In an industrial setting, digital twins are used to improve product design, monitor equipment condition to identify potential degradation, simulate manufacturing operations, and more.
To understand how digital twins enable predictive maintenance, let’s consider a simplified example of predictively maintaining a centrifugal pump. Creating a pump’s digital twin requires building its accurate 3D model; and powering the model with networked data.
To build a 3D model, modeling experts collaborate with mechanical, electrical and process engineers to describe and virtually present physical properties of the pump and its components e.g., an impeller type, the number of suctions, etc. Then, the 3D model is powered with network data relayed from sensors attached to the pump. This data includes records about a pump’s performance, condition and environment e.g., temperature, voltage, inlet pressure, etc.
To improve the model’s functionality, the digital twin network is integrated with enterprise and shop floor management systems. Fetching contextual operational data the digital twin could predict how a pump will function under varied external conditions.
The digital twin-based predictive maintenance network takes in real-time sensor records about the working conditions of a pump and analyzes it against historical data about the pump’s failure modes and their criticality, and contextual data transmitted from enterprise and shop floor management systems e.g., pump’s maintenance data.
A functionally connected network detects abnormal patterns in the incoming sensor data and reflects the patterns in predictive models, which are then used to predict failures. This way, if a pump’s current configuration is likely to lead to a failure, the digital twin network localizes the issue, assesses its criticality, notifies technicians, and recommends a mitigating action.
Along with the prediction of failures, digital twin technology provides the ability to calculate maintenance-related performance indications. Combining historical data about failures, risk factors, machine configuration and operating scenarios, a digital twin can calculate maintenance-related metrics like performance indicators and mean time between failures.
So digital twins provide ability to forecast the behavior of machines under different circumstances. Being an accurate real-time model for an object’s condition and performance, a digital twin is used to run simulations and predict how an object will "behave" under certain factors, e.g., runtime, exposure to severe operating conditions, etc.
To simulate different maintenance scenarios. technicians use digital twins to test maintenance scenarios or particular fixes and see how they work for a piece of equipment before applying them to the physical twin.
Although digital twin-enabled predictive maintenance offers many benefits, its deployment may pose several challenges.
An accurate model should precisely reflect the physical twin’s properties. A digital twin should precisely reflect all the properties of a physical twin, including mechanical eg suction pressure, design temperature, etc. and electrical eg, capacitance, conductivity, etc. ones. It requires input from facility managers, process engineers, electrical engineers, equipment vendors, and other parties, which adds complexity to the deployment.
Detailed blueprints of a machine's failures are required. To predict failures, a digital twin should be fed with data about equipment failure modes. This data should be gathered for an extended period of time to observe a machine throughout its degradation process.
A digital twin requires remodeling with any change in equipment’s configuration or element state. Any modification affecting equipment performance requires a change to its model and underlying algorithms.
Such modifications – at a machine level eg, replacing original parts with made-to-order ones or at a factory level eg, changes to the operational policy are not always reflected in factory specifications, thus, cannot be precisely simulated, which escalates the risk of errors.
Although deploying a digital twin-based predictive maintenance is time-consuming and labor-intensive, the technology offers the ability to timely recognize disruptions in asset performance, forecast potential problems and simulate various maintenance scenarios. It helps enterprises eliminate machine downtime, reduce equipment maintenance costs, improve equipment reliability and extend its lifespan.
Soon, the level of enterprise digitalization is expected to make big gains with predictive maintenance leading the investments race inspired by the improvements arising from applying network driven predictive maintenance solutions. However, some limitations remain to be overcome before fully deployed.
Supply and service chain partners value ability to make the complex as simple as possible; especially when it comes to configuration management tools used downstream of product engineering to manage the as-delivered and as-maintained real world configurations of in-service equipment and long-life assets deployed in the field.
It’s no secret that manufacturers and their supply chain partners are being crushed by an avalanche of complexity along nearly every axis of their business. The unrelenting complexity of ever-increasing customer requirements, product performance expectations, new technology absorption, system integrations, and lengthening product development and use lifecycles is overwhelming.
Added on top of this is a constantly changing layers of organisational complexity in program management, contract funding, business processes, and supply chain partnerships that increasingly have design authority, not just build-to-order responsibility.
To help manage all of this intricacy we have added yet another layer of complexity from the network system architectures, implementations, and integrations of digital applications, and many were created to save ourselves from the pitfalls of complexity. In doing so it seems we have now created a whole new parallel digital world where every element and process must be modelled in exacting detail with all things instantly connected.
Despite all the value of digital technologies to product development and system performance, it has indisputably injected more complexity and cost for the program office who must now manage both physical and digital versions of processes and products. The evidence speaks for itself in the number of new weapons programs which run over budget, are late, or miss performance goals-- even after massive spending on digital automation/integration
While enterprise product lifecycle management systems can improve upon many important functions critical to industry, most systems were initially acquired to start out as a more simple solution. They were often sold as a means for getting control of all the many different materials used across the aerospace manufacturer, then providing for change control and configuration management over the design-to-build part of the lifecycle.
Unfortunately, by the time design data management, application integration, variant management, collaboration, visualisation, digital manufacturing, workflow management, simulation data management, supply chain integration, requirements planning, project planning, cost management and more functions were added onto the product lifecycle construct it is no surprise that many implementations collapsed under their own weight.
The first victims of a delayed or failed product lifecycle strategy are often configuration management professionals working outside of engineering design who are responsible for creating, checking, distributing, maintaining, and enriching product configuration data for others further downstream to consume.
There are typically far more users of configuration management tools and consumers of product configuration data in these down-cycle functions than those found in product engineering. These data users include those in logistics, test, quality assurance, tech pubs, service, and the partner supply chain. Without instant access to “live” configuration data of the as-built or in-service product planners often resort to elaborate spreadsheets and homegrown legacy tools that only specialists fully understand.
Nowhere is the live as-maintained configuration data more important than in the supply and service chains who manufacture components or perform maintenance, repair of in-service assets and equipment located in the field.
Some contractors often do not need or want or afford enterprise-level product lifecycle platforms. If not enterprise product lifecycle management platforms, then what do these configuration management system do users want?
1. Capable and efficient in production use, offering the deep configuration management functionality required to support configuration planning/ identification, status change control and traceability
2. Intuitive and easily mastered in everyday use by the expert who creates data as well as in occasional use by program managers and others who consume or repurpose data.
3. Deployable quickly and rolled out with minimal demand on network resources, no programming and little site customisation required.
4. Compact and right-sized for contractors who must often acquire several solutions to support all their different customers and program contracts.
5. Affordable and maintainable with a low initial cost followed by a low total lifecycle cost of ownership.
6. Flexible to accommodate unforeseen new requirements, uses, projects, workflows, and digital connections.
7. Durable and resilient over the life of long programs and product use, regardless of the original design requirements or the initial contract stipulations.
8. Portable and adaptable across different program contracts at different stages of maturity and deployment.
9. Scalable and robust to accommodate the elastic business cycles of growth and contraction as requirements change throughout the partner chain.
10. Secure and protected in both standalone and connected modes of operation.