Point to the limitation of existing method , the neural computation method of finite element of elasticity - plastic mechanics was studied on the base of variational principle of the second order minimal potential energy in plastic theory . the neural network solving method of elasticity - plastic mechanics based on variational principle of the second order minimal potential energy was presented , and the neural network computation model of finite element of plastic mechanics was given 針對(duì)已有方法的局限性,以塑性理論中的二階段最小勢(shì)能變分原理為基礎(chǔ),對(duì)彈塑性力學(xué)問題的神經(jīng)網(wǎng)絡(luò)有限元計(jì)算方法進(jìn)行了研究,提出了基于二階段最小勢(shì)能變分原理的彈塑性力學(xué)問題的神經(jīng)網(wǎng)絡(luò)求解方法,建立了塑性力學(xué)問題的有限元神經(jīng)網(wǎng)絡(luò)計(jì)算模型。
Evolutionary computation , neural computation and dna molecular biology technique are respectively corresponding to three different levels which are organism , nerve cell and molecular in the process of simulating brainpower . so we can see that the last method that base on simulating and studying on dna of biology is more probably to show up the essence of formation of brainpower 從遺傳進(jìn)化、人工神經(jīng)網(wǎng)絡(luò)和dna分子生物技術(shù)對(duì)智能的模擬過程看,它們分別對(duì)應(yīng)生物群體、生物神經(jīng)元和生物分子三個(gè)截然不同的層次,由此可以看到,基于對(duì)分子生物dna的模擬和研究將有可能更深刻地揭示智能形成的本質(zhì)。
Point to above problems , under the financial support of the national natural science foundation ( exploration of high tech and new concept and new conceive ) , the excellent young teachers program of ministry of education and national excellent doctoral dissertation special foundation , the static and dynamic real - time computation of elasticity - plastic mechanics , solving method of fuzzy finite element and other problems were studied in this paper . and some achievement was gained as following : ( 1 ) based on the positive definiteness of system stiffness matrix of finite element that was modified and the form of potential energy function of elastic body , the linear system of saturation mode ( lssm ) was introduced into the neural computation of finite element , by which the no - error solving of finite element neural net computation was realized in theory 針對(duì)上述問題,在國(guó)家自然科學(xué)基金(高技術(shù)新概念新構(gòu)思探索) 、教育部?jī)?yōu)秀青年教師資助計(jì)劃、高等學(xué)校全國(guó)100篇優(yōu)秀博士學(xué)位論文作者專項(xiàng)基金等的資助下,本文對(duì)彈塑性力學(xué)問題的動(dòng)靜態(tài)的實(shí)時(shí)計(jì)算、模糊有限元的求解方法等問題進(jìn)行了系統(tǒng)和深入的研究,取得了以下成果: ( 1 )根據(jù)有限元總剛矩陣經(jīng)修正后具有正定性的特點(diǎn)以及彈性體勢(shì)能函數(shù)的具體形式,將飽和模式的線性系統(tǒng)(簡(jiǎn)稱為lssm系統(tǒng))引入到有限元的神經(jīng)網(wǎng)絡(luò)計(jì)算中,在理論上實(shí)現(xiàn)了有限元神經(jīng)網(wǎng)絡(luò)計(jì)算的無誤差求解。
Many models , such as back propagation ( bp ) , hopfield , art , have been developed and sometimes several models have to be combined to accomplish a task . to relieve the burden of implementing those models from scratch , we developed a neural computation platform ( ncp ) containing those facilities 正是因?yàn)樵絹碓蕉嗟膽?yīng)用需要神經(jīng)網(wǎng)絡(luò)的支持,我們著手開發(fā)一個(gè)神經(jīng)計(jì)算平臺(tái),該平臺(tái)實(shí)現(xiàn)多種神經(jīng)網(wǎng)絡(luò)模型,例如bp模型、 hopfield模型、 boltzmann機(jī)模型、 art模型、 bam模型、遺傳算法等等。
Neural Computation is a peer-reviewed academic journal covering aspects of neural computation. Articles highlight problems and techniques in modeling the brain, and in the design and construction of neurally-inspired information processing systems.