This paper analyzes the current state of water quality detection equipment and, based on the demand for portable water quality detection systems that are on-site, rapid, accurate, cost-effective, and capable of multi-parameter measurements using spectral analysis, represents the future development direction of water quality detection. By focusing on indicators of heavy metal ion water pollution, this study aims to achieve the “rapid and accurate detection of water quality using spectral analysis” and emphasizes key technologies such as “visible absorption spectroscopy in photoelectric detection technology and spectral analysis”, “spectral denoising methods”, and “Convolutional Neural Network (CNN) modeling and deployment”. A novel combined denoising method integrating Ensemble Empirical Mode Decomposition (EEMD) and Singular Value Decomposition (SVD) is developed and applied for the first time in spectral water quality detection to improve accuracy. The system uses a ZYNQ-based spectral analysis platform to detect heavy metal ion concentrations, enhancing detection speed. Comparative tests with copper ion standard solutions against Chinese national standards show good accuracy and reproducibility. The developed EEMD-SVD method demonstrates superior denoising effectiveness in processing actual spectral data within the water quality detection system.
Combined with photoelectric detection technology and UV-Vis absorption spectroscopy in spectral analysis technology, a multi-parameter portable surface water quality detection system is developed, which can quickly detect phosphate, nitrite, and chemical oxygen demand (COD) and ammonia nitrogen water quality parameters on site. For the substances in the water body that absorb the characteristic wavelengths in the visible part, a camera is used to collect the visible spectrum, and the grayscale image of the visible spectrum image is modeled by a convolutional neural network. The concentration value of substances whose absorption characteristic wavelength is in the ultraviolet band is measured by photoelectric detection technology. The established convolutional neural network model is transplanted into ZYNQ, combined with ultraviolet photoelectric sensor, the concentration value of the detected substance is displayed on the LCD, so as to realize the economy, portability, real-time and rapidity of the water quality detector. Research indicates: The prediction value of convolutional neural network is obtained as the tendency value of sample solution in 8 output types of concentration value, the highest accuracy is 100%, and the lowest is 40%. The highest error of COD concentration value is 10%, which proves that the detection system has practical value with low noise and high precision.