Search

Food safety is closely related to human health. Therefore, named entity recognition technology is used to extract named entities related to food safety, and building a regulatory knowledge graph in the field of food safety can help relevant authorities to regulate food safety issues and mitigate the hazards caused by food safety problems. However, there is no publicly available named entity recognition dataset in the food safety domain. In contrast, the non-standardized Chinese short texts generated from user comments on the web contain rich implicit information that can help identify named entities in specific domains (e.g., food safety domain) where the corpus is scarce. Therefore, in this paper, named entities related to food safety are extracted from these unstandardized texts on the web. However, the existing Chinese named entity identification methods are mainly for standardized texts. Meanwhile, these unstandardized texts have the following problems: (1) their corpus size is small; (2) there are various new and wrong words and noise; (3) and they do not follow strict syntactic rules. These problems make the recognition of Chinese named entities for online texts more challenging. Therefore, this paper proposes the ERNIE-Adv-BiLSTM-Att-CRF model to improve the recognition of food safety domain entities in unstandardized texts. Specifically, adversarial training is added to the model training as a regularization method to alleviate the influence of noise on the model, while self-attention is added to the BiLSTM-CRF model to capture features that significant impact entity classification and improve the accuracy of entity classification. This paper conducts experiments on the public dataset Weibo NER and the self-built food domain dataset Food. The experimental results show that our model achieves a SOTA performance of 72.64% and a good performance of 69.68% for F1 values on the public and self-built datasets, respectively. The validity and reasonableness of our model are verified. In addition, the paper further analyses the impact of various components and settings on the model. The study has practical implications in the field of food safety.

Deep-water fish cage floating collar also referred to as float, bears a load in the form of waves, fishing nets, and moorings, in which the longitudinal wave force is the main type of loading. The long-term continuous effects caused by wave force could cause reduction in strength, or vibration failure in the floating collar. In this study, the peak responses of a single-point mooring (SPM) cage floating collar, due to either static or vibration loadings, were calculated by the finite element method (FEM) based on an elastic model. In this model, the float exhibited macro-plastic deformation when the stress of 26.1 MPa, generated under 100 kN load, was greater than the yield limit (25 MPa). With the increase in order modes from 1 to 18 (1.2–7.9 Hz), the stress increased. Moreover, the harmonic stress corresponding to 8 and 0.1 Hz was clearly higher than that for 0 Hz under 100 kN loads, due to structural resonance. The range of stress values due to the random vibration was 16.0–63.7 MPa, when the angular velocities (k) were in the range of 0.01–16 rad s―1. Moreover, the transient response (34.4 MPa) was maximum when the angular velocity was 10 rad s―1 (range 1–100 rad s―1). The reliability rate of the entire body was 53.1% and 97.0% after 108 loading cycles for 100 kN and 10 kN loads, respectively. Furthermore, the fatigue modes of the key components were determined from the outer triangular tops and inner hexagonal intersections. In short, static analysis, vibration analysis, and fatigue analysis of FEM could be used as reliable ways to evaluate structural strength and failure for floating system. Finally, the floating parts could be strengthened with partially double pipes or optimized by increasing the stiffness, and appropriate damping could be widely used.

During the pneumatic conveying process of automatic feeding systems for deep-water off-shore cage culture, blockages of the pipeline and damage to feed pellets can easily occur. To solve these issues, a numerical simulation of the gas-solid two-phase flow of feed pellets in a pipeline was carried out. Based on gas-solid two-phase flow theory, both a computational fluid dynamics (CFD) model and discrete element model were established. Furthermore, solutions of a coupled CFD-DEM simulation were used to analyze the motion of feed pellets within the pneumatic conveying pipeline and changes in the distribution of pellets at various locations from the initial state to steady-state motion were determined. The pressure in the pipeline at different positions is analyzed and compared, and the pressure drop from the inlet of the pipeline to the stable state of particle movement is obtained. The simulation results provide an important basis for the clogging damage mechanism of feed particles and the optimal design of feeding system equipment.

Due to superior corrosion and rust resistance performance, copper alloy aquaculture netting structures are popular in the aquaculture industry. However, due to initial defects such as creases and corners caused by copper alloy weaving, the fatigue performance of copper alloy netting is greatly affected under periodic loads. This paper presents original test results for fatigue strength and ageing performance of copper alloy wire and netting structures. Compared with the fatigue test results of steel and aluminum materials, the fatigue strength of the actual copper alloy netting structure is relatively low with the fatigue ratio σ f / σ b = 0.06 at 10 6 cycles. The fatigue ratio is only about (1/8–1/4) of that of other metals ( σ f / σ b =(0.4–0.5) for steel and σ f / σ b =(0.25–0.50) for magnesium alloy). Considering the corrosive environment and ageing effects, metallographic structure and the maximum corrosion depths of copper alloy wire under different ageing conditions were measured and compared systematically. After a series of tests on aging and fatigue, it is concluded that the copper alloy material shows better corrosion resistance and aging resistance in seawater immersion environment than the traditional steel alloy or polymer netting. In seawater environment, the fatigue life of copper alloy netting decreases by only 10%, while the fatigue reduction rate of steel material is about 30% and nylon material is about 80%. The experimental results can provide a reference for the anti-fatigue design of copper alloy netting structure.

Due to the typhoon impacts, aquaculture net cages may be exposed to the risk of structural failure as a far-reaching aquaculture equipment. In addition, the fatigue problem of key components due to long-term marine alternating loads can not be ignored. The method is developed independently on processing samples of cage for testing its performance parameters, among which the fatigue Wohler curve is S = -1.022ln (N) + 22.201. By adapting the following methods: Mechanical test, Equivalent load finite element simulation and Full field finite element simulation respectively is verified each other, and the error is less than 5%. The key nodes of the stress concentration of the floating frame are mainly the welding point, the mooring point and the edge area of the I-beam frame at both sides. The damage of the cage which caused by tensile and bending loads should be considered at the same time. And the tensile strength 22.12 MPa and the bending strength 30.58 MPa could be taken as the evaluation standard for the elastic to plastic deformation. Structural fracture occurs when the elongation at break exceeds 340.18%. The fatigue of the cage is mainly because the stress is much greater than the fatigue limit 3.38 MPa. The material model test combined with structural mechanics simulation provides the basis for guiding the structural optimization design of the cage.