Wind turbines are widely installed as the new source of cleaner energy production. Dynamic and random stress imposed on the generator bearing of a wind turbine may lead to overheating and failure. In this paper, a data-driven approach for condition monitoring of generator bearings using temporal temperature data is presented. Four algorithms, the support vector regression machine, neural network, extreme learning machine, and the deep belief network are applied to model the bearing behavior. Comparative analysis of the models has demonstrated that the deep belief network is most accurate. It has been observed that the bearing failure is preceded by a change in the prediction error of bearing temperature. An exponentially-weighted moving average (EWMA) control chart is deployed to trend the error. Then a binary vector containing the abnormal errors and the normal residuals are generated for classifying failures. LS-SVM based classification models are developed to classify the fault bearings and the normal ones. The proposed approach has been validated with the data collected from 11 wind turbines.
To maximize energy extraction, the nacelle of a wind turbine follows the wind direction. Accurate prediction of wind direction is vital for yaw control. A tandem hybrid approach to improve the prediction accuracy of the wind direction data is developed. The proposed approach in this paper includes the bilinear transformation, effective data decomposition techniques, long-short-term-memory recurrent neural networks (LSTM-RNNs), and error decomposition correction methods. In the proposed approach, the angular wind direction data is firstly transformed into time-series to accommodate the full range of yaw motion. Then, the continuous transformed series are decomposed into a group of subseries using a novel decomposition technique. Next, for each subseries, the wind directions are predicted using LSTM-RNNs. In the final step, it decomposed the errors for each predicted subseries to correct the predicted wind direction and then perform inverse bilinear transformation to obtain the final wind direction forecasting. The robustness and effectiveness of the proposed approach are verified using data collected from a wind farm located in Huitengxile, Inner Mongolia, China. Computational results indicate that the proposed hybrid approach outperforms the other single approaches tested to predict the nacelle direction over short-time horizons. The proposed approach can be useful for practical wind farm operations.
Capacitive proximity sensors (CPSs) are ubiquitous because of their simple design, low cost and low consumption. Capacitive displacement sensing, as one of the three sensing modalities, works for long distance and can be unitized to measure more physical quantities compared with capacitive volume and deformation sensing. In this paper, we firstly introduce the concept of capacitive displacement sensing. After that, we present applications of capacitive displacement sensing under three broad categories: distance measurements, indirect measurements, and the applications applied in smart environments. Finally, we discuss the challenges and possible solutions for CPSs development. We show that both the detection range and accuracy of CPS can be improved by multi-sensor fusion, and the application scenarios can be extensive through machine/deep learning approaches. We aim to provide a comprehensive, and state-of-theart review of the capacitive displacement sensing, and inspire more researchers and developers to find wide application perspectives.INDEX TERMS Capacitive proximity sensor (CPS), capacitive displacement sensing, distance measurement, indirect measurement, smart environment.
Despite of an important concern, human bioaerosol emission into subway is not well and directly characterized. Here, we used bioaerosol detector and next generation sequencing methods to investigate time-dependent bioaerosol size distributions in Beijing subway system between March and April, 2015. In contrast to weekends, weekday microbial aerosol results exhibited strong time dependence with higher bacterial and fungal aerosol levels up to 2083 CFU m -3 and 483 CFU m -3 observed, respectively, for the peak hours. During the peak hour (17:30-18:30), bioaerosol emissions at 0.8-3 µm was detected, while about three times higher concentration levels were observed compared to those during the offpeak hour (22:00-23:00). Similar bioaerosol size distributions were observed between ventilation outlets and subway platform air. During off-peak hours, subway bioaerosols had similar size distributions with the outside air. Sequence results revealed a vast array of airborne microbial species which varied from one station to another, but with Aspergillus spp. as dominant fungal species, and Staphylococcus, Pseudomonas as primary bacterial genera including human opportunistic ones. Our results provide direct online observations of human contributions to subway size-resolved bioaerosols, and enhancing ventilation system might help for controlling the exposure especially during the peak-hours.
A novel method to realise a single-feed circularly polarised (CP) microstrip antenna with wide beamwidth and axial-ratio (AR) beamwidth is investigated. Two diagonal metal walls are put at the diagonal sides of the microstrip antenna. The diagonal metal walls can excite the orthogonal radiation fields with the same amplitude and 90°phase difference on the radiating patch for CP with wide beamwidth and AR beamwidth. Some parameters which effect on the performances of the antenna are studied. The simulated and measured results of the reflection coefficients, radiation patterns and AR radiation patterns are presented. The 3-dB beamwidths of the right-hand CP (RHCP) radiation patterns in the xoz-plane and the yoz-plane are 105°and 157°, respectively. The 3-dB AR beamwidths of the RHCP radiation patterns in the xoz-plane and yoz-plane are 100°and 155°, respectively. Good CP characteristics of the new structure antenna have been obtained in the whole operating frequency band.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.