Abstract: The present invention discloses an in-situ monitoring method and apparatus for a power electronic device explosion. A power electronic device is excited to produce an explosion failure by using a fault excitation module. An electrical signal of the power electronic device is monitored in real time by using an electrical signal monitoring module. Gas information of a test cavity is monitored in real time by using a gas monitoring module. External pictures of the power electronic device are captured by using a high-speed image capturing module. Internal pictures of the power electronic device are captured by using a high-speed X-ray imaging module. Each module in the apparatus is triggered to work according to a predetermined time sequence and time interval by using a time sequence control module. The entire apparatus is controlled and data is acquired, stored, and displayed by using a main control module.

Abstract: A transformer health state evaluation method based on a leaky-integrator echo state network includes the following steps: collecting monitoring information in each substation; performing data filtering, data cleaning and data normalization on the collected monitoring information to obtain an input matrix; inputting the input matrix into a leaky-integrator echo state network to generate trainable artificial data, and dividing the artificial data into a training set and a test set in proportion; constructing a deep residual neural network based on a squeeze-and-excitation network, and inputting the training set and the test set for network training; and performing health state evaluation and network weight update based on actual test data. Considering that a deep learning-based neural network needs a large amount of data, the present disclosure uses the leaky-integrator echo state network to generate the artificial training data.

Abstract: An active resonance C-type buoyant flap wave energy converter includes a rigid frame, a flap, a mass center adjustment assembly and a power generation assembly. The rigid frame is connected to a marine facility, and includes a main body and a support shaft provided at a bottom thereof. The flap is swingingly arranged on the support shaft. The flap is located under water surface, and swings back and forth around the support shaft under an action of a wave. The mass center adjustment assembly is configured to adjust a mass center of the flap to make a natural period of the flap same as a wave period, so as to achieve a resonance between the flap and the wave. The power generation assembly is arranged on the support shaft and is located in the flap.

Abstract: A transformer failure identification and location diagnosis method based on a multi-stage transfer learning theory is provided. Simulation is set up first, a winding parameter of a transformer to be tested is calculated, and a winding equivalent circuit is accordingly built. Different failures are configured for the equivalent circuit, and simulation is performed to obtain a large number of sample data sets. A sweep frequency response test is performed on the transformer to be tested, and detection data sets are obtained. Initial network training is performed on simulation data sets by using the transfer learning method, and the detection data sets are further trained accordingly. A failure support matrix obtained through diagnosis is finally fused. The multi-stage transfer learning theory is provided by the disclosure.

Abstract: A device for targeted repair of micro-nano damage of an inner ring of an aeroengine bearing by an electric-magnetic composite field includes a driving device, an ultrasonic shot peening device, a pulsed current generator and a magnet yoke-coil device. The driving device includes a motor and a rotating shaft. The motor drives the rotating shaft to drive a bearing inner ring to synchronously rotate. The ultrasonic shot peening device includes an ultrasonic shot peening cavity, an ultrasonic probe and steel balls, the ultrasonic probe extends into the cavity from an opening in a lower end of the cavity, and the steel balls are placed on the ultrasonic probe. An opening in an upper end of the cavity is placed below the bearing inner ring. The pulsed current generator generates pulsed current on the bearing inner ring. The magnet yoke-coil device can excite a magnetic field around the bearing inner ring.

Abstract: The present invention discloses an optimization method for a screen surface dynamic load of a vibrating screen. The method includes the following steps: step 1. selecting design variables, and establishing an experimental matrix; step 2. performing a response curved surface experiment; step 3. establishing two double-objective optimization models and solving the same to obtain two groups of Pareto solution sets, wherein the solution sets respectively represent screening efficiency optimization paths of the vibrating screen under the conditions of a high screen surface dynamic load and a low screen surface dynamic load; and step 4. calculating an optimization space for a screen surface dynamic load under a high screening efficiency. According to the method of the present invention, the screen surface dynamic load can be directly reduced, and the service life of the screen surface and the whole vibrating screen is prolonged.

Abstract: An automatic abnormal cell recognition method, the method including: 1) scanning a slide using a digital pathological scanner and obtaining a cytological slide image; 2) obtaining a set of centroid coordinates of all nuclei that is denoted as CentroidOfNucleus by automatically localizing nuclei of all cells in the cytological slide image using a feature fusion based localizing method; 3) obtaining a set of cell square region of interest (ROI) images that are denoted as ROI_images; 4) grouping all cell images in the ROI_images into different groups based on sampling without replacement, where each group contains ROW×COLUMN cell images with preset ROW and COLUMN parameters; obtaining a set of splice images; and 5) classifying all cell images in the splice image simultaneously by using the splice image as an input of a trained deep neural network; and recognizing cells classified as abnormal categories.

Abstract: The present disclosure provides a multi-user slice resource allocation method based on competitive game. In the method, first model a system as a two-tier architecture of virtual infrastructure service providers (VInPs) and users, and build a VInP utility model and a user utility model; then divide slice resource allocation into nodes and links, and build a node power consumption model and a link power consumption model, then determine a revenue of the VInP and a revenue of a user; and calculate a total revenue of a slice according to the revenue of the VInP and the revenue of the user, and use the total revenue of the slice as a network model; then solve the network model, where the VInP is used as a seller, the user is used as a buyer, the seller determines an initial price according to a total quantity of slice resources, and the buyer bids on the slice, and allocate the slice resources by using a competitive game mechanism.

Abstract: A method includes steps: 1) obtaining monitoring information of different monitoring points in normal state of power equipment; 2) setting faults and obtaining monitoring information of different fault types, positions, monitoring points of the equipment; 3) taking the monitoring information obtained in steps 1) to 2) as training dataset, taking the fault types and positions as labels, inputting the training dataset and the labels to deep CNN for training; 4) collecting monitoring data, performing verification and classification using step 3), obtaining probability values corresponding to each of the labels; 5) taking classification results of different labels as basic probability assignment values, with respect to a monitoring system composed of multiple sensors, taking different sensors as different evidences for decision fusion, performing fusion processing using the DS evidence theory to obtain fault diagnosis result.

Abstract: The invention discloses a method and a system for correction of the junction temperatures of an IGBT module in a photovoltaic inverter.

Abstract: The disclosure provides an internal thermal fault diagnosing method for an oil-immersed transformer based on DCNN and image segmentation, including: 1) dividing an internal area of a transformer, and using fault areas and normal status as labels of DCNN; 2) through lattice Boltzmann simulation, randomly obtaining multiple feature images of the internal temperature field distribution of the transformer under normal and various fault state modes, and the fault area serves as a label to form the underlying training sample set; 3) obtaining historical monitoring information of the infrared camera or temperature sensor, and forming its corresponding fault diagnosis results into labels; 4) combining all monitoring information contained in each sample into one image, and then extracting the same monitoring information from the samples in the sample set to form a new image; 5) segmenting image sample and then inputting the same into DCNN for training to obtain diagnosis results.

Abstract: A method and a system for identifying third-order model parameters of a lithium battery based on a likelihood function are provided, which relates to a method for estimating battery model parameters of a lithium battery under different temperatures, different system-on-chips (SOCs), and charge-discharge currents. The method includes the following steps. A third-order battery model of the lithium battery is established. A battery model output voltage Ud and a total battery current I under different temperatures, different SOCs, and charge-discharge currents are collected. The likelihood function is adopted to construct an identification model, and the collected data is substituted into the identification model to calculate the battery model parameters. Identified parameters are substituted into the third-order battery model to obtain a battery terminal voltage to be compared with a measured terminal voltage.

Abstract: The disclosure provides a wireless channel scenario identification method and system. The method includes: simulating different wireless channel scenarios to obtain a channel scenario baseband signal y(t)pq; extracting a feature parameter of y(t)pq, extracting an autocorrelation function Ah(t)pq and performing a Fourier transform thereon to obtain a power spectral density function S(t)pq; normalizing S(t)pq to obtain a normalized channel scenario power spectral density function S(t)pq; designing a deep learning network and inputting S(t)pq and a category label pair to train the deep learning network; and for a system with a channel scenario to be identified, collecting a passband signal at its receiving end, obtaining the normalized scenario power spectral density function ?(t)pq, and using ?(t)pq as an input of the trained classifier, the output of the classifier being a label sequence of the channel scenario, and the channel scenario is effectively determined.

Abstract: The present disclosure relates to a multi-functional nanoparticle targeted to breast cancer, a preparation method and use thereof. The multi-functional nanoparticle includes a targeting carrier and a medicament loaded on the targeting carrier; and the targeting carrier is made from recombinant ferritin. Cell experiments verify that the multi-functional nanoparticle has better efficacy and drug release capacity for cancer cells than those of conventional ferritin as a vector. Moreover, the drug delivery system can further achieve optical imaging of tumor cells by loading quantum dots, thus playing a role in cancer diagnosis and treatment.

Abstract: An autonomous robotic exploration method based on a reduced approximated generalized Voronoi graph, the method including: 1) constructing a reduced approximated generalized Voronoi topological map based on a morphological method; 2) obtaining an Next-Best-View and planning a global path from the robot to the Next-Best-View; and 3) navigating to the Next-Best-View along the global path R={r0, r1, r2, . . . , pNBV} based on a visual force field (VFF) algorithm.

Abstract: The present invention discloses an in-situ monitoring method and apparatus for a power electronic device explosion. A power electronic device is excited to produce an explosion failure by using a fault excitation module. An electrical signal of the power electronic device is monitored in real time by using an electrical signal monitoring module. Gas information of a test cavity is monitored in real time by using a gas monitoring module. External pictures of the power electronic device are captured by using a high-speed image capturing module. Internal pictures of the power electronic device are captured by using a high-speed X-ray imaging module. Each module in the apparatus is triggered to work according to a predetermined time sequence and time interval by using a time sequence control module. The entire apparatus is controlled and data is acquired, stored, and displayed by using a main control module.

Abstract: A pneumatic automatic pressure regulating valve for automatic driving of a commercial vehicle includes an upper valve body and a lower valve body that form a chamber of the automatic pressure regulating valve. A quick-acting intake valve assembly and a quick-acting exhaust valve assembly are mounted on the upper valve body. A main valve core assembly is mounted on the lower valve body. The quick-acting intake valve and the quick-acting exhaust valve are normally closed and both are configured to regulate an air pressure in the control chamber A such that air enters the working chamber B to increase a pressure or is vented therefrom to reduce the pressure, thereby controlling a pressure in a brake chamber. The pneumatic automatic pressure regulating valve can be widely applied to autonomous vehicles or unmanned driving. The familiarity dependency of a driver on a valve control system is reduced.

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: An automatic pressure regulating valve for an electro-pneumatic braking system of a commercial vehicle comprises an upper valve body and a lower valve body. The upper valve body includes a normally open switching valve, a quick-acting intake valve, a normally open quick-acting intake valve, a quick-acting exhaust valve, and a control chamber A. A lower valve body includes a relay valve and a working chamber B. The normally open switching valve has a manually controlled air inlet a and an electronically controlled air inlet b, and an air outlet c connected to an air inlet d of the normally open quick-acting intake valve. An air outlet e of the normally open quick-acting intake valve, an air inlet f of the quick-acting exhaust valve and an air outlet i of the quick-acting air intake valve are connected together to the control chamber A.

Abstract: A power electronic circuit fault diagnosis method based on Extremely randomized trees (ET) and Stack Sparse auto-encoder (SSAE) algorithm includes the following. First, collect the fault signal and extract fault features. Then, reduce the dimensionality of fault features by calculating the importance value of all features using ET algorithm. A proportion of the features to be eliminated is determined, and a new feature set is obtained according the value of importance. Further extraction of fault features is carried by using SSAE algorithm, and hidden layer features of the last sparse auto-encoder are obtained as fault features after dimensionality reduction. Finally, the fault samples in a training set and a test set are input to the classifier for training to obtain a trained classifier. And mode identification, wherein the fault of the power electronic circuit is identified and located by the training classifier.