Identification of Coalmine Water Inrush Source with PCA-BP Model Based on Laser-Induced Fluorescence Technology.

The water inrush should been rapidly and accurately identified during preventing coalmine water inrush. The laser induced fluorescent (LIF) spectrum technology provides a new method to identify water inrush with the characteristics of high sensitivity, quick and accurate monitoring. In order to identify water inrush, this paper introduces the spectrum technology of LIF to obtain water inrush fluorescence spectra data. The spectral preprocessing methods of Savitzky-Golay(SG) and Multiplicative Scatter Correction (MSC) have been used to eliminate noise spectra in collecting process. Principal component analysis (PCA) extracts feature information, for SG reprocessing data, when the number of principal component is 3, the cumulative contribution rate can reach 99.76 percent. This method has largely retained the information of original data. This paper chooses the classification model with 3 layers BP neural network, constructing by different training and testing sets. The classification model with SG preprocessing has achieved accurate identification, however, appeared few false identification for MSC and original data. The result shows that SG preprocessing is better than MSC. Research results show that the classification model with PCA and BP neural network can effectively identify coalmine water inrush, and have the strong self-organizing, self-learning ability.

[Research on the Source Identification of Mine Water Inrush Based on LIF Technology and SIMCA Algorithm].

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.

[Application of the Identification of Mine Water Inrush with LIF Spectrometry and KNN Algorithm Combined with PCA].

Rapid identification and classification of mine water inrush is important for flood prevention work underground. This paper proposed a method of KNN combined with PCA identification of water inrush in mine with the laser induced fluorescence spectrum with an immersion probe laser into water samples. The fluorescence spectra of 4 kinds of water samples were obtained. For each set of data preprocessing, the processed data in each sample from 15 sets of data as the training setwith a total of 60 groups. The other 20 groups were used as the prediction set. The data were processed by principal component analysis (PCA), and then the KNN algorithm was used to classify and identify the principal component analysis. During the experiment, the pretreatment method in the principal component number is 2 while the correct rate has reached 100% by KNN classification algorithm.

[Research on the Source Identification of Mine Water Inrush Based on LIF Technology and PLS-DA Algorithm].

Rapid source identification of mine water inrush has great significance for early warning and rescuing after the mine water inrush. Conventional method taking the concentration of ions as the discriminant factor takes such a long time that a method of rapid source identification of mine water inrush is in urgent need. This method is combined with Laser induced fluorescence (LIF) technology and Partial Least Squares-Discriminant Analysis (PLS-DA) algorithm. In the experiment, 405 nm laser was used to excite the water and 100 groups of fluorescence spectrum from 5 different aquifer of the mine were obtained. According to the spectra curve features, the data was compressed to obtain proper spectral data. 15 groups of spectrum of each water inrush samples were applied, with a total of 75 groups of spectrum as the prediction set while the rest of 25 groups of spectrum as the test set. To verify the experimental result, an experimental model was built with soft independent modeling of class analogy (SIMCA) to compare with PLS-DA. The result shows that the fluorescence spectra of different aquifer water samples is of great difference, without any pre-treatment, the PLS-DA algorithm based on the PLS model has higher modeling accuracy compared with SIMCA algorithm, which reaches to 100%, the validation results and the correlation of separation of variables are both more than 0.951, the RMSECV and RMSEP are both less than 0.123, using the model to identify the 5 water samples of test set, the accuracy are up to 100%.

[Method for retrieving pollution gas concentration from Raman lidar return].

Raman lidar is an important tool for the detection of atmosphere pollution, and inversion for lidar returns is an important process. The key for inversion is to get transmission exponential function exp [integral of 0 (R) [alpha(lambda1, z) - alpha(lambda2, z)]]. Three methods with extinction coefficient as the center are presented. First, 532 nm atmospheric extinction coefficient was used to indirectly obtain alpha(lambda1, z) and alpha(lambda2, z). This method has been used generally by people. Two new methods were proposed: 1, reference gas with approximate Raman wavelength is used so that alpha(lambda1, z) = alpha(lambda2, z). 2, Mie-Rayleigh scattered return with wavelength lambda1 or lambda2 is used to compute exp [integral of 0 (R) [alpha(lambda1, z) - alpha(lambda2, z)]].

[Study on characteristics of fluorescence spectra of dissolved organic matter with different water quality].

The fluorescence spectra of dissolved organic matter (DOM) in several types of water samples in combination with laser-induced fluorescence (LIF) measurements were measured in the laboratory, and the spectral characteristics of DOM were analysed. The curve of normalized fluorescence intensity against corresponding concentration of humic acid is showed. The results demonstrate the possibilities of water quality monitoring based upon fluorescence spectral characteristics of DOM by means of LIF method.