基于隐马尔可夫模型的氧乙炔火焰燃烧状态识别研究

资源描述

《基于隐马尔可夫模型的氧乙炔火焰燃烧状态识别研究》由会员分享，可在线阅读，更多相关《基于隐马尔可夫模型的氧乙炔火焰燃烧状态识别研究（59页珍藏版）》请在金锄头文库上搜索。

1、河北大学硕士学位论文基于隐马尔可夫模型的氧乙炔火焰燃烧状态识别研究姓名：高秀艳申请学位级别：硕士专业：电路与系统指导教师：张欣 20100601 ? I ? ? !#?$% ?AB56789: C?DEFGHI?JKLMNOP?QRS(TUVWXYZ? ?_3a?bc?QRd5e;efghi$j(OPkVWXYZ?bc ?lmnop/0qrsOPa?QRtuvwUxJ?y(%OPk ?QRSdtz%OPUn8?op(YZ|? ?(kYZ|?x=YZ|?bc?OPk ?QRop?=?q?(VWXYZ?An? 3kAn?v?r?y?/?(HMM)ka?op /0? qr?(I?( IO

3、 important factor related to production efficiency, safety and environment protection in the production process. The combustion performance indicators can be measured using special equipment, but with the increasing of the types of measuring equipments,the cost increased, and it is not easy to reali

4、ze automation. For the oxyacetylene flame is widely used in the industrial production, the automatic monitoring of its combustion states is played more and more attention. If the combustion states of the oxyacetylene can be identified by computer, it would make the auto-control of the combustion pro

5、cess better and the productivity improved. It is needed to realize the classification and identification of the combustion process based on the machine in order to realize auto-monitoring of combustion process. Flame images are the most direct reflection of combustion. First pretreatment is done on

6、flame images, and parameters that represent combustion states are picked up, and then auto-identification is realized, and better effects can be gotten. The combustion process of the oxyacetylene flame is a random one, it obtains good result using the Hidden Markov Model(HMM) which has good imitatio

7、n ability on the random process. This study is done in this paper. In this study, CCD camera is used as optical sensor, and the oxyacetylene flame images and image sequences gotten from CCD are used as monitoring values. In the pretreatment process of the images, the advantages and disadvantages of

8、traditional methods of filter and segment are analyzed, and AVMF and a new way which segment images in the RGB color channels are proposed, then characteristic parameters that can reflect the characteristics of the oxyacetylene flame images most are picked up. During the study, Artificial Neural Net

9、work (ANN),1-d HMM with single characteristic vector and 2-d HMM are used to train the model of the combustion process of oxyacetylene flame, and the identification accuracy and computation speed are analyzed. Based on the conclusion above, a new technique called 1-d and multi-step HMM was proposed

10、to build HMM of the combustion process of oxyacetylene flame, and the characteristic sequences of the images are used as the training data instead of the images. For the image sequences to be identified, their combustion state sequences can be obtained using viterbi algorithm after picking up the ch

11、aracteristic parameter vectors, so the combustion process of oxyacetylene can be classified and identified. The experiment under MATLAB6.5 proves thataccording to Abstract III the characteristics of the oxyacetylene flame image, adopting 1-d and multi-step classification method can cut down time, im

12、prove the real-time and the identifying accuracy. Key words Oxyacetylene Flame; Image Process; Recognition; HMM; MATLAB 1 1 ? 1 ? 1.1? w3?#?$?%?A B56789:C?DE?FGHI?J?KLMNOP?5?tu?QR S( ?YZ?6?Ry?S?78,9:9;,J?v$ %sA(?bc?rB?C?D?ER?F?(?G)?= H?IG?P?EYZ?5 ? ? (JKLk?#YZd5?M% ?N?.?,OLk?$YZd5? ?3?v ? ? ? ?( ,G?

13、v?YZ9:?3? ?G?fv?3?( ? ?U?*C?T R? ?G ?B?*?H ?1fU?1?S) R?G?B ?=fl ? 0?1 ? k?k?fl ?)? RRGB ?1K| 2.1 i( 2 “fi fl 5 2.1RGB ?3 HSI ?3?Hue ?Saturation ? Chroma?Intensity ? Brightness;?(?UK?O?I ?6?|p?cd? ?O?H ? S ?6?g?(? ?|p?m?“3)C?HSI ?K| 2.2 i? ka? Ma H ?fl k)?6? R ?a S fl ? )?6?HFfe?e?a I fl ?1?U? ?v?R;56?(?v?;eEe?G?veEe?( ?/0?k?0,1? R?G?B fl ak? HSI ? ? H?S?I ?6/T? )( 3 1 BGRI+=? ! ),min( )( 3 1BGR BGR S + =? ? 2.2HSI ? H DEF? 6 + + = 212 )()( 2)()( arccos BGBRGR BRGR H? # 2.3?)* !|?Na? Q.fqr?k|?x=q? |?k|?%? , ;?|? ?Kk?ABCD?N|E?N“fv?( ? TU?fl ?Ln%|?l?i0OF?m?H“f( 0?|fJ?fl ?m/?K? ?G?“3?$vH?

展开阅读全文