Fuzzy Sarsa Learning and the proof of existence of its stationary points

This paper provides a new Fuzzy Reinforcement Learning (FRL) algorithm based on critic‐only architecture. The proposed algorithm, called Fuzzy Sarsa Learning (FSL), tunes the parameters of conclusion parts of the Fuzzy Inference System (FIS) online. Our FSL is based on Sarsa, which approximates the Action Value Function (AVF) and is an on‐policy method. In each rule, actions are selected according to the proposed modified Softmax action selection so that the final inferred action selection probability in FSL is equivalent to the standard Softmax formula. We prove the existence of fixed points for the proposed Approximate Action Value Iteration (AAVI). Then, we show that FSL satisfies the necessary conditions that guarantee the existence of stationary points for it, which coincide with the fixed points of the AAVI. We prove that the weight vector of FSL with stationary action selection policy converges to a unique value. We also compare by simulation the performance of FSL and Fuzzy Q‐Learning (FQL) in terms of learning speed, and action quality. Moreover, we show by another example the convergence of FSL and the divergence of FQL when both algorithms use a stationary policy. Copyright © 2008 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society     

Uniaxial compressive strength prediction through a new technique based on gene expression programming

Proper estimation of rock strength is a critical task for evaluation and design of some geotechnical applications such as tunneling and excavation. Uniaxial compressive strength (UCS) test can be measured directly in the laboratory; nevertheless, the direct UCS determination is time-consuming and expensive. In this study, feasibility of gene expression programming (GEP) model in indirect determination of UCS values of sandstone rock samples is examined. In this regard, several laboratory tests including Brazilian test, density test, slake durability test and UCS test were conducted on 47 samples of sandstone which were collected from the Dengkil, Malaysia. Considering multiple inputs, several GEP models were constructed to estimate UCS of the rock and finally, the best GEP model was selected. In order to indicate capability of the proposed GEP model, linear multiple regression (LMR) was also performed. It was found that the GEP model is superior to LMR one in terms of applied performance indices. Based on coefficient of determination (R ²) of testing datasets, by proposing GEP model, it can be improved from 0.930 (which was obtained by LMR model) to 0.965. As a result, it is concluded that the proposed models in this study, could be utilized to estimate UCS of similar rock type in practice.

     

Laser scan planning based on visibility analysis and space partitioning techniques

This paper presents a methodology to develop an automatic process planning system applied for scanning parts with free-form surfaces by using a laser stripe system mounted on a coordinate measuring machine (CMM). The part has been modelled using a STL format that permits the automatic recognition of any part surface. The valid orientations of the scanning device are obtained in order to guarantee the visibility of the zone to be scanned and also to be compatible with the constraints imposed by the process. With the aim to speed up the calculation of valid orientations, we apply different methods like space partitioning techniques base on kd-tree as well as back-face culling algorithms. Once the space occupied by the part is partitioned in regions, recursive ray traversal algorithms are used in order to exclusively check for intersection the part triangles of the STL model that can potentially be traversed by each laser beam direction. In order to reduce the scanning time related to laser orientation changes, part triangles must be classified into a set of clusters based on their common visibility orientations. Finally, the scanning paths for each cluster are generated as well as the joining paths between them by taking into consideration depth of field and laser beam width.     

Grain misorientation in thixo-billets prepared by melt stirring

For semi solid metal (SSM) slurries, in addition to the morphology, size, distribution and percentage of the solid phase particles, the microstructure of individual solid particles is another important parameter to be considered. This is particularly an issue when SSM billets are prepared by continuous stirring of the melt to temperatures below liquidus, as in the case of electromagnetic stirring of Al–Si alloys.Microstructural evolution of the electromagnetically stirred Al–Si alloy is investigated by means of optical and electron microscopy. Electron backscatter diffraction (EBSD) analysis of the stirred and unstirred cast billets has shown stirring to generate local misorientation within individual solid particles. This is an indication of growing dendrites undergoing plastic deformation during the course of SSM slurry preparation. The formation of dislocations and their subsequent rearrangement into subgrain boundaries has been shown by EBSD analysis and TEM studies of thin foil specimens respectively.     

Effect of delayed icing on quality changes of iced rainbow trout (Onchorynchus mykiss)

The effect of delayed icing on quality deterioration of rainbow trout (Onchorynchus mykiss) iced 0, 4 and 8 h after catch was assessed by chemical, microbiological and sensory methods. Total volatile basic nitrogen (TVB-N), free fatty acids (FFA), peroxide value (PV) and thiobarbituric acid (TBA) values increased during the pre-icing duration. Delayed icing led to significant increased (p < 0.05) in total viable counts (TVC) throughout the period of storage. This study showed that sensory analysis of rainbow trout correlated well with microbiological analysis. Results of this study according microbiological and sensory data indicated that the shelf-life of rainbow trout stored in ice immediately after catch was approximately 9–11 days, while delay in icing for 4 and 8 h shortened the shelf-life was around 5–7 and 1–3 days, respectively.     

A systems approach to validating the water vision of the Aral Sea Basin

Abstract:

The governments of the Aral Sea Basin countries, in cooperation with international organizations (UNESCO and World Bank) came up with a “water vision “for the region until 2025. The landlocked Aral Sea has been suffering from an imbalance in water evaporation, and, water inflow from its two main sources — Amu Darya and Syr Darya rivers, when the planners in the former Soviet Union from the 1960s diverted the river waters for irrigation. The irrigated area has increased from the 1960s by two‐thirds to 7 million hectares and the population by three‐fold to 50 million in the basin countries. Consequently the inflow to the Aral Sea from these two rivers decreased from 55 km³ in 1960 to a few km³ during the 1980s and 1990s. This has resulted in one of the worst man‐made ecological disasters of the century. In this paper, we examine different scenarios to achieve the vision goals and whether it is indeed feasible. Using IWMI basin‐oriented water accounting principles, we have shown that significant amount of water is being wasted in the region. Our analysis concludes that though not all the vision goals are likely to be met over the next 25 years, the inflow into the Aral Sea can be increased to over 20 km³ through better management and use of water resources.     

Observed extinction by clouds at 95 GHz

Measurements of backscattered power were made in maritime stratus clouds with a 95 GHz radar mounted on an aircraft. The aircraft also carried probes for in situ cloud measurements of liquid water content (LWC) and hydrometeor size distribution. Horizontal flight segments of 5-10 km length, over which the LWC was relatively uniform, were selected for analysis. Mean values of LWC ranged from 0.05 to 0.8 g/m³. The observations yielded an extinction coefficient of 4.6 dB/km per g/m³ of cloud water     

Neural computing approach for predicting vaporization enthalpy of pure hydrocarbons and petroleum fractions

The current collaboration was aimed to approximate the heat of vaporization for petroleum fractions and pure hydrocarbons through using the multi-layer perceptron artificial neural network (MLP-ANN) based on the specific gravity, molecular weight, and boiling point temperature. Furthermore, Levenberg Marquardt algorithm was utilized to train the ANN structure and optimize its tuning parameters. Another comparison was carried out between the outcomes of suggested MLP-ANN model and six well-known correlations. Better results were observed for predicting heat of vaporization by the MLP-ANN model with the obtained value of mean relative error (MRE) and R-squared (R²) equal to 1.31% and 0.9962%, respectively. This computational approach can be applied in the petroleum engineering for a precise determination of heat of vaporization.     

Intrinsic relationship between energy consumption,pressure, and leakage in water distribution systems

The basic implications of changes in delivery pressure on system energy use and cost, on leakage, excess pressure, and environmental impacts are explored. An analytical expression is first developed to characterize the primary relationships between energy use, leakage and pressure for a simple pipe segment. Then, two more realistic case studies, based on varying versions of the Anytown network, are considered. The results indicate that energy use responds more to changes in the delivery pressure in systems with higher leakage rates while reductions in pressures curtail energy use and leakage more dramatically in low resistance systems. Perhaps more surprisingly, systems with more effective water storage and thus uniform pressures tend to have higher leakage rates, greater energy usage, and higher GHG emissions relative to systems relying on direct pumping. The generalization that results from these studies is perhaps predictable but has profound implications: the higher the delivery pressure the greater will likely be the amount of water wasted and energy dissipated.