Search

An artificial neural network (ANN) extracts knowledge from a training dataset and uses this acquired knowledge to forecast outputs for any new set of inputs. When the input/output relations are complex and highly non-linear, the ANN needs a relatively large training dataset (hundreds of data points) to capture these relations adequately. This paper introduces a novel assisted-ANN modeling approach that enables the development of ANNs using small datasets, while maintaining high prediction accuracy. This approach uses parameters that are obtained using the known input/output relations (partial or full relations). These so called assistance parameters are included as ANN inputs in addition to the traditional direct independent inputs. The proposed assisted approach is applied for predicting the residual strength of panels with multiple site damage (MSD) cracks. Different assistance levels (four levels) and different training dataset sizes (from 75 down to 22 data points) are investigated, and the results are compared to the traditional approach. The results show that the assisted approach helps in achieving high predictions&rsquo, accuracy (&lt, 3% average error). The relative accuracy improvement is higher (up to 46%) for ANN learning algorithms that give lower prediction accuracy. Also, the relative accuracy improvement becomes more significant (up to 38%) for smaller dataset sizes.

PurposeThis paper focuses on quantifying and ranking the “7-Deadly” Wastes in the warehouse environment. The purpose of this paper is to develop a prioritized road map that would guide the implementation of the “7-Deadly” Wastes and their related waste-reduction practices in a warehouse environment for improving warehouse operational performance.Design/methodology/approachA four-stage approach was used to achieve the objectives of the study. A Delphi technique was employed to develop indicators of waste-reduction practices at the warehouse activities level and categorize them according to the “7-Deadly” wastes. Whereas categories ranked based on statistical analysis, a regression analysis was used to explore the impacts of this ranking.FindingsThe results of the regression analysis showed a significant influence of the ranked “7-Deadly” wastes on warehouse operational performance. The paper develops a road map for implementing waste-reduction practices in the warehouse.Originality/valueThe paper proposes a road map comprising warehouse waste categories. It develops an integrated approach to quantify, rank and prioritize initiatives to adopt the categories of the “7-Deadly” Wastes that would (not) affect warehouse operational performance.

The mechanical properties of extruded Polyvinylchloride (PVC) composites cannot be easily predicted due to the nonlinear nature of the relationship between the composite’s composition and the resulting after-production properties. In the work presented herein, supervised artificial neural network (ANN) modeling is used to predict and optimize three properties (tensile strength, ductility and density) of PVC composites having different weight percentages of virgin PVC, CaCO3, plasticizers, and recycled PVC. Different ANN models, designed and analyzed through factorial design and analysis of variance methodology, were evaluated using an experimental dataset which was designed according to the mixture design of experiments approach. The results show that the constituents-mechanical properties relationship of PVC composites’ can be accurately estimated using several ANN models including Levenberg-Marquardt/6-[18-9]3-3/Radial basis and Levenberg-Marquardt/6-[9-18]3-3/Log sigmoid models. The results also show that the ANN modeling is capable of determining the optimal weight percentages of the different PVC composite constituents in order to achieve a required composite property.

The design of manual-order-picking warehouses is a combination of interdependent decisions with enormous possible varieties in design components. The strong interrelationship between these componen...

In this study, machine learning algorithms (MLA) were employed to predict and classify the tensile strength of polymeric films of different compositions as a function of processing conditions. Two film production techniques were investigated, namely compression molding and extrusion-blow molding. Multi-factor experiments were designed with corresponding parameters. A tensile test was conducted on samples and the tensile strength was recorded. Predictive and classification models from nine MLA were developed. Performance analysis demonstrated the superior predictive ability of the support vector machine (SVM) algorithm, in which a coefficient of determination and mean absolute percentage error of 96% and 4%, respectively were obtained for the extrusion-blow molded films. The classification performance of the MLA was also evaluated, with several algorithms exhibiting excellent performance.

Polyvinyl chloride (PVC) products are typically complex composites, whose quality characteristics vary widely depending on the types and proportions of their components, as well as other processing factors. It is often required to optimize PVC production for specific applications at the highest cost efficiency. This study describes the design and analysis of a statistical experiment to investigate the effects of different parameters over the mechanical properties of PVC intended for use in electrical wire insulation. Four commonly used mixture components, namely, virgin PVC, recycled PVC, calcium carbonate, and a plasticizer, and two process variables, type of plasticizer and filler particle size, were examined. Statistical tools were utilized to analyze and optimize the mixture while simultaneously finding the proper process parameters. The mix was optimized to achieve required strength and ductility, as per ASTM D6096 while minimizing cost. The paper demonstrates how statistical models can help ...

The study focuses on the monitoring of the performance of a photovoltaic system, influenced by the climatic characteristics of a particular geographical area, in which the photovoltaic system is installed. This paper presents the results obtained by monitoring, from February 2017 to January 2018, the 5 MWp photovoltaic system that was installed on the campus of Jordan University of Science and Technology (JUST), Jordan. The tilt angle is 15°, and the azimuth angle is 0°. The values of energy and power generated, final yield, reference yield, photovoltaic system efficiency, performance ratio, and cell temperature losses were analyzed and correlated to the climatic characteristics of the site, such as insolation, ambient temperature, and wind speed. System Advisor Model was employed to give model simulation results. A comparison of the actual performance and the simulated one was given. An economic analysis was also carried out and showed that the annual internal rate of return was 30.11%, and the payback period was 4.32 years.

This paper explores the utility of supervised machine learning algorithms in predicting the tensile strength of high density polyethylene film produced by extrusion-blown molding process. Three algorithms were used: Artificial Neural Networks, Decision Tree, and kNearest Neighbors. Eleven input parameters, five materials related and six process related; were modeled in the algorithms. The application of algorithms demonstrated their capability in predicting the intended property of the extrusion-blown process products.

Purpose: This paper presents an implementation of the Six Sigma DMAIC approach implementing lean tools and facilities layout techniques to reduce the occurrence of different types of nonconformities in the carpeting process. Such carpeting process can be found in several industries including construction, aviation, and automotive. Design/methodology/approach: The improvement process was built through a sequential implementation of appropriate interconnected tools at each phase of the DMAIC approach. Utilized tools included: Pareto analysis, control charts, Ishikawa chart, 5-Whys, failure mode and effect analysis, process capability ratio, value stream map, and strategic layout planning. Findings: The carpeting process capability, quality of the product, customer satisfaction, and cost of poor quality were significantly improved. Explicitly, the sigma level was improved from 2.297 to 2.886 and the defects per million opportunities was reduced from 21615 to 3905. Originality/value: This paper has demonstrated the coherent implementation of several quality tools, value stream map, and systematic layout planning within the DMAIC approach.

This study aims to optimally set the operational parameters of pulsed green laser welding with copper. Multi input parameters and critical-to-quality outputs were considered. The chosen inputs were power, pulse duration and pressured air flow, while the outputs were the maximum force handled by the welding joint and the penetration level of the laser weld. Design and analyses for single-response and two-response optimization were presented using response surface methodology, Analysis of variance (ANOVA), and overlaid contour plots. The results indicated that power and pulse duration have the most significant effect on both the maximum force handled and the penetration level. Air flow showed little to no effect on the force handled and critical effect on the penetration level.

Industrial thinking is being applied in efforts to try to stem the flow of migrants to Europe. In particular, industrial production in the Middle East is being subsidized by the European Union. This is being done with good intentions. However, positive outcomes are limited. In this paper, it is explained that limited positive outcomes are inevitable, because industrial thinking is too out-of-date and out-of-place to address the causes of mass migration in the Middle East. By contrast, “leapfrog” socio-technical systems could be applied to address the complex causes of mass migration, not as socio-economic crises, but as opportunities for mutual prosperity growth.