Logo image
Back
A Dynamic Data Driven Applications Systems (DDDAS)-Based Digital Twin IoT Framework
Book chapter   Peer reviewed

A Dynamic Data Driven Applications Systems (DDDAS)-Based Digital Twin IoT Framework

Sarah Malik, Rakeen Rouf, Krzysztof Mazur and Antonios Kontsos
Dynamic Data Driven Applications Systems
03 Nov 2020
DOI: https://doi.org/10.1007/978-3-030-61725-7_6

Abstract

Data processing Diagnostics Digital Twin Edge computing Fog computing Internet of Things Machine learning
One of the key elements of DDDAS is the ability to create a feedback control loop from the sensory system to the model to enable more accurate and fast data-driven analysis. When constructing such a framework, it is especially important to provide an efficient, filtered data stream to the model. To address this need, this investigation describes a DDDAS-based Digital Twin IoT Framework which comprises three layers, namely the Edge, Fog and Cloud. The Edge is composed of either commercial sensing data acquisition systems or by sensors without any commercial system being involved. The Edge layer is connected to the Fog which is a decentralized computing layer that consists of an in-house built Internet of Things (IoT) device. Within the Fog, real-time data is aggregated, parsed, filtered, and passed through a layer of user-defined algorithms. These algorithms can be either predefined or made using an interactive algorithm building application. The main goal of the algorithms used at the Fog, is to reduce the incoming data and classify it into known classes. This process allows a real-time data flow to the Cloud, as only important decision-making components of the data is propagated. The algorithms are trained in the Cloud layer using historic data to enable stronger confidence in Prognostics and Remaining Useful Life (RUL) calculations. The Cloud is also responsible for hosting a user interface (UI) to interact with the Edge and Fog Layers and the Digital Twin model. The UI enables users to start, stop, and modify their data acquisition and visualize their analytics in (near) real-time. In the proposed study, sensing data obtained through mechanical testing using a carbon composite will be leveraged for the framework. Diagnostics and Prognostics leveraging a probability framework will be conducted on the sensor data.

Metrics

7 Record Views
10 citations in Scopus

Details

Logo image