Knowledge-based systems using neural networks for electron beam welding process of reactive material (Zircaloy-4)

Bead-on-plate welding of zircaloy-4 (a reactive material) plates was conducted using electron beam according to central composite design of experiments. Its predictive models were developed in the form of knowledge-based systems in both forward and reverse directions using neural networks. Input parameters considered for this welding of reactive metals were accelerating voltage, beam current and weld speed. The responses of the welding process were measured in terms of bead width, depth of penetration and micro-hardness. Forward mapping of the welding process was conducted using regression analysis, back-propagation neural network (BPNN), genetic algorithm-tuned neural network (GANN) and particle swarm optimization algorithm-tuned neural network (PSONN). Reverse mapping of this process was also carried out using the BPNN, GANN and PSONN-based approaches. Neural network-based approaches could model this welding process of reactive material in both forward and reverse directions efficiently, which is required for the automation of the same. The performance of the neural network models was found to be data-dependent. The BPNN could outperform the other two approaches for most of the cases but not all in both the forward and reverse mappings.     

Polymer waste recycling over “used” catalysts

Catalytic degradation of high-density polyethylene (HDPE) was carried out under nitrogen using a laboratory fluidised bed reactor operating at 360 °C with catalyst to polymer feed ratio of 2:1 and at 450 °C with catalyst to polymer feed ratio of 6:1 under atmospheric pressure. The catalysts used in this study were ZSM-5, US-Y, ASA, fresh FCC (fluid catalytic cracking) commercial catalyst (Cat-A) and equilibrium FCC catalysts with different levels of metal poisoning were studied. The initial results for polymer degradation at 360 °C (catalyst to polymer ratio of 2:1) in a fluidised bed reactor in terms of the yield of volatile hydrocarbon products were: model catalysts>commercial FCC catalyst>E-Cats. However, when the process conditions more closely resembled to FCC conditions, the fresh commercial FCC catalyst was more favourable in terms of the yield of volatile hydrocarbon products. The degradation of HDPE over E-Cats although reduced was similar to ASA in product selectivity and yield, and the level of metal contamination did not affect the product stream generated. A simple economic evaluation of polymer recycling process is reported showing that a catalytic system based on E-Cats appears comparable in costs to a commercial thermal cracking plant.     

O3/H2O2 Treatment of Methyl-terf-Butyl Ether in Contaminated Waters: Effect of Background COD on the O3-Dose

The destruction of methyl-tert-butyl ether (MTBE) in contaminated waters by O₃/H₂0₂ process was studied and the influence background COD, alkalinity, and hydrogen peroxide and MTBE concentrations on process treatment efficiency and ozone dosage was investigated. The treatment efficiency was evaluated by an Efficiency Index, which is based on electrical energy requirement for ozone production. It was found that the treatment efficiency decreases linearly with increasing concentrations of MTBE at constant background COD and with background COD at constant MTBE concentration. A simplified kinetic scheme was presented to account for these observations.     

Formal process algebraic modeling,verification, and analysis of an abstract Fuzzy Inference Cloud Service

In cloud computing, services play key roles. Services are well defined and autonomous components. Nowadays, the demand of using Fuzzy inference as a service is increasing in the domain of complex and critical systems. In such systems, along with the development of the software, the cost of detecting and fixing software defects increases. Therefore, using formal methods, which provide clear, concise, and mathematical interpretation of the system, is crucial for the design of these Fuzzy systems. To obtain this goal, we introduce the Fuzzy Inference Cloud Service (FICS) and propose a novel discipline for formal modeling of the FICS. The FICS provides the service of Fuzzy inference to the consumers. We also introduce four novel formal verification tests, which allow strict analysis of certain behavioral disciplines in the FICS as follows: (1) Internal consistency, which analyzes the service in a strict and delicate manner; (2) Deadlock freeness; (3) Divergence freeness; and (4) Goal reach ability. The four tests are discussed and the FICS is verified to ensure that it can pass all these tests.     

The Shape Boltzmann Machine: A Strong Model of Object Shape

A good model of object shape is essential in applications such as segmentation, detection, inpainting and graphics. For example, when performing segmentation, local constraints on the shapes can help where object boundaries are noisy or unclear, and global constraints can resolve ambiguities where background clutter looks similar to parts of the objects. In general, the stronger the model of shape, the more performance is improved. In this paper, we use a type of deep Boltzmann machine (Salakhutdinov and Hinton, International Conference on Artificial Intelligence and Statistics, 2009) that we call a Shape Boltzmann Machine (SBM) for the task of modeling foreground/background (binary) and parts-based (categorical) shape images. We show that the SBM characterizes a strong model of shape, in that samples from the model look realistic and it can generalize to generate samples that differ from training examples. We find that the SBM learns distributions that are qualitatively and quantitatively better than existing models for this task.     

Bathymetry and siltation rate for Dokan Reservoir,Iraq

The Dokan Reservoir dam is a concrete cylindrical arch with gravity abutments, located on the Lesser Zab River about 60 km from the city of Sulaimani in north‐eastern Iraq. A bathymetric survey was conducted in November 2014 for a period of 10 days, using an echo sounder of 200‐kHz single beam. The survey results indicated an annual average sediment deposition of 3.8 million m³. Thirty‐two sediment samples were collected from the reservoir bed. The ratio of gravel, sand, silt and clay was 15:14:48:23, respectively. The reservoir bed is covered mainly with silt. The sediments are composed of silty clay (77.6%), silty sandy clay (10%), sandy gravely silty clay (1.2%) and gravely sandy silty clay (1%).     

Application of supercritical fluid chromatography in the quantitative analysis of minor components (carotenes,vitamin E,sterols, and squalene) from palm oil

The application of supercritical fluid chromatography (SFC) coupled with a UV variable-wavelength detector to isolate the minor components (carotenes, vitamin E, sterols, and squalene) in crude palm oil (CPO) and the residual oil from palm-pressed fiber is reported. SFC is a good technique for the isolation and analysis of these compounds from the sources mentioned. The carotenes, vitamin E, sterols, and squalene were isolated in less than 20 min. The individual vitamin E isomers present in palm oil were also isolated into their respective components, α-tocopherol, α-tocotrienol, γ-tocopherol, γ-tocotrienol, and δ-tocotrienol. Calibration of all the minor components of palm as well as the individual components of palm vitamin E was carried out and was found to be comparable to those analyzed by other established analytical methods.     

Prediction of human breast and colon cancers from imbalanced data using nearest neighbor and support vector machines

This study proposes a novel prediction approach for human breast and colon cancers using different feature spaces. The proposed scheme consists of two stages: the preprocessor and the predictor. In the preprocessor stage, the mega-trend diffusion (MTD) technique is employed to increase the samples of the minority class, thereby balancing the dataset. In the predictor stage, machine-learning approaches of K-nearest neighbor (KNN) and support vector machines (SVM) are used to develop hybrid MTD-SVM and MTD-KNN prediction models. MTD-SVM model has provided the best values of accuracy, G-mean and Matthew's correlation coefficient of 96.71%, 96.70% and 71.98% for cancer/non-cancer dataset, breast/non-breast cancer dataset and colon/non-colon cancer dataset, respectively. We found that hybrid MTD-SVM is the best with respect to prediction performance and computational cost. MTD-KNN model has achieved moderately better prediction as compared to hybrid MTD-NB (Naïve Bayes) but at the expense of higher computing cost. MTD-KNN model is faster than MTD-RF (random forest) but its prediction is not better than MTD-RF. To the best of our knowledge, the reported results are the best results, so far, for these datasets. The proposed scheme indicates that the developed models can be used as a tool for the prediction of cancer. This scheme may be useful for study of any sequential information such as protein sequence or any nucleic acid sequence.     

An improved Differential Evolution algorithm using learning automata and population topologies

A new variant of Differential Evolution (DE), called ADE-Grid, is presented in this paper which adapts the mutation strategy, crossover rate (CR) and scale factor (F) during the run. In ADE-Grid, learning automata (LA), which are powerful decision making machines, are used to determine the proper value of the parameters CR and F, and the suitable strategy for the construction of a mutant vector for each individual, adaptively. The proposed automata based DE is able to maintain the diversity among the individuals and encourage them to move toward several promising areas of the search space as well as the best found position. Numerical experiments are conducted on a set of twenty four well-known benchmark functions and one real-world engineering problem. The performance comparison between ADE-Grid and other state-of-the-art DE variants indicates that ADE-Grid is a viable approach for optimization. The results also show that the proposed ADE-Grid improves the performance of DE in terms of both convergence speed and quality of final solution.     

Effect of the use of mineral filler on the properties of concrete

Engineers of the concrete technology are increasingly concerned with the material passing through a sieve of the size under 0.149 mm. Materials called very fine aggregate or mineral filler may affect the performance of concrete in an either positive or a negative way. Discussions on aggregate containing very fine material are vitally important. Washing the aggregate residue has been the sole way to solve this matter to date. This is mainly based on the debatable opinion that materials of this kind are regarded as clay material. The goal of the study was to determine how the content of mineral filler might affect properties of concrete. Two types of aggregates with different amounts of cement and mineral filler were used. Basically, mineral filler replaced sand. The effect of applying different amounts of mineral filler on concrete was then determined. The addition of 7-10% of mineral filler to fine aggregate (0-2 mm) was found to considerably improve the properties of concrete.