With the rapid growth of researches toward computer vision and pattern recognition, methods that based on convolutional neural network (CNN) have shown unique advantages on handwritten characters recognition, also provided impressive results. This paper proposes a model based on CNN to deal with matters of handwritten Chinese character recognition. Different with conventional recognition system, in this model, input images are preprocessed by median filtering to smooth and reduce noise. For testing the stability and performance of the model, two testes are managed respectively. In integral test, experimental results show that the accuracy rate of recognition approach to 90.91% after 5000 times training, mean square error is decreased to 0.0079 at last. Meanwhile, this system also has a good performance at real-time test.

Excessive levels of Pb²⁺ and Cd²⁺ in seawater pose significant combined toxicity to marine organisms, resulting in harmful effects and further threatening human health through biomagnification in the food chain. Traditional methods for detecting marine Pb²⁺ and Cd²⁺ rely on laboratory analyses, which are hindered by limitations such as sample degradation during transport and complex operational procedures. In this study, we present an electrochemical sensor based on intelligent mobile detection devices. By combining G-COOH-MWCNTs/ZnO with differential pulse voltammetry, the sensor enables the efficient, simultaneous detection of Pb²⁺ and Cd²⁺ in seawater. The G-COOH-MWCNTs/ZnO composite film is prepared via drop-coating and is applied to a glassy carbon electrode. The film is characterized using cyclic voltammetry, electrochemical impedance spectroscopy, and scanning electron microscopy, while Pb²⁺ and Cd²⁺ are quantified using differential pulse voltammetry. Using a 0.1 mol/L sodium acetate buffer (pH 5.5), a deposition potential of −1.1 V, and an accumulation time of 300 s, a strong linear correlation was observed between the peak response currents of Pb²⁺ and Cd²⁺ and their concentrations in the range of 25–450 µg/L. The detection limits were 0.535 µg/L for Pb²⁺ and 0.354 µg/L for Cd²⁺. The sensor was applied for the analysis of seawater samples from Maowei Sea, achieving recovery rates for Pb²⁺ ranging from 97.7% to 103%, and for Cd²⁺ from 97% to 106.1%. These results demonstrate that the sensor exhibits high sensitivity and stability, offering a reliable solution for the on-site monitoring of heavy metal contamination in marine environments.

Copper is an essential element in living organisms and is crucial in marine ecosystems. However, excessive concentrations can lead to seawater pollution and pose a risk of toxicity to marine organisms, as it is a heavy metal. In addition, it can enter the human body through the food chain, potentially endangering human health. Consequently, there is increasing focus on the rapid and highly sensitive detection of copper ions (Cu²⁺). We prepared a graphite carbon electrode modified with graphitised multi-walled carbon nanotubes/copper(II) ion carrier IV (GMWCNT/copper(II) ion carrier IV/glassy carbon electrode (GCE)) using a drop-coating method. Scanning electron microscopy (SEM) analysis revealed that the composite material film possessed a large surface area. Incorporating this composite material significantly enhanced the adsorption capacity for ions on the electrode surface and greatly improved conductivity. Differential pulse anodic stripping voltammetry (DPASV) was employed to quantify copper levels in seawater. Under optimal experimental conditions, a strong linear relationship was observed between the Cu²⁺ response peak current and its concentration within a range of 50–500 µg L⁻¹, with a correlation coefficient of 0.996. The GMWCNT/copper(II) ion carrier IV/GCE exhibited excellent stability and reproducibility, achieving a low detection limit for Cu²⁺ at 0.74 µg L⁻¹ when applied to copper detection in seawater. Furthermore, spiked recovery rates ranging from 98.6% to 102.8% demonstrated the method’s high sensitivity, convenient operation, and practical value for real-world applications in detecting Cu²⁺ levels in seawater.

Phenanthrene (PHE), as a structurally simple, tricyclic, polycyclic aromatic hydrocarbon (PAHs), is widely present in marine environments and organisms, with serious ecological and health impacts. It is crucial to study fast and simple high-sensitivity detection methods for phenanthrene in seawater for the environment and the human body. In this paper, a immunosensor was prepared by using a multi-wall carbon nanotube (MWCNTs)-chitosan oligosaccharide (COS) nanocomposite membrane loaded with phenanthrene antibody. The principle was based on the antibody–antigen reaction in the immune reaction, using the strong electron transfer ability of multi-walled carbon nanotubes, coupled with chitosan oligosaccharides with an excellent film formation and biocompatibility, to amplify the detection signal. The content of the phenanthrene in seawater was studied via differential pulse voltammetry (DPV) using a potassium ferricyanide system as a redox probe. The antibody concentration, pH value, and probe concentration were optimized. Under the optimal experimental conditions, the response peak current of the phenanthrene was inversely proportional to the concentration of phenanthrene, in the range from 0.5 ng·mL⁻¹ to 80 ng·mL⁻¹, and the detection limit was 0.30 ng·mL⁻¹. The immune sensor was successfully applied to the detection of phenanthrene in marine water, with a recovery rate of 96.1~101.5%, and provided a stable, sensitive, and accurate method for the real-time monitoring of marine environments.

Hg(II), as an extremely hazardous heavy metal contaminant in the environment, poses a significant potential hazard to human health and ecosystems. A GR-MWCNTs-COOH/CeO₂/Nafion composite film-modified glassy carbon electrode was prepared using the drop-casting method in this study. The GR-MWCNTs-COOH/CeO₂/Nafion/GCE was electrochemically investigated through cyclic voltammetry (CV) and differential pulse stripping voltammetry (DPSV). Additionally, the surface morphologies of the composite film were evaluated using scanning electron microscopy (SEM). The conditions, such as buffer solution, pH, deposition potential, deposition time, modified film thickness, and Nafion content, were optimized. Under optimal experimental conditions, a good linear relationship between the peak current response of Hg(II) and its concentration in the range of 5–100 μg·L⁻¹ was observed, with a detection limit of 0.389 μg·L⁻¹. When it was used to detect Hg(II) in offshore seawater, the recovery rate ranged from 94.72% to 103.8%, with RSDs ≤ 5.79%.

Cavitation is typically observed when high-pressure submerged water jets are used. A composite nozzle, based on an organ pipe, can increase shear stress on the incoming flow, significantly enhancing cavitation performance by stacking Helmholtz cavities in series. In the present work, the flow field of the composite nozzle was numerically simulated using Large Eddy Simulation and was paired with the response surface method for global optimizing the crucial parameters of the composite nozzle to examine their effect on cavitation behavior. Utilizing peak gas-phase volume percent as the dependent variable and the runner diameter, Helmholtz chamber diameter, and Helmholtz chamber length as independent variables, a mathematical model was constructed to determine the ideal parameters of the composite nozzle through response surface methodology. The optimized nozzle prediction had an error of only 2.04% compared to the simulation results, confirming the accuracy of the model. To learn more about the cavitation cloud properties, an experimental setup for high-pressure cavitation jets was also constructed. Impact force measurements and high-speed photography tests were among the experiments conducted. The simulated evolution period of cavitation cloud characteristics is highly consistent with the experimental period. In the impact force measurement experiment, the simulated impact force oscillates between 256 and 297 N, and the measured impact force oscillates between 260 N and 289 N, with an error between 1.5% and 2.7%. The simulation model was verified by experimental results. This study provides new insights for the development of cavitation jet nozzle design theory.