Digital Twins can be built for any part of your process or any physical entity of your production process. Below, we unpack a few different types of Digital Twins found in manufacturing, including the pros and cons of each type.
Asset Digital Twins
An asset Digital Twin is a digital replica of a physical asset on your factory floor. For instance, you can have a Digital Twin of a boiler, digestor, or slicer. Teams can access all the data and attributes for that particular asset within their digital systems.
An asset Digital Twin makes it easier to track individual machine performance, understand optimal production settings, and track maintenance patterns to enhance your predictive maintenance strategy.
Cons of an asset Digital Twin
However, it can be difficult to understand how an asset’s performance impacts a particular outcome (e.g. lower quality or flow times). This is because the data captured by an asset Digital Twin is only specific to the asset itself; it doesn’t account for how the asset interacts with processes, people, or other machines during production.
It is also possible to build a Digital Twin of the assets on your production line. This makes it possible to collect and organize the data generated on your production line in a more encompassing manner—similar to the data an MES may collect. This kind of Digital Twin is typically referred to as a Digital Thread.
Rather than build out a Digital Twin for each individual asset, a Digital Thread makes it easier to collect, see, and analyze the data produced by collecting and processing data throughout the entire production life cycle. This can save you time and money over building a Digital Twin for each individual machine on your line and can help improve performance.
Cons of a Digital Thread
The shortfall with a Digital Thread is that it is still difficult to attribute your production outcomes to the correct cause of variation in the process. For instance, let’s say one of your product batches fails quality inspection. With a Digital Thread, it can be difficult to know where the quality misstep took place. As a result, it’s nearly impossible to trace the data back and understand what happened during production that may have had an impact on the batch’s quality.
Even with asset data from the time that a batch was in production, teams don’t have a clear understanding of where the batch was in the production process at a given time. This makes it difficult to understand where they should look within the production process to identify a possible machine issue or improvement. In other words, a Digital Thread can make it harder to troubleshoot production issues because you can’t connect key input variables to the outcome (key output variables).
A Digital Thread can make it harder to troubleshoot production issues because you can’t connect key input variables to the outcome (key output variables)
Additionally, if the quality issue was caused by something other than a machine—say, the batch sat too long in a storage tank before moving to the next phase of production—the data may not be captured at all. This makes root cause analysis difficult for teams to perform, hindering your capacity to continuously improve your processes.
Lastly, it may be difficult to modify or change a Digital Thread if you have to change out a piece of equipment or add a new piece of equipment. You may have to go back to your third-party vendor and have them make changes to the Digital Twin model to account for any asset changes on your line. This can be a costly adjustment, especially as future asset changes occur on the shop floor.
Process Digital Twin
A process Digital Twin is built to be a digital replica encapsulating the exact manufacturing conditions of each final product. Process Digital Twins are built to give you a comprehensive look at each product coming off the line. Data is continuously collected, cleansed, and structured, covering all relevant data from suppliers and raw materials through the final product. It follows the flow of materials and accounts for every asset, process variable, lag time, and final characteristic (e.g. quality data, weather/moisture during production, etc.). Braincube’s Digital Twins are an example of Digital Twins built by process.
As a result, a process Digital Twin depicts every step and data point of your process, all contextualized by time-series data. In other words, you can know what happened in production and how long it was happening. Process Digital Twins enable you to drill down and see the key inputs and outputs by individual product, batch, or serial number. As a result, the process model captures an exact replica of every production run for the most accurate, relevant, and comprehensive Digital Twin.
This is more advanced than a Digital Thread because a process Digital Twin attributes data from production to the final outcome. Since a process Digital Twin is built with process experts and follows the process map, teams can understand with confidence where a specific batch or serial code was at any point during production, as well as isolate any cause of variation in the process settings or conditions.
Braincube also accounts for lag time in your production process. This includes how long materials sit in a specific vessel when the materials pass through a change of state process, or even how long (and the conditions) where raw materials were stored before use. As a result, you have the cleanest data set possible and a full picture of your production process without skipping or streamlining steps.
By bringing together process data with outcome results, teams can leverage this information via advanced applications to obtain transformative results. This is a key step towards understanding how to hit your goals and replicate your golden batch time and time again. For example, Braincube’s Advanced Analysis app leverages its own CrossRank AI to tell you the impacting variables on any of your objectives and the recommended settings to run at your best.
Cons of a process Digital Twin
The wide variety of use cases and advanced agility of a process Digital Twin are the results of a detailed process map build-out. In order to be effective and fully agile, you’ll need the involvement of your whole factory—including IT and SMEs—to ensure an accurate process map is built. It takes time to work with a third-party vendor, but it’s important that your Digital Twin vendor captures and understands your full production process if you are to have continued success using your Digital Twin for any use case.
One thing that typically happens early in the digital transformation process is that companies build multiple types of Digital Twins. This ad hoc approach to designing and implementing different Digital Twins for different, isolated needs can cause problems down the road. This can lead to architectural data inconsistencies and unnecessary complexity. As a result, it’s a struggle to maintain your data and can cause trouble down the road.
There is also a chance that, during your initial meetings with a third-party Digital Twin vendor, you discover that your factory is not collecting the necessary data. In order to work correctly, process Digital Twins need comprehensive access to data coming from every part of your production process. This means that, as an organization, you’ll need to be fairly advanced with your data collection. If you have built previous Digital Twins piecemeal, this may be more difficult to overcome.
Process Digital Twins can help you overcome siloed data problems but may mean taking a few steps back before you can move forward with a viable solution.
How Digital Twins are built for manufacturing
Selecting the right type of Digital Twin (e.g. asset, thread, or process) depending on your needs and objectives is one component of your digitalization strategy. You should also consider how Digital Twins are built, as this can have an impact on your ROI and overall digital effectiveness.
Braincube’s advanced Digital Twin is unique compared to most manufacturing Digital Twins on the market. To start, our product Digital Twin continuously and automatically collects data from relevant sources (e.g., machines, systems, flows, etc.) and includes calculated variables for lag times or other flows when no sensors exist.
Once built, data is continuously ingested through Braincube middleware to ensure teams always have access to updated, accurate production information. This unique differentiation means teams don’t need to manually pull or prepare data to understand what happened during production. The Digital Twin continuously updates for each product.
The usability of your data is another point to consider. All Digital Twins are designed to capture data, but the data is only valuable when put to use. Some Digital Twin products may clean your data, but this still means your data science teams need to sift through which data is meaningful when they are working on a study.
Leveraging Digital Twins with other 4.0 tech: IIoT Platforms, applications, and more
Other Digital Twin models structure your data, making it available to teams in a universally usable format. The caveat is that the data is still only in a “usable format” for highly technical teams that know what to do with it. Unless someone knows how to use the data in a custom algorithm or model, data doesn’t have much use for teams.
As a result, the data isn’t truly democratized for everyone at your organization. If advanced technical skills are necessary to derive value from the data, then a large portion of your employees are still unable to make discoveries and drive progress forward.
If advanced technical skills are necessary to derive value from data, then a large portion of your employees are still unable to make discoveries and drive progress forward. It will be difficult to obtain true digital transformation.
Basing Braincube-powered Digital Twins on your process map allows our middleware to cleanse data (removing outliers, merging formats, ETL) as well as produce up-to-date product data. This transforms your production data into interconnected information, making it available for further visualization, analysis, decision making, and innovation.
Braincube’s IIoT Platform was designed to democratize data and empower Citizen Data Scientists. Our comprehensive product suite leverages business intelligence applications, connectors, and self-service AI. These tools it possible for everyone at your organization to draw value from your Digital Twins.
The IIoT platform stores data from your Digital Twins into a centralized environment accessible to a wide group of users. Your Braincube-built Digital Twin serves as the single source of truth for your organization. Teams can rely on Digital Twins to solve quality concerns, identify process optimizations, or even build predictive models either in Braincube’s suite of apps or other systems. Process improvement discoveries are discovered, tested, and implemented faster using a Digital Twin in manufacturing.
Braincube’s Digital Twin: designed for manufacturing
Braincube builds Digital Twin by starting with what our customers want to learn about their processes. Our teams of manufacturing experts use a data transformation framework to ensure the right data, goals, and factors are part of the process.
By working alongside our team of experts, you have the option to be as hands-on in your journey as possible. Leverage our teams for the initial build and then train your teams to update tags or build new digital twins. You can also ask our teams to do it with you: the choice is yours.
Our goal was to build a multi-factor technology that starts with a customer’s challenge or objective in mind and with the right App suite to leverage it. In this sense, our Digital Twin works in conjunction with what you want to achieve.
With so many different Digital Twin vendors, types, and build-outs, it can be hard to find the right choice for your manufacturing company. Like all digital transformation initiatives, choosing what type of Digital Twin is right for you starts with laying a strong strategy.
Knowing where you are now can help you choose a Digital Twin solution that works with you into the future. Understand both your goals and your current connectivity state before you start vetting vendors.
Building Digital Twins can be time-consuming and may require your teams to work closely with a vendor for some time. If done effectively, though, you can find significant gains and ROI from your Digital Twins, enabling your company to break through current and future challenges.
Avril’s implementation of Braincube led to better sales and storage forecasts, the implementation of individualized dashboards for employees to track relevant KPIs, and the autonomy needed to make improvements in continuous based on changing business and economic needs.
Digital Twins are something we often hear about in manufacturing. With so much buzz around using Digital Twins to find new revenue streams, optimize, and improve, Laurent Laporte, CEO and co-founder of Braincube discusses his experience in leveraging a Digital Twin to drive decisions.
A Braincube-powered Digital Twin is automatically built for every product, serial number, or batch that is produced. The Digital Twin is an exact replica of the entire process flow. Learn how Braincube’s advanced process Digital Twin stands out from the crowd.