Application on Automatic Chemical Detection Technique Based on NN

Abstract:

Take example for the Neural Networks Distinguishing Chemical Agents (NNDCA) model, the study and application about the multi-sensors information fusion (MSIF) technology is researched, the model of Naval Ships Chemical Detection (NSCD) system based on multi-sensors fusion is built, the basic method of the NNDCA is analyzed, and the realization idea of the NNDCA model is put forward. For fastness and accuracy and automation, connecting the wavelet analysis with the neural networks organically, the model of the NNDCA by the returning neural networks with deviation unit and the method of the feature extraction for the chemical agents based on the wavelet analysis are established. After analyzing and discussing the results a conclusion is drawn that it is a kind of valid method to realize the automation and intelligence of distinguishing chemical agents using the neural networks combined with the multi-sensors.

• Periodical: Advanced Materials Research (Volumes 108-111)
• Pages: 1515-1520
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.108-111.1515
• Online since: May 2010
• Authors: Ming Hu Zhang, Hui Chuan Wang, Shi Jun Lv, De Hu Wang, Jian Song
• Keywords: Automatic Detection, Feature Extraction, Model Realization Thought, Neural Network Distinguishing Chemical Agents (NNDCA) Model, Wavelet Analysis

References

[1] Zhu Y M, Li X R. Unified fusion rules in the multi-sensor multi-hypothesis network decision systems. IEEE Transactions on Systems, Man and Cybernetics, Part A, 2003, 33(4): 502～513.

DOI: 10.1109/tsmca.2003.809211

[2] Zhu Y M, Song E B, Zhou J, et al Optimal dimensionality reduction of sensor data in multi-sensor estimation fusion. IEEE Transactions on Signal Processing, 2005, 53(5): 1631～1639.

DOI: 10.1109/tsp.2005.845429

[3] Song Sh P, Que P W, Zhang W Y. Design of Line-focusing Ultrasonic Transducer Array Used for Flaw Detection in Seabed Pipelines. Chinese Journal of Scientific Instrument, 2006, 27(5): 547 ～550. (in Chinese).

[4] Sun S L. Distributed optimal component fusion weighted by scalars for fixed-lag Kalman smoother. Automatica, 2005, 41(12): 2153～2159.

DOI: 10.1016/j.automatica.2005.06.014

[5] Ghasem Mirjalily. Blind Adaptive Decision Fusion for Distributed Detection. IEEE Transactions on Aerospace and Electronic Systems, 2003, 39(1): 34～51.

DOI: 10.1109/taes.2003.1188892

[6] Han Ch Zh, Zhu H Y. Multi-sensor information fusion and automation. Acta Automaticsa Sinica, 2002, (28): 117～124. (in Chinese).

[7] Liu Y, Gao X G, Lu G Sh, et al. Weighted Attribute Information Fusion Based on OWA Aggregation Operator. Chinese Journal of Scientific Instrument, 2006, 27(3): 322～325. (in Chinese).

[8] Zhang M H, Ding Zh H, Bai Y. Study on multi-sensor fusion technology in naval ships chemical detection system. Chinese Journal of Scientific Instrument, 2006, 27(12 Supp. ): 119～123. (in Chinese).

[9] Luo Z Q. Universal decentralized estimation in a bandwidth constrained sensor network. IEEE Transactions on Information Theory, 2005, 51(6): 2210～2219.

DOI: 10.1109/tit.2005.847692

[10] Feng Zh Q, Yang Y H. Fusion recognition of dot target multi-spectrum data based on ANN. Optics and Precision Engineering, 2003, 11(4): 412～415. (in Chinese).

[11] Wang L G, Zhang L H, Kang J L. Study on the neural networks for distinguishing chemical agents based on the wavelet analysis. Transactions of Beijing Institute of Technology, 2006, 26(2): 120～124. (in Chinese).

[12] Zhang M H, Pang G C, Liu H, et al. Chemical agent identification technology for naval ships chemical detection. Journal of Guangxi Normal University: Natural Science Edition, 2008, 26(1): 220～223. (in Chinese).