Digital twins are incorporating leading-edge technologies, enabling the creation of more complex twins and a thicker, stronger so-called digital thread.
Listed below are the key technology trends impacting the twin’s theme, as identified by GlobalData.
Digital twins will play a huge role as 5G realises its potential and then transitions to 6G communication services. Using digital twins in a 6G environment could allow users to explore and monitor the real world without temporal or spatial constraints. Users will be able to observe changes or detect problems remotely through digital twins. They could even interact with twins using virtual reality (VR) devices or holographic displays.
Vendors are teaming up to deliver propositions for digital twins in specific markets. Engineering and project management companies, for example in the energy industry, are working with energy management and automation companies and engineering and industrial software companies on digital twin’s technology for the upstream oil and gas markets.
The partnerships are intended to help oil and gas companies improve asset performance, increase sustainability, and maximise return on investment (RoI). The outcome is the enabling of remote operations and production assurance through a digital twin that mirrors all aspects of an operating asset.
The pharma industry is already using digital twins to predict the outcome of processes, which leads to a reduced number of physical, real-world tests or process completions required to discover and validate drug candidates. The Swedish Digital Twin Consortium believes digital twins could be used to personalise medicine. It aims to construct network models and then computationally match those twins with numerous drugs to identify the most effective.
The concept involves constructing digital twins of the patient, based on the integration of thousands of disease relevant variables. Each twin is computationally tested with one or more of thousands of drugs. The drug that has the best effect on the twin is used to treat the patient.
Significant work is required to ensure that the data used by a digital twin is fit for purpose. Typically, enterprise data is error-prone due to human mistakes or duplicate entries. The insights a digital twin provides are only as accurate as the data it uses. Such a need makes it imperative that organisations standardise their data collection practices and regularly cleanse their data to remove duplicate and erroneous entries.
There are several causes of poor-quality data, including differing standards across an enterprise and the use by different departments of dissimilar names or codes to identify a specific asset. Other causes of poor data are sensor data faults, sensor noise, missing data, stuck values, and outlier data. Outliers are common in real-life data and are typically easy for humans to spot but may be time-consuming to correct for large datasets.
This is an edited extract from the Digital Twins- Thematic Research report produced by GlobalData Thematic Research.