Search

A microgrid is a proven effective way to integrate renewable resources. This study presents an innovative control concept for decentralized AC microgrids, which is based on the architectural advantage of a radial microgrid structure. Under the proposed concept, power sharing between the distributed sources is achieved without droop control. Thus the need for a secondary control level is eliminated. Moreover, the use of explicit communication is replaced in the paper by a novel coordination mechanism based on the locally measured currents. The paper shows that, with a special design of the current control of grid-feeding converters, the proposed microgrid automatically provides equitable sharing of the load demand amongst the distributed generators (DGs). Moreover, the dynamic responses of the DGs are identical and decoupled from one another. It is further shown that the proposed AC microgrid is stable in the presence of any type of load. The findings of the paper are validated by simulations and laboratory experiments.

This paper proposes a novel and robust version of Model Predictive Control scheme for AC drives based on Voltage Source Inverter (VSI) with Active Front End (AFE). The main feature of the proposed MPC is elimination of Common Mode Voltage (CMV) without imposing a penalty on the corresponding term in the cost function, but rather by a smart utilisation of the restricted set of switching states in a computationally efficient algorithm. Furthermore, the paper proposes to split the conventional MPC scheme into separate Control and Modulation stages, and to enhance the Control stage by integral action, and the Modulation stage - by a Feedback Quantizer. The resulting AC drive scheme provides high tracking accuracy over the full speed range, robustness to disturbances and parameters error, coupled with practically zero CMV and consequently - very low levels of conducted and radiated electromagnetic interference (EMI). This makes the proposed scheme a competitive alternative to the existing AC drive solutions in the most challenging industrial applications. The benefits of the proposed scheme are validated by simulation and experiment.

This paper proposes control augmentations to allow two Static Synchronous Compensators (STATCOMs) devices to operate in parallel from a shared DC bus. Two parallel connected four-wire STATCOMs will be shown to be highly susceptible to an uncontrolled circulating current in the neutrals when operating with a three degree of freedom current control scheme. The circulating current can be calculated from the local inverter phase currents and neutral current. This paper shows the circulating component is readily suppressed by a neutral voltage offset that is determined by a proportional controller (P). The controller is validated by both simulation and experimental results.

Building models that are both interpretable and accurate is an unresolved challenge for many pattern recognition problems. In general, rule-based and linear models lack accuracy, while deep learning interpretability is based on rough approximations of the underlying inference. However, recently, the rule-based Tsetlin Machines (TMs) have obtained competitive performance in terms of accuracy, memory footprint, and inference speed on diverse benchmarks (image classification, regression, natural language understanding, and game-playing). TMs construct rules using human-interpretable conjunctive clauses in propositional logic. These, in turn, are combined linearly to solve complex pattern recognition tasks. This paper addresses the accuracy-interpretability challenge in machine learning by introducing a TM with integer weighted clauses - the Integer Weighted TM (IWTM). The intent is to increase TM interpretability by reducing the number of clauses required for competitive performance. The IWTM achieves this by weighting the clauses so that a single clause can replace multiple duplicates. Since each TM clause is formed adaptively by a Tsetlin Automata (TA) team, identifying effective weights becomes a challenging online learning problem. We solve this problem by extending each team of TA with another kind of automaton: the stochastic searching on the line (SSL) automaton. We evaluate the performance of the new scheme empirically using five datasets, along with a study of interpretability. On average, IWTM uses 6.5 times fewer literals than the vanilla TM and 120 times fewer literals than a TM with real-valued weights. Furthermore, in terms of average memory usage and F1-Score, IWTM outperforms simple Multi-Layered Artificial Neural Networks, Decision Trees, Support Vector Machines, K-Nearest Neighbor, Random Forest, Gradient Boosted Trees (XGBoost), Explainable Boosting Machines (EBMs), as well as the standard and real-value weighted TMs. IWTM finally outperforms Neural Additive Models on Fraud Detection and StructureBoost on CA-58 in terms of Area Under Curve, while performing competitively on COMPAS.

Medical applications challenge today's text categorization techniques by demanding both high accuracy and ease-of-interpretation. Although deep learning has provided a leap forward in regard to accuracy, this leap comes at the sacrifice of interpretability. In this paper, we introduce a text categorization approach that leverages the recently introduced Tsetlin Machine to address this accuracy-interpretability challenge. Briefly, we represent the terms of a text as propositional variables. From these variables, we capture categories using simple propositional formulae, such as: IF “rash” AND “reaction” AND “penicillin” THEN Allergy. The Tsetlin Machine learns these formulae from labeled text, utilizing conjunctive clauses to represent the particular facets of each category. Therefore, also the absence of terms (negated features) can be used for categorization purposes. Our empirical comparisons with Naïve Bayes classifiers, decision trees, linear support vector machines (SVMs), random forest, long short-term memory (LSTM) neural networks, and other techniques, are quite conclusive. Using relatively simple propositional formulae, the accuracy of the Tsetlin Machine either outperforms or performs approximately on par with the best evaluated methods on both the 20 Newsgroups and IMDb datasets, as well as on a clinical dataset containing authentic electronic health records (EHRs). On average, the Tsetlin Machine delivers the best recall and precision scores across the datasets. The main merit of the proposed approach is thus its capacity for producing human-interpretable rules, while at the same time achieving acceptable accuracy. We believe that our novel approach can have a significant impact on a wide range of text analysis applications, providing a promising starting point for deeper natural language understanding with the Tsetlin Machine.

Qualitative assessments of the blink reflex are used clinically to assess neurological status in critical care, operating room, and rehabilitative settings. Despite decades of literature supporting the use of quantitative measurements of the blink reflex in the evaluation of multiple neurological disorders, clinical adoption has failed. Thus, there remains an unmet clinical need for an objective, portable, non-invasive metric of neurological health that can be used in a variety of settings. We have developed a high-speed videographybased device to trigger, record, and analyze a blink reflex. A pilot study was performed to compare the device's measurements to the published literature of electromyographic measurements, currently the gold standard. The study results indicate that the device is a viable tool to obtain fast, objective, and quantitative metrics of a blink reflex, and has promise as a non-invasive diagnostic assessment of neurological health.