This blog is the second in a three-part Aras Primer on the Digital Twin. Part 1 reviewed what a Digital Twin is, Part 2 will present the Digital Twin in various industrial contexts, and Part 3 will bring the information back around and focus on use cases.
The Digital Twin provides significant benefits to manufacturers and others in asset-intensive industries. In Part 1 of this series, we defined the Digital Twin. This second blog will share insights into how the Digital Twin is used in various industrial contexts, including Digital Twin in AI, predictive maintenance, and a section on how to build a Digital Twin.
Although there are unlimited possibilities on how to utilize Digital Twins to improve business outcomes, we thought we would provide a few examples for inspiration:
Product as a Service (PaaS)
Many industrial companies are still managing product-related data in spreadsheets, which leads to a loss of visibility, traceability, and the risk of incorrect information. The volume of product data is constantly increasing, and companies like The Finnish compressor manufacturer Tamturbo find themselves struggling with data silos. The company switched to Aras Innovator® to create "a central station” for all our product-related data. “Now, we can’t imagine being without it,” said CEO Igor Nagaev. Read the case study or watch the demo for more information about Tamturbo’s “Air as a Service” initiative.
Over the Air (OTA) updates
An excellent example of where the opportunity lies is with the software running on products today. The Digital Twin configuration creates the context; otherwise, your simulations of an over-the-air (OTA) software's impact on products is just an estimation or a guess, which is not good for customer relations. When simulation moves out to the field, it becomes operational simulation. It is about trying to understand what a product’s been through in its lifetime that might affect its operation once we apply an update. Simulation can have a more significant presence in the physical world if the context is there. You then can predict based on an individual configuration of an individual asset and use simulations to predict what will happen if we replace a part or update software.
Predictive Maintenance
Another opportunity is the simulation of what will happen if I change something in a Digital Twin configuration and simulate behaviors based on what is happening to the Digital Twin now. For example, let’s say that we start to see failures in the products once we reach a specific temperature; we can then use that data to predict what will happen if the temperature goes up even further to see those failures. It's simulating not only the current version of the Digital Twin but also simulating based on the real-time feedback that we're getting from the product.
What is a Digital Twin in manufacturing?
There are many use cases for the Digital Twin across the product lifecycle in manufacturing a product. For the manufacturer, technology is available now to link product data as it is created in the design, engineering, and manufacturing stages and to capture it as it changes. We call this the Digital Thread. Many manufacturers realize the importance of creating digital threads between departments. At the final stage of the product manufacture, there is a need to connect everything to the final product. This Digital Twin Configuration displays the as-built configuration of a product – and links all product data history, decisions, who made them, and why, including the CAD models, simulations, and requirements.
Combining the digital thread with each Digital Twin configuration can also help by capturing reliable data from the operating asset in the field that can help OEMs validate design intent versus operational context and make appropriate design changes. Creating the Digital Twin configuration allows many individuals or groups access to this information that has been traditionally siloed and, for the most part, unavailable once the asset is in operation.
What is a Digital Twin in AI?
Predictive Maintenance is the ability to determine when maintenance should be performed based on the asset’s operating conditions in the field. Technology advancements in sensors, analytics, and simulation can be the solution to predicting maintenance problems, but only when a Digital Twin configuration approach is considered. An individual asset’s context must be used as a baseline to predict failure with data generated from IoT sensors and validated with simulation models. The key is to develop corresponding business processes to support asset configuration changes, the ability to collect IoT data specific to individual configurations, and the use of simulation to build a digital model of the specific asset configuration. Predictive maintenance will yield significant results to organizations' maintenance effectiveness using the above framework.
How do you build a Digital Twin?
This may all sound great, but how do you get started? If you are a manufacturer, you need to ensure your “as-built” configuration is as accurate and detailed as possible. This creates a digital thread by capturing all serialized electrical, electronic, mechanical, and software components
and linking them to engineering parts and their related history. CAD models, simulations, requirements, change orders, and so on are considered based on the value they can provide in supporting your required use cases.
If you are in operations and maintenance, you can start by keeping accurate records of your inspections—track what a product’s configuration looks like when it arrives and ensure this information is digital, not paper-based. It should be in a searchable database, inspectable, and maintained. Whatever the business case, the Digital Twin configuration should be able to extend out to installation, commissioning, and operation at a customer site, allowing it to update the configuration as things change. This will enable you to start capturing additional data from the field where your product is maintained.
The ultimate goal is for product manufacturers to have a Digital Twin configuration from when the product is built and to continue that configuration until that individual physical product is retired and recycled. If you can achieve that vision, you are going to significantly increase the long-term value delivered by the complex products you maintain and operate.
Stay tuned for Part 3 coming soon. In the meantime, if you would like to learn more about the Digital Twin, visit our solutions page.