【導讀】自動化立體倉庫作為現(xiàn)代物流系統(tǒng)的重要組成部分，是一種多層存放貨物的高架。倉庫系統(tǒng)，它是在不直接進行人工干預(yù)的情況下自動地存儲和取出物流的系統(tǒng)?，F(xiàn)代工業(yè)社會發(fā)展的高科技產(chǎn)物，對提高生產(chǎn)率、降低成本有著重要意義。機構(gòu)進行分析設(shè)計、選取與尺寸計算。升機構(gòu)的設(shè)計、伸叉機構(gòu)設(shè)計、行走機構(gòu)設(shè)計、機體支架設(shè)計及其他裝置設(shè)計等內(nèi)容。計一臺性能完備的雙立柱式巷道堆垛起重機。堆垛起重機是自動化立體倉庫中最重要的起重運輸設(shè)備，是代表立體倉庫的標志。的關(guān)注并已開始應(yīng)用于汽車、電子、醫(yī)藥、煙草、裁減、郵電等許多行業(yè)。早是在二戰(zhàn)期間被美國用來存儲油料、槍支、器械等物品。立體倉庫并得到廣泛應(yīng)用。車牽引一節(jié)裝有起重機的車廂，由起重機來完成貨物的存取與運輸。前的人力相比具有了提高勞動生產(chǎn)率、降低勞動成本等優(yōu)點，但行走所需空間大，而發(fā)展起來的專用起重機，通常簡稱堆剁機。

　　

【正文】 [14]龔桂義 .機械設(shè)計課程設(shè)計圖冊第三版：高等教育出版社， [15]有軌巷道式高層貨架倉庫設(shè)計規(guī)范， JB/T90181999 [16]巷道式堆垛起重機形式與基本參數(shù)， JB/T29601999 [17]有軌巷道式堆垛起重技術(shù)條件， JB/T70161993 [18]有軌巷道式堆垛起重術(shù)語， JB/ [19]有軌巷道式堆垛起重技安全規(guī)范， JB/ [20] 2021 AOI Help [EB/OL].2021 [21]OMRON 可編程控制器程序設(shè)計手 [Z].1999 [22]Yong Huang and Seiji Yansuno practical design method of fuzzy control based on control surface [J].Journal of Japan Society for Fuzzy Theory and System， 1999,11 致 謝 能順利完成本次畢業(yè)論文設(shè)計，首先與我的指導老師 王慧文 老師的悉心教導分不開的，在此，我先向 王 老師致以我深深的謝意！ 本次論文設(shè)計從論文的選題、撰寫、修改直到打印完成自始自終都是在 王 老師的悉心指導和不斷勉勵下完成的 王 老師淵博的學識、嚴謹?shù)乃季S使我受益非淺； 王 老師一絲不茍的鉆研精神，嚴謹求實的治學態(tài)度，執(zhí)著忘我的工作作風，獨樹一幟的思維方式，無時無刻不在影響著我，一定讓我終身難忘。他的言傳身教，將會永遠指導著我今后的學習和工作中勇往直前。 在此，還要感謝 車輛工程專 業(yè)的各位老師，在大學四年里給我專業(yè)知識上的教導以及進行畢業(yè)論文工作中所給予的幫助，他們的不倦教誨 和點撥定將成為我今日點滴海量機械畢業(yè)設(shè)計，請聯(lián)系 Q99872184 31 知識的來源。 感謝圖書館、電子閱覽室的各位老師予以我的關(guān)心和幫助。 還要感謝我的學友和朋友對我的關(guān)心和幫助，他們的啟發(fā)和友愛互助的精神給予我論文寫作極大的幫助。 最后，再次向在這次畢業(yè)設(shè)計中所有幫助過我的人表示忠心的感謝！ 附 錄 A Geic Algorithm Optimization On Crane Transmission In Neural Network Abstract： The fuzzy optimization mathematic model is established to design crane transmission. The method of secondclass prehensive evaluation was used by the optimal level cut set, thus the optimal level value of every fuzzy constraint can be attained, and the fuzzy optimization is transformed into the usual optimization. The Fast Back Propagation of neural work algorithm is adopted to train feedforward works so as to fit relative coefficient. Then the fitness function with penalty terms is built by penalty strategy, neural works program is recalled, solver functions of Geic Algorithm Toolbox of Matlab software are adopted to solve the optimization mathematic model. Index ： TermsCrane Mechanism。 Geic Algorithm Optimization。 Neural Networks. 海量機械畢業(yè)設(shè)計，請聯(lián)系 Q99872184 32 FUZZY OPTIMIZATION MATHEMATICAL MODEL OF TRACTION MECHANISM Design sample: A involute helicoidal worm gearing is adopted in crane transmission, which has principal parameters as follows: rated power Pe=, output speed , output torque T2=, gear ratio u=, working load factor k=. The worm is machined and heattreated 45 steel and the tooth corona of gear is made of machined ZQA1 94 A. Specifying objective function In order to economize nonferrous metal of tooth corona of worm gear, the objective function should be specified that the volume of tooth corona of worm gear in traction mechanism incline to minimum=. According to , d0, di2 and b are outer diameters, inner diameters and face width of tooth corona of worm gear respectively, thus the volume of tooth corona is。 where Therefore the objective function is where mmodule of gear。 d1reference diameter of gear。 z1number of start of worm. configure drawing of worm gear B. Selecting design variables According to equation of the objective function, Z1 ,m,d1should be selected as design variables, that is: 海量機械畢業(yè)設(shè)計，請聯(lián)系 Q99872184 33 C. Establishing fuzzy constraints Considering the random character of the value of design parameters and some factors whose value is very indefinite such as loading property and material quality, the fuzzy constraints are set up, including the property and boundary constraints. 1)Limit of number of start of worm: to power drive, z1=1~2。 2)Limit of module of gear:2≤ m≤ 8。 3)Limit of the lead angle γ of the worm for guaranteeing the efficiency of the worm gearing: 3≤γ≤ 8,tan γ=mz1/d1。 4)Constraint of contact strength of worm gear: Where Zethe material elasticity factor, σ hthe contact stresses of worm gear。 [σ h]the fuzzy value of the allowable contact stresses of worm gear. 5)Constraint of tooth beam strength of worm gear: Where σ f the beam stress of gear teeth。 [σ f]fuzzy value of the allowable bending stress of worm gear teeth。 Yf the profile factor for worm gear teeth. 6)Constraint of the stiffness of worm: The worm is supported between two bearings, if the worm shaft bends too much, that is, the teeth will not mesh properly, and the result will be excessive wear and early failure. So the maximum deflection is Where Ft1the tangential force of the worm(N), F r1the radial force of the worm(N), Ethe modulus of elasticity(Mpa), Ithe inertia moment of the dangerous crosssection of worm(mm4) Lthe distance of the worm bearings (mm), L=0 .9muz1. 海量機械畢業(yè)設(shè)計，請聯(lián)系 Q99872184 34 OPTIMIZATION MATHEMATICAL MODEL OF TRACTION MECHANISM The key of this method is how to decide the optimal level value. Several factors, such as factor class, factor fuzziness and the different influence of the factors on the different optimal level values, were considered and the method of secondclass prehensive evaluation was used based on the optimal level cut set, thus the optimal level value λ *of every fuzzy constraint can be attained, that is λ*= the fuzzy optimization problem is converted into the usual optimization problem. RELATION COEFFICIENT BY NEURAL NETWORKS Neural works are posed of simple element operating in parallel. These elements are inspired by biological nervous systems. As in nature, the work function is determined largely by the connections between elements. We can train a neural work to perform a particular function by adjusting the values of the connections (weights)between elements. Commonly neural works are adjusted, or trained, so that a particular input leads to a specific target output based on a parison of the output and the target, until the work output matches the target. Some points on relation curve between teeth number Z2 and the profile factor Yf of worm gear are selected as training sample data, the Fast Back Propagation are adopted to train feedforward works, the weights and biases of the work are updated. Then neural works is simulated by the function of N