外文翻譯--基于實(shí)例推理的夾具設(shè)計

1、<p><b>　　英文原文</b></p><p>　　Application and development</p><p>　　Of case based reasoning in fixture design</p><p>　　Abstract: Based on the case based designing (CBD)

2、 methodology, the fixture similarity is in two respects: the function and the structure information. Then, the computer aided fixture design system is created on case based reasoning (CBR),in which the attributes of the

3、main features of workpiece and structure of fixture as case index code are designed for the retrieve of the similar cases, and the structure and hierarchical relation of case library are set up for store. Meanwhile, the

4、algorithm b</p><p>　　Keywords: case based reasoning ;fixture design; computer aided design(CAD)</p><p>　　Fixtures are devices that serve as the purpose of holding the workpiece securely and accu

5、rately, and maintaining a consistent relationship with respect to the tools while machining. Because the fixture structure depends on the feature of the product and the status of the process planning in the enterprise, i

6、ts design is the bottleneck during manufacturing, which restrains to improve the efficiency and leadtime. And fixture design is a complicated process, based on experience that needs comprehen</p><p>　　1 Cons

7、truction of a Case Index and Case Library</p><p>　　1.1 Case index</p><p>　　The case index should be composed of all features of the workpiece, which are distinguished from different fixtures. Us

8、ing all of them would make the operation in convenient. Because the forms of the parts are diverse, and the technology requirements of manufacture in the enterprise also develop continuously, lots of features used as the

9、 case index will make the search rate slow, and the main feature unimportant, for the reason that the relative weight which is allotted to every feature must dim</p><p>　　Therefore, considering the practical

10、ity and the demand of rapid design, the case index includes both the major feature of the workpiece and the structure of fixture. The case index code is made up of 16 digits: 13 digits for case features and 3 digits for

11、case identification number.</p><p>　　The first 13 digits represent 13 features. Each digit is corresponding to an attribute of the feature, which may be one of“*”, “？”, “1”, “2”,…,“A”,“B”,…, “Z”,…, etc. In w

12、hich, “*” means anyone, “?” uncertain, “0” nothing.</p><p>　　The system rules: fixture type, workpiece shape, locating model cannot be “*”or“?”. When the system is designed, the attribute information of the

13、three items does not have these options, which means the certain attribute must be selected. </p><p>　　The last three digits are the case identification number, which means the 13 digits of the case feature

14、are the same, and the number of these three digits is used for distinguishing them.</p><p>　　The system also rules: “000” is a prototype case, which is used for retrieval, and other cases are “001”,“002”,…,

15、 which are used for reference cases to be searched by designers. If occasionally one of them needs to be changed as the prototype case, first it must be required to apply to change the one to “000”, and the former is cha

16、nged to referential case automatically.</p><p>　　The construction of the case index code is shown in Fig.1.</p><p>　　1.2 Case library</p><p>　　The case library consists of lots of p

17、redefined cases. Case representation is one of the most important issues in case based reasoning. So compounding with the index code,.</p><p>　　1.3 Hierarchical form of Case</p><p>　　The structu

18、re similarity of the fixture is represented as the whole fixture similarity, components similarity and component similarity. So the whole fixture case library, components case library, component case library of fixture a

19、re formed correspondingly. Usually design information of the whole fixture is composed of workpiece information and workpiece procedure information, which represent the fixture satisfying the specifically designing funct

20、ion demand. The whole fixture case is made up of </p><p>　　2 Strategy of Case Retrieval</p><p>　　In the case based design of fixtures ,the most important thing is the retrieval of the similarity

21、, which can help to obtain the most similar case, and to cut down the time of adaptation. According to the requirement of fixture design, the strategy of case retrieval combines the way of the nearest neighbor and knowle

22、dge guided. That is, first search on depth, then on breadth; the knowledge guided strategy means to search on the knowledge rule from root to the object, which is firstly searched by </p><p>　　Retrieval algo

23、rithms:</p><p>　　1)According to the case index information of fixture case library, search the relevant case library;</p><p>　　2)Match the case index code with the code of each case of the case

24、library, and calculate the value of the similarity measure;</p><p>　　3)Sort the order of similarity measure, the biggest value, which is the most analogical case.</p><p>　　Similarity between two

25、 cases is based on the similarity between the two cases. features. The calculation of similarity measure depends on the type of the feature. The value of similarity can be calculated for numerical values, for example, co

26、mpareWorkpiece with the weight of 50kg and 20kg. The value can also be calculated between non numerical values, for example, now the first 13 digits index code is all non numerical values. The similarity measure of a fix

27、ture is calculated as follows:</p><p>　　where S is the similarity measure of current fixture, n is the number of the index feature, is the weight of each feature, is the similarity measure of the attribute

28、 of the i2th feature with the attributeof relative feature of the j-th case in the case library. At the same time, , the value counts as follows:</p><p><b>　　.</b></p><p>　　Where

29、is the value of the index attribute of the i-th feature, and is the value of attribute of the relative i-th feature of the j-th case in case library.</p><p>　　So there are two methods to select the analogic

30、al fixture. One is to set the value. If the values of similarity measure of current cases were less than a given value, those cases would not be selected as analogical cases. When the case library is initially set up, an

31、d there are only a few cases, the value can be set smaller. If there are lots of analogical cases, the value should get larger. The other is just to set the number of the analogical cases (such as10), which is the larges

32、t value of si</p><p>　　3 Case adaptation and Case Storage</p><p>　　3.1 Case adaptation</p><p>　　The modification of the analogical case in the fixture design includes the following

33、three cases:</p><p>　　1) The substitution of components and the component;</p><p>　　2) Adjusting the dimension of components and the component while the form remains; </p><p>　　3) T

34、he redesign of the model.</p><p>　　If the components and component of the fixture are common objects, they can be edited, substituted and deleted with tools, which have been designed.</p><p>　　3

35、.2 Case storage</p><p>　　Before saving a new fixture case in the case library, the designer must consider whether the saving is valuable. If the case does not increase the knowledge of the system, it is not

36、necessary to store it in the case library. If it is valuable, then the designer must analyze it before saving it to see whether the case is stored as a prototype case or as reference case. A prototype case is a represent

37、ation that can describe the main features of a case family. A case family consists of those cases </p><p>　　From the concept that has been explained, the following strategies are adopted:</p><p>

38、;　　1) If a new case matches any existing case family, it has the same first 13 digits as an existing prototype case, so the case is not saved because it is represented well by the prototype case. Or is just saved as a re

39、ference case (the last 3 digits are not “000”, and not the same with others) in the case library.</p><p>　　2) If a new case matches any existing case family and is thought to be better at representing this c

40、ase family than the previous prototype case, then the prototype case is substituted by this new case, and the previous prototype case is saved as a reference case.</p><p>　　3) If a new case does not match an

41、y existing case family, a new case family will be generated automatically and the case is stored as the prototype case in the case library.</p><p>　　4 Process of CBR in Fixture Design</p><p>　　A

42、ccording to the characteristics of fixture design, the basic information of the fixture design such as the name of fixture, part, product and the designer, etc. must be input first. Then the fixture file is set up automa

43、tically, in which all components of the fixture are put together. Then the model of the workpiece is input or designed. The detailed information about the workpiece is input, the case index code is set up, and then the C

44、BR begins to search the analogical cases, relying on the si</p><p>　　5 Illustrating for Fixture Design by CBR</p><p>　　This is a workpiece (seeFig.4). Its material is 45# steel. Its name is seat

45、. Its shape is block, and the product batch size is middle, etc. A fixture is turning fixture that serves to turn the hole, which needs to be designed.</p><p>　　The value of feature, attribute, case index co

46、de and weight of the workpiece is show n in Tab.2.</p><p>　　Through searching, and calculating the similarity, the case index code of the most similar case is 19325513321402000, and the detailed information

47、is show n in Tab. 3.</p><p>　　The similarity is calculated as follows:</p><p>　　So the value of similarity measure of the fixture which needs to be designed with the most analogical case in case

48、 library is 0.806, and the structure of the most analogical case is shown in Fig.5.</p><p>　　After having been substituted the component, modified the locating model and clamp model, and adjusted the relativ

49、e dimension, the new fixture is designed, and the figure is show n in Fig.6.</p><p>　　As there is not the analogical fixture in the case library, the new fixture is restored in to the case library. The case

50、index code is 19325513311402000.</p><p>　　6 Conclusion</p><p>　　CBR, as a problem solving methodology, is a more efficient method than an expert system to simulate human thought, and has been de

51、veloped in many domains where knowledge is difficult to acquire. The advantages of the CBR are as follows: it resembles human thought more closely; the building of a case library which has self learning ability by saving

52、 new cases is easier and faster than the building of a rule library; and it supports a better transfer and explanation of new knowledge that is more d</p><p><b>　　中文</b></p><p><b

53、>　　應(yīng)用和發(fā)展</b></p><p>　　基于實(shí)例推理的夾具設(shè)計</p><p>　　摘要：基于案例的設(shè)計（CBD）方法，夾具相似性體現(xiàn)在兩個方面:功能和結(jié)構(gòu)信息。然后，計算機(jī)輔助夾具設(shè)計系統(tǒng)是建立在基于案例的推理（CBR），并對工件和夾具結(jié)構(gòu)的主要特征屬性作為案例索引代碼用于檢索類似的情況，并且結(jié)構(gòu)和案例庫的層次關(guān)系建立商店，同時，算法在檢索相似案例知識的引導(dǎo)，案例

54、策略適應(yīng)在離子和案例庫中案例驗(yàn)證如果貓離子數(shù)是用來區(qū)分相似的案例，該系統(tǒng)在某工程中的應(yīng)用提高了設(shè)計效率，取得了良好的效果。</p><p>　　關(guān)鍵詞：基于案例的推理；夾具設(shè)計；計算機(jī)輔助設(shè)計（CAD）</p><p>　　夾具裝置，作為夾持工件的安全的目的地，并且維護(hù)方面的工具的一致性關(guān)系，而加工。因?yàn)閵A具的結(jié)構(gòu)取決于產(chǎn)品的特點(diǎn)以及在企業(yè)中的地位的計劃，它的設(shè)計制造過程中的瓶頸，制約提高

55、效率和交貨期。夾具的設(shè)計是一個復(fù)雜的過程，根據(jù)經(jīng)驗(yàn)，需要一系列的設(shè)計問題包括工件的結(jié)構(gòu)綜合定性知識，制造過程與加工環(huán)境。這也是一個使用傳統(tǒng)的CAD工具時，非常耗費(fèi)時間的工作（如詞素文字，CATIA、PRO/E），在進(jìn)行詳細(xì)設(shè)計的任務(wù)是好的，但提供很少的利益利用以往設(shè)計經(jīng)驗(yàn)和資源，這正是提高效率的關(guān)鍵因素?；诎咐耐评恚–BR）方法適應(yīng)以前解決的情況下為以下四個步驟建立一個新的問題的解決方案：檢索，重用，修改，并保留[ 1 ]。這是一個

56、比一個專家系統(tǒng)模擬人類思維的運(yùn)用更有用的方法，因?yàn)樘岢鲱愃频陌咐蛻?yīng)用了一些修改似乎是自我解釋和更直觀的人類。于是各種基于案例的設(shè)計支持工具已經(jīng)開發(fā)了眾多的地區(qū)[ 2-4 ]，如在注射成型設(shè)計，建筑設(shè)計，壓鑄模的設(shè)計，工藝規(guī)劃，并在夾具設(shè)計。太陽用六個數(shù)字組成，包括工件形狀，機(jī)械部分，該索引編碼套管，第一定位裝置，定位裝置和夾緊裝置第二[ 5 ]。但是該系統(tǒng)不能用于除鉆夾具其他燈具類型，并</p><p>　　1

57、 一個案例檢索和案例庫的建設(shè)</p><p><b>　　1.1例指數(shù)</b></p><p>　　案例索引應(yīng)該由工件的所有特征，是區(qū)別于不同的夾具。使用所有這些會使操作方便。因?yàn)榈貐^(qū)的形式是多種多樣的，并在企業(yè)的制造技術(shù)的要求也不斷發(fā)展，作為案例索引的許多功能將使搜索速度慢，和主要特點(diǎn)不重要，因?yàn)橄鄬?quán)重分配給每個特征，必須減少。另一方面，它是很難包括案例索引的所有

58、功能。</p><p>　　因此，從實(shí)用化、快速的設(shè)計需求，案例索引包括工件的主要特征和夾具結(jié)構(gòu)。案例索引代碼由16位數(shù)：13位數(shù)的情況下識別號案件的特點(diǎn)和3個數(shù)字。</p><p>　　前13個數(shù)字代表13個特點(diǎn)。每個數(shù)字對應(yīng)的特征的屬性，這可能是一個“*”，“？”，“1”，“2”，……，“A”，“B”，……，“Z”，……，等等。其中，“*”是指任何人，”？“不，”0“沒有什么。<

59、/p><p>　　系統(tǒng)規(guī)則：夾具，工件形狀，定位模型不能“*”或“？“。當(dāng)系統(tǒng)的設(shè)計，該三個項(xiàng)目的屬性信息，沒有這些選項(xiàng)，這意味著一定的屬性必須選擇。</p><p>　　最后三位數(shù)字是如此的識別號碼，即案例特征的13位數(shù)字是相同的，和這三個數(shù)字的位數(shù)是用來區(qū)分。</p><p>　　該系統(tǒng)還規(guī)定：“000”是一個原型的情況下，這是用于檢索，和其他案件的“001”，“0

60、02”，……，這是用于要搜索的設(shè)計者參考案例。如果偶爾他們當(dāng)中的一個需要改變?yōu)樵偷那闆r下，首先必須將改變一個“000”，和前改為自動參考案例。</p><p>　　的情況下，指數(shù)代碼結(jié)構(gòu)如圖1所示。</p><p><b>　　1.2例庫</b></p><p>　　案例庫包含預(yù)定義的眾多案例。案例的表示是基于案例推理的最重要的問題。所以復(fù)合

61、指標(biāo)代碼，。</p><p><b>　　1.3個層次的案例</b></p><p>　　夾具的結(jié)構(gòu)相似性表示作為整個夾具的相似性，相似性和相似性成分組成。所以整個夾具實(shí)例庫，組件的案例庫，案例庫的夾具元件形成相應(yīng)。通常整個夾具設(shè)計信息是由工件信息和工件程序的信息，這是專門設(shè)計滿足功能需求的夾具。整個夾具實(shí)例是由功能部件，這是由功能部件的名稱和編號描述。組件的情況下代

62、表成員。（功能組件和其他結(jié)構(gòu)部件，主要驅(qū)動參數(shù)，數(shù)量，和他們的約束關(guān)系。）的組件的情況下（夾具的最低層）的功能組件和其他組件的結(jié)構(gòu)。在現(xiàn)代燈具設(shè)計有參數(shù)化標(biāo)準(zhǔn)件和常用的非標(biāo)準(zhǔn)件的大量。這樣的組件的情況下，圖書館應(yīng)記錄，它使他們這樣的規(guī)格參數(shù)。</p><p><b>　　2.案例檢索策略</b></p><p>　　基于案例的夾具設(shè)計，最重要的是相似性檢索，以獲得最相

63、似的情況下，和降低的時間適應(yīng)。根據(jù)夾具的設(shè)計要求，案例檢索策略相結(jié)合的方式，最近的鄰居和知識引導(dǎo)。那是，深度優(yōu)先搜索，然后在廣度；知識引導(dǎo)策略意味著對從根到對象的知識規(guī)則的搜索，這是由夾具類型首先搜索，然后通過工件的形狀，然后通過定位方法。例如，如果指數(shù)代碼包括夾具式銑床夾具，搜索是為所有的銑削夾具，然后箱工件形狀，對1plane + 2pine定位方法第三。如果沒有匹配的話，那么對深度搜索停止，并返回上一層，和檢索所有相關(guān)案件的廣度。

64、</p><p><b>　　檢索算法：</b></p><p>　　1）根據(jù)夾具的案例庫的案例索引信息，搜索相關(guān)案例庫；</p><p>　　2）的情況下，指數(shù)代碼與每個案例的案例庫代碼匹配，并計算出的值的相似性度量；</p><p>　　3）的相似性度量的順序，最大的價值，這是最相似實(shí)例。</p>&l

65、t;p>　　兩起案件之間的相似性是基于兩個案例之間的相似性。特征。相似性度量的計算取決于類型的特征。相似的值可以計算出的數(shù)值，例如，與50公斤的重量compareworkpiece 20公斤。值也可以計算非數(shù)值之間，例如，現(xiàn)在第一個13位數(shù)代碼都是非數(shù)值索引。一個夾具的相似性度量的計算如下：</p><p>　　其中S是當(dāng)前夾具的相似性度量，n是指數(shù)的特征數(shù)量，是每個特征的重量，是用在案例庫中案例屬性的第j

66、個相對特征的i2th特征屬性的相似性度量。同時，，價值數(shù)如下：</p><p>　　的第i個特征指標(biāo)屬性的價值在哪里，是在案例庫的第j下相對i特征屬性的值。</p><p>　　所以選擇類比夾具的兩種方法。一是要設(shè)置的值。如果目前的情況下，相似度量值均小于給定值，這些案件將不被選擇作為類比案例。當(dāng)案例庫的初步建立，只有少數(shù)情況下，該值可設(shè)定較小。如果有相似事例很多，應(yīng)該得到更大的價值。另一

67、個是建立類推的案件數(shù)量（如10），這是最大的值的排序順序的相似性度量。</p><p>　　3.例適應(yīng)和案例存儲</p><p><b>　　3.1例適應(yīng)</b></p><p>　　在夾具設(shè)計的相似實(shí)例的修改包括以下三例：</p><p>　　1）組件的替代和組件；</p><p>　　2）調(diào)整

68、組件的尺寸和成分而形成仍然；</p><p><b>　　3）模型的設(shè)計。</b></p><p>　　如果零件和夾具組件是常見的對象，他們可以編輯和刪除，替換工具，已被設(shè)計。</p><p><b>　　3.2例存儲</b></p><p>　　在案例庫中保存新的夾具實(shí)例之前，設(shè)計者必須考慮的是節(jié)

69、約寶貴的。如果不增加系統(tǒng)的知識，不需要存儲在案例庫。如果它是有價值的，那么設(shè)計師就必須分析它，拯救它是否是存儲為原型的情況下，或作為參考的情況下在。一個原型是一個表示可以描述個案家庭的主要特點(diǎn)。一例家族是指那些案件指標(biāo)代碼庫中的情況下，具有相同的前13個數(shù)字和不同的最后三位數(shù)字。一個原型的情況下，最后三位數(shù)字是“000”。參考的情況下，屬于同一家族的原型的情況下，由不同的最后三位杰出的。</p><p>　　從已

70、解釋的概念，采用以下策略：</p><p>　　1）如果一個新的案例匹配任何存在的情況下，家庭，它具有相同的前13個數(shù)字作為一個現(xiàn)有的原型實(shí)例，所以并不是因?yàn)樗怯稍偷那闆r下，很好的體現(xiàn)?；蛑皇亲鳛橐粋€參考案例（最后3位數(shù)字是不是“000”，并與別人不一樣）在案例庫。</p><p>　　2）如果一個新的案例匹配任何存在的情況下，家庭和被認(rèn)為是更好的代表這種情況下的家庭比以前的原型實(shí)例，

71、然后原型以新案子取代，和以前的原型的情況下被保存作為參考的情況下。</p><p>　　3）如果一個新的案件不符合任何現(xiàn)有情況的家庭，一個新的案例的家庭將自動生成和案例存儲在案例庫的原型實(shí)例。</p><p>　　4 CBR的夾具設(shè)計過程</p><p>　　根據(jù)夾具設(shè)計的特點(diǎn)，對夾具設(shè)計如夾具，部分的名稱的基本信息，產(chǎn)品設(shè)計師，必須先輸入等。然后夾文件自動設(shè)置，其

72、中所有的夾具組件放在一起。然后對工件的模型輸入或設(shè)計。輸入的工件的詳細(xì)信息的情況下，指數(shù)代碼設(shè)置，然后開始搜尋相似案例推理，依靠的相似性度量，并篩選出最相似實(shí)例。如果需要的話，情況來滿足當(dāng)前的設(shè)計，并恢復(fù)到案例庫。該過程的流程圖如圖3所示。</p><p>　　5CBR的夾具設(shè)計說明</p><p>　　這是一個工件（seefig。4）。材料為45 #鋼。它的名字是座。它的形狀是塊，和產(chǎn)品

73、的批量大小中等，等。一個夾具，夾具，用于把車孔，需要設(shè)計。</p><p>　　特征，屬性值，指數(shù)代碼和工件的重量在選項(xiàng)卡顯示2 N。</p><p>　　通過搜索，計算相似度，最相似的案例的情況下，指數(shù)代碼為19325513321402000，和詳細(xì)信息顯示在標(biāo)簽3</p><p>　　相似度的計算方法如下：</p><p>　　因此，需要

74、設(shè)計的最為相似的案例案例庫的夾具相似性度量的值是0.806，和最相似實(shí)例的結(jié)構(gòu)如圖5所示。</p><p>　　經(jīng)取代的組件，修改了定位模型和夾具模型，和調(diào)整的相對尺寸，設(shè)計新的夾具，和圖顯示在圖6。</p><p>　　因?yàn)闆]有在案例庫中相似的夾具，夾具的新恢復(fù)的案例庫。的情況下，指數(shù)代碼為19325513311402000。</p><p><b>　

75、　6 結(jié)論</b></p><p>　　CBR，作為一個解決問題的方法，是一種比模擬人類思維的專家系統(tǒng)更有效的方法，并已在許多領(lǐng)域的知識是很難獲得的開發(fā)。案例推理方法的優(yōu)點(diǎn)如下：它類似于人類的思想更加緊密；一個案例庫，通過節(jié)約新病例的自我學(xué)習(xí)能力更容易，比一個規(guī)則庫的建設(shè)速度更快的建設(shè)；并支持更好的轉(zhuǎn)移和新知識的解釋，比規(guī)則庫的不同。提出了一種對CBR的夾具設(shè)計框架已用Visual C++實(shí)現(xiàn)，在U