Xiaowei Chen

Chemical Oxygen Demand (COD) is one of the indicators of organic pollution in water bodies. The rapid and accurate detection of COD is of great significance to environmental protection. To address the problem of COD retrieval errors in the absorption spectrum method for fluorescent organic matter solutions, a rapid synchronous COD retrieval method for the absorption–fluorescence spectrum is proposed. Based on a one-dimensional convolutional neural network and 2D Gabor transform, an absorption–fluorescence spectrum fusion neural network algorithm is developed to improve the accuracy of water COD retrieval. Results show that the RRMSEP of the absorption–fluorescence COD retrieval method is 0.32% in amino acid aqueous solution, which is 84% lower than that of the single absorption spectrum method. The accuracy of COD retrieval is 98%, which is 15.3% higher than that of the single absorption spectrum method. The test results on the actual sampled water spectral dataset demonstrate that the fusion network outperformed the absorption spectrum CNN network in measuring COD accuracy, with the RRMSEP improving from 5.09% to 1.15%.

Spectrometric quantification of nitrate and COD in water under random turbidity interference using an interpolation dataset augmentation method and one-dimensional convolutional neural network.

Ultraviolet-visible absorption spectroscopy is widely used to monitor water quality, and rapid optical signal detection is a key technology in the process of spectrum measurement. In this paper, an ultrafast spectrophotometer system that can achieve spectrum data acquisition in a single flash of the xenon lamp (within 200 ns) is introduced, and a real-time denoising method for the spectrum is implemented on a field programmable gate array (FPGA) to work cooperatively with the nanosecond spectrum acquisition system, in order to guarantee the quality of the spectrum signals without losing running speed. The hardware of the data acquisition and processing system are constructed on a Xilinx Spartan 6 FPGA chip and its peripheral circuit, including an analog to digital converter and a complementary metal-oxide-semiconductor transistor (CMOS) sensor’s diver circuit. An oversampling method that is suitable for the CMOS sensor’s output is proposed, which works on the CMOS sensor’s dark current noise and readout noise. Another moving-average filter method is designed adaptively, which works on the low-frequency component to filter out the residual spectrum noise of the spectrum signal. The implementation of the filter on the FPGA has been optimized by using a pipelined structure and dual high-speed random-access memory (RAM). As a result, the CMOS linear image sensor successfully captured the spectrum of xenon flash light at the readout clock frequency of 500 kHz and the processing manipulation to the full UV-Vis spectrum data was accomplished at a sub-microsecond speed performance. After the digital filter and oversampling technology were implemented, the coefficient of variation of the measurements reduced from 9.57% to 1.74%, while the signal noise ratio (SNR) of the absorption spectrum increased nine times, compared to the raw data of the CMOS sensor’s output. The tests towards different analyte samples were conducted, and the system shows good performance on distinguishing different concentrations of different analyte solutions on both ultra-violet and visible spectrum bands. The present work showcases the potential of the CMOS sensor’s technique for the fast detection of contaminated water containing nitrate and organic compounds.

Recent years, research on the detection of heavy metals in Traditional Chinese Medicine (TCM) by laser induced breakdown spectroscopy (LIBS) have gradually increased. Current main methods of establishing calibration curve are based on grounding and pelleting of the tested samples. Although compared to digested samples, grounding and pelleting of the sample is already quite simple, it cannot fully reflect the advantages of LIBS: rapid analysis, and, also, the uneven distribution of heavy metals in the TCM is ignored. In order to avoid grinding and pelleting sample to be tested, and to achieve microdamage quantitative analysis by LIBS, this article presents a new method for establishing calibration curve. The experiment in this paper based on a study with Cd and Pb in leaves of laurel. The preparation of calibration samples and the establishment of calibration methods for microdamage quantitative analysis were presented, which proved the feasibility of microdamage quantitative analysis by LIBS. The square of the linear relationship coefficient R of Pb was higher than 0.82. This method provides a guiding method for the rapid quantitative analysis of heavy metals in TCM by LIBS.

The establishment and development of a set of methods of oil accurate recognition in a different environment are of great significance to the effective management of oil spill pollution. In this work, the concentration-emission matrix (CEM) is formed by introducing the concentration dimension. The principal component analysis (PCA) is applied to extract the spectral feature. The classification methods, such as Probabilistic Neural Networks (PNNs) and Genic Algorithm optimization Support Vector Machine (SVM) parameters (GA-SVM), are used for oil identification and the recognition accuracies of the two classification methods are compared. The results show that the GA-SVM combined with PCA has the highest recognition accuracy for different oils. The proposed approach has great potential in rapid and accurate oil source identification.

Developing fast and accurate fluorescence detection technology of oil spill is significant for quantitative analysis in unexpected oil spill events. As the oil sample concentration increases, the fluorescence spectrum produces red-shift behavior, which seriously affects the quantitative detection of concentration. In this work, a three-dimensional concentration-emission matrix (CEM) was constructed by using a series of emission spectra with different levels of concentration at the excitation wavelength of 266 nm. The database is the interpolated CEM of six samples using bicubic interpolation in the concentration dimension. With matrix similarity matching, the database was used to achieve quantification of the concentration of oil samples. The recovery rates of prediction for test samples and weathering samples of six oil samples were between 86.8% and 116.11%, with relative errors of predictions ranging from 2.09% to 15.2%. The results show that this method can provide accurate quantitative determination of the concentration of different oil samples.

A new method for load forecasting based on LS-SVM, PSO and wavelet transform is proposed. The wavelet transform is adopted to decompose the historical data, so the approximate part and several detail parts are obtained. The results of wavelet transform are predicted by a separate LS-SVM predictor. PSO is employed to determine these parameters of SVM model. The novel forecast model integrates the advantage of WT, PSO and LS-SVM. Compared with other predictors, this forecast model has greater generality ability and higher accuracy.