Abstract: A cooperative control method and system for electro-hydraulic hybrid braking of a middle-low speed maglev train is provided, which relates to the field of vehicle braking control. The method includes: denoising operation data of a middle-low speed maglev train; using a controlled autoregressive integrated moving average model as an electro-hydraulic hybrid braking process model for the middle-low speed maglev train, and processing denoised operation data by using a least square method to determine parameters in the controlled autoregressive integrated moving average model; establishing a generalized predictive control model with time lag compensation according to the controlled autoregressive integrated moving average model and a Smith predictor; and performing cooperative control on an electro-hydraulic hybrid braking process of the middle-low speed maglev train by using the generalized predictive control model with time lag compensation.

Abstract: A bearing fault diagnosis method based on a fuzzy broad learning mode includes steps of constructing an initial fuzzy broad learning model based on a broad learning system and a fuzzy system, training the initial fuzzy broad learning model through training set data to obtain a target fuzzy broad learning model. The training set data includes a plurality of bearing vibration signal data with a fault type label; and a membership value of a bearing vibration signal data to be tested is calculated by the target fuzzy broad learning model. A fault type of the bearing to be tested is determined based on the membership value. The bearing fault diagnosis method reduces learning time. When determining the fault type of the bearing to be tested by the target fuzzy broad learning model, it has strong robustness, fast diagnosis speed and high fault diagnosis accuracy.

Abstract: A fault detection method and system for tunnel dome lights based on an improved localization loss function. The method includes: constructing a dataset of tunnel dome light detection images; acquiring a you only look once (YOLO) v5s neural network based on the improved localization loss function; training the YOLO v5s neural network according to the dataset to obtain a trained YOLO v5s neural network; acquiring a to-be-detected tunnel dome light image; detecting, with the trained YOLO v5s neural network, the to-be-detected tunnel dome light image to obtain position coordinates of luminous dome lights; and determining, according to the position coordinates of the luminous dome lights, whether a fault occurs in the tunnel dome lights. The present disclosure can accurately localize the tunnel dome lights and label the positions, and can detect whether the tunnel dome lights work normally according to a relative positional relationship between the labeled dome lights.

Abstract: A fault detection method and system for tunnel dome lights based on an improved localization loss function. The method includes: constructing a dataset of tunnel dome light detection images; acquiring a you only look once (YOLO) v5s neural network based on the improved localization loss function; training the YOLO v5s neural network according to the dataset to obtain a trained YOLO v5s neural network; acquiring a to-be-detected tunnel dome light image; detecting, with the trained YOLO v5s neural network, the to-be-detected tunnel dome light image to obtain position coordinates of luminous dome lights; and determining, according to the position coordinates of the luminous dome lights, whether a fault occurs in the tunnel dome lights. The present disclosure can accurately localize the tunnel dome lights and label the positions, and can detect whether the tunnel dome lights work normally according to a relative positional relationship between the labeled dome lights.

Abstract: The embodiments of the present disclosure provide a terminal force soft-sensing method of a hydraulic manipulator.

Abstract: The embodiments of the present disclosure provide a terminal force soft-sensing method of a hydraulic manipulator.

Abstract: Disclosed is a traffic flow forecasting method based on a multi-mode dynamic residual graph convolution network, including following steps: constructing a relationship matrix and an adaptive matrix to learn the site dependence relationship for historical traffic data of traffic stations; using multi-mode dynamic graph convolution to extract traffic characteristics corresponding to different traffic modes; embedding the graph convolution into the gated cyclic neural network to realize the combination of space dependence and time dependence of traffic flow; connecting the network by using the dynamic residual, and combining the input traffic data with the decoding data to obtain the final forecasting value. The application utilizes two different methods to construct adjacency matrix, effectively captures traffic flow characteristics corresponding to different traffic modes, and dynamically fuses traffic flow characteristics of two different modes.

Abstract: A method for preparing a large-size two-dimensional layered metal thiophosphate crystal includes the following steps: 1) weighing raw materials of indium spheres, phosphorous lumps and sulfur granules according to a predetermined amount and proportion, mixing them, and using iodine as a transport agent and potassium iodide as a molten salt; 2) adding the raw materials, the iodine and the potassium iodide to a reaction vessel together, and vacuum sealing it under a certain pressure, and then subjecting it to a high-temperature reaction; 3) taking out the products after the reaction, and washing the products to remove the residual iodine and potassium iodide and obtain large-size two-dimensional layered metal thiophosphate crystals. This method is simple and highly efficient.

Abstract: An alternating current (AC)-side symmetrically-split single-phase inverter for decoupling, which includes an H-bridge inverter, the H-bridge inverter includes an upper half-bridge structure and a lower half-bridge structure that are symmetrical to each other, the upper half-bridge structure includes an upper half-bridge first unit and an upper half-bridge second unit in parallel, the upper half-bridge first unit includes an insulated-gate bipolar transistor G1, a diode D1, and a capacitor C3 in parallel, the upper half-bridge second unit includes an insulated-gate bipolar transistor G3, a diode D3, and a capacitor C4 in parallel; and the lower half-bridge structure includes a lower half-bridge first unit and a lower half-bridge second unit in parallel, the lower half-bridge first unit includes an insulated-gate bipolar transistor G2, a diode D2, and a capacitor C1 in parallel, the lower half-bridge second unit includes an insulated-gate bipolar transistor G4, a diode D4, and a capacitor C2 in parallel.

Abstract: Provided are a data processing method, an electronic device and a storage medium. The method include: acquiring pending word vectors; acquiring multi-head attention vectors based on the pending word vectors, the multi-head attention vectors including first and second multi-head attention vectors; acquiring, based on the first multi-head attention vector, a first hidden semantic representation corresponding to the sentence; acquiring, based on the second multi-head attention vector, a second hidden semantic representation corresponding to the target word; acquiring a classification feature vector, based on the first and second hidden semantic representations; and acquiring, based on the classification feature vector, a sentiment polarity category of the sentence, and performing a sentiment classification on the sentence.

Abstract: A method for preparing a large-size two-dimensional layered metal thiophosphate crystal includes the following steps: 1) weighing raw materials of indium spheres, phosphorous lumps and sulfur granules according to a predetermined amount and proportion, mixing them, and using iodine as a transport agent and potassium iodide as a molten salt; 2) adding the raw materials, the iodine and the potassium iodide to a reaction vessel together, and vacuum sealing it under a certain pressure, and then subjecting it to a high-temperature reaction; 3) taking out the products after the reaction, and washing the products to remove the residual iodine and potassium iodide and obtain large-size two-dimensional layered metal thiophosphate crystals. This method is simple and highly efficient.

Abstract: The disclosed technology includes a computerized ionospheric tomography method based on vertical boundary truncation rays, which relates to the technical field of computerized ionospheric tomography (CIT). The method includes: obtaining an initial ionospheric electron density (IED) of each voxel in a target region and an ionospheric total electron content (TEC) value along a propagation path from a global navigation satellite system (GNSS) satellite; extending the target region so that GNSS stations within a certain range beyond the target region are encompassed within the target region; for GNSS stations within a certain range in the target region, calculating a vertical boundary truncation TEC value; for the GNSS stations within the target region, calculating a vertical boundary truncation TEC value; and building a three-dimensional CIT model based on the vertical boundary truncation TEC values PrTEC and PsTEC.

Abstract: A sensor system for measuring an angle of a gate of an isolating switch of overhead lines, comprising an optical fiber angle sensor, a base, a support plate, a light source fiber, a laser transmitter, an aluminum box, a relay, a step-down power module, a control circuit board, a photoelectric converter, and a receiving optical fiber. The support plate is arranged on an upper part of a pillar insulator; the optical fiber angle sensor is arranged on the base to detect a rotation angle of the gate; the laser transmitter is controlled to emit a laser beam into the light source fiber; the laser beam is received by the receiving optical fiber and transmitted to the photoelectric converter to convert a light intensity into a voltage signal; the converted voltage signal is transmitted to the control circuit board for processing, and the angle of the gate is output.

Abstract: The present disclosure discloses an electromagnetic multistage adjustable variable inertance and variable damping device. Iron cores are magnetized by winding electromagnetic coil windings outside the iron cores and applying an electric current action to the electromagnetic coil windings, and air gap magnetic fields are generated by the magnetized iron cores and permanent magnets in air gaps to cause the variation of shear damping forces between a driving shear plate and magnet yokes and between driven shear plates and magnet yokes, which avoids that the mechanical properties of an inerter cannot be fully utilized due to the friction caused by mutual contact among parts, thereby realizing multistage real-time adjustability of an instance coefficient and a damping coefficient of the device.

Abstract: Disclosed are a method and a system for multi-objective optimization of urban train operation. Firstly, speed limit information, slope information and curve radius information of a real train route are obtained, a section is segmented into non-equal sub-sections according to the above information about actual line characteristics, and then a longitudinal dynamics model of the train is constructed in combination with basic vehicle data of the train. Next, energy consumption of the train operation, section operation time, actual parking positions, and rates of acceleration change are calculated, so as to construct a multi-objective optimization model of train operation. Afterwards, a multi-objective differential evolution algorithm is used to solve the multi-objective optimization model, in order to obtain a Pareto optimal solution set of each operation district. Finally, an optimal solution is obtained which takes all objectives into comprehensive consideration, and an optimal train speed curve is generated.

Abstract: The disclosure discloses a method for dynamically monitoring the content of a rare earth element (REE) component based on a time-series feature. Using an image information acquisition device to periodically acquire a time-series image of a rare earth (RE) solution to be monitored; extracting a time-series feature of the time-series image in a mixed color space; determining whether a time-series feature value of the time-series image is in an expected interval of the mixed color space; calculating a histogram intersection distance between the time-series image and a sample image in a sample data set in the HSV color space, and determining the content of the REE component corresponding to the time-series image according to a component content corresponding to a sample image with a larger histogram intersection distance, if the determination result indicates no; otherwise, directly waiting for the acquisition of a time-series image at a next sampling time point.

Abstract: The present disclosure provides an inspection system for contact network damage detection, including: a laser imaging radar, an X-ray transmitter, a booster, an X-ray receiver, and a control circuit board. The laser imaging radar emits a laser beam to a contact line for scanning. A laser radiation reflected by the contact line is received, and a continuous analog signal is generated, which is restored to a real-time image of the contact line. After the analog signal is converted into a digital signal on the control circuit board, a height of the contact line in a horizontal direction is calculated to determine a wear degree on an outer surface of the contact line. The booster boosts electric energy obtained by the pantograph on the contact line and supply power to the X-ray transmitter.

Abstract: The video monitoring system collects a video data stream in real time; the device inspection system collects and uploads an image of each electrical device along a line; the voice communication system realizes a voice call between an inspection staff and a back-end monitoring staff; the environmental monitoring system monitors a temperature, a humidity, and a water intake in the traction substation and each electrical device; the fire alarm system monitors a fire in the traction substation; the sulfur hexafluoride gas monitoring system monitors a sulfur hexafluoride gas leakage in an electrical device; the security prevention system collects alarm information; the power lighting monitoring system collects operation information of a power lighting device; the power monitoring system monitors an input current and voltage and an output current and voltage of the traction substation in real time. The information is transmitted to the railroad dispatching center.

Abstract: The disclosure relates to a method for predicting contents of cerium, praseodymium and neodymium components based on virtual samples and a system thereof. The method comprises: obtaining mixed solution of cerium, praseodymium and neodymium in a rare earth extraction process; extracting an H, an S, and an I color feature of a preprocessed image in an HSI color space to obtain an original data sample; constructing a stochastic configuration network model of the content of neodymium component; performing linear midpoint interpolation on the stochastic configuration network model to obtain virtual data samples; fusing original data samples and virtual data samples; reconstructing stochastic configuration network model by using fused data samples; determining content of neodymium component according to reconstructed stochastic configuration network model; and determining contents of cerium and praseodymium according to the content of neodymium component.

Abstract: The present invention discloses a prediction control method and system for component contents in a rare earth extraction process. The prediction control method includes: establishing an Elman neural network model of a rare earth extraction process; obtaining a predicted output value of the rare earth extraction process through the Elman neural network model of the rare earth extraction process; calculating an optimal set value through steady-state optimization; dynamically predicting an extractant flow increment and a detergent flow increment based on the predicted output value and the optimal set value; and controlling component contents in the rare earth extraction process according to the extractant flow increment and the detergent flow increment.