Isaac Squires

Establishing optimised lithium-ion battery manufacturing processes is a multi-factored, application dependent, and typically resource-intensive challenge, involving the assembly and testing of large numbers of cells over a long period of time. This effectively slows the development and adoption of new technologies. In this work, we adopt and evaluate an accelerated artificial intelligence (AI) assisted method for optimisation of cell manufacturing processes, utilising an LiMn _x Fe _1-x PO ₄ (LMFP) cathode as a model system. Electrode microstructure (controlled via the calendaring process) was optimised for 4680 cylindrical cell performance via AI analysis of microscopy images and electrochemical data from only a relatively small number of manufactured coin cells, dramatically reducing needed development time and cost. Through this analysis, an optimised electrode density for high power performance (2.8 g cm ^-3 ) was identified and experimentally verified. The optimised density, balancing electronic and ionic transport, provided enhanced volumetric energy density under fast-charging conditions (1 C – 3 C, geared for electric vehicles). This study quantitatively outlines the role of LMFP electrode density on performance and highlights the growing relevance of AI-based approaches as an effective tool in advancing lithium-ion battery research and development.

Modelling lithium-ion battery behavior is essential for performance prediction and design improvement. However, this task is challenging due to processes spanning many length scales, leading to computationally expensive models. Reduced order models have been developed to address this, assuming a “separation of scales” between micro- and macroscales. This study compares two approaches: direct microstructure-resolved 3D domain electrochemical modelling and a simplified 1D homogenized model, similar to the Doyle-Fuller-Newman model. The research investigates the validity of the scale separation assumption in continuum electrode-level models by varying scale separation factors, boundary conditions, and geometries. The findings reveal increases in deviation between the 3D models and 1D models for more tortuous, less porous microstructures, especially under higher discharge rates. However, under realistic conditions, with an electrode featuring eight particles across its thickness and typical transport properties, the 3D model predicts only a slight (2%) increase in current compared to the 1D model at a high rate of 7C (approximately j ≈ 350 Am⁻²). These results suggest that the separation of scales assumption in the DFN model is generally suitable for a wide range of operating conditions. However, 1D models may overlook local variations in electrolyte concentration and potential, crucial for understanding degradation mechanisms.

An individualised (HRTF) is very important for creating realistic (VR) and (AR) environments. However, acoustically measuring high-quality HRTFs requires expensive equipment and an acoustic lab setting. To overcome these limitations and to make this measurement more efficient HRTF upsampling has been exploited in the past where a high-resolution HRTF is created from a low-resolution one. This paper demonstrates how (GAN) can be applied to HRTF upsampling. We propose a novel approach that transforms the HRTF data for direct use with a convolutional (SRGAN). This new approach is benchmarked against three baselines: barycentric upsampling, (SH) upsampling and an HRTF selection approach. Experimental results show that the proposed method outperforms all three baselines in terms of (LSD) and localisation performance using perceptual models when the input HRTF is sparse (less than 20 measured positions).

An individualised head-related transfer function (HRTF) is very important for creating realistic virtual reality (VR) and augmented reality (AR) environments. However, acoustically measuring high-quality HRTFs requires expensive equipment and an acoustic lab setting. To overcome these limitations and to make this measurement more efficient HRTF upsampling has been exploited in the past where a high-resolution HRTF is created from a low-resolution one. This paper demonstrates how generative adversarial networks (GANs) can be applied to HRTF upsampling. We propose a novel approach that transforms the HRTF data for direct use with a convolutional super-resolution generative adversarial network (SRGAN). This new approach is benchmarked against three baselines: barycentric upsampling, spherical harmonic (SH) upsampling and an HRTF selection approach. Experimental results show that the proposed method outperforms all three baselines in terms of log-spectral distortion (LSD) and localisation performance using perceptual models when the input HRTF is sparse (less than 20 measured positions).

We present a novel inpainting algorithm for microstructural image data using generative adversarial networks. This enables fast artefact removal via a simple graphical user interface.

3D microstructural datasets are commonly used to define the geometrical domains used in finite element modelling. This has proven a useful tool for understanding how complex material systems behave under applied stresses, temperatures and chemical conditions. However, 3D imaging of materials is challenging for a number of reasons, including limited field of view, low resolution and difficult sample preparation. Recently, a machine learning method, SliceGAN, was developed to statistically generate 3D microstructural datasets of arbitrary size using a single 2D input slice as training data. In this paper, we present the results from applying SliceGAN to 87 different microstructures, ranging from biological materials to high-strength steels. To demonstrate the accuracy of the synthetic volumes created by SliceGAN, we compare three microstructural properties between the 2D training data and 3D generations, which show good agreement. This new microstructure library both provides valuable 3D microstructures that can be used in models, and also demonstrates the broad applicability of the SliceGAN algorithm.

Applying ultrathin MgO as the top component of a ZnO/MgO electron transport layer enhances the performance of organic photovoltaics.