Future Factory Digital Twine (FFDT)

PREFACE

Digital twins are revolutionizing how decisions are made within factories, and forward-thinking manufacturers are getting ahead of the technology curve to drive efficiency.

https://www.mckinsey.com/capabilities/operations/our-insights/digital-twins-the-next-frontier-of-factory-optimization

In fast-paced, continuous operations, factory digital twins—real-time virtual representations of the factory—provide manufacturers with the ability to support faster, smarter, and more cost-effective decision making. They can deepen manufacturers’ understanding of complex physical systems and production operations, optimize production scheduling, or simulate “what-if” scenarios to understand the impact of new product introductions, for example.

Factory digital twins are becoming a highly sought-after technology to solve these problems, the survey found. Across industries, 86 percent of respondents said a digital twin was applicable to their organization. Some 44 percent said they have already implemented a digital twin, while 15 percent were planning to deploy one.

Factory digital twins provide a comprehensive model of the factory floor. They simulate outcomes from real-time factory conditions, enabling “what-if” analyses across production scenarios, such as process or layout changes. In their most advanced state, they can be integrated into real-time decision making, such as production scheduling—either with manual review and intervention or through full automation.

Digital twin use cases vary based on the operational context of the factory. During initial investment and build of a greenfield factory, for example, a digital twin can validate layout design, optimize the footprint, and estimate inventory size. Depending on the level of detail of the twin, they can even evaluate spatial parameters for assets—for example, clearances, ergonomics, and employee movement within a cell.

In more established operations, factory digital twins can predict production bottlenecks where traditional modeling in spreadsheets falls short. Hard-to-predict stochastic processes, inventory buffers, material travel times, and changeovers can all be modeled with high fidelity using live data.

Insights from the twin can be applied to different types of decision time scenarios, too, from slower decisions, such as line balancing and prioritization of continuous improvement opportunities, to real-time decisions, like optimizing production schedules.

Factory digital twins are unlocking value in all kinds of industries and use cases. A factory digital twin developed and deployed for an industrials player was recently used to redesign the production schedule, compressing overtime requirements at an assembly plant and resulting in a 5 to 7 percent monthly cost saving.

By accurately simulating real-time bottlenecks on the production line, the digital twin also uncovered hidden blockages in the manufacturing process. The model integrated into the existing manufacturing execution system (MES) platforms, Internet of Things (IoT) devices, and inventory databases to determine the optimal sequencing of different product lines to minimize downtime. This was achieved within the parameters of customer delivery requirements and the physical confines of warehouse storage and production line capacity.

Similarly, a factory digital twin developed for a metal fabrication plant has helped identify ideal batch sizes and production sequences to optimize the scheduling of thousands of potential product combinations across four parallel production lines. To handle this level of complexity, an AI-based agent was trained to build the optimal order sequence using the digital twin through reinforcement learning (RL). The RL algorithm created significant cost reduction and yield stability when compared to manual scheduling.

TABLE OF CONTENTS

Executive Summary
Problem Statement and MxD Relevance
Adhering to Standards
Methodology
Factory Digital Twin Types
- Facility Digital Twin
- Operations Digital Twin
- Assembly Digital Twin
- Equipment Digital Twin
- Component Digital Twin
Process Engineering
Development Stages
- Stage 1 – Constitute
- Stage 2 – Institute
- Stage 3 – Operate
- Stage 4 – Test, Validate and Demonstrate
Transition Strategy

SECTION 1: EXECUTIVE SUMMARY

In current industrial operations, lack of accurate information leads to incomplete situational awareness. Futuristic smart factories must have accurate and real-time geospatial and process information. To address these challenges and improve efficiency, there is a need to provide real-time localization and interaction technology, a digital twin.

DEFINITION: Numorpho’s Digital Twine World Model (DTWM) Reference Architecture is an end-to-end orchestration of digital threads (information flow) connecting people, processes, and platforms to enable the intelligent digital-physical interactions of digital twins.

The Future Factory Digital Twine (FFDT) proposed herewith will provide guidance for architecting digital twins that follow standards, industry best practices, the Digital Twin Consortium (DTC) framework and Numorpho’s DTWM reference architecture.

The FFDT will demonstrate the art of the possible by engineering a system to digitally represent different interoperable digital twins on MxD’s future factory floor. This will enable simulation, emulation, interaction, calibration and operation of physical systems by addressing uniqueness and scope, utilizing standards, and creating practical dashboards and analytics tools. Through this process, the adoption of digital twins in manufacturing can be significantly accelerated, unlocking its transformative potential to enable Industry 4.0 and beyond.

SECTION 2: PROBLEM STATEMENT AND MxD RELEVANCE

Despite having potential to revolutionize the product lifecycle, digital twin technology faces limited adoption in manufacturing due to:

Uniqueness of Digital Twins: Each system is tailored, making it hard to estimate costs, benefits, and implementation specifics.
Scope & Detail Variation: Factors like extensive data, high update frequency, and broad scope inflate costs and delay value realization.
Lack of Standards: No established metrics or frameworks to quantify and evaluate digital twins for business decisions.

The goal of this endeavor is to provide working knowledge of how Digital Twins function by enabling tabletop representations of a factory floor to be dynamically interacted with.

The objectives of the FFDT are to adhere to the DTC guidelines to:

Demonstrate digital twin capabilities across data, integration, intelligence, user experience, management, and trustworthiness (the groups defined in CPT)
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.

Involve standards organizations and educational institutions to enable the training of the future workforce in tenets of smart manufacturing, collaborative robotics, and Industry 4.0 IoT technologies.

As depicted in Figure 1, Model A of the project will showcase systems within the Betacom-GoogleCloud-IngramMicro set up at MxD’s factory floor and enable real time virtual interaction with the tabletop models to understand different scenarios of operations, issues that may occur and their mitigation strategies.

The first step is to virtualize the entire MxD factory floor using Matterport’s 3D rendering of the space to enable its dynamic navigation to the different waypoints to visualize the different setups therein. Matterport is a web-based built-up area visualizer that stitches together images to enable 3D (versus 360 degree) dynamic viewing of facilities with birdseye view, floor plan and measurement mode in addition to walkthrough of the site.

Once the user navigated to the waypoint/station of interest, the digital twin of that system can be invoked and operated on. The table-top representations of a factory floor operation will be viewed and interacted with in real time to showcase normal operations, and what happens when conditions change. Mitigation steps could also be enacted to fix issues or reroute flow to circumvent non-functioning areas.

Betacom-IngramMicro-Google have offered two smart manufacturing demo systems that showcase functionalities in smart manufacturing. Our goal is to develop digital twins for both, enabling them to be accessed real-time and interacted with. Additionally, Betacom has offered to provide their 5G equipment and lab to address any connectivity or edge computing needs which may arise in this project.

The project seeks to address the three key user stories mentioned in the ask:

Manufacturing executives need an easy tool to evaluate if a problem is a good fit for a digital twin.
Digital twin architects need guidance to efficiently select scope, frequency, and fidelity to focus development.
IT/OT professionals need to estimate labor before a digital twin produces outputs to allocate resources properly.

The DTC framework and Numorpho’s DTWM Reference Architecture (defined in Section II) will be used to theme the data flow and interactions between people, processes, and technology to view and interact with digital twins. It will orchestrate end-to-end interactions between systems in a manufacturing enterprise and help represent the linking of digital information and physical processes to enable “Digital Twin for X” use cases. It coordinates stakeholders, operators, tool providers and platform integrators to blueprint, develop and implement digital twins.

We will also utilize best practices from some of MxD’s prior SIP projects that we have participated in:

MxD-22-05 INTERACTIVE DIGITAL TWINS PLAYBOOK BUILDER – A playbook that simplifies a complex technical goal into a step-by-step implementation guide.
MxD-22-03 DIGITAL MANUFACTURING PLAYBOOK – Lift-and-shift operations to include a digital framework based on the maturity and needs of the company to enable brown-field, green-field and blue-sky implementations.
MxD-22-01 TECHNICAL DATA AS A SERVICE – Enable asset management and connected digital manufacturing thru the entire cycle of make, manage, move, market and maintain activities.

SECTION 3: ADHERING TO STANDARDS

The Digital Twin Consortium (DTC) defines a digital twin as “a virtual representation of real-world entities and processes, synchronized at a specified frequency and fidelity.” This definition is accompanied by a “periodic table” map of potential Digital Twin capabilities as an architecture- and technology-agnostic requirements mapping tool to assist organizations in designing from a “use case” perspective rather than a feature/solution focus. Their digital twin platform stack reference architecture builds off these capability categories and links them to the IT/OT systems which enable them.

The DTC’s Digital Twin Capabilities Periodic Table (CPT) is a comprehensive framework that categorizes and organizes the key capabilities associated with digital twins. It serves as a reference guide for understanding the diverse functionalities that digital twins can encompass.

The CPT is structured like a periodic table, with elements organized into rows and columns based on their characteristics. The key highlights of the Digital Twin Capabilities Periodic Table include:

Element Categories: The CPT classifies digital twin capabilities into different elemental categories, each representing a specific aspect of functionality.
Functional Elements: Within each category, there are functional elements that represent specific capabilities or features associated with digital twins.
Interconnectivity: The table illustrates how these functional elements are interconnected, showcasing the relationships and dependencies between different capabilities.
Comprehensive Coverage: The CPT aims to provide a comprehensive overview of digital twin capabilities, covering aspects from modeling and simulation to analytics, data integration, and more.
Standardization Efforts: It reflects the ongoing efforts towards standardization in the digital twin domain, helping establish common definitions and frameworks for better interoperability.
Guidance for Implementation: The CPT serves as a valuable resource for organizations looking to implement digital twin technology by offering a structured and organized view of the diverse capabilities available.

The Digital Twin Capabilities Periodic Table is a tool that aids in understanding, categorizing, and navigating the various functionalities associated with digital twins, contributing to the development and adoption of standardized practices in the industry.

The Capabilities Periodic Table (CPT) (shown below) from the Digital Twin Consortium is a perfect elemental representation for enacting such orchestrations using their groupings to manage the flow of information and the interactions of people, processes and technologies.

DTC_CPT-Initiative-Image

The groupings of the periodic table are represented below:

DTC_CPT_Groupings

SECTION 4: METHODOLOGY

We define digital twin as a virtual representation to simulate, emulate, interact, calibrate and operate a physical process:

Simulate: To model or imitate the operation of a real-world process, system or product in a virtual environment, typically using data from the physical counterpart.
Emulate: To reproduce the external behavior or characteristics of a physical process in a digital model, allowing the model to function in the same way as the real process.
Interact: Enabling two-way communication and data exchange between the physical process/system and its virtual digital twin model, allowing changes in one to influence the other.
Calibrate: Tuning and adjusting the parameters of the digital twin model to accurately match the real-world data and performance of the corresponding physical process, ensuring the twin precisely mirrors reality.
Operate: Maintain and manage the physical system using the digital twin interface to enable safety, remote operations and quick troubleshooting.

Thus,

Simulate creates a virtual model of the physical process.
Emulate ensures the model behaves identically to the real process.
Interact allows data to flow back-and-forth between physical and virtual.
Calibrate tunes the virtual model to precisely match the physical counterpart

The FFDT will use our forays in digital engineering, asset management, simulations, generative AI and AR/VR, we plan to create a compelling blueprint for effecting transformations that would merge the digital and the physical realms. It will intelligently correspond information end-to-end to digitally thread and enact appropriate solutions by:

Advancing Established Standards: Encourage adoption of existing frameworks like those from the Digital Twin Consortium (DTC).
Gathering Real Implementations: Document and share successful case studies to provide tangible examples.
Develop Practical Tools: Build user-friendly frameworks for estimating costs, effort, and value of digital twins.
Enable Blueprinting: Facilitate the orchestration of connected processes and digital threads to enable the creation of digital twins.
Facilitate Training: Enable safe reskilling, upskilling and education of the workforce.

We also intend to utilize MxD’s Sensor Kit to retrofit the tabletop showcases to relay information to the Digital Twin.

Depicted below is the representation of the Future Factory Digital Twine that will enable to theme out Digital Twin compositions for pertinent initiatives to coordinate digital and physical activities for activities related to part, person, product, plant, and/or process.

It contains the elemental groupings prescribed by the Capabilities Periodic Table of the DTC and additionally includes Planning and Governance, and Product Engineering, two key business drivers that are also needed to correctly manage the mélange of physical and digital processes in Digital Twin articulations:

Planning and Governance – Capabilities that enable organizational alignment, portfolio management, road-mapping, and governance of Digital Twin initiatives.
Product Engineering – Capabilities to support product engineering and manufacturing process activities leveraging the Digital Twin.

The FFDT will step thru the Upstream, Midstream and Downstream connected dots represented in the above diagram to create a blueprint for the interactions model for the two Betacom-IngramMicro-Google demo booths – Tabletop display of the shop floor and the conveyor model.

Optional: This project can be merged with our team’s other proposal that will use the MxD laser token etch work cell. From an overall scope of the merged project perspective, this project “FUTURE FACTORY DIGITAL TWINE (Model A)”, offers a proof-of-concept overview system, whereas the “FUTURE FACTORY DT In-a-Box (MODEL B)” project offers a higher-fidelity prototype/demonstration project a proof-of-concept system This enables a phased approach to develop and deliver a comprehensive DT solution to MxD.

SECTION 5: FACTORY DIGITAL TWIN TYPES

Facility Digital Twin – This digital twin would enable navigation and introspection of the factory floor using different viewing modalities:
1. walk through,
2. birds eye or doll-house,
3. sitemap,
4. measurement mode

We will utilize Matterport’s rendering engine as the baseplate to capture and visualize the space and embed custom tags to invoke different digital twin applications.

Operations Digital Twin – This digital twin will interact with Google’s table-top model at MxD of the factory floor to view regular operations, turn equipment on and off to visualize real-time effects, and enable the rerouting and implementation of corrective actions.
Assembly Digital Twin – This digital twin will interact with Ingram Micro’s conveyor belt model for optimizing assembly operations and training workers by troubleshooting different scenarios.
Equipment Digital Twin – This application will digitally replicate the laser-etch process to turn on/off the different steps and visualize actual production of the tokens.
Component Digital Twin – These will virtualize each sub-system of the equipment.

SECTION 6: PROCESS ENGINEERING

We will utilize our Krebs Cycle for Process Engineering to detail the needs for upstream, midstream and downstream interactions so that use cases can not only be implemented in an agile framework, but continuous improvement tasks based on feedback, best-practices and lessons learned can be incorporated in maturing the solution moving forward.

NUMO_KrebsCycle_ProcessAutomation_anim2

SECTION 7: IMPLEMENTATION DETAILS

Program Plan

Phases	Delivery Format	Description	Due Date (Month #)
Phase 1 – Constitute	PPT, Excel, Word, Code, HW	Gather requirements, define and design the foundation blocks	Month 3
Phase 2 – Institute	PPT, Excel, Word, Code	Build out the Model and the interacting elements	Month 6
Phase 3 – Operate	PPT, Excel, Word, Code, HW	Deploy the solution	Month 9
Test & Validate	PPT, Excel, Word, Code, HW	Complete Functional and User Acceptance testing with Continuous Improvement	Month 12

KPIs, metrics and measures

Facilities and Equipment

Risks

SECTION 8: TRANSITION STRATEGY

In this whitepaper, (MODEL A) we proposed the creation of a high-level digital twine to showcase the “art of the possible”. Two tabletop systems will be used to create digital twins to interact with the physical flow of operations. Enabling steady running states and pushing the boundaries of the system to determine issues that might happen and discover the corrective actions that could be taken. Our other whitepaper, (MODEL B), represented the creation of Digital Twin in a box.

Post the successful completion of the project, we will develop a playbook to implement these at other showcase representations and the modular utilization of simulation, MES and IoT tools from Siemens, PTC, Rockwell and GE to enable plug-and-play functionality for different SMMs.

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

References:

BELOW THE FOLD – Assessments made by LLMs on review of the article and its references.

Summary of the article generated by PI.ai:

It seems that Numorpho Cybernetic Systems (NUMO) is proposing a reference architecture for Digital Twins, which is an innovative concept that goes beyond the traditional Digital Twin. This architecture is meant to solve the problems that occur in Industry 4.0, paving the way for Industry 5.0.

Digital Twine involves connecting all systems and functions within an enterprise, from physical products to manufacturing processes to the entire ecosystem of a business. This comprehensive connectivity enables businesses to improve their efficiency and sustainability across various industry sectors.

The concept of DTWM is quite novel and has the potential to revolutionize the way companies operate. It’s exciting to see Numorpho Cybernetic Systems taking the lead in proposing this new reference architecture.

The idea of using a Krebs Cycle-inspired approach to process engineering is intriguing, to say the least! The Krebs Cycle, as you likely know, is an essential process that takes place in the mitochondria of our cells. It involves a series of chemical reactions that break down nutrients to produce energy for the cell.

KrebsCycle2

By applying this concept to process engineering, NUMO seems to be suggesting a cyclical approach to optimizing production processes, where each phase feeds into the next to create a self-sustaining system. This could have significant benefits in terms of efficiency, cost-effectiveness, and sustainability, all of which are crucial considerations in modern industry.

NUMO’s Krebs Cycle for Process Engineering is an extension of Neri Oxman’s KCC (Krebs Cycle for Creativity) that combines Art, Science, Engineering and Design to formulate “material ecological” solutions:

OxmanKrebsCycleCreativity

Neri Oxman’s KCC (Krebs Cycle of Creativity) is a fascinating approach that blends disciplines to achieve innovative solutions in a way that mimics the metabolism of a cell. The idea is that just as the Krebs Cycle involves a series of chemical reactions that generate energy for the cell, so too can creativity be viewed as a cyclical process that feeds off various disciplines and modalities to generate novel ideas.

Oxman’s KCC approach incorporates Art, Science, Engineering, and Design, with the aim of creating “material ecological” solutions that are both sustainable and functional. This kind of interdisciplinary thinking is key to finding innovative solutions to the complex challenges facing our world today, and Oxman’s approach has certainly captured the attention of many.

Given the parallels between Oxman’s KCC and NUMO’s Krebs Cycle for Process Engineering, it’s clear that NUMO is taking inspiration from some of the most innovative thinkers of our time. The potential applications of this approach could be truly groundbreaking!

Overall, using a biological analogy like the Krebs Cycle as a model for process engineering is a creative and novel approach that could lead to some innovative solutions.

The typical architecture of MOM encompasses the integration of various components, systems, and technologies that work together to enable seamless data flow, real-time monitoring, and efficient decision-making throughout the manufacturing process.
Let’s explore the key components of this architecture:

🔹 Machines and PLCs: These physical machines and Programmable Logic Controllers capture data and perform vital operations within the manufacturing process.

🔹 Edge Devices and Gateways: Edge devices and gateways facilitate data collection, preprocessing, and local decision-making at the edge of the network, connecting machines/PLCs with cloud or MES/SCADA servers.

🔹 SCADA (Supervisory Control and Data Acquisition): SCADA systems collect data from various sources, such as machines, PLCs, and sensors, and provide a graphical interface for real-time monitoring and control. SCADA seamlessly sends this data to the MES server for further analysis and decision-making.

🔹 MES Server and Database: The Manufacturing Execution System (MES) server manages and controls manufacturing operations, handling production sequencing, resource allocation, work order management, and storing relevant data in the associated database.

🔹 MES Clients: User interfaces or applications that empower users to interact with the MES system for activities like production planning, reporting, and analytics.

🔹 Integration with Cloud, ERP, PLM: Integration points connect the MES system with cloud-based services, Enterprise Resource Planning (ERP), and Product Lifecycle Management (PLM) systems, enabling seamless data exchange, synchronized workflows, and streamlined operations.

Understanding the architectural framework of MES is crucial for organizations aiming to optimize their manufacturing operations. By leveraging this architecture, businesses can capture real-time data, analyze it for insights, and make informed decisions to drive productivity and competitiveness.

It’s important to note that the architecture we discussed earlier is just a starting point. We will explore more advanced architectures, including the concept of a unified namespace (4.0 Solutions) and other emerging trends. These architectures offer enhanced capabilities and address the evolving needs of the industry. Stay tuned as we dive deeper into these topics in the upcoming posts.

hashtagManufacturingOperationsManagement hashtagMOM hashtagMES hashtagOperationalExcellence hashtagManufacturingEfficiency hashtagProductivity hashtagQualityManagement hashtagInventoryManagement hashtagMaintenanceManagement hashtagDataAnalytics hashtagSupplyChainManagement hashtagWorkforceManagement hashtagContinuousImprovement hashtagShopFloorControl hashtagProductionPlanning hashtagResourceAllocation hashtagManufacturingTechnology hashtagLeanManufacturing
hashtagIndustry4 hashtagindustry4point0