Search

The Kano model is an extensively used technique for understanding different types of customer preferences. It classifies product features based on the effects of their performance on the overall customer satisfaction. Compared to surveys, numerous online reviews can be easily collected at a lower cost. This paper proposes an explainable neural network-based approach for the Kano categorisation of product features from online reviews. First, product feature words are identified by clustering nouns based on word embedding. Subsequently, the sentiments of the product feature words are determined by conducting the Vader sentiment analysis. Finally, the effects of the sentiments of each product feature on the star rating are estimated using explainable neural networks. Based on their effects, the product features are classified into the Kano categories. A case study of three Fitbit models is performed to validate the proposed approach. The Kano categorisation by the proposed approach is compared with the results of a previous product feature word clustering and ensemble neural network-based method. The results exhibit that the former presents a more reliable performance than the latter. The proposed approach is automated after providing several hyperparameters and can assist companies in conducting the Kano analysis with increased speed and efficiency. [ABSTRACT FROM AUTHOR]

Due to recent technological advancements, automation and autonomous solutions are gaining increasing popularity. Yet, a lack of in-depth investigations is noticed on the potential environmental benefits and economic repercussions of implementing autonomous systems. The present study aims to fill part of this gap by quantifying the environmental and economic sustainability of a robotic lawn mower, in comparison with human-operated counterparts. Combining life cycle assessment and life cycle costing methodologies, and by defining adequate functional units, building simulation models, and collecting life cycle inventory data, a systematic comparative study between autonomous and conventional lawn mowers is performed on their environmental and economic impacts. Through this multi-indicator analysis, environmental and economic trade-offs between the autonomous and conventional mowing solutions are quantitatively discussed for key relevant usage scenarios, from mowing an average residential yard to maintaining larger fields like a football stadium or a schoolyard. Concretely, sensitivity analyses on key parameters influencing the performance of the autonomous mower have been conducted to evaluate the environmental and economic benefits of an augmented robotic mower. While optimising the path planning of the current robotic mower would lead to the most substantial savings, improvements on the battery performance, cutting width, and speed of the autonomous solution appear as other promising areas for future work. [ABSTRACT FROM AUTHOR]

This article proposes a method with light data requirements for generating robust wind farm layouts. Robustness in this work is quantified as the lowest energy conversion efficiency of the wind farm across all wind directions. A quadratic integer programming formulation for generating robustness-maximizing layouts is presented. Small instances of the proposed formulation can be solved to optimality using branch and bound. A modified greedy algorithm that guarantees solution feasibility with regards to inter-turbine safety distance is proposed to find solutions to larger problem instances. A series of experiments were conducted using real world wind data collected at two sites to demonstrate the trade-offs in power generation between robust layouts and power output maximizing layouts. The results show a loss of around 1.1% in hourly power generation in return for an increase in minimum power output of 1% to 45% across all directions for robust layouts generated in the experiments. The increase in robustness largely depends on the shape and orientation of the wind farm relative to the dominant wind direction, as well as the difference between the average wind speed at the site of the wind farm and rated wind speed of the turbines. [ABSTRACT FROM AUTHOR]

The 0-1 quadratic knapsack problem (QKP) in wind farm layout optimization models possible turbine locations as nodes, and power loss due to wake effects between pairs of turbines as edges in a complete graph. The goal is to select up to a certain number of turbine locations such that the sum of selected node and edge coefficients is maximized. Finding the optimal solution to the QKP is difficult in general, but it is possible to obtain a tight upper bound on the QKP's optimal value which facilitates the use of heuristics to solve QKPs by giving a good estimate of the optimality gap of any feasible solution. This article applies an upper bound method that is especially wellsuited to QKPs in wind farm layout optimization due to certain features of the formulation that reduce the computational complexity of calculating the upper bound. The usefulness of the upper bound was demonstrated by assessing the performance of the greedy algorithm for solving QKPs in wind farm layout optimization. The results show that the greedy algorithm produces good solutions within 4% of the optimal value for small to medium sized problems considered in this article. [ABSTRACT FROM AUTHOR]

Remanufacturing is emerging as a promising solution for achieving green, profitable businesses. This article considers a manufacturer that produces new products and also remanufactured versions of the new products that become available at the end of their life cycle. For such a manufacturer, design decisions at the initial design stage determine both the current profit from manufacturing and future profit from remanufacturing. To maximize the total profit, design decisions must carefully consider both ends of product life cycle,i.e. manufacturing and end-of-life stages. This article proposes a decision-support model for the life-cycle design using mixed-integer nonlinear programming. With an aim to maximize the total life-cycle profit, the proposed model searches for an (at least locally) optimal product design (i.e. design specifications and the selling price) for the new and remanufactured products. It optimizes both the initial design and design upgrades at the end-of-life stage and also provides corresponding production strategies, including production quantities and take-back rate. The model is extended to a multi-objective model that maximizes both economic profit and environmental-impact saving. To illustrate, the developed model is demonstrated with an example of a desktop computer. [ABSTRACT FROM PUBLISHER]

This article presents a multi-scenario decomposition with complementarity constraints approach to wind farm layout design to maximize wind energy production under region boundary and inter-turbine distance constraints. A complementarity formulation technique is introduced such that the wind farm layout design can be described with a continuously differentiable optimization model, and a multi-scenario decomposition approach is proposed to ensure efficient solution with local optimality. To combine global exploration and local optimization, a hybrid solution algorithm is presented, which combines the multi-scenario approach with a bi-objective genetic algorithm that maximizes energy production and minimizes constraint violations simultaneously. A numerical case study demonstrates the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Selecting the appropriate components to share in product family design is not a trivial decision; especially when a firm wants to protect the most sensitive information contained in their products from being exposed to users, third-party manufacturers, or undesirable agents. This article proposes tools to help designers identify sets of components containing sensitive information, as well as components that are candidates for sharing amongst the family. It also finds the most desirable component arrangement in each product that facilitates sharing while protecting the sensitive information that has been previously identified. The proposed framework is applied to three printers in which the architecture used for the ink cartridges and printheads are significantly different. Third-party manufacturers and remanufacturers offer their own alternatives for these subsystems (ink cartridges and printheads) since the customer for printer supplies is always looking for a cheaper alternative; meanwhile, the original equipment manufacturers attempt to secure their products and retain their customers with original supplies. The functional description of the system is analysed to identify the sensitive components for each printer; then, the optimal clustering strategy is found, as well as the set of components that are candidates for sharing, according to their connectivity and the security considerations. [ABSTRACT FROM PUBLISHER]

Product family design via component sharing is a widely practiced approach for offering sufficient variety to the market in an economical way. When discussing product family design, most previous research has focused on its benefits in the design and manufacturing stages. This article highlights another important aspect of product family design: the impact of component sharing on end-of-life management. This article presents a quantitative model for assessing product family design from an end-of-life perspective. Using mixed integer programming, the developed model identifies an optimal strategy for managing product take-back and end-of-life recovery, thereby assessing the product family design in terms of its profitability in end-of-life management. Especially, the model incorporates increased component interchangeability by component sharing. A design study of a smart phone family is presented, as an illustration, and the results show that the model can assess profitability of a family design and highlight preferred family design alternatives. [ABSTRACT FROM AUTHOR]

The design of an architecture for a family of products is a challenging task. Traditionally, only a single product case is considered when optimization techniques are used to define the optimum clustering of the components, or in other words the module definition for the product. This article proposes a framework to analyse multiple products of a given family and achieve an optimal module definition considering component sharing across some or all the products. The optimal sharing decision process is implemented with a dual objective function: a 'minimum description length' representation of the overall product architecture, and the 'impact metric' description of the selected components to share. An illustration example is developed for three digital cameras of the same brand and the results reveal the recommended set of components to share across the family as well as the optimal architecture for each one of the products. [ABSTRACT FROM AUTHOR]

This article proposes a top-down product family design methodology that enables product design engineers to identify the optimal number of product architectures directly from the customer preference data set by employing data mining attribute weighting and clustering techniques. The methodology also presents an efficient component sharing strategy to aid in product family commonality decisions. Two key data mining models are presented in this work to help guide the product design process: (1) the ReliefF attribute weighting technique that identifies and ranks product attributes, and (2) the X-means clustering approach that autonomously identifies the optimal number of candidate products. Product family commonality decisions are guided by once again employing the X-means clustering technique, this time to identify the components across product families that are most similar. A family of prototype aerodynamic air particle separators is used to evaluate the efficiency and validity of the proposed product family design methodology. [ABSTRACT FROM AUTHOR]