Search

Decision-making for remanufacturing is more complicated than that of traditional manufacturing because used or new components can be selected to remanufacture products. It becomes difficult to determine the various options of the components and their subsequent effect on the options at the same time. In fact, all decisions made in one remanufacturing activity will have a direct impact on the decisions taken in subsequent activities and this will affect profitability. Therefore, a decision-making model is proposed to support businesses in each remanufacturing activity by using mixed-integer linear programming to maximise profit and minimise operational time. It remains unknown whether component commonality always benefits remanufacturing. Therefore, this research contributes to the literature by quantifying and controlling the impact of component commonality on the objectives under different reworking scenarios characterised by the percentage of reworked components, reworking time, and reworking cost. When reworking costs and the percentage of reworked components are higher, the effect of component commonality on profit fluctuation increases. The remanufacturer can control these situations by reducing reworking costs, selecting specific patterns of component commonality that generate high profits or choosing the appropriate percentage of reworked components depending on various scenarios. [ABSTRACT FROM AUTHOR]

User performance is highly correlated with design variables of a system. Such association can be described as display–control relationship. In this study, a neural network-based methodology is proposed to identify and quantify the association among design variables (inputs) and to compute their relative influences (RIs) on the two performance measures (outputs) of user response time and response accuracy, using artificial neural network, generalised regression neural network, support vector regression (SVR), multiple linear regression and response surface model. Based on the results of the comparison, it is found that neural network-based methods are more reliable than SVR-based methods in computing the RI of design variables. As a result of our analysis, the best option for optimising each of the measures is suggested. Some useful observations about the design of man–machine systems are also presented, discussed and visualised. In the study of man–machine systems, quantitative methods are seldom adopted for examining the mappings between various displays and controls under a variety of operating conditions. The major contribution of this study is to provide some insights into the usefulness of quantitative methods in evaluating man–machine design in terms of display–control compatibility and to extract explanatory information from renowned black box systems such as neural networks. [ABSTRACT FROM PUBLISHER]

Customer satisfaction in purchasing new products is an important issue that needs to be addressed in today's competitive markets. A product with good affective design excites consumer emotional feelings to buy the product. Affective design often involves complex and multi-dimensional problems for modelling and maximising affective satisfaction of customers. Machine learning is commonly used to model and maximise the affective satisfaction, since it is effective in modelling nonlinear patterns when numerical data relevant to the patterns is available. This review article presents a survey of commonly used machine learning approaches for affective design when two data streams, traditional survey data and modern big data, are used. A classification of machine learning technologies is first provided for traditional survey data. The limitations and advantages of machine learning technologies are discussed. Since big data related to affective design can be captured from social media, the prospects and challenges in using big data are discussed to enhance affective design, in which limited research has so far been attempted. This review article is useful for those who use machine learning technologies for affective design, and also provides guidelines for researchers who are interested in incorporating big data and machine learning technologies for affective design. [ABSTRACT FROM AUTHOR]

A new approach using genetic algorithms (GAs) is proposed to determine lot streaming (LS) conditions in a job-shop scheduling problem (JSP). LS refers to a situation that a job (lot) can be split into a number of smaller jobs (sub-lots) so that successive operations of the same job can be overlapped. Consequently, the completion time of the whole job can be shortened. By applying the proposed approach called LSGAVS, two sub-problems are solved simultaneously using GAs. The first problem is called the LS problem in which the LS conditions are determined and the second problem is called JSP after the LS conditions have been determined. Based on timeliness approach, a number of test problems will be studied to investigate the optimum the LS conditions such that all jobs can be finished close to their due dates in a job-shop environment. Computational results suggest that the proposed model, LSGAVS, works well with different objective measures and good solutions can be obtained with reasonable computational effort. [ABSTRACT FROM AUTHOR]

Product development involves several processes in which product planning is the first one. Several tasks normally are required to be conducted in the product-planning process and one of them is to determine settings of design attributes for products. Facing with fierce competition in marketplaces, companies try to determine the settings such that the best customer satisfaction of products could be obtained. To achieve this, models that relate customer satisfaction to design attributes need to be developed first. Previous research has adopted various modelling techniques to develop the models, but those models are not able to address interaction terms or higher-order terms in relating customer satisfaction to design attributes, or they are the black-box type models. In this paper, a method based on genetic programming (GP) is presented to generate models for relating customer satisfaction to design attributes. The GP is first used to construct branches of a tree representing structures of a model where interaction terms and higher-order terms can be addressed. Then an orthogonal least-squares algorithm is used to determine the coefficients of the model. The models thus developed are explicit and consist of interaction terms and higher-order terms in relating customer satisfaction to design attributes. A case study of a digital camera design is used to illustrate the proposed method. [ABSTRACT FROM AUTHOR]