Battery management toolset employs digital twins
Article By : Majeed Ahmad
The R2022b release of MATLAB and Simulink has introduced two new features to simplify and automate model-based design for engineers and researchers.
The R2022b release of MATLAB and Simulink has introduced two new features to simplify and automate model-based design for engineers and researchers. First, Simscape Battery provides design tools and parameterized models for various types of battery management systems (BMS). Second, Medical Imaging Toolbox provides tools for medical imaging applications to design, test, and deploy diagnostic and radiomics algorithms that use deep learning networks.
Figure 1 Simscape Battery enables designers to define battery pack architecture, model heat transfer, visualize layout, and customize model fidelity. Source: MathWorks
Graham Dudgeon, principal product manager for electrical systems modeling at MathWorks, says that innovation in battery management systems is at an all-time high. And the BMS growth is primarily attributed to electric vehicles (EVs). Simscape Battery enables engineers and researchers to create digital twins, run virtual tests of battery pack architectures, design battery management systems, and evaluate battery system behavior across normal and fault conditions.
For instance, the Battery Pack Model Builder in Simscape lets engineers interactively create and evaluate different battery pack architectures. Simscape Battery also automates the creation of simulation models that match desired pack topology and includes cooling plate connections so that electrical and thermal responses can be evaluated (Figure 2).
Figure 2 Simscape Battery allows engineers to explore cell-to-cell temperature variation and measure cooling efficiency. Source: MathWorks
Next, Medical Imaging Toolbox allows medical researchers, scientists, engineers, and device designers to perform multi-volume 3D visualization, multimodal registration, segmentation, and automated ground truth labeling for training deep learning networks on medical images. In short, it delivers an end-to-end image analysis workflow for medical designs.
Figure 3 The Medical Image Labeler app in the toolbox interactively labels ground truth data, semi-automates or automates the labeling process, and exports labeled data for AI workflows. Source: MathWorks
Medical Imaging Toolbox—encompassing apps, functions, and workflows for designing and testing diagnostic imaging applications—lets medical designers train predefined deep learning networks. Moreover, medical professionals can import, preprocess, and analyze radiology images from various imaging modalities: projected X-ray imaging, computed tomography (CT), magnetic resonance imaging (MRI), ultrasound (US), and nuclear medicine (PET, SPECT).
This article was originally published on Planet Analog.
Majeed Ahmad, Editor-in-Chief of EDN and Planet Analog, has covered the electronics design industry for more than two decades.