Comparison of multi-objective evolutionary algorithms in hybrid Kansei engineering system for product form design

Understanding the affective needs of customers is crucial to the success of product design. Hybrid Kansei engineering system (HKES) is an expert system capable of generating products in accordance with the affective responses. HKES consists of two subsystems: forward Kansei engineering system (FKES) and backward Kansei engineering system (BKES). In previous studies, HKES was based primarily on single-objective optimization, such that only one optimal design was obtained in a given simulation run. The use of multi-objective evolutionary algorithm (MOEA) in HKES was only attempted using the non-dominated sorting genetic algorithm-II (NSGA-II), such that very little work has been conducted to compare different MOEAs. In this paper, we propose an approach to HKES combining the methodologies of support vector regression (SVR) and MOEAs. In BKES, we constructed predictive models using SVR. In FKES, optimal design alternatives were generated using MOEAs. Representative designs were obtained using fuzzy c-means algorithm for clustering the Pareto front into groups. To enable comparison, we employed three typical MOEAs: NSGA-II, the Pareto envelope-based selection algorithm-II (PESA-II), and the strength Pareto evolutionary algorithm-2 (SPEA2). A case study of vase form design was provided to demonstrate the proposed approach. Our results suggest that NSGA-II has good convergence performance and hybrid performance; in contrast, SPEA2 provides the strong diversity required by designers. The proposed HKES is applicable to a wide variety of product design problems, while providing creative design ideas through the exploration of numerous Pareto optimal solutions.     

A hybrid Kansei engineering design expert system based on grey system theory and support vector regression

Nowadays customers choose products strictly in terms of their specific demands. How to quickly and accurately catch customers’ feelings and transform them into design elements and vice versa becomes an important issue. This study explores the bi-directional relationship between customers’ demands or needs and product forms by using a novel integral approach. High-price machine tools are used as our demonstration target. This integral approach adopts the “grey system theory (GST)”, and the state-of-the-art machine learning based modeling formalism “support vector regression (SVR)” in the “Kansei engineering (KE)” process. The GST is used to effectively determine the influence weighting of form parameters on product images and the SVR is used to precisely establish the mapping relationship between product form elements and product images. Furthermore, for practical concerns, a user-friendly design hybrid design expert system was developed based on the proposed novel integral schemes.     

Incorporating affective customer needs for luxuriousness into product design attributes

In a highly competitive market, customers' product affection is a critical factor to product success. However, understanding customers' affective needs is difficult to grasp; product design practitioners often misunderstand what customers really want. In this study we report our experience in developing and using an affective design framework that identified critical affective features customers have on products and are systematically incorporated into product design attributes. To identify key affective features such as luxuriousness, we utilized the Kansei engineering methodology. This approach consists of three steps: (1) selecting related affective features and product design attributes through a comprehensive literature survey, expert panel opinion, and focus group interviews; (2) conducting evaluation experiments; and (3) developing Kansei models using multivariate statistical analysis and analyzing critical product design attributes. To demonstrate applicability of the proposed affective design framework, 30 customers and 30 product design practitioners participated in an evaluation experiment for car crash pads, and 44 customers and 20 designers participated in an evaluation experiment for two interior room products (wallpapers and flooring materials). The evaluation experiments were conducted via systematically developed questionnaires consisting of a 7‐point semantic differential scale and a 100‐point magnitude estimation scale. The results of the experiments were analyzed using principal component regression and quantification theory type I method. Using the analyzed survey data, the relationship between luxuriousness and related affective features and product design attributes were identified. This relationship indicated that there was a significant difference in the perception of luxuriousness between customers and designers. Consequently, it is expected that the results of this study could provide a foundation for developing affective products. © 2009 Wiley Periodicals, Inc.     

基于犹豫模糊语言术语集和粒子群优化算法的产品造型设计感性评价方法

产品造型感性评价反映了用户的意象感知,具有模糊性与不确定性,用户常难以准确描述其感 性偏好而表现出犹豫。针对该问题,引入犹豫模糊语言术语集(HFLTSs)描述用户感性评价,基于其数学算子构 建犹豫模糊语言共识模型以测度用户认知一致性程度,借助粒子群优化算法(PSO)实现非共识条件下用户评价 矩阵的优化与共识达成,通过逼近理想解排序法对产品造型方案进行优劣排序,提出了基于 HFLTSs 和 PSO 的 产品造型设计感性评价流程。以汽车充电桩造型方案感性评价为例,验证了 HFLTSs 有助于解决用户感性认知 的不确定问题,结合 PSO 能够提高犹豫模糊语言评价的一致性,从而提升产品造型感性评价质量。     

A classification-based Kansei engineering system for modeling consumers’ affective responses and analyzing product form features

In the product design field, modeling consumers’ affective responses (CARs) for product form design is very helpful for developing successful products. It is also important for product designers to identify critical product form features (PFFs) to aid them in producing appealing products. In the present paper, a classification-based Kansei engineering system (KES) is proposed for modeling CARs and analyzing PFFs in a systematic manner. First, single adjectives are collected as initial affective dimensions for consumers to evaluate a set of representative products in the first questionnaire experiment. Factor analysis (FA) combined with Procrustes analysis (PA) is then used to extract representative affective dimensions. Second, these representative adjectives are regarded as class labels for consumers to describe their affective responses toward product form design. A large set of product samples are analyzed and their PFFs are encoded into numerical format. In the second questionnaire experiment, consumers are asked to assign one most suitable class labels to each product samples. A multiclass support vector machine (SVM) classification model is constructed for relating CARs and the PFFs. Optimal training parameters of SVM can be determined by a two-step cross-validation (CV). Third, support vector machine recursive feature elimination (SVM-RFE) is applied to pin point critical PFFs by wither using overall ranking or class-specific ranking. The relative importance of each PFF can be also analyzed by examining the weight distribution of the PFFs in each elimination step. A case study of digital camera design is also given to demonstrate the effectiveness of the proposed method.     

Simulated annealing-based immunodominance algorithm for multi-objective optimization problems

Based on the simulated annealing strategy and immunodominance in the artificial immune system, a simulated annealing-based immunodominance algorithm (SAIA) for multi-objective optimization (MOO) is proposed in this paper. In SAIA, all immunodominant antibodies are divided into two classes: the active antibodies and the hibernate antibodies at each temperature. Clonal proliferation and recombination are employed to enhance local search on those active antibodies while the hibernate antibodies have no function, but they could become active during the following temperature. Thus, all antibodies in the search space can be exploited effectively and sufficiently. Simulated annealing-based adaptive hypermutation, population pruning, and simulated annealing selection are proposed in SAIA to evolve and obtain a set of antibodies as the trade-off solutions. Complexity analysis of SAIA is also provided. The performance comparison of SAIA with some state-of-the-art MOO algorithms in solving 14 well-known multi-objective optimization problems (MOPs) including four many objectives test problems and twelve multi-objective 0/1 knapsack problems shows that SAIA is superior in converging to approximate Pareto front with a standout distribution.     

Design optimization of a spatial six degree-of-freedom parallel manipulator based on artificial intelligence approaches

Optimizing the system stiffness and dexterity of parallel manipulators by adjusting the geometrical parameters can be a difficult and time-consuming endeavor, especially when the variables are diverse and the objective functions are excessively complex. However, optimization techniques that are based on artificial intelligence approaches can be an effective solution for addressing this issue. Accordingly, this paper describes the implementation of genetic algorithms and artificial neural networks as an intelligent optimization tool for the dimensional synthesis of the spatial six degree-of-freedom (DOF) parallel manipulator. The objective functions of system stiffness and dexterity are derived according to kinematic analysis of the parallel mechanism. In particular, the neural network-based standard backpropagation learning algorithm and the Levenberg–Marquardt algorithm are utilized to approximate the analytical solutions of system stiffness and dexterity. Subsequently, genetic algorithms are derived from the objective functions described by the trained neural networks, which model various performance solutions. The multi-objective optimization (MOO) of performance indices is established by searching the Pareto-optimal frontier sets in the solution space. Consequently, the effectiveness of this method is validated by simulation.     

改进的约束优化多目标遗传算法及工程应用

利用多目标法处理约束条件,提出一种改进的基于多目标优化的遗传算法用于求解约束优化问题。该算法将约束优化问题转化为两个目标的多目标优化问题; 利用庄家法构造非劣个体,将种群分为支配子种群和非支配子种群,以一定概率分别从支配子种群和非支配子种群中选择个体进行算术交叉操作,引导个体逐步向极值点靠近,增强算法的局部搜索能力,对非支配子种群进行多样性变异操作。8个标准测试函数和3个工程应用的仿真实验结果表明了该算法的有效性。     

Integrating affective features with engineering features to seek the optimal product varieties with respect to the niche segments

In recent years, the popularity of smart phones substantially leads to poor sales of the low-end digital cameras. One of the most astounding industry news is Kodak’s bankruptcy in 2011 although Kodak was a pioneer in the field of digital still cameras. In reality, not only functional capability but also affective design can influence user purchase intentions on consumer electronics. In this paper, both affective features (AFs), and engineering features (EFs) are considered to achieve successful product planning. In particular, two critical issues are addressed: (1) market partitioning and (2) product differentiation. Initially, Kansei engineering is employed to capture user attitude toward AFs. Then, a classification tree is constructed to carry out effective market partitioning. Secondly, correspondence analysis is applied to capture user perceptions of EFs for identifying the core features that best characterize distinct market segments. Finally, VIKOR (VlseKriterijumska Optimizacija I Kompromisno Resenje) ranking is conducted to prioritize various product portfolios to accomplish product differentiation. In summary, the presented framework can help industrial practitioners transform diverse customer requirements into attractive alternatives while keep controllable manufacturing costs.     

基于免疫算法和EDA 的混合多目标优化算法

在免疫多目标优化算法的基础上,引入了分布估计算法(EDA)对进化种群进行建模采样的思想,提出了一种求解复杂多目标优化问题的混合优化算法HIAEDA(hybrid immune algorithm with EDA for multi-objectiveoptimization).HIAEDA 的进化过程混合了两种后代产生策略:一种是基于交叉变异的克隆选择算子,用于在父代种群周围进行局部搜索的同时开辟新的搜索区域;另一种是基于EDA 的模型采样算子,用于学习多目标优化问题决策变量之间的相关性,提高算法求解复杂多目标优化问题的能力.在分析两种算子搜索行为的基础上,讨论了两者在功能上的互补性,并利用有限马尔可夫链的性质证明了HIAEDA 算法的收敛性.对测试函数和实际工程问题的仿真实验结果表明,HIAEDA 与NSGAII 算法和基于EDA 的进化多目标优化算法RM-MEDA 相比,在收敛性和多样性方面均表现出明显优势,尤其是对于决策变量之间存在非线性关联的复杂多目标优化问题,优势更为突出.     

Multi-objective optimization of expensive electromagnetic simulation models

Vast majority of practical engineering design problems require simultaneous handling of several criteria. For the sake of simplicity and through a priori preference articulation one can turn many design tasks into single-objective problems that can be handled using conventional numerical optimization routines. However, in some situations, acquiring comprehensive knowledge about the system at hand, in particular, about possible trade-offs between conflicting objectives may be necessary. This calls for multi-objective optimization that aims at identifying a set of alternative, Pareto-optimal designs. The most popular solution approaches include population-based metaheuristics. Unfortunately, such methods are not practical for problems involving expensive computational models. This is particularly the case for microwave and antenna engineering where design reliability requires utilization of CPU-intensive electromagnetic (EM) analysis. In this work, we discuss methodologies for expedited multi-objective design optimization of expensive EM simulation models. The solution approaches that we present here rely on surrogate-based optimization (SBO) paradigm, where the design speedup is obtained by shifting the optimization burden into a cheap replacement model (the surrogate). The latter is utilized for generating the initial approximation of the Pareto front representation as well as further front refinement (to elevate it to the high-fidelity EM simulation model level). We demonstrate several application case studies, including a wideband matching transformer, a dielectric resonator antenna and an ultra-wideband monopole antenna. Dimensionality of the design spaces in the considered examples vary from six to fifteen, and the design optimization cost is about one hundred of high-fidelity EM simulations of the respective structure, which is extremely low given the problem complexity.     

数据驱动的贝叶斯SVR自适应建模及昂贵约束多目标代理优化

实际工程中的多目标优化问题往往具有黑箱特性且需要耗时的功能性评估,采用传统的进化优化方法求解,存在计算成本高昂且难以实现的问题.考虑代理优化方法在处理需要功能性评估工程设计问题中的高效性,提出一种小样本数据驱动下的贝叶斯SVR自适应建模及昂贵约束多目标代理优化方法.该方法在实现过程中选取贝叶斯SVR模型以减少功能性评估过程的昂贵仿真成本,利用最大化约束期望改进矩阵聚合策略进行新设计方案选取,并通过小样本信息的不断更新实现数据驱动下的贝叶斯SVR模型自适应更新和逐步优化.贝叶斯SVR模型具有强的边界刻画能力及预测不确定性度量功能,可为新样本挑选提供预测精度保障及潜在的改进方向.所提出的切比雪夫距离和曼哈顿距离聚合策略从样本填充的改进范围考虑,使其具有较强的改进边界探索能力,在多变量优化问题中具有计算复杂度低、适用性强的特点.测试函数及工程实例结果表明:1)所提出的方法可在小样本条件下有效减少昂贵仿真成本,提升昂贵约束多目标问题的优化效率;2)获取昂贵约束多目标问题的Pareto前沿在收敛性、多样性及空间分布性方面均具有一定优势.     

A Kansei mining system for affective design

Affective design has received much attention from both academia and industries. It aims at incorporating customers' affective needs into design elements that deliver customers' affective satisfaction. The main challenge for affective design originates from difficulties in mapping customers' subjective impressions, namely Kansei, to perceptual design elements. This paper intends to develop an explicit decision support to improve the Kansei mapping process by reusing knowledge from past sales records and product specifications. As one of the important applications of data mining, association rule mining lends itself to the discovery of useful patterns associated with the mapping of affective needs. A Kansei mining system is developed to utilize valuable affect information latent in customers' impressions of existing affective designs. The goodness of association rules is evaluated according to their achievements of customers' expectations. Conjoint analysis is applied to measure the expected and achieved utilities of a Kansei mapping relationship. Based on goodness evaluation, mapping rules are further refined to empower the system with useful inference patterns. The system architecture and implementation issues are discussed in detail. An application of Kansei mining to mobile phone affective design is presented.     

Nonlinear channel equalizer design using directional evolutionary multi-objective optimization

In this paper, a new equalizer learning scheme is introduced based on the algorithm of the directional evolutionary multi-objective optimization (EMOO). Whilst nonlinear channel equalizers such as the radial basis function (RBF) equalizers have been widely studied to combat the linear and nonlinear distortions in the modern communication systems, most of them do not take into account the equalizers’ generalization capabilities. In this paper, equalizers are designed aiming at improving their generalization capabilities. It is proposed that this objective can be achieved by treating the equalizer design problem as a multi-objective optimization (MOO) problem, with each objective based on one of several training sets, followed by deriving equalizers with good capabilities of recovering the signals for all the training sets. Conventional EMOO which is widely applied in the MOO problems suffers from disadvantages such as slow convergence speed. Directional EMOO improves the computational efficiency of the conventional EMOO by explicitly making use of the directional information. The new equalizer learning scheme based on the directional EMOO is applied to the RBF equalizer design. Computer simulation demonstrates that the new scheme can be used to derive RBF equalizers with good generalization capabilities, i.e., good performance on predicting the unseen samples.     

基于产品感性定制模型的顾客协同设计系统

为使产品定制模型更加适合缺少相关领域专业知识的大众消费者,建立了基于感性工学的产品感性定制模型。引入配件感性性能指数、产品感性性能矩阵对产品感性性能进行量化。使用层次分析法实现了求解与顾客对产品感性性能需求对应的产品工程配置的方法。并应用产品感性定制模型,构建了基于Web和虚拟现实技术的顾客协同设计系统。     

Selecting representative affective dimensions using Procrustes analysis: an application to mobile phone design

Collecting affective responses (ARs) from consumers is crucial to designers aspiring to produce an appealing product. Adjectives are frequently used by researchers as an affective means by which consumers can describe their subjective feelings regarding a specific product design. This study proposes a Kansei engineering (KE) approach for selecting representative affective dimensions using factor analysis (FA) and Procrustes analysis (PA). A semantic differential (SD) experiment is used to examine consumers' ARs toward a set of representative product samples. FA is employed to extract the underlying latent factors using an initial set of affective dimensions. A backward elimination process based on PA is used to determine the relative significance of adjectives in each step according to the calculated residual sum of squared differences (RSSDs) to finally obtain the ranking of the initial set of adjectives. Additionally, the results of the proposed approach are compared to the method that combines FA and two-stage cluster analysis (CA). A case study of mobile phone design is provided to demonstrate the analysis results.     

Evolution strategies and multi-objective optimization of permanent magnet motor

When designing a permanent magnet motor, several geometry and material parameters are to be defined. This is not an easy task, as material properties and magnetic fields are highly non-linear and the design of a motor is therefore often an iterative process. From an engineering point of view, we usually want to maximize the efficiency of the motor and from an economic point of view we want to minimize the cost of the motor. As these two things seldom go hand in hand, the goal is to find the best efficiency per cost. The scope of this paper is therefore to investigate the applicability of evolution strategies, ES to effectively design and optimize parameters of permanent magnet motors. Single as well as multi-objective optimization procedures are carried out. A modified way of creating the strategy parameters for the ES algorithm is also proposed and has together with the standard ES algorithm undergone a comprehensive parameter study for the parameters ρ and λ. The results of this parameter study show a significant improvement in stability and speed with the use of the modified ES version. To find the most effective selector for a multi-objective optimization, MOO, of the motor a performance examination of 4 different selectors from the group of programs called PISA has been made and compared for MOO of the efficiency and cost of the motor. This performance examination showed that the indicator based evolutionary algorithm, IBEA, and hypervolume estimation algorithm, HypE, selectors performed almost equally good on this MOO problem where the HypE selector only had a slightly better performance indicator.     

基于文化微粒群优化算法的DNA编码研究

对DNA编码约束进行研究,选择汉明测量以及相似度作为DNA序列集设计的主要约束,并结合连续性约束与GC Content约束,将序列集设计问题抽象为带有强约束的多目标优化问题,采用文化微粒群算法解决该多目标优化问题。仿真结果表明,该混合算法针对DNA编码序列设计问题,在求解最优值能力、解的稳定性方面都能取得较好的效果。     

产品形态多意象蛛网灰靶决策模型

针对概念设计中多意象设计方案决策困难的现象,提出了一种产品形态多意象蛛网灰靶决策方法。首先,运用感性工学相关方法获取设计主体的认知数据,结合熵权法及博弈论思想构建基于设计主体认知数据的综合评价模型,并根据各意象的设计主体综合评价数据确定各意象的权重关系;其次,通过人工选择的方式从产品形态进化系统中选择多个进化方案,运用蛛网图表征各进化方案的意象关系,构建多意象蛛网灰靶决策模型,计算决策系数,对其进行比较排序,得到符合设计主体认知的相对最优方案;最后,应用灰色关联分析法验证该决策模型的可行性。结果表明,该模型能够帮助设计师在设计决策阶段快速、准确地确定符合多设计主体认知的多意象方案,为产品方案的多意象决策提供了新的理论和方法。     

基于感性工学的产品客户化配置设计

基于感性工学理论及产品平台设计思想,提出了一种产品客户化配置设计方法.通过感性评价的问卷调查方式及回归分析方法建立感性意象与设计参数间的量化关系,同时辨识出平台参数与个性参数;在保持平台参数不变的基础上,改变个性参数进行产品造型以作为第二次问卷调查的样本.通过喜好评价的问卷调查形式,采用聚类分析方法对顾客进行基于喜好相似度的客户群聚类,并采用多项式回归模型建立各自的喜好度与个性参数间的量化关系模型,从而得到各个客户群的符合其最佳满意度的个性参数配置.最后,以手机机身设计为例进行说明.