CFNN-PSO: An Iterative Predictive Model for Generic Parametric Design of Machining Processes

ABSTRACT

Every production process consists of a large number of dependent and independent variables, which substantially influence the quality of the machined parts. Due to the large impact of process variabilities, it is difficult to design optimal models for the machining processes. Mathematical or numerical models for production processes are resource driven, which are not cost effective approaches in terms of computation and economical production. In this paper, a new artificial neural network (ANN) based predictive model is introduced, which exploits particle swarm optimization (PSO) algorithm to minimize the root mean square errors (RMSE) for the network training. This approach can effectively obtain an optimized predictive model that can calculate precise output responses for the production processes. In order to verify the proposed approach, two case studies are considered from literature and shown to produce significant improvements. Furthermore, the proposed model is validated on abrasive water jet machining (AWJM) with industrial garnet abrasives and optimal machining conditions have been obtained with optimized responses, which are substantially improved while compared with gray relational analysis (GRA).     

Exploiting symmetries for scaling loopy belief propagation and relational training

Judging by the increasing impact of machine learning on large-scale data analysis in the last decade, one can anticipate a substantial growth in diversity of the machine learning applications for “big data” over the next decade. This exciting new opportunity, however, also raises many challenges. One of them is scaling inference within and training of graphical models. Typical ways to address this scaling issue are inference by approximate message passing, stochastic gradients, and MapReduce, among others. Often, we encounter inference and training problems with symmetries and redundancies in the graph structure. A prominent example are relational models that capture complexity. Exploiting these symmetries, however, has not been considered for scaling yet. In this paper, we show that inference and training can indeed benefit from exploiting symmetries. Specifically, we show that (loopy) belief propagation (BP) can be lifted. That is, a model is compressed by grouping nodes together that send and receive identical messages so that a modified BP running on the lifted graph yields the same marginals as BP on the original one, but often in a fraction of time. By establishing a link between lifting and radix sort, we show that lifting is MapReduce-able. Still, in many if not most situations training relational models will not benefit from this (scalable) lifting: symmetries within models easily break since variables become correlated by virtue of depending asymmetrically on evidence. An appealing idea for such situations is to train and recombine local models. This breaks long-range dependencies and allows to exploit lifting within and across the local training tasks. Moreover, it naturally paves the way for the first scalable lifted training approaches based on stochastic gradients, both in an online and a MapReduced fashion. On several datasets, the online training, for instance, converges to the same quality solution over an order of magnitude faster, simply because it starts optimizing long before having seen the entire mega-example even once.     

An Extended Replication of an Experiment for Assessing Methods for Software Requirements Inspections

We have performed an extended replication of the Porter-Votta-Basili experiment comparing the Scenario method and the Checklist method for inspecting requirements specifications using identical instruments. The experiment has been conducted in our educational context represented by a more general definition of a defect compared to the original defect list. Our study involving 24 undergraduate students manipulated three independent variables: detection method, requirements specification, and the order of the inspections. The dependent variable measured is the defect detection rate. We found the requirements specification inspected and not the detection method to be the most probable explanation for the variance in defect detection rate. This suggests that it is important to gather knowledge of how a requirements specification can convey an understandable view of the product and to adapt inspection methods accordingly. Contrary to the original experiment, we can not significantly support the superiority of the Scenario method. This is in accordance with a replication conducted by Fusaro, Lanubile and Visaggio, and might be explained by the lack of individual defect detection skill of our less experienced subjects.     

Central venous oxygen saturation and thoracic admittance during dialysis: new approaches to hemodynamic monitoring

Intradialytic hypotension (IDH) is one of the most important short-term complications to hemodialysis (HD). Inadequate cardiac filling due to a reduction in the central blood volume is believed to be a major etiological factor. The aim of this study was to evaluate whether these pathophysiologic events are reflected in the central venous oxygen saturation (ScO(2)) and thoracic admittance (TA) during dialysis. Twenty ambulatory HD patients, 11 hypotension prone (HP) and 9 hypotension resistant, with central vascular access, were monitored during 3 HD sessions each. ScO(2), TA, finger blood pressure (BP), and relative change in blood volume (DeltaBV) were measured and sampled continuously. The relative TA decrease and DeltaBV were both largest in the HP group (p<0.05 for both), whereas ScO(2) decreased only in HP patients (p<0.001). Baseline TA was lower in the HP group (p<0.01). Changes in ScO(2) and TA correlated much closer than did changes in ScO(2) and DeltaBV (r=0.43 and 0.18, respectively). Our results suggest that an intradialytic decrease in cardiac output, as reflected by a fall in ScO(2), is a common feature to HD patients prone to IDH. In patients using a central vascular access, ScO(2) and TA measurements may be more specific to the pathophysiologic events preceding IDH than DeltaBV-the current standard monitoring method.     

The influence of hydroelectric power generation on the body composition of juvenile Atlantic salmon

The fat and protein content, and thus energy resources of young (parr) Atlantic salmon (Salmo salar) were examined in a temperate river. Juvenile salmon exhibited distinct seasonal patterns of energy storage and use. The lowest levels of energy were found towards the end of winter (mean mass specific energy about 4.3 kJ·g^?1). There was a rapid accumulation of fat in spring/early summer in spite of low‐water temperatures (highest mean content of mass specific energy of about 5.0 kJ·g^?1 in June). By early autumn (August) there was a rapid depletion of fat and energy resources. The decline in specific energy during late summer was of the same magnitude as the corresponding winter decline. Furthermore, total fat and protein content, and thus energy resources of juveniles below a hydroelectric power plant (hydrostation (HS)) differed from those at a (lower) reference station (RS). The younger fish exhibited higher gains, but also larger losses of energy resources compared to corresponding values at the RS. Specifically during the summer, young of year (YOY) had 31% lower total energy content at the regulated site (mean 1.27 kJ per individual) than the RS (mean 1.84 kJ). Higher mortality may occur at the site most affected by the hydroelectric plant, where energy resources on average were higher, but where depletion was also most severe. Copyright © 2006 John Wiley & Sons, Ltd.     

Oxidative Stability of Polyunsaturated Edible Oils Mixed With Microcrystalline Cellulose

The oxidative stability of mixtures of edible oils containing polyunsaturated fatty acids (PUFA) and microcrystalline cellulose (MCC) was investigated. The mixtures studied consisted of oils of either camelina (CAM), cod liver (CLO), or salmon (SO) mixed with either colloidal or powdered MCC. A 50:50 (w/w) ratio of oil:MCC resulted in an applicable mixture containing high levels of PUFA edible oil and dietary fiber. The oxidative stability of the formulated mixtures and the pure oils was investigated over a period of 28 days. The peroxide value (PV) was assessed as a parameter for primary oxidation products and dynamic headspace gas chromatography mass spectrometry (GC/MS) was used to analyze secondary volatile organic compounds (VOC). CAM and the respective mixtures were oxidatively stable at both 4 and 22 °C during the storage period. The marine oils and the respective mixtures were stable at 4 °C. At 22 °C, an increase in hydroperoxides was found, but no increase in VOC was detected during the time-frame investigated. At 42 °C, prominent increases in PV and VOC were found for all oils and mixtures. Hexanal, a common marker for the degradation of n-6 fatty acids, propanal and 2,4-heptadienal (E,E), common indicators for the degradation of n-3 fatty acids, were among the volatiles detected in the headspace of oils and mixtures. This study showed that a mixture containing a 50:50 ratio of oil:MCC can be obtained by a low-tech procedure that does not induce oxidation when stored at low temperatures during a period of 1 month.     

Interface structure and strength of ultrasonically wedge bonded heavy aluminium wires in Si-based power modules

In this paper the microscopical structure of wedge bonded interfaces is investigated, with a focus on what effect the power in the ultrasonic bonding and the initial microscopical structure of the \(Al\) wire have on the quality of the bonding. The quality evaluation is based on mapping the microscopical restructuring of the wire grains during bonding and thereby assessing the effective bonding area. Three approaches are utilized in the interface characterization: mechanical shear test, optical microscopy combined with micro-sectioning, and scanning electron microscopy assisted by focused ion beam milling. The shear test is applied to quantify the strength of the bonded interfaces, while the other methods are used to map the grain reconstruction caused by the bonding. From the results it is possible to map a 3D image of the wire deformation, and the grain refinement region which is the dominating parameter with respect to fatigue related cracking of the interfaces. It is found that the bonding power, as well as the initial wire structure directly affects the refinement region and thereby the strength of the interface.     

Differential graphical games for H∞ control of linear heterogeneous multiagent systems

Differential graphical games have been introduced in the literature to solve state synchronization problem for linear homogeneous agents. When the agents are heterogeneous, the previous notion of graphical games cannot be used anymore and a new definition is required. In this paper, we define a novel concept of differential graphical games for linear heterogeneous agents subject to external unmodeled disturbances, which contain the previously introduced graphical game for homogeneous agents as a special case. Using our new formulation, we can solve both the output regulation and H_∞ output regulation problems. Our graphical game framework yields coupled Hamilton‐Jacobi‐Bellman equations, which are, in general, impossible to solve analytically. Therefore, we propose a new actor‐critic algorithm to solve these coupled equations numerically in real time. Moreover, we find an explicit upper bound for the overall ‐gain of the output synchronization error with respect to disturbance. We demonstrate our developments by a simulation example.