介紹了模擬人類皮膚結(jié)構(gòu)而設(shè)計(jì)的光纖智能皮膚觸覺(jué)傳感器,它輸出信號(hào)為多路和非線性的,采用傳統(tǒng)方法處理有一定的困難. 為此,利用了準(zhǔn)共路光路補(bǔ)償方法對(duì)信號(hào)進(jìn)行預(yù)處理,分析表明在一定程度上可以消除光源起伏和外界光路隨機(jī)微彎損耗以及溫度變化所帶來(lái)的干擾. 又采用人工神經(jīng)網(wǎng)絡(luò)對(duì)其進(jìn)行信號(hào)處理. 為了簡(jiǎn)化網(wǎng)絡(luò),探測(cè)面被劃分成9 個(gè)網(wǎng)格區(qū)域,并聯(lián)合使用了Kohonen 算法和BP 模型. 測(cè)試的結(jié)果表明,對(duì)施加在智能皮膚表面上任意一點(diǎn)上的外加壓力,可以分辨出外加壓力的大小和位置.
關(guān)　鍵　詞:光纖智能皮膚;人工神經(jīng)網(wǎng)絡(luò);觸覺(jué)傳感器
Abstract :An artificial neural network was used to process. The mult1idimensional and nonlinear output s of the sensor array. It’s difficult to process the signal in t raditional way. Pret reated by a quasi- syn-optical path compensating method , which eliminates the interferences resultign f rom fluctuating voltage and tempera2 ture. To simplify the network , skin was divided into nine sections ,and both kohonen arithmetic and BP model were used . Result s show that when an intelligent skin was pressed , the sensor can reliably estimate
teh magnitude of pressure value and it s position.
Key words :fiber-optical intelligent skin ; artificial neural network ; tactile sensor