Abstract: Disclosed is an intelligent collision avoidance method for a swarm of unmanned surface vehicles based on deep reinforcement learning; firstly, a theoretical framework of autonomous learning collision avoidance of a swarm of unmanned surface vehicles based on deep reinforcement learning is proposed, and the LSTM neural network memory ability is integrated to realize the continuity of collision avoidance actions; then, according to the USV environment in the framework, the characterization method is obtained, and the USV collision avoidance reward and punishment function is proposed to evaluate the collision avoidance effect; finally, an intelligent collision avoidance training system for a swarm of unmanned surface vehicles is formed. The simulation and verification of this disclosure show that the USV trained in this disclosure can navigate safely in the collision avoidance environment with a swarm of unmanned surface vehicles and realize intelligent collision avoidance.

Abstract: The present invention belongs to animal experiments field, disclosed a single factor modeling-constraint method and device for mice chronic fatigue syndrome, the modeling-constraint method is specifically using mineral water bottle to restraint mice; the mineral water bottle is divided into upper, middle and lower parts; the body of mineral water bottle is uniformly drilled for mice to breathe; the inner of the mineral water bottle is blocked by a cardboard to reduce the move space of mice; cover the mice through the divided bottle; one end of the opening is tightly attach to the wall, the other end is tightly attach to the mice feeding box, and keeping 30 minutes to restraint. The present invention utilizes mineral water bottle to make three simple restraint tube, not only saves the costs of experiment, but also turns waste into treasure, which is a simple operation, and increases the possibility of the experiment.

Abstract: Disclosed is a method for measuring surface energy of aggregates based on static drop method, comprising (1) aggregates grinding and pretreatment; (2) obtaining the surface texture index; (3) calculating the surface energy based on static drop method experiment; (4) fitting to obtain a functional relationship between the surface texture index and surface energy; (5) calculating the surface energy of the original aggregate. The method considers the influence of the grinding process on the surface texture of the aggregates when measuring the surface energy of the aggregates, which significantly improves the accuracy of the static drop method test. The static drop method can be used to replace the vapor adsorption method to test the surface energy of aggregate, and the low-cost optical contact angle instrument can replace the expensive magnetic suspension weight balance system to test the surface energy of aggregate, which greatly reduces the test cost.

Abstract: Disclosed is a method and device for automatic detection of vessel draft depth, which processes the image of a vessel's hull and extracts local area image blocks with vessel's water gauge scale separately to improve the pertinence of data processing and reduce the complexity of data processing; and based on a multi-task learning network model, performing data processing on local area image blocks to extract scale characters and waterline position, reducing the computational complexity of the model; finally, based on the relative positions of the scale and waterline, determining the vessel's draft depth, thus achieving automatic acquisition of the vessel's draft depth, this method greatly improves the efficiency of reading the vessel's draft depth.

Abstract: A thermoelectric array display and a manufacturing method thereof are provided. The thermoelectric array display includes at least a first pixel, where the first pixel includes a bottom electrode, a P-type thermoelectric leg, an N-type thermoelectric leg, and a top electrode; the P-type thermoelectric leg is arranged on the bottom electrode; and the P-type thermoelectric leg is connected in series to the N-type thermoelectric leg by the top electrode. The thermoelectric array display has strong concealment of information transmission, can effectively reduce heat generation of a device, and can implement long-distance signal transmission.

Abstract: A surface water quality monitoring method based on a high spatial resolution satellite includes: step 1. building standard surface water quality pools by mixing natural water bodies with clean water in different proportions to obtain surface water quality data; step 2. obtaining high spatial resolution remote sensing images for processing; step 3. identifying remote sensing bands with higher correlation through correlation analysis by presetting ratio values of remote sensor data bands and the standard surface water quality pools; step 4. building a water quality parameter retrieval model, and comparing and retrieving the remote sensing bands with higher correlation and the surface water quality data to obtain water quality data; and step 5. identifying abnormal points of the water quality based on the water quality data and water quality data threshold of the surface water.

Abstract: A method of constructing an indoor wall corner two-dimensional semantic map based on a robot platform includes controlling, by the master control computer, the robot platform to move indoors, collecting, by the lidar sensor, a distance between an indoor object and the robot platform and a direction angle between the indoor object and the robot platform in real time and transmitting the distance and the direction angle to the master control computer, and obtaining, by the master control computer, an environment grid map and a real-time pose of the robot platform by processing the distance between the indoor object and the robot platform and the direction angle between the indoor object and the robot platform based on Gmapping algorithm; constructing a semantic segmentation data set as a training set on the master control computer and obtaining a predicted non-wall corner semantic label.

Abstract: The present invention belongs to the field of optical technology, disclosing a quadrilateral common-path time-modulated interferometric spectral imaging device and method. The present invention sets up a moving mirror scanning mechanism in a quadrilateral common path interferometer for generating optical path differences that vary with time, so that the quadrilateral common-path time-modulated interferometric spectral imaging device operates in the staring observation mode. The invention can make the quadrilateral common-path time-modulated interferometric spectral imaging device not only retain the advantages of common optical path spectroscopic technology, but also obtain high spectral resolution.

Abstract: Based on ICESat-2 high-resolution data, the disclosure proposes a method for mapping tree height.

Abstract: A method and system for fingerprint positioning based on 5G multi-beam downlink signals, includes: extracting multi-beam SSB from 5G downlink signals, and obtaining multi-beam SSS signal and DM-RS signal from multi-beam SSB; calculating multi-beam reference signal received power RSRP based on multi-beam SSS signal and DM-RS signal; calculating the RSSI of 5G downlink synchronization channel based on multi-beam SSB autocorrelation, and calculating the multi-beam reference signal received quality RSRQ based on multi-beam RSRP and RSSI; stacking the multi-beam RSRP and RSRQ to form multi-beam fingerprint features; inputting multi-beam fingerprint characteristic into neural networks, and the neural networks output positioning results.

Abstract: A method and a system for comprehensively evaluating reliability of a multi-chip parallel IGBT module are provided. The method includes: establishing a gate-emitter voltage reliability model of the multi-chip parallel IGBT module, performing a chip fatigue failure test, and selecting a gate-emitter voltage as a failure characteristic quantity; establishing a transconductance reliability model of the multi-chip parallel IGBT module, performing a bonding wire shedding failure test, and selecting a transmission characteristic curve of the module as a failure characteristic quantity; using a Pearson correlation coefficient to characterize a degree of health of the IGBT module, and respectively calculating degrees of health PPMCCC and PPMCCB in different degrees of chip fatigue and bonding wire shedding failure states; and comprehensively evaluating the reliability of the multi-chip parallel IGBT module according to PPMCCC and PPMCCB.

Abstract: The present invention relates to a method for preparing high-purity vanadium pentoxide from vanadium-bearing shale by all-wet process. The technical solution is: the “Gradient continuous leaching system of vanadium-bearing shale” is used to wet activate and compound leach vanadium-bearing shale to obtain vanadium-containing acid leachate. The “pH adjusting device of the vanadium-containing acid leachate” is used to adjust the pH of vanadium-containing acid leaching leachate. The post-treatment solution is subjected to hydroxime countercurrent extraction after oxidation, and the raffinate returns to the water using in the wet activation and electrodialysis after neutralization, and the loaded organic phase is regenerated by countercurrent reduction stripping. The regenerated organic phase directly returns to hydroxime countercurrent extraction.

Abstract: A method and system for predicting an insulated gate bipolar transistor (IGBT) lifetime based on compound failure mode coupling are provided. First, a simultaneous failure probability model of a bonding wire and a solder layer is calculated. Next, expectancy of the simultaneous failure probability model is calculated and recorded as a lifetime under a coupling effect. A coupling function relation is established. A lifetime of the solder layer and a lifetime of the bonding wire are predicted. An IGBT lifetime prediction model not taking the coupling effect into account is established. An IGBT lifetime prediction model taking the coupling effect into account is established. In the disclosure, the lifetime of the IGBT module under the coupling effect of the solder layer and the bonding wire may be accurately predicted.

Abstract: A neural-network-based-implemented ophthalmologic intelligent consultation method includes: performing correction filtering on a consultation voice of a patient, framing the voice into a consultation voice frame sequence, generating a consultation text corresponding to the consultation voice frame sequence based on phoneme recognition and phoneme transcoding, and extracting an ophthalmologically-described disease; performing gray-level filtering, primary picture segmentation, and size equalization operation on an eye picture set of the to-be-diagnosed patient to acquire a standard eyeball picture group; extracting eye white features, pupil features and blood vessel features from the standard eyeball picture group, performing lesion feature analysis on the eye white features, the pupil features and the blood vessel features to acquire an ophthalmologically-observed disease, and based on the ophthalmologically-observed disease and the ophthalmologically-described disease, generating a consultation result.

Abstract: The present invention relates to the field of inland vessel identification and ranging technology, and discloses a method, system, medium, equipment and terminal for identifying and ranging inland vessels. In the stage of vessel identification, based on the classical YOLO-V4 network model, the MobileNetV1 network is used to replace the feature extraction network CSPDarknet53 of the YOLO-V4 model; In the stage of vessel ranging, a binocular stereo vision ranging model is established, and the FSRCNN is used for super-resolution reconstruction of the original image pairs to enhance the vessel feature information; the ORB algorithm is used to achieve feature detection and matching at the sub-pixel level to obtain the parallax value between image pairs, and the depth information of the vessel target is obtained by triangulation principle and coordinate conversion.

Abstract: Disclosed in the present invention is hyperspectral image classification method based on context-rich networks. The method comprises a training stage and a prediction stage, wherein the training stage comprises image pre-processing, sample selection and network training. Firstly, performing normalization on a hyperspectral image, and then randomly selecting an appropriate proportion of marked samples from each category to generate a label map, and performing training by using the designed network; in the prediction stage, directly inputting the whole image into the trained network and obtaining a final classification result. By means of the present invention, data pre-processing, feature extraction, the process of context-rich information capturing, and classification are taken into comprehensive consideration in the whole flow; and the classification of a hyperspectral image is realized by means of constructing an end-to-end network.

Abstract: A test device for an automatic pressure regulating valve of an electronic braking system includes a test device composed of an air supply, a pneumatic circuit, a valve, a sensor, a signal processing unit, and a control unit. By subjecting an automatic pressure regulating valve to a bench test including a functional test, a static performance test, a dynamic performance test, an air tightness test, a leakage test, and a brake chamber braking force test, the present disclosure avoids the high risk of a field test, improves the test efficiency, and ensures the test consistency. An automatic pressure regulating valve is tested before being loaded on a vehicle, and parameters of the automatic pressure regulating valve are continuously modified through tests to improve the performance, such that the automatic pressure regulating valve can meet the real-time, fast, independent, and accurate regulation requirements of EBS of commercial vehicles.

Abstract: An interferometric demodulation system for a large capacity fiber grating sensing network is provided by the present disclosure, comprising: a continuous light output end of the nanoscale wide-spectrum light source is connected to an input end of the pulse optical modulator, an output end of the reference grating is connected to an input end of the grating array sensing network, and a third communication end of the optical circulator is connected to an input end of the optical amplifier, an output end of the optical amplifier is connected to an input end of the Mach-Zehnder interferometer, three-channel signal output ends of the Mach-Zehnder interferometer are respectively connected to signal input ends corresponding to the embedded signal processor through the photoelectric converter, and the embedded signal processor controls the heating device to control a temperature of an any one of interference arms of the Mach-Zehnder interferometer.

Abstract: A granite stone powder phosphoric acid-based geopolymer and a preparation method thereof are provided. The granite stone powder phosphoric acid-based geopolymer is prepared from following raw materials in parts by weight: 35-70 parts of granite stone powder, 15-50 parts of metakaolin, 8-50 parts of fly ash, 8-30 parts of acid activation solution and 8-30 parts of solvent.

Abstract: The disclosure provides a method, an apparatus and a computer device for three-dimensional reconstruction of an indoor structure based on a two-dimensional video, wherein the method comprises: generating a color point cloud of three-dimensional structure of a house by using the video data of the house; regularizing the color point cloud of the house; extracting a plan of the house based on the color point cloud of the house; and constructing a three-dimensional model of the house in real life. The disclosure realizes autonomous and rapid construction of a three-dimensional model of a house by the general public, and realizes a low-cost, efficient and convenient three-dimensional visual digital representation of the house.