectives are to:

• Demonstrate digital twin capabilities across data, integration, intelligence, user experience, management and trustworthiness.
• Match digital twin fidelity to the problem statement and curate minimum viable datasets.
• Develop a methodology to estimate level of effort based on DTC capability maturity levels.
• Document the implementation in a reusable case study.

Approach

The digital twins will be architected using the DTC Platform Stack architecture as a reference model covering the IT/OT platform, virtual representations, service interfaces, and applications.

Key technical capabilities will include:

Bidirectional synchronization mechanisms with real-time industrial data leveraging OPC UA Pub/Sub.
Interoperable data exchange between digital twins using DTDL schemas.
Common semantic data models aligned with industry ontologies.
Containerization and microservices architecture for loose coupling.
Cloud and edge processing to meet latency and autonomy requirements.
Visualization and analytics applications built on digital twin data.
Security and governance based on trustworthiness principles of privacy, safety, reliability.

The methodology for level of effort estimation will be based on the DTC capability maturity model covering data integration complexity, synchronization frequency, solution scope, and more.

Outcomes
The project will demonstrate interoperable digital twins spanning production environments using open standards. The implementation experience will provide real-world validation and improvements to the DTC reference model. The level of effort methodology will lower barriers to adoption. The documented case study will aid manufacturers exploring digital twin initiatives.

<- Back to Episode 37   On to Episode 39 ->

NITIN UCHIL Founder, CEO & Technical Evangelist
nitin.uchil@numorpho.com

References:

• The Coming Wave by Mustafa Suleyman