基于徑向基網(wǎng)絡的鋼板表面缺陷檢測算法研究



摘  要

作為鋼鐵工業(yè)的主要產(chǎn)品形式之一, 鋼板已經(jīng)成為汽車、機械制造、化工、航空航天和造船等工業(yè)不可缺少的原材料, 因此其表面質(zhì)量的優(yōu)劣將直接影響這些產(chǎn)品的最終性能和質(zhì)量。在鋼板制造過程中, 由于連鑄鋼坯、軋制設備、加工工藝等多方面的原因, 導致鋼板表面出現(xiàn)裂紋、氧化皮、結(jié)疤、輥印、刮傷、空洞、針眼、折疊、表面分層等不同類型的表面缺陷, 這些缺陷不僅影響產(chǎn)品的外觀, 更嚴重地降低了產(chǎn)品的抗腐蝕性、耐磨性和疲勞強度等性能。

神經(jīng)網(wǎng)絡理論作為一門新興學科, 近年來被廣泛應用于鋼板的表面缺陷檢測中, 但大部分都是基于BP 神經(jīng)網(wǎng)絡進行識別的, BP 網(wǎng)絡的缺點是對于干擾量非常敏感、隱含層節(jié)點數(shù)需要經(jīng)過多次嘗試、學習速度慢且易陷入局部極小點。

本文使用RBF 神經(jīng)網(wǎng)絡( RBFNN)對鋼板缺陷數(shù)據(jù)集進行計算機仿真,將缺陷識別結(jié)果與期望結(jié)果進行對比。 由于其結(jié)構(gòu)簡單,每個隱含層節(jié)點映射函數(shù)是不同的非線性函數(shù),所以可以保證快速的學習速度, 并且是全局最優(yōu)。

關(guān)鍵詞：徑向基函數(shù)（RBF）；人工神經(jīng)網(wǎng)絡；鋼板表面缺陷；缺陷識別

 


 


 


 


 


 




Abstract

As one of the major forms of production in steel industry，steel sheet has now become a kind of indispensable material for many industries like automobile，mechanical ma nufacturing，chemistry，aviation，astr0navigation，ship building，etc．Its surface quality affects the final production’S perform ance and quality. In steel manufacturing process, because continuous casting billet, rolling equipment, processing technology and so on various causes, the steel plate surface occurrence crackle, descaling, scarring and roller and scratches, hollow, needle, folding, surface layer etc of different types of surface flaws that not only affect the product's appearance, the more severely reduced products corrosion resistance, abrasion resistance and fatigue strength of performance.

Neural network theory, as a new subject, widely used in recent years in the steel sheet surface defects detection, but mostly based on BP neural network to identify, BP network drawback is for interference quantity quite sensitive, hidden nodes several need after many attempts, the slow learning speed and easy into the local minimum points.

The paper uses RBF neural network (RBFNN) to recognize the fault dataset of iron sheets using computer simulations. The recognized results are compared with the expected outputs. Due to its simple structure, a variety of mapping functions, and rapid learning speed, RBFNN can achieve a global optimization.


Keywords: Radial Basis Function (RBF); Artificial Neural Network; Surface Defect; Defect Recognition


 


 




目  錄

第一章 緒 論 1

1.1  課題的研究目的 1

1.2  課題研究的意義 1

1.3  課題研究的內(nèi)容與方法 2

第二章 模式識別技術(shù)與人工神經(jīng)網(wǎng)絡介紹 4

2.1  模式識別技術(shù) 4

2.1.1  模式識別的基本概念 4

2.1.2  識別對象的特征及其提取 4

2.1.3  模式識別分類 5

2.2  人工神經(jīng)網(wǎng)絡簡介 6

2.2.1  人工神經(jīng)網(wǎng)絡模型 6

2.2.2  人工神經(jīng)網(wǎng)絡發(fā)展史 7

2.2.3  人工神經(jīng)網(wǎng)絡的分類及學習規(guī)則 8

2.2.4  人工神經(jīng)網(wǎng)絡的應用 12

第三章 基于徑向基網(wǎng)絡的鋼板表面缺陷檢測仿真實現(xiàn) 14

3.1  徑向基網(wǎng)絡基本介紹 14

3.1.1  徑向基網(wǎng)絡模型 14

3.1.2  徑向基網(wǎng)絡的結(jié)構(gòu)與特點 15

3.2  MATLAB神經(jīng)網(wǎng)絡工具箱簡介 17

3.3  基于徑向基網(wǎng)絡的鋼板表面缺陷檢測仿真實現(xiàn) 18

3.3.1  鋼板表面缺陷檢測過程設計 18

3.3.2 仿真結(jié)果分析 27

結(jié)論 29

參考文獻 30

致  謝 31

附  錄 32

1.程序矩陣 32

2．程序清單 34

3．實驗流圖 36