Abstract: A DC/DC converter fault diagnosis method based on an improved sparrow search algorithm, includes: establishing an simulation module of the converter, selecting a leakage inductance current of a transformer as a diagnosis signal, and collecting diagnosis signal samples under OC faults of different power switching devices of the converter as a sample set; improving a global search ability of a sparrow search algorithm by using a Levy flight strategy; dividing the sample set into a training set and a test set, preliminarily establishing an architecture of a deep belief network, and initializing network parameters; optimizing a quantity of hidden-layer units of the deep belief network by using an improved sparrow search algorithm, to obtain a best quantity of hidden-layer units of the deep belief network; and training an optimized deep belief network obtained based on the improved sparrow search algorithm, and obtaining a fault diagnosis result based on a trained network.

Abstract: A DC/DC converter fault diagnosis method based on an improved sparrow search algorithm, includes: establishing an simulation module of the converter, selecting a leakage inductance current of a transformer as a diagnosis signal, and collecting diagnosis signal samples under OC faults of different power switching devices of the converter as a sample set; improving a global search ability of a sparrow search algorithm by using a Levy flight strategy; dividing the sample set into a training set and a test set, preliminarily establishing an architecture of a deep belief network, and initializing network parameters; optimizing a quantity of hidden-layer units of the deep belief network by using an improved sparrow search algorithm, to obtain a best quantity of hidden-layer units of the deep belief network; and training an optimized deep belief network obtained based on the improved sparrow search algorithm, and obtaining a fault diagnosis result based on a trained network.

Abstract: A method for diagnosing transformer fault based on a deep coupled dense convolutional neural network, includes: obtaining datasets of dissolved gas in oil of a transformer in normal and fault states; expanding the datasets by using an adaptive synthetic oversampling method; performing, in a form of a two-dimensional matrix, feature reconstruction on characteristic gas dissolved in the oil; building a transformer fault diagnosis model based on a deep coupled dense convolutional neural network; and dividing an expanded dataset into a training set and a test set, and taking the two-dimensional matrix as an input of the deep coupled dense convolutional neural network and a set label as an output to train the network to obtain a fault diagnosis model. The present disclosure can resolve a problem that a fault diagnosis accuracy rate of the transformer is low due to insufficient and unbalanced fault samples in the dissolved gas in the oil.

Abstract: The present invention relates to a magnetic navigation-guided tear-away sheath for cardiac conduction bundle pacing, including a sheath body and a joint fixedly connected to a rear end of the sheath body. The sheath body includes a front flexible section and a rear fixed section, and the front flexible section is freely bendable. An outer surface near a head end of the front flexible section is provided with a plurality of pairs of half-ring magnets, two half-ring magnets in each pair of half-ring magnets are symmetrically disposed and form a ring, and a gap is kept between the two half-ring magnets. The head end of the front flexible section is provided with three electrodes uniformly disposed in a circumferential direction, and the three electrodes can be freely combined two by two, to form three electrode pairs used to record and position an intracardiac potential.

Abstract: A system for suppressing noise and enhancing speech and a related method are disclosed. The system trains a neural network model that takes banded energies corresponding to an original noisy waveform and produces a speech value indicating the amount of speech present in each band at each frame. The neural model comprises a feature extraction block that implements some lookahead. The feature extraction block is followed by an encoder with steady down-sampling along the frequency domain forming a contracting path. The encoder is followed by a corresponding decoder with steady up-sampling along the frequency domain forming an expanding path. The decoder receives scaled output feature maps from the encoder at a corresponding level. The decoder is followed by a classification block that generates a speech value indicating an amount of speech present for each frequency band of the plurality of frequency bands at each frame of the plurality of frames.

Abstract: A multi-port valve includes a valve housing and a valve core. The valve housing includes a plurality of ports arranged in a circumferential direction. All the ports are grouped into at least two port groups. Each of the port groups includes a main port and a plurality of sub-ports. The valve core is rotatably mounted to the valve housing and defines at least two flow channels. The multi-port valve has a plurality of work modes in response to the valve core rotated as regard to the valve housing to different positions. In different work modes, each of said at least two flow channels is configured to selectively communicate one of the main ports with one of the sub-ports.

Abstract: A wake-up word for a digital assistant may be specified by a user to trigger the digital assistant to respond to the wake-up word, with the user providing one or more initial pronunciations of the wake-up word. The wake-up word may be unique, or at least not determined beforehand by a device manufacturer or developer of the digital assistant. The initial pronunciation(s) of the keyword may then be augmented with other potential pronunciations of the wake-up word that might be provided in the future, and those other potential pronunciations may then be pruned down to a threshold number of other potential pronunciations. One or more recordings of the initial pronunciation(s) of the wake-up may then be used to train a phoneme recognizer model to better recognize future instances of the wake-up word being spoken by the user or another person using the initial pronunciation or other potential pronunciations.

Abstract: A domain adaptation module is used to optimize a first domain derived from a second domain using respective outputs from respective parallel hidden layers of the domains.

Abstract: A compound represented by structural formula (I) and a pharmaceutically acceptable salt thereof and a pharmaceutical composition comprising the compound or the pharmaceutically acceptable salt thereof, can be used for treating diseases such as obesity, hyperlipidemia, hypercholesterolemia, and diabetes and also for treating other diseases such as NASH, atherosclerosis, cardiovascular diseases, hypothyroidism, thyroid cancer and other related disorders and diseases

Abstract: A code adaptation mechanism automatically integrates the variable names of a pasted source code snippet into variable names defined in a pre-existing partial source code program. The variable names from the pasted source code snippet are replaced with anonymized values. A deep learning model predicts the most likely variable name from the pre-existing partial source code program to replace each anonymized value. The deep learning model is trained on numerous variable usage patterns from various source code programs to learn to predict the most likely mapping of an undefined variable name from the pasted source code snippet to a variable name in the pre-existing partial source code program thereby generating a syntactically and semantically correct program.

Abstract: A constrained decoding technique incorporates token constraints into a beam search at each time step of a decoding process in order to generate viable candidate sequences that are syntactically and semantically correct. The token constraints identify source code tokens or sequences of tokens that should appear in a candidate sequence. The token constraints are generated from checking whether a token predicted at each decoding step is feasible for a partial solution based on the production rules of the grammar of the programming language, the syntactic correctness of a partial sequence, and/or static type correctness.

Abstract: A false positive vulnerability system detects whether a software vulnerability identified by a static code vulnerability analyzer is a true vulnerability or a false positive. The system utilizes deep learning models to predict whether an identified vulnerability is accurate given the source code context of the identified vulnerability. A neural encoder transformer model is trained to classify a false positive given the method body including the identified vulnerability. A neural decoder transformer model is trained to predict a candidate line-of-code to complete a prompt inserted into the context of the identified vulnerability. The candidate line-of-code that successfully completes the prompt is used as a signal to identify that the identified vulnerability is a false positive.

Abstract: The invention relates to a compound represented by general Formula I, a stereoisomer thereof, a pharmaceutically acceptable salt thereof, a pharmaceutically acceptable ester thereof, a pharmaceutically acceptable hydrate thereof or pharmaceutically acceptable solvate thereof and the invention also relates to a pharmaceutical composition comprising the compound, and a preparation method for the compound and a use of the compound.

Abstract: Provided are a video processing method and apparatus, an electronic device, a storage medium and a program product. The method includes steps described below. A to-be-processed video is acquired, and a first face key point of a first target object in the to-be-processed video is recognized, where the first face key point corresponds to a mask key point in a three-dimensional human face mask special effect; and the three-dimensional human face mask special effect is added to video frames of the to-be-processed video to obtain a target video, where the mask key point in the three-dimensional human face mask special effect moves with the corresponding first face key point.

Abstract: The present invention relates to a substituted benzimidazole derivative as represented by formula (I) and a pharmaceutically acceptable salt, a polymorph, a tautomer, a stereoisomer, a hydrate, a solvate or an isotopic variant of the derivative.

Abstract: Disclosed is a method for preparing a C-nucleoside compound represented by Formula (III) or salt thereof. The present method has a high reaction yield, is simple to operate, uses a single metal reagent, has stable reaction temperature conditions, does not require frequent changes to the reaction system during the operation process, is suitable for scale-up synthesis, is suitable for large-scale production of Remdesivir, and has low costs.

Abstract: Embodiments of the present disclosure disclose a mounting bracket and a self-propelled robot. The mounting bracket includes a housing, a rotating shaft and a magnetic positioning assembly. The housing is provided with an inner cavity. The rotating shaft is configured to rotate about an axis in the inner cavity. The magnetic positioning assembly includes a first magnetic element and a second magnetic element which are respectively arranged on the housing and the rotating shaft. The laser distance sensor is attached to the rotating shaft and configured to rotate about the axis. The mounting bracket is configured to prevent the rotating shaft from deviating from the axis by generating a force between the first magnetic element and the second magnetic element in a radial direction of the rotating shaft.

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: A domain adaptation module is used to optimize a first domain derived from a second domain using respective outputs from respective parallel hidden layers of the domains.

Abstract: The present invention provides a range-finding method, apparatus, system, and non-transitory computer-readable storage medium. The method includes: acquiring a predicted number of interrupts of a single-chip microcomputer; acquiring a to-be-measured signal; triggering a first output of a comparator according to a strength of the to-be-measured signal and a preset trigger threshold; recording an ultrasonic signal and acquiring an actual number of interrupts according to the first output; and adjusting the trigger threshold according to the predicted number of interrupts and the actual number of interrupts, where the adjusted trigger threshold is used to trigger the first output next time.