#Artificial Intelligence #53 – technologies underpinning the digital twin

Welcome to #Artificial Intelligence #53

Our courses are getting filled up fast and Digital twins starts tomorrow.

If you want to study with us at #universityofoxford for our next course see:?Developing Artificial Intelligence Applications using Python and TensorFlow.

Re the digital twins course, I was having a conversation with an IoT expert and I suggested that IoT plays a relatively small role in digital twins.

This might sound a bit odd, but I believe it is valid

In episode 51, I explained the need for an open source digital twin builder and the elements that comprise such an architecture.

Expanding on that idea, I want to discuss here the technologies underlying the digital twin based on a paper which I was reading (link below)

There are three technology categories for DIGITAL twin

1. data related technologies
2. high-fidelity modeling technologies, and
3. model based simulation technologies.

?DATA RELATED technologies

• Data is the basis of digital twin. Sensors, gauges, RFID tags and readers, cameras, scanners, etc. should be chosen and integrated to collect total-element data for digital twin.
• The application layer protocols include HTTP, MQTT, CoAP, XMPP, AMQP, DDS, and OPC UA.
• The communication technologies were 4 G, 5 G, NB-IoT, LoRaWAN, Sigfox, Bluetooth, 802.11 ah, 802.11n, ZigBee, Z-Wave, and WirelessHART. Angrish et al.

?High-fidelity modeling technologies

• Models of digital twin comprise semantic data models and physical models.
• Semantic data models are trained by known inputs and outputs, using artificial intelligence methods.
• Physical models require comprehensive understanding of the physical properties and their mutual interaction.
• To balance computational effort and accuracy, before creating digital twin model of a complex system, engineers should identify which components are crucial for the system’s functionality and define the modeling level of each component. Thus, high-fidelity model of digital twin can be built according to different modeling level.
• Digital twin modeling can usually start with physics-based modeling. Black-box modeling using data or grey-box modeling using a combination of physics and data are also feasible.

?Model BASED SIMULATION technologies

• Simulation models over different levels of detail, over all involved disciplines, and over lifecycle phases must be integrated.
• Digital twin should provide an interface to different models and data in different granularities and keep them consistent.

?

A summary of technologies is as below

Source: https://doi.org/10.1145/3241403.3241417?

We can also consider digital twins in terms of phases of digital twins

DESIGN PHASE

MANUFACTURING PHASE

SERVICE PHASE

RETIRE PHASE

Source: https://doi.org/10.1145/3241403.3241417?

?

Open questions for me:

·??????What is the role of MLOps in Digital twins?

·??????How do we manage composite digital twins

·??????How do we manage real time dgital twins

?

In this view, the twin is at the centre of the design for cyber physical processes but it also means IoT plays a relatively less significant role in the Digital Twin

Source for above image: Architectural aspects of digital twins in IIoT systems by Somayeh Malakuti and Sten Grüne

Source for post : Review of digital twin about concepts, technologies, and industrial applications by Mengnan Liu, Fang Shuiliang, Huiyue Dong and Cunzhi Xu