Search

Given the low accuracy of the traditional electricity theft detection method based on one-dimensional electricity consumption data mining and analysis， a detection method for electricity theft by distribution network users based on a hybrid neural network is proposed. Firstly， to enhance the characteristic difference between the electricity consumption of normal users and that of power theft users， the Markov transition field （MTF） is used to transform one-dimensional electricity consumption data into two-dimensional graphs. Moreover， to improve the accuracy and generalization of the model， profile data of users' electricity consumption is introduced. Then， the hybrid neural network is used to extract and fuse the feature quantities of the preprocessed two-dimensional electricity consumption graphs and profile data respectively to detect electricity theft by distribution network users. Finally， the effectiveness and accuracy of the proposed method are verified through two sets of comparison experiments. The experimental results show that the method based on a hybrid neural network is superior to other models in detection accuracy of electricity theft， recall rate， and AUROC （area under the receiver operating characteristics）， and has higher detection performance.

Abstract Grass carp, Ctenopharyngodon idella, is the largest freshwater aquaculture fish species worldwide. However, its environmental impacts are increasingly controversial. In this paper, we considered the production of a 1500 g commercial grass carp as an example, analyzed through a life cycle assessment. The results showed that the indicators of global warming potential (GWP), acidification potential, eutrophication potential, freshwater eco‐toxicity potential (FAETP), land competition (LC), and fossil energy consumption of producing 1 kg of grass carp were equivalent to 5.7267 kg of CO2, 0.0648 kg of 1,4‐DCB0, 0.0010 kg of P, 0.0276 kg of SO2, 8.2951 m2, 0.3491 kg of oil, respectively, and were mainly from feed processing and water pollution. Compared with pig, beef, and sheep production, grass carp production has lower environmental impacts, but in terms of GWP, FAETP, and LC were significantly higher than chicken production, especially water pollution and discharge, which is an important consideration. This study clarifies the direction of grass carp production and key focus areas include producing low carbon and nitrogen emission feed, application of ecological engineering aquaculture system, intelligent mechanization technology and equipment.

Fused Deposition Modeling（FDM） has the advantages of fast forming speed and simple operation. Printing speed, printing layer thickness and printing temperature affect the equivalent stress of the workpieces, and then affect its mechanical properties. It is different from direct setting printing temperature as the initial temperature in the birth and death unit simulation. Through experiment and fluid simulation, the temperature of the single fuse when it contacts the plate is got, as the initial temperature of the multilayer superposition simulation. We calculate and fit out the function of heat transfer coefficient, considering printing parameters. With the FDM Multi Layer Stacking simulation, the stress of the workpieces under different parameters is got. Then correlated and compared with the tensile strength obtained by the tensile test under the same parameters. From the point of the stress, we analyzed the influence of the printing parameters on the tensile strength. The supplementary experiment is designed, and find the tensile strength of ploylactic acid（PLA） workpieces reach the maximum when the printing layer thickness is as far as small, the printing speed and the printing temperature are appropriate.

Pond aquaculture is an important aquacultural model worldwide in which ammonia-oxidizing bacteria (AOB) are crucial for the removal of ammonia from water. The influence of light irradiation on AOB in an aquaculture pond was studied using artificial simulation wastewater under dark/light cycles of 24 h/0 h (L0), 12 h/12 h (L12), and 0 h/24 h (L24). The ammonia oxidation rates (AORs) in groups L0, L12, and L24 were 9.88 ± 0.19 mg h−1, 6.01 ± 0.32 mg h−1, and 1.85 ± 0.09 mg h−1, respectively. Long-term exposure to light had a serious impact on the AOR and decreased the abundance of Nitrosomonas spp. and their ammonia monooxygenase genes. To determine the protective effect of microalgae on AOB, different doses of freeze-dried Chlorella spp. powder were added to the nitrifying bacteria community. The photoinhibition rate of chlorophyll a (Chla) in the groups with 300 and 1300 µg L−1 of added Chlorella were 32.85% and 28.77%, respectively, while the Chla in the 2200 µg L−1 Chlorella-added group was only 0.01%, with no significant differences (p > 0.05) in AOR between the dark/light treatment subgroups. Fluorescence in situ hybridization showed that AOB, nitrite-oxidizing bacteria, and algae coexist and grow together without free AOB in the nitrifying bacterial community. It was suggested that microalgae enhance the resistance of AOB to light irradiation in a pond through the shading effect provided by algal chlorophyll and the close symbiotic relationship between microalgae and AOB. [ABSTRACT FROM AUTHOR]