【正文】 to search on the knowledge rule from root to the object, which is firstly searched by the fixture type, then by the shape of the workpiece, thirdly by the locating method. For example, if the case index code includes the milling fixture of fixture type, the search is just for all milling fixtures, then for box of workpiece shape, the third for 1plane+ 2pine of locating method. If there is no match of it, then the search stops on depth, and returns to the upper layer, and retrieves all the relative cases on breadth. Case adaptationThe modification of the analogical case in the fixture design includes the following three cases:1) The substitution of ponents and the ponent。2) Adjusting the dimension of ponents and the ponent while the form remains。 3) The redesign of the model.If the ponents and ponent of the fixture are mon objects, they can be edited, substituted and deleted with tools, which have been designed. Case storageBefore 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 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 representation that can describe the main features of a case family. A case family consists of those cases whose index codes have the same first 13 digits and different last three digits in the case library. The last three digits of a prototype case are always “000”. A reference case belongs to the same family as the prototype case and is distinguished by the different last three digits.From the concept that has been explained, the following strategies are adopted: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 reference case (the last 3 digits are not “000”, and not the same with others) in the case library.2) If a new case matches any existing case family and is thought to be better at representing this case 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.3) If a new case does not match any existing case family, a new case family will be generated automatically and the case is stored as the prototype case in the case library.3. ConclusionCBR, as a problem solving methodology, is a more efficient method than an expert system to simulate human thought, and has been developed 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 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 different than the rule library. A proposed fixture design framework on the CBR has been implemented by using Visual C ++, UG/Open API in U n graphics with Oracle as database support, which also has been integrated with the 32D parametric mon ponent library, mon ponents library and typical fixture library. The prototype system, developed here, is used for the aviation project, and aids the fixture designers to improve the design efficiency and reuse previous design resources.基于事例推理的夾具設(shè)計(jì)研究與應(yīng)用夾具是以確定工件安全定位準(zhǔn)確為目的的裝置，并在加工過程中保持工件與刀具或機(jī)床的位置一致不變。因?yàn)閵A具的結(jié)構(gòu)依賴于產(chǎn)品的特點(diǎn)和在企業(yè)規(guī)劃中加工工序的地位,所以它的設(shè)計(jì)是制造過程中的瓶頸,制約著效率的提高. 夾具設(shè)計(jì)是一個(gè)復(fù)雜的過程,需要有從大量的設(shè)計(jì)論文中了解質(zhì)量知識(shí)的經(jīng)驗(yàn)，這些設(shè)計(jì)論文包括工件的結(jié)構(gòu)設(shè)計(jì)、涉及加工工藝，和加工環(huán)境。當(dāng)用這些擅長(zhǎng)繪制詳細(xì)設(shè)計(jì)圖的傳統(tǒng)的CAD工具（如Unigraphics、CATIA、Pro/E)時(shí),這仍然是一項(xiàng)非常耗時(shí)的工作，但是利用以往的設(shè)計(jì)經(jīng)驗(yàn)和資源也不能提供一些益處,而這正是提高效率的關(guān)鍵因素. 基于事例推理 (CBR) 的方法適應(yīng)以往個(gè)案解決的辦法,建立一個(gè)新問題的方法,主要有以下四步驟:檢索、利用、修改,，因?yàn)樘岢鲆粋€(gè)類似的情況,和采用一些修改,似乎不言自明,，如在注射成型及設(shè)計(jì)、建筑設(shè)計(jì)、模具設(shè)計(jì)投死, 規(guī)劃過程中,還有夾具設(shè)計(jì). 孫用六個(gè)數(shù)字組成代碼參數(shù),包括工件的形狀、機(jī)械部分、軸襯,第一定位裝置,第二定位裝置和夾緊裝置. 但這個(gè)系統(tǒng)不能用于除鉆床夾具外的其他夾具類型,不能解決儲(chǔ)存需要保留的同一參數(shù)代碼的問題,這在CBR中是非常重要的.1. 事例參數(shù)和事例圖書館的建立 事例參數(shù)事例參數(shù)應(yīng)該由工件的所有的特征組成，來區(qū)別不同的夾具. 使用他們能夠使操作方便. 因?yàn)榱慵男螤钍嵌喾N多樣的, 在生產(chǎn)企業(yè)中制造的技術(shù)要求也不斷發(fā)展,許多特征作被用做事例參數(shù)將會(huì)使搜索速度降低,其主要特征是不重要的,因?yàn)榉峙浣o每個(gè)特征的比重必須減少. 另一方面,事例參數(shù)包含所有的特征是困難的。 事例的層次化夾具的結(jié)構(gòu)相似被認(rèn)為是整個(gè)夾具，成分和內(nèi)容相似。所以，整個(gè)夾具事例庫(kù)，成分事例庫(kù)，夾具的成分事例庫(kù)形成相同。整個(gè)夾具的設(shè)計(jì)資料通常是由工件資料和工件加工資料組成,，它是用功能成分的名字和數(shù)字來進(jìn)行描述的。成分事例代表成員（成分功能和其他結(jié)構(gòu)成分，主要驅(qū)動(dòng)參數(shù)，數(shù)字，和它們的約束關(guān)系）。成分事例（夾具的最低層）是功能成分和和其他成分的結(jié)構(gòu)。在現(xiàn)代夾具設(shè)計(jì)中有很多參數(shù)化準(zhǔn)件和普通非標(biāo)準(zhǔn)件。所以成分事例圖書館應(yīng)記錄特殊參數(shù)和保持它們的方法。2. 事例修改的策略在基于事例的夾具設(shè)計(jì)中，最重要的是相似點(diǎn)的修改，這樣能有助于獲得最相似的事例，以及縮短適應(yīng)時(shí)間。根據(jù)夾具設(shè)計(jì)的需求，事例修改的策略使最接近的事例方法和知識(shí)指導(dǎo)結(jié)合起來。首先在深度上查找，然后在寬度上；知識(shí)指導(dǎo)策略意味著在來自客觀事物根源的知識(shí)規(guī)則上查找，這就要首先查找固定類型，然后查找工件的形狀，第三查找定位方法。例如，如果事例索引碼包括夾具類型的磨削夾具，就只查找所有的磨削夾具，然后查找工件形狀的盒子，第三查找一個(gè)平面兩個(gè)銷的定位方法。如果沒有合適的，就查找深度標(biāo)點(diǎn)，然后回到最上層，然后再找所有與寬度相關(guān)的事例。夾具設(shè)計(jì)中相似事例的修改包括以下三個(gè)階段：1）成分的替代2）保持形式不變，調(diào)整成分的特性3）模型重新設(shè)計(jì)如果夾具的成分是普通的物品，它們能通過使用工具被修改，代替以及刪除，這些已經(jīng)被設(shè)計(jì)好了。 在將一個(gè)新的事例保存到事例庫(kù)之前，設(shè)計(jì)者必須考慮保存是否有價(jià)值。如果這個(gè)事例不能增加系統(tǒng)的知識(shí)，就沒有必要把它保存到事例庫(kù)里。如果它有價(jià)值的話，設(shè)計(jì)者在保存之前必須分析一下，看看這個(gè)事例是否作為標(biāo)準(zhǔn)事例或參考事例被存儲(chǔ)了。一個(gè)標(biāo)準(zhǔn)事例是一個(gè)描述同族事例主要特征的標(biāo)準(zhǔn)。一個(gè)同族事例是有事例庫(kù)中索引碼前13位相同而最后三位不同的那些事例組成的。一個(gè)標(biāo)準(zhǔn)事例的最后三位通常是“000”。一個(gè)參考事例屬于同族標(biāo)準(zhǔn)事例，最后三位用不同數(shù)字區(qū)分。從被解釋的概念中，可采用以下方法：1)如果一個(gè)新的事例和任何一個(gè)存在的事例族一致，和一個(gè)存在的標(biāo)準(zhǔn)事例的前13位數(shù)相同，那么這個(gè)事例就不能存儲(chǔ)因?yàn)橐呀?jīng)這種標(biāo)準(zhǔn)事例了?；蛘咧荒茏鳛橐粋€(gè)參考事例保存（最后三位不是“000”，而且和其它的不一樣）在事例庫(kù)中。2)如果一個(gè)新的事例和任何一個(gè)存在的事例族一致，并且被認(rèn)為代替這個(gè)事例族要比以前的標(biāo)準(zhǔn)事例好，那么這個(gè)標(biāo)準(zhǔn)事例就被這個(gè)新的事例代替，以前的標(biāo)準(zhǔn)事例作為一個(gè)參考事例保存。3)如果一個(gè)新的事例和任何一個(gè)存在的事例族不一致，一個(gè)新的事例族將會(huì)自動(dòng)產(chǎn)生，并作為標(biāo)準(zhǔn)事例保存到事例庫(kù)中。3. 結(jié)論基于事例推理，作為一個(gè)問題解決的方法，是一個(gè)比模仿人類思想的專業(yè)系統(tǒng)更有效的方法，已經(jīng)在很多難獲取知識(shí)的領(lǐng)域里得到發(fā)展?；谑吕评淼膬?yōu)點(diǎn)如下：它和人類的思想很相似；一個(gè)事例庫(kù)通過保存新事例獲得自學(xué)能力，它比有慣例庫(kù)更快更容易，它可以更好的傳遞和解釋新的知識(shí)，這和慣例庫(kù)有很大的不同?；谑吕评碇刑岢龅囊粋€(gè)夾具設(shè)計(jì)的框架已經(jīng)被實(shí)行了，使用的是支持基礎(chǔ)數(shù)據(jù)的VC++，UG電腦繪圖軟件。這個(gè)框架也已經(jīng)和普通成分庫(kù)和典型夾具庫(kù)結(jié)合起來。這個(gè)發(fā)展的標(biāo)準(zhǔn)系統(tǒng)，用于航空項(xiàng)目，幫助夾具設(shè)計(jì)者提高設(shè)計(jì)效率和重新使用先前的設(shè)計(jì)