一種利用神經(jīng)網(wǎng)絡(luò)的故障模糊診斷系統(tǒng)
A NEURAL NETWORK BASED FAULT FUZZY DIAGNOSTIC SYSTEM
-
摘要: 本文提出一種神經(jīng)網(wǎng)絡(luò)與模糊邏輯相結(jié)合的故障診斷系統(tǒng),該系統(tǒng)包括2個(gè)方面:模糊推理模塊和規(guī)則學(xué)習(xí)模塊。模糊推理規(guī)則記憶在網(wǎng)絡(luò)的記憶層中,記憶節(jié)點(diǎn)的激活水平則反映了輸入矢量與已記憶規(guī)則的匹配程度;規(guī)則學(xué)習(xí)模塊通過(guò)自組織聚類(lèi)過(guò)程自動(dòng)生成規(guī)則。作為該診斷系統(tǒng)的一個(gè)應(yīng)用實(shí)例,模擬了旋轉(zhuǎn)主軸的故障診斷試驗(yàn)。Abstract: A fault fuzzy diagnostic system (FFDS) based on neural network and fuzzy logic hybrid is proposed. FFDS consists of two modes: a fuzzy inference mode and a rules learning mode. The fuzzy inference rules are stored in the memory layer. The excitation levels of the memory neurons reflect the matching degree between the input vector and the prototype rules. In the rules learning mode, the rules can be produced automatically through the cluster process. As a application case of this diagnostic system, the fault diagnosis experiment of the rotating axis is simulated.
-
Sorsa T, et al. IEEE Trans. on SMC, 1991, SMC-21(4): 815-825.[2]Peng Y, Reggia J A. IEEE Trans. on SMC, 1989,SMC-19(2): 285-298.[3]Buckley J J,et al. On the equivalence of neural networks and fuzzy expert system.Proc.In ter. Joint Conf. on NN Baltimore: 1992, 691-695.[4]Keller J M, Hunt,t D J. IEEE Trans. on PAMI, 1985, PAMI-7(6): 693-699.[5]應(yīng)行仁,曾南.自動(dòng)化學(xué)報(bào),1991,17(1): 63-67.[6]Kosko B. Neural network fuzzy systems. Englewood Cliffs, NJ: Preatice-Hall, 1991,327-334.[7]Kong S G, Kosko B. IEEE Trans. on NN, 1991, NN-2(1): 118-124. -
計(jì)量
- 文章訪問(wèn)數(shù): 2043
- HTML全文瀏覽量: 93
- PDF下載量: 360
- 被引次數(shù): 0
下載:
