Search

This paper introduces novel techniques based on Machine Learning (ML) algorithms for a Photovoltaic integrated Shunt Active Power Filter performance improvement. The first goal is to design an efficient maximum power point tracking MPPT strategy in order to harness the largest amount of energy possible. Thereby, a new hybrid Support Vector Machine Regression Perturb and Observe (SVM regression-P&O) algorithm is proposed. The SVM block improves the tracking speed by predicting an initial duty cycle, whereas a small fixed-step P&O algorithm ensures a high MPPT accuracy. The second purpose is to upgrade harmonics detection by exploiting the characteristics of intelligent learning of Adaline combined with ML algorithm. Therefore, a novel SVM regression-Adaline PQ strategy is designed. The SVM block generates the predicted initial weights of Adaline, thus ensuring fast identification of the DC active power component. In addition, the ability of this design to work with a small learning rate parameter allows an accurate harmonics extraction in contrast with the Adaptive Adaline technique where the performances are highly dependent on the chosen learning rate parameter. A comparative analysis of various ML models are carried out in order to get the best output prediction for each SVM regression block. Simulations have been performed to confirm the supremacy of the new strategies over intelligent and classical techniques. Finding exhibits a significant decrease of PV energy losses (up to 99%), a minor overshoot with an impressively decrease of the harmonics extraction’s response time (up to 98.8%), and a PVSAPF power quality enhancement under online intermittent weather conditions and variable nonlinear load.

With the development of industrialization, fine particulate matter (PM2.5) severely chills the health of people. Studies have shown that the variation of PM2.5 concentration is related to the Global Navigation Satellite System (GNSS) tropospheric delay. Therefore, it is possible to use the widely distributed continuous operation reference station (CORS) to monitor and predict PM2.5 concentrations with high time resolution. In this paper, the zenith wet delay (ZWD) of five CORS located in Baoding, Hebei Province, China, from Sep 2014 to Feb 2015, is calculated firstly. Then, the correlation between PM2.5 and ZWD is investigated. Finally, the experimental data including PM2.5, ZWD, temperature, air pressure, and relative humidity data sampled in one hour are used to establish PM2.5 concentrations online prediction model based on support vector machine regression (SVMR) model with metabolic method. The experimental results show that in autumn and winter, the correlation coefficient between daily-mean PM2.5 and ZWD is mainly larger than 0.4, and the correlation coefficient between hourly mean PM2.5 and ZWD is mainly larger than 0.3. Meanwhile, in daily cycle analysis, air temperature, air pressure and relative humidity are related to PM2.5 concentration. Finally, Using SVMR model with metabolic method, by combining GNSS and meteorological factors, ideal short-term prediction accuracy is achieved, which shows that the use of GNSS and meteorological factors is potential in predicting PM2.5 concentration.

One of the key components in protein structure prediction by protein threading technique is to choose the best overall template for a given target sequence after all the optimal sequence-template alignments are generated. The chosen template should have the best alignment with the target sequence since the three-dimensional structure of the target sequence is built on the sequence-template alignment. The traditional method for template selection is called Z-score, which uses a statistical test to rank all the sequence-template alignments and then chooses the first-ranked template for the sequence. However, the calculation of Z-score is time-consuming and not suitable for genome-scale structure prediction. Z-scores are also hard to interpret when the threading scoring function is the weighted sum of several energy items of different physical meanings. This paper presents a support vector machine (SVM) regression approach to directly predict the alignment accuracy of a sequence-template alignment, which is used to rank all the templates for a specific target sequence. Experimental results on a large-scale benchmark demonstrate that SVM regression performs much better than the composition-corrected Z-score method. SVM regression also runs much faster than the Z-score method. [ABSTRACT FROM PUBLISHER]

This paper presents a novel model-free approach for modeling friction for servo-motion systems. The proposed approach uses the support vector machine networks to parameterize the static friction mapping. The procedure of constructing such networks from a finite amount of training (sampling) data is developed based on support vector machine regression (SVMR). The validity of the proposed approach has been experimentally verified. [ABSTRACT FROM PUBLISHER]

In this letter, the support vector machine (SVM) regression approach is introduced to model the three-dimensional (3-D) high density microwave packaging structure. The SVM is based on the structural risk minimization principle, which leads to a good generalization ability. With a 3-D vertical interconnect used as an example, the SVM regression model is electromagnetically developed with a set of training data and testing data, which is produced by the electromagnetic simulation. Experimental results suggest that the developed model performs with a good predictive ability in analyzing the electrical performance [ABSTRACT FROM PUBLISHER]