This paper presents the theoretical derivation and implementation of a novel direct power control for open-winding brushless doubly-fed reluctance generator (OW-BDFRG). As one of the promising brushless candidates, the OW-BDFRG is characterized with two stator windings fed by a dual controllable two-level three-phase converters through a common DC bus with common mode voltage elimination. The parameter-free control strategy is designed to obtain maximum power point tracking with variable speed constant frequency (VSCF) for wind energy conversion systems (WECSs). Compared to the traditional three-level converter systems, the DC bus voltage, ACside voltage and capacity ratings of the proposed converter system are notably high while the reliability, redundancy and fault tolerance are significantly improved. Effectiveness, correctness and robustness of the proposed control strategy and the common mode voltage elimination scheme are evaluated and confirmed through simulation and experimental tests on a 42 kW generator prototype typical for VSCF-WECS. Index Terms-Brushless doubly-fed machines, power control, common mode voltage, open-winding, variable speed constant frequency, maximum power point tracking. NOMENCLATURE u p , u c Power, control winding phase voltages [V] i p , i c Power, control winding phase currents [A] R p , R c Power, control winding resistances [Ω] p p , p c , p r Power, control and rotor pole pairs L p , L c Power, control winding self-inductan. [H] ψ p , ψ c Power, control winding flux linkages [Wb] ψ pc , L pc Mutual flux [Wb] and inductance [H] f p , f c , ω p , ω c Power, control winding frequencies [Hz] and their angular frequencies [rad/s]

This paper presents the simulation and experimental evaluation of a novel power error comparison direct power control (PEC-DPC) strategy of the open-winding brushless doubly-fed reluctance generator (OW-BDFRG) for wind energy conversion systems (WECSs). As one of the promising candidates for limited speed range application of pump-alike and wind turbine with partially-rated converter. The emerging OW-BDFRG employed for the proposed PEC-DPC is fed via dual low-cost two-level converters, while the DPC concept is derived from the fundamental dynamic analyses of the calculated and controllable electrical power and flux of the BDFRG with two stators measurable voltage and current. Compared to the traditional two-level and three-level converter systems, the OW-BDFRG requires lower rated capacity of power devices and switching frequency converter, though have more flexible switching mode, higher reliability, redundancy and fault tolerance capability. The performance correctness and effectiveness of the proposed DPC strategy with the selected and optimised switching vector scheme are evaluated and confirmed on a 25 kW generator test rig. Index Terms-Brushless doubly-fed wind power generators, open-winding, direct power control, dual two-level converters. I. INTRODUCTION T HE brushless doubly-fed (reluctance) generators (BD-FGs) [1], [2] have some essential features in dealing with issues related to reliability and maintenance operation in long-running variable speed constant frequency (VSCF). Such advantages are due to their robust structure since carbon brushes and slip-rings are eradicated. Moreover they adopt a similar doubly-excited feature similar to doubly-fed induction generators (DFIGs). The BDFGs have evolved from DFIGs but moved the rotor winding to the stator, thus characterised by two standard distributed three-phase stators with different Manuscript

Nowadays, global public health crises are occurring more frequently, and accurate prediction of these diseases can reduce the burden on the healthcare system. Taking COVID-19 as an example, accurate prediction of infection can assist experts in effectively allocating medical resources and diagnosing diseases. Currently, scholars worldwide use single model approaches or epidemiology models more often to predict the outbreak trend of COVID-19, resulting in poor prediction accuracy. Although a few studies have employed ensemble models, there is still room for improvement in their performance. In addition, there are only a few models that use the laboratory results of patients to predict COVID-19 infection. To address these issues, research efforts should focus on improving disease prediction performance and expanding the use of medical disease prediction models. In this paper, we propose an innovative deep learning model Whale Optimization Convolutional Neural Networks (CNN), Long-Short Term Memory (LSTM) and Artificial Neural Network (ANN) called WOCLSA which incorporates three models ANN, CNN and LSTM. The WOCLSA model utilizes the Whale Optimization Algorithm to optimize the neuron number, dropout and batch size parameters in the integrated model of ANN, CNN and LSTM, thereby finding the global optimal solution parameters. WOCLSA employs 18 patient indicators as predictors, and compares its results with three other ensemble deep learning models. All models were validated with train-test split approaches. We evaluate and compare our proposed model and other models using accuracy, F1 score, recall, AUC and precision metrics. Through many studies and tests, our results show that our prediction models can identify patients with COVID-19 infection at the AUC of 91%, 91%, and 93% respectively. Other prediction results achieve a respectable accuracy of 92.82%, 92.79%, and 91.66% respectively, f1-score of 93.41%, 92.79%, and 92.33% respectively, precision of 93.41%, 92.79%, and 92.33% respectively, recall of 93.41%, 92.79%, and 92.33% respectively. All of these exceed 91%, surpassing those of comparable models. The execution time of WOCLSA is also an advantage. Therefore, the WOCLSA ensemble model can be used to assist in verifying laboratory research results and predict and to judge various diseases in public health events.

No abstract

Abstract