This paper focuses on the automated learning of driver braking “signature” in the presence of road anomalies. Our motivation is to improve driver experience using preview information from navigation maps. Smartphones facilitate, due to their unprecedented market penetration, the large-scale deployment of advanced driver assistance systems. On the other hand, it is challenging to exploit smartphone sensor data because of the fewer and lower quality signals, compared to the ones on board. Methods for detecting braking behavior using smartphones exist, however, most of them focus only on harsh events. Additionally, only a few studies correlate longitudinal driving behavior with the road condition. In this paper, a new method, based on deep neural networks and the sliding correlation coefficient, is proposed for the spatio-temporal correlation of road anomalies and driver behavior. A unique deep neural network structure, that requires minimum tuning, is proposed. Extensive field trials were conducted and vehicle motion was recorded using smartphones and a data acquisition system, comprising an inertial measurement unit and differential GPS. The proposed method was validated using the probabilistic Receiver Operating Characteristics method. The method proves to be a robust and flexible tool for self-learning driver behavior.

Learning Driver Braking Behavior Using Smartphones, Neural Networks and the Sliding Correlation Coefficient: Road Anomaly Case Study

Analyses of trends increasing annual wind power plant capacity and power generation in the World and Europe are presented in this paper. Investigated main problems of increasing the power generation of renewable energy sources in distributed power grids. Proposed ways to decide them by taking into account the supply of power balance, reliability operating of the power grid, and electric power quality. Observed the daily power generation during the 2019 year for typical onshore wind power plant, which consists of 1 turbine type V-100/2.00 MW. The influence of the meteorological factors on the power generation of RESs was determined with usage Spearman's rank correlation coefficient.

Distribution of Wind Power Generation Dependently of Meteorological Factors

Review of Signal Processing Techniques and Machine Learning Algorithms for Power Quality Analysis

Electrical power supply is one of the most important issues to utilities, equipment manufactures and customers. Good power quality is defined in terms of voltage, current and frequency. The problems manifested in these electrical quantities may lead to disturbances in power quality. The effect of poor power quality can cause equipment for failure and breakdown, as the most of power electronic devices fail to sustain voltage variations and may stops working. Power quality disturbances must be detected and localized in order to avoid such incidents which will cause huge economic loss in industrial as well as in commercial areas. The power quality events are classified according to disturbance duration specifically, short and long duration events. Short duration voltage events namely, voltage interruption, sag and swell occur from 0.5 cycle to 1 min with respective decrease or increase in the rms voltage. This paper gives detection and characterization of these voltage events by extracting the features using discrete wavelet transform (DWT). These features are again utilized for the classification of these events using rule based fuzzy logic. This combination of DWT and fuzzy logic gives classification of power quality disturbances. Several simulations on detection and characterization by DWT are performed. Classification in case of these short duration voltage event is important. Hence this novel classification of all these voltage disturbance using fuzzy logic is presented to demonstrate the effectiveness of proposed method.

Detection, characterization and classification of short duration voltage events using DWT and fuzzy logic

A hybrid method for fault location estimation in a fixed series compensated lines

https://cyberleninka.org/article/n/1148755.pdf

Nejra Čišija

Papers

Wavelets as a tool for power system dynamic events analysis – State-of-the-art and future applications