Abstract: Disclosed is a ship detection and tracking method and device, the method comprises: pre-training a yolov5s network model with a first preset number of high-speed moving object datasets to obtain an initial ship detection model; adding a preset attention mechanism to the initial ship detection model to obtain a transitional ship detection model; inputting a second preset number of annotated ship datasets into the initial ship detection model with the preset attention mechanism for training to obtain a target ship detection model; inputting an original ship video frame into the target ship detection model, and outputting the position information of the ship to be tracked; performing ship video image tracking on the ship to be tracked according to the position information. This disclosure performs pre-training, which only requires a small amount of annotated ship data to determine the target ship detection model, achieving video image tracking of the target ship.

Abstract: Provided are a similar material for a rock slope model test under water-rock interaction, and a preparation method and use thereof. The similar material is prepared from raw materials including the following components: an iron powder, a quartz sand, a barite powder, a gypsum, glycerin, water, a gypsum retarding agent, and a dispersible polymer powder. Further, the method for preparing the similar material for a rock slope model test under water-rock interaction is also provided.

Abstract: The present disclosure provides a hydraulic phosphogypsum (PG)-based cementitious material, and a preparation method and use thereof, belonging to the technical field of cementitious materials. The present disclosure provides a hydraulic PG-based cementitious material, including the following raw materials: modified PG particles and an auxiliary active powder, where the modified PG particles have a dosage of 50 wt % to 95 wt %; the modified PG particles are obtained by conducting modification on original PG particles through a calcareous material, and the calcareous material has a mass 3% to 5% of that of the original PG particles; and the original PG particles have typical dimensions of: a length of 50 ?m to 200 ?m and an aspect ratio of 1.5 to 5; and at least 80% of materials in the auxiliary active powder have a particle size of less than or equal to 60 ?m. In the present disclosure, the hydraulic PG-based cementitious material adopts a particle accumulation method of gap grading.

Abstract: An automatic pressure regulating valve for multiple levels of driving automation of a commercial vehicle includes an upper valve body, a lower valve body, a piston, a main valve core assembly, a switching valve, a quick-acting intake valve, and a quick-acting exhaust valve. The switching valve, the quick-acting intake valve and the quick-acting exhaust valve are all mounted at an upper end of the upper valve body. The piston is located in a chamber formed by the upper valve body and the lower valve body to divide the chamber into an upper control chamber and a lower chamber. The main valve core assembly is mounted in the lower valve body. The automatic pressure regulating valve is applicable to a commercial vehicle allowing for multiple levels of driving automation.

Abstract: Disclosed is method for evaluating influence of humidity on adhesion of asphalt-aggregate adhesion, the method includes the following steps: S1 putting multiple pull-out specimens into constant temperature and humidity phases with different relative humidity for curing, after the humidity reaches equilibrium, carrying out macroscopic mechanical pull-out test out and obtaining images of two aggregate surfaces of each broken pull-out specimen; S2 cropping the images, and then importing the cropped images into the Images Pro Plus software; S3 obtaining asphalt peeling rate according to the pixel value and calculation formula of asphalt peeling rate; S4 according to the asphalt peeling rate, asphalt cohesive energy and asphalt-aggregate binding energy, combined with calculation formula of asphalt-aggregate interface energy, obtaining asphalt-aggregate interface energy, and evaluating asphalt-aggregate adhesion according to the interface energy.

Abstract: Disclosed is a method for calculating surface energy matching index of specific surface area of asphalt mortar-aggregate, including the following steps: determining surface energy parameter of aggregate by vapor adsorption method; determining surface energy parameter of filler by improved capillary rising method; determining specific surface area of asphalt mixture aggregate by specific surface area coefficient method; using an automatic specific surface area and pore analyzer to determine the specific surface area of the filler; calculating adhesive bond energy of the asphalt mixture and adhesive bond energy under liquid condition; calculating the surface energy matching index of asphalt mortar-aggregate. The beneficial effects of this disclosure include: the water stability of asphalt mixture is improved because the influence of the surface energy matching index of the specific surface area of asphalt mortar-aggregate is considered.

Abstract: A transformer failure diagnosis method and system based on an integrated deep belief network are provided. The disclosure relates to the fields of electronic circuit engineering and computer vision. The method includes the following: obtaining a plurality of vibration signals of transformers of various types exhibiting different failure types, retrieving a feature of each of the vibration signals, and establishing training data through the retrieved features; training a plurality of deep belief networks exhibiting different learning rates through the training data and obtaining a failure diagnosis correct rate of each of the deep belief networks; and keeping target deep belief networks corresponding to the failure diagnosis correct rates that satisfy requirements, building an integrated deep belief network through each of the target deep belief networks, and performing a failure diagnosis on the transformers through the integrated deep belief network.

Abstract: An airborne LiDAR point cloud filtering method based on super-voxel ground saliency is provided. The method begins by denoising the input LiDAR point cloud, employing a boundary-preserving TBBP super-voxel algorithm for super-voxel segmentation. The super-voxels are categorized into scanning bands in N directions based on their centroid coordinates. Subsequently, each direction's scanning bands are sorted, segmented, and their saliency values are computed. Utilizing saliency values as coordinating factors, an energy function for the optimal filtering plane is constructed and minimized, leading to the determination of the optimal segmentation plane. Ground and non-ground points are classified based on the segmentation plane, thereby establishing the point cloud filtering results. The use of super-voxel-based saliency calculation in this invention enables preliminary vertical filtering of target point clouds, addressing the challenge of misclassifying point clouds with concave structures as ground points.

Abstract: The invention relates to an insulating gas mixture for replacing SF6 gas as well as its formulation method and application. The insulating gas mixture is composed of a fluorocarbon gas and a helium gas, and the formulation method includes filling the fluorocarbon gas and the helium gas in a vacuum-sealed container.

Abstract: This invention relates to the field of power electronics, specifically addressing an IGBT (Insulated Gate Bipolar Transistor) collector current online detection device and method based on gate current. The detection method involves processing the IGBT gate drive waveform using a Miller plateau detection module to extract the Miller plateau region in the gate drive waveform. The IGBT gate current integration module extracts the voltage across the IGBT gate drive resistor, integrates the voltage waveform during the Miller plateau period, and uses the integration result to characterize the gate current during the Miller plateau. Three sets of integrator output voltages and collector currents under different load currents are measured, and a second-order polynomial fitting is performed internally in the DSP (Digital Signal Processor) to derive a function representing the collector current as a function of the integrator output voltage.

Abstract: The present disclosure provides an oral care composition and a preparation method, and an application thereof. The composition includes: a drug-loaded micelle, wherein the drug-loaded micelle includes a polymer micelle and an enamel restoration drug physically wrapped in the polymer micelle, and the polymer micelle is micelle particles formed by a water-soluble polymer with a structure shown by Formula I in an aqueous solution with presence of tannic acid and the micelle particles have a shell connected to a salivary protein polypeptide through chemical bonds. The oral care composition in the present disclosure enables the salivary protein polypeptide to adhere to the surfaces of teeth so as to open the borate ester bond between the tannic acid and the water-soluble polymer in an acidic environment generated by the dental caries and release the tannic acid and sodium fluoride, thus achieving the purpose of preventing dental caries and restoring tooth defects.

Abstract: The present disclosure provides a periodic time slot scheduling method for a wireless network. The method includes: connecting a plurality of nodes by using a wireless network; constructing time slot parameter sets of nodes in the wireless network and an interval array between time slots of each of the nodes; calculating an acceptable total time interval of each of the nodes in the wireless network, selecting a node with a minimum acceptable total time interval in the wireless network as a time slot allocation node, allocating a time slot for each time slot request of the time slot allocation node, and allocating a time slot for each time slot request of a remaining node except the time slot allocation node in the wireless network; and detecting and determining a delay of time slot allocation.

Abstract: Provided is a method and system for predicting tumor mutation burden (TMB) in triple negative breast cancer (TNBC) based on nuclear scores and histopathological whole slide images (WSIs). The method includes the following steps: first, screening the histopathological WSIs of TNBC; calculating a TMB value of each patient according to gene mutation of each patient with TNBC, and dividing the TMB values into two groups with high and low TMB according to a set threshold; dividing the histopathological WSIs of TNBC into patches of a set size; screening a certain number of patches with high nuclear scores according to a nuclear score function; then building a convolutional neural network (CNN) classification model, and stochastically initializing parameters in the CNN classification model; and finally, putting the screened patches into the built CNN classification model for training, so as to automatically predict high or low TMB with the histopathological WSIs of TNBC.

Abstract: A La-element micro-alloyed AlCrFeNiTi bulk alloy with high corrosion resistance and wear resistance and a preparation method therefor and applications thereof are provided. The alloy includes the following chemical components in corresponding percentages: 2.05 wt % to 2.15 wt % of Al, 20.50 wt % to 20.65 wt % of Cr, 34.50 wt % to 35.54 wt % of Ni, 18.80 wt % to 19.16 wt % of Ti, 1.05 wt % to 1.15 wt % of La, and the balance of Fe and inevitable impurities, wherein the chemical components need to meet the following three relations at the same time: (1) 18.57?Fe/La?22.00; (2) 6.47?Fe/(La+Al)?7.45; and (3) 1.05?Fe/(La+Ti)?1.16. Compared with AISI 310S stainless steel, the alloy is improved by 280% to 290% in hardness, reduced by 4% to 7% in friction coefficient, and reduced by 17% to 34% in wear amount, increased by 73% to 77% in self-corrosion potential, and decreased by 96% in corrosion current density on average.

Abstract: A Nb-element micro-alloyed bulk multi-component alloy with high-temperature resistance and wear resistance, a preparation method therefor, and applications thereof are provided. The alloy includes chemical components at corresponding contents: 2.10-2.24 wt % of Al, 20.70-20.86 wt % of Cr, 35.20-35.54 wt % of Ni, 19.10-19.46 wt % of Ti, 0.70-0.85 wt % of Nb, and the balance of Fe and unavoidable impurities, and the chemical components need to simultaneously meet relations: (1) 24.76?Fe/Nb?31.72; (2) 6.81?Fe/(Nb+Al)?7.93; (3) 1.04?Fe/(Nb+Ti)?1.13. Wear resistance of the alloy is 4-5 times higher than that of a traditional wear-resistant material NM500 in terms of the same hardness. After two-step tempering heat treatment under the same parameters, the NM500 is reduced in hardness by 58.64-68.93% with respect to its quenched and tempered condition, and the hardness of material of this invention is reduced by 31.75-37.74% with respect to its as-cast condition.

Abstract: Disclosed are a vector synchronization method and system, the method includes: converting a three-phase instantaneous value of a power grid voltage into a two-phase voltage vector component through employing a power grid voltage vector phase angle at a previous moment; subtracting the d-axis voltage vector component from the power grid vector amplitude to obtain a d-axis voltage component deviation; performing gain and integral operations on the d-axis voltage component deviation to obtain a power grid vector amplitude; performing gain, integral and proportional-integral operations on the q-axis voltage component deviation to obtain a power grid voltage vector phase angle; respectively converting the d-axis voltage component deviation and the q-axis voltage component deviation into a q-axis current compensation signal and a d-axis current compensation signal of the grid-connected inverter; and the small interference stability of the grid-connected inverter is enhanced by adopting d-axis and q-axis current com

Abstract: The present disclosure provides an accurate inversion method and system for aboveground biomass of urban vegetations considering vegetation types.

Abstract: A method and a system for diagnosing an open circuit (OC) fault of an insulated gate bipolar transistor (IGBT) of a T-type three-level (T23L) inverter under multiple power factors based on instantaneous current distortion are provided. Similar characteristics of current distortion may be caused by an OC fault of a T23L inverter, making it is difficult to locate the fault. The method for diagnosing an OC fault of a grid-connected T23L inverter, can diagnose the OC fault hierarchically; four switch transistors in a phase can be divided into two groups according to the similarity analysis of current distortion under different power factors; group-based fault diagnosis is realized by half cycles in which a zero domain occurs; and then, a specific switching signal is injected to realize equipment-based OC fault diagnosis. The OC fault diagnosis of a T23L inverter is realized without additional hardware circuits.

Abstract: An intelligent assistance system and a method for berthing and unberthing based on multi-tugboat collaboration are provided.

Abstract: A real-time measurement system for mechanical parameters of rock slag during excavation includes a rock slag conveyor belt configured to convey rock slag; cleaning device, located on both sides of the rock slag conveyor belt, configured to clean the rock slag; an image acquisition device, located behind the cleaning device and on both sides and above the rock slag conveyor belt, configured to collect images of rock slag; an on-site loading device, for conducting on-site mechanical loading procedure on the rock slag to obtain on-site mechanical parameters. The on-site loading device includes a loading bottom plate, a push plate and a pressure head. The loading bottom plate is provided with a loading area. The push plate is located on the loading bottom plate and pushed by a pushing mechanism to push the rock slag.