计算机辅助设计与图形学学报
計算機輔助設計與圖形學學報
계산궤보조설계여도형학학보
Journal of Computer-Aided Design & Computer Graphics
2015年
11期
2192-2200
,共9页
刘新儒%刘圣军%唐进元%周炜
劉新儒%劉聖軍%唐進元%週煒
류신유%류골군%당진원%주위
遗传算法%LM算法%遗传LM算法%粗糙度参数%函数拟合
遺傳算法%LM算法%遺傳LM算法%粗糙度參數%函數擬閤
유전산법%LM산법%유전LM산법%조조도삼수%함수의합
genetic algorithm%LM algorithm%GA-LM algorithm%surface roughness parameters%function fitting
为解决现有基于统计和随机过程理论等方法无法给出粗糙度参数直观计算的问题, 基于函数逼近理论提出一种通过优化函数模板来构造粗糙度参数计算公式的方法. 首先利用遗传算法优化初始函数模板各参数, 得到一组全局近似最优解集;再以此解集作为初值,用Levenberg–Marquardt (LM)算法求解更好的局部最优解集,并交替使用遗传算法和LM算法, 直到收敛或达到算法最大切换次数; 最后根据收敛精度、逼近性能对函数模板进行增长或剪枝,并继续交替使用 2 种优化算法直到满足循环退出条件. 数值实验表明, 该算法具有较好的寻优能力和较强的鲁棒性,能用于构造粗糙度参数计算公式, 操作简单且具有一定的工程实用价值.
為解決現有基于統計和隨機過程理論等方法無法給齣粗糙度參數直觀計算的問題, 基于函數逼近理論提齣一種通過優化函數模闆來構造粗糙度參數計算公式的方法. 首先利用遺傳算法優化初始函數模闆各參數, 得到一組全跼近似最優解集;再以此解集作為初值,用Levenberg–Marquardt (LM)算法求解更好的跼部最優解集,併交替使用遺傳算法和LM算法, 直到收斂或達到算法最大切換次數; 最後根據收斂精度、逼近性能對函數模闆進行增長或剪枝,併繼續交替使用 2 種優化算法直到滿足循環退齣條件. 數值實驗錶明, 該算法具有較好的尋優能力和較彊的魯棒性,能用于構造粗糙度參數計算公式, 操作簡單且具有一定的工程實用價值.
위해결현유기우통계화수궤과정이론등방법무법급출조조도삼수직관계산적문제, 기우함수핍근이론제출일충통과우화함수모판래구조조조도삼수계산공식적방법. 수선이용유전산법우화초시함수모판각삼수, 득도일조전국근사최우해집;재이차해집작위초치,용Levenberg–Marquardt (LM)산법구해경호적국부최우해집,병교체사용유전산법화LM산법, 직도수렴혹체도산법최대절환차수; 최후근거수렴정도、핍근성능대함수모판진행증장혹전지,병계속교체사용 2 충우화산법직도만족순배퇴출조건. 수치실험표명, 해산법구유교호적심우능력화교강적로봉성,능용우구조조조도삼수계산공식, 조작간단차구유일정적공정실용개치.
Based on the function approximation theory, the formulas for calculating surface roughness parameters are obtained by optimizing the coefficients of the function template. At first, a global approximate solution set is obtained by optimizing the initial function template using genetic algorithm. Then, the set is taken as the initial value of Levenberg–Marquardt (LM) algorithm to obtain the better local optimal solution set, and the two algo-rithms are used in turn until the solutions are convergent or the largest switching times are reached. At last, ac-cording to the convergence precision of the solutions and the value of each monomial, the growth or trim opera-tion is conducted on the function template, and the two optimization algorithms are executed again; until the ter-mination conditions are satisfied. The numerical simulation examples show the algorithm has the better ability to find the optimal solution and the good robustness. Moreover, the method is easy to carry out, and can be used in engineering practice.