Application of Multi-Objective Evolutionary Optimization Algorithms to Reactive Power Planning Problem

This paper presents a new approach to treat reactive power (VAr) planning problem using multi-objective evolutionary algorithms (EAs). Specifically, strength Pareto EA (SPEA) and multi-objective particle swarm optimization (MOPSO) approaches have been developed and successfully applied. The overall problem is formulated as a nonlinear constrained multi-objective optimization problem. Minimizing the total incurred cost of the VAr planning problem and maximizing the amount of available transfer capability (ATC) are defined as the main objective functions. The aim is to find the optimal allocation of VAr devices in such a way that investment and operating costs are minimized and at the same time the amount of ATC is maximized. The proposed approaches have been successfully tested on IEEE 14 buses system. As a result a wide set of optimal solutions known as Pareto set is obtained and encouraging results show the superiority of the proposed approaches and confirm their potential to solve such a large-scale multi-objective optimization problem. Copyright © 2009 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.     

Using convolutional features and a sparse autoencoder for land-use scene classification

In this article, we propose a novel approach based on convolutional features and sparse autoencoder (AE) for scene-level land-use (LU) classification. This approach starts by generating an initial feature representation of the scenes under analysis from a deep convolutional neural network (CNN) pre-learned on a large amount of labelled data from an auxiliary domain. Then these convolutional features are fed as input to a sparse AE for learning a new suitable representation in an unsupervised manner. After this pre-training phase, we propose two different scenarios for building the classification system. In the first scenario, we add a softmax layer on the top of the AE encoding layer and then fine-tune the resulting network in a supervised manner using the target training images available at hand. Then we classify the test images based on the posterior probabilities provided by the softmax layer. In the second scenario, we view the classification problem from a reconstruction perspective. To this end we train several class-specific AEs (i.e. one AE per class) and then classify the test images based on the reconstruction error. Experimental results conducted on the University of California (UC) Merced and Banja-Luka LU public data sets confirm the superiority of the proposed approach compared to state-of-the-art methods.     

Burial and thermal history simulation of the subsurface Paleozoic source rocks in Faghur basin,north Western Desert,Egypt: Implication for hydrocarbon generation and expulsion history

Paleozoic Zeitoun, Desouqy and Dhiffah formations represent source rocks to hydrocarbon in Faghur basin, north Western Desert, Egypt. They are characterized by a sufficient amount of organic matter belonging to kerogen type III and mixed type II/III, which are in maturation stage. A 1D-basin modeling was performed by using geological and geochemical data of the Paleozoic source rocks from five wells in Faghur basin, north Western Desert, Egypt. These data used in 1D basin modeling for constructing and understanding of burial and thermal geo-histories of Faghur basin and for simulating and predicting the timing of petroleum and expulsion for the Paleozoic source rocks in the studied wells. Burial and thermal history models indicate that the Zeitoun Formation entered onset of oil generation in the studied wells during Late Cretaceous (100.10–91.65 my) with transformation ratio (TR) 10–25, peak oil during Late Cretaceous (91.65–79.30 my) with TR 25–50 and late oil stage at Late Cretaceous (79.30 my-0) to present day with TR 50–60.45. Desouqy Formation entered onset of oil generation also during Late Cretaceous (94.43–73.60 my) with TR 10–25 in the studied wells, peak oil during Late cretaceous (73.60–62.40 my) with TR 25–50 and Late oil stage during Late Cretaceous to present day (62.40 my-0) with TR 50–61.82. Dhiffah Formation entered onset of oil generation in the studied wells during Early to Late Cretaceous (102.11–92.27 my) with TR 10–25, peak oil during Late Cretaceous (92.27–86.40 my) with TR 25–50 and late oil stage at Late Cretaceous to present day (86.40 my-0) with TR 50–67.27. No cracking oil to gas in the studied Paleozoic source rocks in the studied wells. These basin modeling results also suggest that the Paleozoic source rocks act as an effective source rock where a significant amount of petroleum is expected to be generated and expelled to any nearby prospect reservoir rocks in the Faghur basin.     

Effect of temperature and cooling regime on mechanical properties of high‐strength low‐alloy steel

This paper presents results from experimental studies on the effect of temperature on mechanical properties of high‐strength low‐alloy ASTM A572 steel commonly used in structural members in bridges. A set of high‐temperature tensile strength tests and post‐temperature exposed residual strength tests is carried out on ASTM A572 steel coupons in 20–1000 °C temperature range. The residual strength tests on high‐temperature exposed steel coupons are carried out after subjecting the coupons to two methods of cooling, namely, air cooling and water quenching. Results from these tests indicate that temperature‐dependent strength and stiffness degradation in A572 steel follow the same trend as that of carbon steel but with some variations. A572 steel recovers almost 100% of its room temperature yield strength when heated to temperature up to 600 °C, regardless of the method of cooling, while the extent of strength degradation in coupons subjected to heating beyond 600 °C is dependent on heated temperature and method of cooling. Data generated in these tests are utilized to generate high‐temperature stress–strain and residual stress–strain response of A572 steel. These results are also utilized to propose temperature‐dependent strength, elastic modules, and residual strength reduction factors of A572 steel, which can be used in evaluating residual response of fire‐exposed steel structures. Copyright © 2015 John Wiley & Sons, Ltd.