A unified fault detection and isolation (FDI) and fault tolerant control (FTC) strategy for the diesel engine's air management system has been formulated. Diesel engines need to comply with the strict emission requirements for which they are equipped with specialized sub-systems for the purpose, such as the variable geometry turbo (VGT) charger and exhaust gas recirculation (EGR). Hardware-based controls tend to make the system more complex and prone to structured and unstructured faults. This calls for an advanced FTC technique that can ensure desired level of emissions even in the presence of minor system malfunctions. The scheme proposed in this paper detects, isolates and estimates the structured faults and minimizes their effects by re-positioning the actuators using integral sliding mode (ISM) control. Estimating the magnitude of structured faults help to reduce the ISM controller gains, eventually reducing the chattering. The stability of the system is analyzed using Lyapunov stability criterion. Simulations have been performed using fully validated industrial scale model of a diesel engine to elucidate the effectiveness of our scheme.

HiC is a widely used technique to study the 3D organization of the genome. Due to its high sequencing cost, most of the generated datasets are of coarse quality, consequently limiting the quality of the downstream analyses. Recently, multiple deep learning-based methods have been proposed to improve the quality of these data sets by increasing their resolution through upscaling. However, the existing works do not thoroughly evaluate these methods using HiC reproducibility metrics across different HiC experiments to establish their applicability in real-world scenarios. This study extensively compares deep learning-based HiC upscaling methods on real-world, low-quality HiC datasets. We evaluate these models using HiC reproducibility metrics on data from three cell lines - GM12878 (lymphoblastoid), K562 (human erythroleukemic), and IMR90 (lung fibroblast) - obtained from different HiC experiments. We show that the deep-learning techniques evaluated in this study, trained on downsampled data, cannot upscale real-world, low-quality HiC matrices effectively. More importantly, we also show that retraining these methods on examples of real-world data improves their performance and similarity on target experimental data sets. However, even with retraining, our downstream analyses on the output of these methods suggest that these methods fail to capture the biological signals in the real-world inputs with high sparsity. Therefore, our study highlights the need for rigorous evaluation and identifies specific areas that need improvement concerning current deep learning-based HiC upscaling methods.

No abstract

No abstract

No abstract