Search results

The paper describes the methods of manufacturing process optimization, using Taguchi experimental design methods with historical process data, collected during normal production.

The objectives are achieved with two separate techniques: the Retrospective Taguchi approach selects the designed experiment's data from a historical database, whilst in the Neural Network (NN) – Taguchi approach, this data is used to train a NN to estimate process response for the experimental settings. A case study illustrates both approaches, using real production data from an aerospace application.

Detailed results are presented. Both techniques identified the important factor settings to ensure the process was improved. The case study shows that these techniques can be used to gain process understanding and identify significant factors.

The most significant limitation of these techniques relates to process data availability and quality. Current databases were not designed for process improvement, resulting in potential difficulties for the Taguchi experimentation; where available data does not explain all the variability in process outcomes.

Manufacturers may use these techniques to optimise processes, without expensive and time‐consuming experimentation.

The paper describes novel approaches to data acquisition associated with Taguchi experimentation.

The purpose of this paper is to study the individual investors’ preferences towards stock selection in social media environments. The study is conducted to understand the implications and conceptual directions for the corporates and financial advisors to understand the choices of individual investors applied in financial markets. Further, this study aims to examine the selection of the most preferred social media platform and behavioral intentions of investors towards selection of investment portfolios in Indian stock markets.

A questionnaire was designed based on the technique of conjoint analysis and was responded by 428 respondents belonging to the Northern region of India. The estimation of preference functions in Conjoint Analysis was designed by using orthogonal arrays and was calculated using the ordinary least square regression technique.

This study reveals that while making selection of desired investment portfolios, the investors give highest preference to social media platforms in terms of highest utility value and range followed by their preference for behavioral intentions to invest. Among different social media platforms, the investors preferred Twitter the most, followed by Facebook and the primary interest of investors was observed towards Intra-day trading purposes and balanced portfolio investments in financial markets. The major reason behind opting the social media platforms was selection of speculative stocks.

The actual individual investment behavior cannot be observed through the survey, which limits the external validity of the study.

The paper presents a very important practical tool that can help financial advisors, opinion leaders and corporates in defining their target audience more sharply for investment-related advice. The findings revealed by the study will put them in a better position to understand how investors differ behaviorally and they will get acquainted with their choices and preferences while making investment decisions in the backdrop of social media environments. The preferences of the investors based on social media usage discovered by the study will not only enable the individual investors understand their own preferences, but those of the other investors as well in terms of planned investment decisions and choices.

The paper is a first of its kind to empirically identify the individual investors and their preferences and choices by applying conjoint analysis in the new social media environment. The study thus integrates the gap between marketing theories and emerging theories of behavioral finance to understand the investor behavior in a better way.

Presents a new approach to adjust system availability levels which is based on the integration of total quality management principles with mathematical models for system availability. It is shown here that system availability levels can be improved and operating costs reduced if teams are used to evaluate and modify the operations of a system. The technique used here encourages continuous improvement and evaluation of systems, and demonstrates how coherent and consistent team judgements may be reached. A real case study that involves six engineers from a worldwide manufacturer of business computer systems is used to illustrate the application of the approach.

In the light of increased competition and introduction of advanced technologies into financial service sectors, financial institutions felt the need to apply marketing concepts and techniques. In particular, assessment and understanding of credit card customers′ needs and wants have become very important. It is known that people develop their first brand loyalties when they are between the ages of 18 and 25. Accordingly, college students as an important part of the youth market offer great opportunities for credit card companies. With this in mind, the purpose of this empirical study is to determine the important factors influencing credit card selection behaviour of college students via conjoint analysis. The results of this study offer important managerial implications for policy makers at the banks, financial institutions and other credit card dispensing retail outlets.

Jacquard woven fabrics are widely used in various sections of upholstery industry, where mattress cover is one of them. Strength of jacquard woven mattress fabric depends on several factors. The objective of this study is to model the multi‐linear relationship between fibre, yarn and fabric parameters on the strength of fabric using artificial neural network (ANN) and Taguchi design of experiment (TDOE) methodologies.

TDOE was applied to determine the optimum design values and the contribution of each parameter. Robustness (performance) of models is measured by root mean squared error (RMSE). These tools will enable the user to predict the fabric strength from number of given inputs. It also provides the knowledge related to the contribution of fibre, yarn and fabric parameters on fabric strength. Fabrics tested in this study made from different fibre types and max/min level for several fabric and yarn‐related parameters. The models generated with TDOE and ANN methodologies were compared with the actual experimental data.

It was found that ANN model gives better approximation with the minimum RMSE.

The data taken from factory are related with jacquard woven fabric.

This study has many practical implications that brings up a general approach for textile industry. During manufacturing, waste or scrap ratio can be reduced and production planning become more efficient.

Firstly, before starting manufacturing in factory, we can easily predict the strength of woven fabric using the defined factors. This makes the model usable at the planning stage of the fabric. Secondly, the contribution of factors affecting fabric strength was determined. The ANN model generated in this study helps the engineers of planning department at the company easy to plan the manufacturing of fabric with a good estimation of fabric strength before the production order.

Experimental design (ED) is a powerful technique which involves the process of planning and designing an experiment so that appropriate data can be collected and then analysed by statistical methods, resulting in objective and valid conclusions. It is an alternative to the traditional inefficient and unreliable one‐factor‐at‐a‐time approach to experimentation, where an experimenter generally varies one factor or process parameter at a time keeping all other factors at a constant level. This paper presents a step‐by‐step approach to the optimisation of a production process (of retaining a metal ring in a plastic body by a hot forming method) through the utilisation of Taguchi methods of experimental design. The experiment enabled the behaviour of the system to be understood by the engineering team in a short period of time and resulted in significantly improved performance (with the opportunity to design further experiments for possible greater improvements).

This paper aims to emphasize compared experimental analysis of influence of hybrid and classic moulds on the properties of moulded parts and the processing parameters. Such analysis enables optimization of processing parameters in case of the hybrid mould.

Representative moulded part and appropriate hybrid and classic moulds have been designed and manufactured. The experimental work contains a screening design and the main central composite design for analysing the performance of both moulds and moulded parts properties. In case of hybrid mould a numerical optimization of processing parameters was used.

It was found that hybrid moulds can be successfully applied for production of thin‐wall moulded parts with some limitations. The compressibility of prototype mould inserts was higher compared to classic inserts. The differences in thermal properties of mould inserts materials result in different moulded part properties and mould cavity wall temperature fields. These differences can be reduced by optimizing the processing parameters.

RT technologies can be usefully applied for fast production of moulds for injection moulding. The potential user of hybrid moulds should be aware of the influence of prototype inserts on the moulded part properties. Guidelines for optimization can be used for fast achieving of parameters from optimal processing window.

This paper shows a detailed analysis of influence of hybrid and classic moulds on the thermoplastic moulded part properties. Some of these influences are explained in detail, which was not found in the related papers. In this paper, a further step was made by optimizing the processing parameters in case of hybrid mould.

Fearing that their voice and SMS business will be substituted by IP‐based services from internet companies, mobile operators are developing various IP multimedia subsystem (IMS) based technologies to enable richer communication services. They reason that since the new rich communication services – such as enhanced presence, group communication and seamless switching between devices and media types within the same communication session – provide secure and more reliable services than those offered by internet companies – Skype, Whatsapp and Google+, for instance – consumers will readily appreciate their services and consequently use them. This paper seeks to address these issues.

To validate these claims, this study analyzes the results of a conjoint survey among 82 respondents in The Netherlands, France and Spain. Are users really willing to adopt these rich communication services and, if so, do issues like reliability, privacy and security impact their decision?

The results indicate that while users are most interested in “group communication” features of rich communication services, they appreciate other services like “switching devices”, “switching media during communication sessions” and “file‐sharing”. Still, for all services, reliability, security and interoperability (i.e. switching between devices) are valued as important requirements.

These findings contribute to the debate on platform competition, as these rich communication services are provided on the basis of the IMS platform, while competing services are offered via an internet base platform.

This paper contributes to the discussion in the mobile telecommunications domain on whether and how operators can counter the threat from internet players that look to take over their voice and SMS business. Theoretically, this paper will contribute both to understanding why users intend to adopt advanced mobile services and creating insight into the consumer‐related factors that drive the war between competing service platforms.

The purpose of this paper is to analyze the wastewater discharge and a zero-wastewater-discharge (ZWD) reproduction plan is designed for a paper mill in Taiwan.

The proposed model of ZWD reproduction planning is established using the fuzzy comprehensive evaluation and Taguchi method to determine the overall wastewater recovery rate. Still the prior studies failed to address a systematic approach to optimize the waste water recovery rate.

The optimal solution for clean water is 500 tons, recovery electrodialysis reversal is 345 tons, the wastewater reuse performance is 1.3 and waste heat recycling performance is 0.8, the larger number is performed well. The results shows that the maximum overall waste water recovery rate is 97.8 percent.

A paper mill is strived for improving their sustainable development. In real situation, there is a need to address the qualitative information and qualitative data to carry out the optimal ZWD reproduction planning.

The production-distribution (P-D) problems are two critical problems in many industries, in particular, in manufacturing systems and the supply chain management. In previous researches on P-D planning, the demands of the retailers and their inventory levels have less been controlled. This may lead into huge challenges for a P-D plan such as the bullwhip effects. Therefore, to remove this challenge, the purpose of this paper is to integrate a P-D planning and the vendor-managed inventory (VMI) as a strong strategy to manage the bullwhip effects in supply chains. The proposed P-D-VMI aims to minimize the total cost of the manufacturer, the total cost of the retailers, and the total distribution time simultaneously.

This paper presents a multi-objective non-linear model for a P-D planning in a three-level supply chain including several external suppliers at the first level, a single manufacturer at the second level, and multi-retailer at the third level. A non-dominated sorting genetic algorithm and a non-dominated ranking genetic algorithm are designed and tuned to solve the proposed problem. Then, their performances are statistically analyzed and ranked by the TOPSIS method.

The applicability of the proposed model and solution methodologies are demonstrated under several problems. A sensitivity analysis indicates the market scale and demand elasticity have a substantial impact on the total cost of the manufacturer in the proposed P-D-VMI.

Although the P-D planning is a popular approach, there has been little discussion about the P-D planning based on VMI so far. The novelty comes from developing a practical and new approach that integrates the P-D planning and VMI.