Research on the Source Identification of Mine Water Inrush Based on LIF Technology and SIMCA Algorithm
YAN Peng-cheng1, ZHOU Meng-ran1*, LIU Qi-meng2, 3, ZHANG Kai-yuan1, HE Chen-yang1
1. College of Electrical and Information Engineering, Anhui University of Science and Technology, Huainan 232001, China 2. Anhui Provincial Key Lab of Geohazards Prevention and Environment Protection, Huainan 232001, China 3. College of Earth and Environment, Anhui University of Science and Technology, Huainan 232001, China
Abstract:Rapid source identification of mine water inrush is of great significance for early warning and prevention in mine water hazard. According to the problem that traditional chemical methods to identify source takes a long time, put forward a method for rapid source identification of mine water inrush with laser induced fluorescence (LIF) technology and soft independent modeling of class analogy (SIMCA) algorithm. Laser induced fluorescence technology has the characteristics of fast analysis, high sensitivity and so on. With the laser assisted, fluorescence spectrums can be collected real-time by the fluorescence spectrometer. According to the fluorescence spectrums, the type of water samples can be identified. If the database is completed, it takes a few seconds for coal mine water source identification, so it is of great significance for early warning and post-disaster relief in coal mine water disaster. The experiment uses 405 nm laser emission laser into the 5 kinds of water inrush samples and get 100 groups of fluorescence spectrum, and then put all fluorescence spectrums into preprocessing. Use 15 group spectrums of each water inrush samples, a total of 75 group spectrums, as the prediction set, the rest of 25 groups spectrums as the test set. Using principal component analysis (PCA) to modeling the 5 kinds of water samples respectively, and then classify the water samples with SIMCA on the basis of the PCA model. It was found that the fluorescence spectrum are obvious different of different water inrush samples. The fluorescence spectrums after preprocessing of Gaussian-Filter, under the condition of the principal component number is 2 and the significant level α=5%, the accuracy of prediction set and testing set are all 100% with the SIMCA to classify the water inrush samples.
Key words:Mine water inrush;Source identification;Laser induced fluorescence;Soft independent modeling of class analogy;Principal component analysis
闫鹏程1,周孟然1*,刘启蒙2, 3, 张开远1,何晨阳1 . LIF技术与SIMCA算法在煤矿突水水源识别中的研究 [J]. 光谱学与光谱分析, 2016, 36(01): 243-247.
YAN Peng-cheng1, ZHOU Meng-ran1*, LIU Qi-meng2, 3, ZHANG Kai-yuan1, HE Chen-yang1 . Research on the Source Identification of Mine Water Inrush Based on LIF Technology and SIMCA Algorithm . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(01): 243-247.