姜曉波 凃康瑋



摘 ?要: 現代文化創意產品的創新需要設計師花費大量的腦力勞動,并需要結合感性與理性思維。因此,高質量的產品設計需要花費相當長的時間。為了在保證產品多樣化和質量的同時,有效提高設計效率,提出一種基于模擬退火算法的文化創意產品設計優化方法。首先以造型元素為基礎對模型幾何拓撲屬性進行分析,生成三角網格樣本點。然后通過面相似性計算分析構建相應鄰接矩陣,并使用模擬退火算法對目標最大團進行挖掘,從而模擬人類創新思維的設計過程。以卡通表情造型為創新設計實例進行算法仿真,并以遺傳算法作為對比驗證提出方法的有效性和實用性。
關鍵詞: 產品設計; 模擬退火算法; 三角網格; 面相似性計算; 設計過程模擬; 算法驗證
中圖分類號: TN911.1?34; TB472; TP183 ? ? ? ? ? ? 文獻標識碼: A ? ? ? ? ? ? ? 文章編號: 1004?373X(2019)19?0135?04
Abstract: The innovation of modern cultural creative products require designers to spend a lot of mental labor, and needs to combine sensibility and rational thinking. Therefore, high quality product design takes a long time. In order to improve the design efficiency while ensuring product diversification and quality, an optimization method for cultural creative product design based on simulated annealing algorithm is proposed. The geometrical topological properties of the model are analyzed based on the modeling elements. The triangular mesh sample points are generated. The corresponding adjacency matrix is constructed by means of the surface similarity calculation analysis. The simulated annealing algorithm is used to mine the target maximum group, which simulates the design process of human innovative thinking. The algorithm simulation is carried out with cartoon expressions as an example of innovative design. The validity and practicability of the proposed method are verified by genetic algorithm as a contrast object.
Keywords: product design; simulated annealing algorithm; triangular mesh; surface similarity calculation; design process simulation; algorithm verification
進入21 世紀以來,全世界不同地域和國家之間的文化交流越來越頻繁,極大促進了文化創意產業的快速發展。我國在政策和意識導向上均對文化創新有著較大的扶持力度。但是隨著社會工作節奏的不斷加快,產品更新換代的速度也隨之不斷提高,用戶多樣化的情感需求也逐漸增多,因此如何進行創新設計以不斷滿足消費者的各種需求,成為現代文化創意產品研發設計的關鍵問題。文化創意產品造型效果的好壞是每一個設計師十分重視的問題,但是現代文化創意產品的創新需要設計師花費大量的腦力勞動,需要運用探索性思維,并結合感性與理性思維。因此,高質量的產品設計需要花費相當長的時間[1?3]。如何利用先進的智能設計技術來縮短創意產品造型研發周期,提高設計的效率和產品質量,降低人工成本,具有較高的經濟和科學研究價值[4?5]。
目前,基于計算機智能技術的產品造型研究尚處于起步階段,其中較為典型的算法為遺傳算法。文獻[6]提出一種基于遺傳算法優化神經網絡的筆記本產品造型設計評價。文獻[7]提出結合元胞遺傳算法和標準遺傳算法的產品造型創新設計新方法,為創新設計提供了有效的輔助與支持。文獻[8]針對文化產品的造型設計提出遺傳算法的設計元素多目標優化模型,并以小音箱為例進行了有效性驗證,得到了較好的效果。雖然同為智能進化算法,但是模擬退火與遺傳算法有一定的不同之處。模擬退火算法采用單個個體進行進化且由參數問題[t]控制,然后通過一定的操作產生新的解,根據當前解的優劣和溫度參數[t]確定是否接受當前的新解[9?11]。相比基于遺傳算法的產品造型設計,模擬退火算法更加有利于模擬設計思維中的細化設計過程。因此,本文提出一種基于模擬退火算法的文化創意產品設計優化方法。以卡通表情造型為創新設計實例進行算法仿真,并以遺傳算法作為對比驗證提出方法的有效性和實用性。



本文提出基于模擬退火算法的文化創意產品設計優化方法。以造型元素為基礎,生成符合幾何拓撲屬性的三角網格樣本點,并使用模擬退火算法對最大團的最優化問題進行挖掘求解。卡通表情造型的具體應用實驗證明了提出方法的可行性和高效性。但是僅以相似值為量化評估指標不能較為全面地客觀評價算法的挖掘性能,實際應用仍需尋找適用度較廣的指標。因此,后續將對基于智能進化算法的產品造型設計評估指標開展進一步研究。
參考文獻
[1] BERG L P, VANCE J M. Industry use of virtual reality in pro?duct design and manufacturing: a survey [J]. Virtual reality, 2017, 21(1): 1?17.
[2] CHU C H, WANG I J, WANG J B, et al. 3D parametric human face modeling for personalized product design [J]. Advanced engineering informatics, 2017, 32: 202?223.
[3] TANG D, YIN L, ULLAH I. Product design knowledge management based on design structure matrix [J]. Advanced engineering informatics, 2018, 24(2): 159?166.
[4] FEI T, CHENG J, QI Q, et al. Digital twin?driven product design, manufacturing and service with big data [J]. International journal of advanced manufacturing technology, 2018, 94(9/12): 3563?3576.
[5] WATKINS M A, HIGGINSON M, PHILIP Richard Clarke. Enhancing graduate employability in product design [J]. Higher education, skills and work?based learning, 2018, 8(1): 80?93.
[6] 林琳,張志華,張睿欣.基于遺傳算法優化神經網絡的產品造型設計評價[J].計算機工程與設計,2015(3):789?792.
LIN Lin, ZHANG Zhihua, ZHANG Ruixin. Evaluation of pro?duct form design based on BP neural network trained by genetic algorithm [J]. Computer engineering and design, 2015(3): 789?792.
[7] 蘇建寧,陳肖,張書濤,等.基于進化算法的產品造型創新設計方法研究[J].工程設計學報,2016,23(2):136?142.
SU Jianning, CHEN Xiao, ZHANG Shutao, et al. Product styling innovative design method based on evolutionary algorithm [J]. Chinese journal of engineering design, 2016, 23(2): 136?142.
[8] 伍琴,呂健,潘偉杰,等.基于案例的文化創意產品設計方法研究[J].工程設計學報,2017,24(2):121?133.
WU Qin, L? Jian, PAN Weijie, et al. Research on design method of cultural creative products based on case [J]. Journal of engineering design, 2017, 24(2): 121?133.
[9] RUI Z, CHENG W. A simulated annealing algorithm based on block properties for the job shop scheduling problem with total weighted tardinessobjective [J]. Computers & operations research, 2017, 38(5): 854?867.
[10] CRUZ?CH?VEZ M A, MART?NEZ?RANGEL M G, CRUZ?ROSALES M H. Accelerated simulated annealing algorithm applied to the flexible job shop scheduling problem [J]. International transactions in operational research, 2017, 24(5):1119?1137.
[11] KANAGARAJ G, JAWAHAR N. A simulated annealing algorithm for optimal supplier selection using the reliability?based total cost of ownership model [J]. International journal of procurement management, 2009, 2(3): 244?266.
[12] CHEN H, WU C, ZUO L, et al. Optimization of detailed schedule for a multiproduct pipeline using a simulated annea?ling algorithm and heuristic rules [J]. Industrial & engineering chemistry research, 2017, 56(17): 5092?5106.