【正文】 genetic algorithm which only reserves the best algorithm is an adaptive searching technique based on a selection and reproduction mechanism found in the natural evolution process, and it was pioneered by Holland in the has bee very famous with its global searching, parallel puting, better robustness, and not needing differential information during , it also has some demerits, such as poor local searching, premature converging, as well as slow convergence recent years, these problems have been this paper, an improved genetic algorithm with variant chromosome length and variant probability is with some critical functions shows that it can improve the convergence speed significantly, and its prehensive performance is better than that of the genetic algorithm which only reserves the best section 1, our new approach is optimization examples, in section 2, the efficiency of our algorithm is pared with the genetic algorithm which only reserves the best section 3 gives out the , some proofs of relative theorems are collected and presented in of the algorithm Some theorems Before proposing our approach, we give out some general theorems(seeappendix)as follows: Let us assume there is just one variable(multivariable can be divided into many sections, one section for one variable)x ∈ [ a, b ] , x ∈ R, and chromosome length with binary encoding is 1Minimal resolution of chromosome is s = ba 2l1Theorem 2Weight value of the ith bit of chromosome iswi = bai1(i = 1,2,…l)2l1Theorem 3Mathematical expectation Ec(x)of chromosome searching step with onepoint crossover is Ec(x)= baPc 2lwhere Pc is the probability of 4Mathematical expectation Em(x)of chromosome searching step with bit mutation is Em(x)=(ba)Pm Mechanism of algorithmDuring evolutionary process, we presume that value domains of variable are fixed, and the probability of crossover is a constant, so from Theorem 1 and 3, we know that the longer chromosome length is, the smaller searching step of chromosome, and the higher resolution。otherwise continue 4 If end condition is satisfied, stop。(2k1)22121j=12j=12Furthermore, probability of taking place crossover on each locus of k1chromosome is equal, namely l , after crossover, mathematical expectation of chromosome searching step is 1Ec(x)=229。(ba)11ba1(2k1)=cPc where l is large, l2l21Ec(x)=229。wi=229。最后，一些關(guān)鍵功能的測試表明，我們的解決方案可以顯著提高遺傳算法的收斂速度，其綜合性能優(yōu)于只保留最佳個(gè)體的遺傳算法。近些年，這個(gè)問題被廣泛地進(jìn)行了研究。第二部分，通過幾個(gè)優(yōu)化例子，將該算法和只保留最佳個(gè)體的遺傳算法進(jìn)行了效率的比較。同時(shí)，交叉概率與搜索步驟成正比。最后，應(yīng)當(dāng)指出，染色體長度的改變不會使個(gè)體適應(yīng)性改變，因此它不影響選擇（輪盤賭選擇）。Gt=1其中G是當(dāng)前進(jìn)化的一代，favg是個(gè)體的平均適應(yīng)度。在進(jìn)化過程中，我們跟蹤到當(dāng)代個(gè)體平均適應(yīng)度的累計(jì)值。進(jìn)化的開始階段，較短染色體（可以是過短，否則它不利于種群多樣性）和較高的交叉和變異概率會增加搜索步驟，這樣可進(jìn)行更大的域名搜索，避免陷入局部最優(yōu)。最后，相關(guān)定理的證明過程可見附錄。一些關(guān)鍵功能的測試表明，我們的解決方案可以顯著提高遺傳算法的收斂速度，其綜合性能優(yōu)于只保留最佳個(gè)體的遺傳算法。它以其全局搜索、并行計(jì)算、更好的健壯性以及在進(jìn)化過程中不需要求導(dǎo)而著稱。Pm mli2121一種新的改進(jìn)遺傳算法及其性能分析摘要：雖然遺傳算法以其全局搜索、并行計(jì)算、更好的健壯性以及在進(jìn)化過程中不需要求導(dǎo)而著稱，但是它仍然有一定的缺陷，比如收斂速度慢。i=1i=1llbai1baPm, where Pm is the probability of Mutation probability of genes on each locus of chromosome is equal, say Pm, therefore, mathematical expectation of mutation searching step is Em(x)=229。[(2i1)l]=c(1l)2212l212l21k=1llba187。Pc2j1=and the latter evaluates convergence better analyze online and offline performance of testing function, w e multiply fitness of each individual by 10, and we give a curve of 4 000 and 1 000 generations for f1 and f2, respectively.(a)online(b)online Online and offline performance of f1(a)online(b)online Online and offline performance of f2From and , we know that online performance of our approach is just little worse than that of the fourth case, but it is much better than that of the second, third and fifth case, whose online performances are nearly the the same time, offline performance of our approach is better than that of other four In this paper, based on some general theorems, an improved genetic algorithm using variant chromosome length and probability of crossover and mutation is with some critical functions shows that it can improve convergence speed of genetic algorithm significantly, and its prehensive performance is better than that of the genetic algorithm which only reserves the best With the supposed conditions of section 1, we know that the validation of Theorem 1 and Theorem 2 are 3 Mathematical expectation Ec(x)of chromosome searching step with one point crossover is baPc2lEc(x)=where Pc is the probability of As shown in , we assume that crossover happens on the kth locus, ’s locus from k to l do not change, and genes on the locus from 1 to k are crossover, change probability of genes on the locus from 1 to k is 2(“1” to “0” or “0” to “1”).So, after crossover, mathematical expectation of chromosome searching step on locus from 1 to k isk11ba1baEck(x)=229。ft=1avg(t)where G is the current evolutionary generation, is individual average When the cumulative average fitness increases to k times(k 1, k ∈ R)of initial individual average fitness, we change chromosome length to m times(m is a positive integer)of itself , and reduce probability of crossover and mutation, which can improve individual resolution and reduce searching step, and speed up algorithm procedure is as follows:Step 1 Initialize population, and calculate individual average fitness and set change parameter equal to , Step 2 Based on reserving the best individual of current generation, carry out selection, regeneration, crossover and mutation, and calculate cumulative average of individual average fitness up to current generationfavg。最后，對論文主要研究內(nèi)容和取得的技術(shù)成果進(jìn)行了總結(jié)，提出了存在的問題和不足，同時(shí)對機(jī)器人技術(shù)的發(fā)展和應(yīng)用進(jìn)行了展望。本文提出了一種算法簡單、易于實(shí)現(xiàn)、理論意義明確的步進(jìn)電機(jī)變速控制策略:定時(shí)器常量修改變速控制方案。在物料抓取機(jī)械手軟件的設(shè)計(jì)上，采用的是模塊化結(jié)構(gòu)，分為系統(tǒng)初始化模塊、數(shù)據(jù)處理模塊和故障狀態(tài)檢測與處理等幾部分?？刂撇糠质钦麄€(gè)物料抓取機(jī)械手系統(tǒng)設(shè)計(jì)關(guān)鍵和核心，它在結(jié)構(gòu)和功能上的劃分和實(shí)現(xiàn)直接關(guān)系到機(jī)器人系統(tǒng)的可靠性、實(shí)用性，也影響和制約機(jī)械手系統(tǒng)的研制成本和開發(fā)周期。由于步進(jìn)電機(jī)能夠直接接收數(shù)字量，響應(yīng)速度快而且工作可靠并無累積誤差，常用作數(shù)字控制系統(tǒng)驅(qū)動機(jī)構(gòu)的動力元件，因此，在驅(qū)動裝置中采用由步進(jìn)電機(jī)構(gòu)成的開環(huán)控制方式，這種方式既能滿足控制精度的要求，又能達(dá)到經(jīng)濟(jì)性、實(shí)用化目的，在此基礎(chǔ)上，對步進(jìn)電機(jī)的功率計(jì)一算及選型問題經(jīng)行了分析。本文結(jié)合塑料一次擠出成型機(jī)和塑料抓取機(jī)械手的研制過程中出現(xiàn)的問題，綜述近幾年機(jī)器人技術(shù)研究和發(fā)展的狀況，在充分發(fā)揮機(jī)、電、軟、硬件各自特點(diǎn)和優(yōu)勢互補(bǔ)的基礎(chǔ)上，對物料抓取機(jī)械