Multi-criteria expertness based cooperative Q-learning

One of the most influential points in cooperative learning is the type of exchanging information. If the content of exchanging information among agents is rich, cooperation gives rise to better results. To extract proper knowledge of agents during the cooperation process, some expertness measures that assign expertness levels to the other agents are used. In this paper, a new method named Multi-Criteria Expertness based cooperative Q-learning (MCE) is proposed that utilizes all of the expertness measures and attempts to enrich the exchanging information more efficiently. In MCE, all expertness measures are considered simultaneously and collective knowledge is equal to the combination of learned knowledge by each of expertness measures. The experimental results confirm outstanding performance of the proposed method on a sample maze world and a hunter-prey problem.     

Modeling and solving the bi-objective capacitated location-routing problem with probabilistic travel times

The location-routing problem (LRP) is a relatively new research area within location analysis that concerns simultaneously both the problems of location of facilities and routing of vehicles among the established facilities and the demand points. In this work, we address the capacitated LRP with probabilistic travel times, which may arise in many practical contexts in logistics and supply chain management, and present some bi-objective mathematical programming formulations to model the problem using different stochastic programming approaches. The first objective is to minimize the overall system-wide costs, while the second objective concerns minimization of the maximum delivery time to the customers. In all the cases, the deterministic equivalents of the stochastic models have been extracted. To solve the resulted models, a variable neighborhood descent-based heuristic is proposed and finally computational study is performed and numerical results are reported.     

Marine Water Quality Assessment Of Synthetic-Based Drilling Waste Discharges

Drilling muds or fluids used in drilling operations serve several functions: they lubricate the drill bit; maintain borehole pressure; clean and condition the hole; and flush rock cuttings to the surface. Drilling mud also adheres to rock cuttings, as can formation oil. Barite is used as a weighting agent, which approximately makes up approximately 33% of synthetic mud. It contains traces of heavy metals, which contribute to the toxicity of drilling waste. As environmental issues attract increasing public awareness, the treatment and disposal of spent drilling fluids and contaminated rock cuttings from drilling operations have become sensitive issues for offshore operations around the world. Within the last decade, the oil and gas industry has introduced synthetic-based drilling fluids as substitutes for oil-based fluids. This pollution prevention measure has been complemented by improvements in solid control systems technology. This paper adopts the current U.S. Environmental Protection Agency methodology for a hypothetical case study of an oil field on the East Coast of Canada to determine the water quality impacts of disposal of drilling wastes. The concentration of pollutants at the edge of the mixing zone in the water column and pore water are estimated and compared with Canadian water quality guidelines for protection of aquatic life.     

A clustering approach to identify the time of a step change in Shewhart control charts

Control charts are the most popular statistical process control tools used to monitor process changes. When a control chart indicates an out‐of‐control signal it means that the process has changed. However, control chart signals do not indicate the real time of process changes, which is essential for identifying and removing assignable causes and ultimately improving the process. Identifying the real time of the change is known as the change‐point estimation problem. Most of the traditional methods of estimating the process change point are developed based on the assumption that the process follows a normal distribution with known parameters, which is seldom true. In this paper, we propose clustering techniques to estimate Shewhart control chart change points. The proposed approach does not depend on the true values of the parameters and even the distribution of the process variables. Accordingly, it is applicable to both phase‐I and phase‐II of normal and non‐normal processes. At the end, we discuss the performance of the proposed method in comparison with the traditional procedures through extensive simulation studies. Copyright © 2008 John Wiley & Sons, Ltd.     

Fault-tolerant switched reluctance motor drive using adaptive fuzzy logic controller

An adaptive fuzzy controller has been designed to develop a high-performance fault-tolerant switched reluctance motor (SRM) drive. The fuzzy controller continuously adapts its properties to regulate the machine torque as desired by the drive system even under fault conditions. The adaptation of the fuzzy membership functions results in extended conduction period and increased peak current of the healthy phases to deliver the commanded torque, as much as possible. The adaptive fuzzy controller provides smooth torque output with minimum ripple, even under fault conditions, yielding a high-performance SRM drive with fault-tolerant capability.     

Phytate and mineral content in different milling fractions of some Pakistani spring wheats

Six Pakistani wheat cultivars, namely C-273, Inqulab-91, Pasban-90, Parwaz-94, Shahkar-95 and Rohtas-90, were included in the present study. The kernel weight of the wheat cultivars varied from 31.43 to 36.76 g (per thousand kernels), Parwaz-94 having the highest and Rohtas-90 having the lowest. The test weight of cultivars ranged from 70.23 (Shakar-95) to 76.13 kg hL^–1 (Pasban-90). The bran contained the highest amount of phytic acid (6.12%) in C-273 followed by whole-wheat flour (2.23%) in Inqulab-91, and straight-grade flour (0.24%) in Parwaz-94. The phytate content was reduced during the baking of bread and chapati. The bread scores and other quality characteristics varied significantly among cultivars. The total bread scores ranged from 35.20 to 42.00, out of a possible fifty, with Parwaz-94 being the highest. The concentration of minerals varied widely in different milling fractions of various wheat cultivars. The concentration of Cu, Fe, Mn and Zn ranged from 5.00 to 52.50, 26 to 147.50, 0.00 to 97.00, 9.0 to 80.80 ppm, respectively, in different milling fractions of the wheat cultivars. The total chapati scores ranged from 22.40 to 24.20 of a possible score of 30. The minimum chapati scores were found in Rohtas-90 and Parwaz-94, while Inqulab-91 produced the maximum score.     

PI and fuzzy estimators for tuning the stator resistance in directtorque control of induction machines

Direct torque control (DTC) of induction machines uses the stator resistance of the machine for estimation of the stator flux. Variations of stator resistance due to changes in temperature or frequency make the operation of DTC difficult at low speeds. A method for the estimation of changes in stator resistance during the operation of the machine is presented. The estimation method is implemented using proportional-integral (PI) control and fuzzy logic control schemes. The estimators observe the machine stator current vector to detect the changes in stator resistance. The performance of the two methods are compared using simulation and experimental results. Results obtained have shown improvement in DTC at low speeds     

Effect of silica fume on the concrete-steel bond

Silica fume is used as an admixture to concrete to improve the engineering properties. Additions of silica fume improve the bond between concrete and steel reinforcing bars. The authors describe a laboratory study which explores the ultimate pullout load of steel reinforcing bars from concrete enhanced with silica fume. Les fumees de silice utilisees comme adjuvant ameliorent les proprietes techniques du beton et notamment l'adherence entre le beton et les fers d'armature. Les auteurs decrivent une etude de laboratoire qui porte sur la resistance a l'arrachement des fers d'armature dans du beton traite aux fumees de silice.