George Panoutsos

A self-driving laboratory, combining automated synthesis, characterisation, and cloud-based AI, was developed to optimise the synthesis of polymer nanoparticles by RAFT dispersion polymerisation.

Powder bed fusion (PBF) is an original additive manufacturing technique for creating 3D parts layer-by-layer. While there are numerous benefits to this process, the complex undergoing physical phenomena are challenging to analytically model and interpret. Hence, integrated and control-oriented 3D models are lacking in the current literature. As a result, the state of the art in process control for the powder bed fusion (PBF) process is not as advanced as in other manufacturing processes. Reinforcement learning is a machine learning, data-driven mathematical and computational framework that can be used for process control while addressing this challenge (lack of control-oriented models) effectively. Its flexible formulation and its trial-and-error nature make reinforcement learning suitable for processes where the model is intricate or even unknown. The focus of this research work is selective laser melting, which is a laser-based PBF process. For the first time in the literature we demonstrate the benefits of a reinforcement learning process control framework for multiple layers (complete 3D parts) and we highlight the importance of stability during training. The presented case studies confirm the effectiveness of the proposed control framework, directly addressing heat accumulation issues while demonstrating effective overall process control, hence opening up opportunities for further research and impact in this area.

In the pursuit of advanced Predictive Health Management (PHM) for Proton Exchange Membrane Fuel Cells (PEMFCs), conventional data-driven models encounter considerable barriers due to data reconstruction resulting in poor data quality, and the complexity of models leading to insufficient interpretability. In addressing these challenges, this research introduces TabNet, a model aimed at augmenting predictive interpretability, and integrates it with an innovative data preprocessing technique to enhance the predictive performance of PEMFC health management. In traditional data processing approaches, reconstruction methods are employed on the original dataset, significantly reducing its size and consequently diminishing the accuracy of model predictions. To overcome this challenge, the Segmented Random Sampling Correction (SRSC) methodology proposed herein effectively eliminates noise from the original dataset whilst maintaining its effectiveness. Notably, as the majority of deep learning models operate as black boxes, it becomes challenging to identify the exact factors affecting the Remaining Useful Life (RUL) of PEMFCs, which is clearly disadvantageous for the health management of PEMFCs. Nonetheless, TabNet offers insights into the decision-making process for predicting the RUL of PEMFCs, for instance, identifying which experimental parameters significantly influence the prediction outcomes. Specifically, TabNet’s distinctive design employs sequential attention to choose features for reasoning at each decision-making step, not only enhancing the accuracy of RUL predictions in PEMFC but also offering interpretability of the results. Furthermore, this study utilized Gaussian augmentation techniques to boost the model’s generalization capability across varying operational conditions. Through pertinent case studies, the efficacy of this integrated framework, merging data processing with the TabNet architecture, was validated. This work not only evidences that the effective data processing and strategic deployment of TabNet can markedly elevate model performance but also, via a visual analysis of the parameters’ impact, provides crucial insights for the future health management of PEMFCs.

The optimisation of crop harvesting processes for commonly cultivated crops is of great importance in the aim of agricultural industrialisation. Nowadays, the utilisation of machine vision has enabled the automated identification of crops, leading to the enhancement of harvesting efficiency, but challenges still exist. This study presents a new framework that combines two separate architectures of convolutional neural networks (CNNs) in order to simultaneously accomplish the tasks of crop detection and harvesting (robotic manipulation) inside a simulated environment. Crop images in the simulated environment are subjected to random rotations, cropping, brightness, and contrast adjustments to create augmented images for dataset generation. The you only look once algorithmic framework is employed with traditional rectangular bounding boxes for crop localization. The proposed method subsequently utilises the acquired image data via a visual geometry group model in order to reveal the grasping positions for the robotic manipulation.