Abstract: A configuration for reporting OOD samples for neural network optimization. The apparatus receives, from a base station, a configuration to report an OOD dataset for a machine learning model. The apparatus detects an occurrence of one or more OOD events. The apparatus reports the OOD dataset comprising the one or more OOD events based on the configuration to report OOD dataset. The apparatus receives, from the base station, an update to the machine learning model. The OOD dataset may comprise raw data related to the one or more OOD events, or may comprise extracted latent data corresponding to features of raw data related to the one or more OOD events.

Abstract: A photographing device for a vehicle and relates to the field of automatic driving technology is disclosed. The specific solution is that the photographing device includes a seat; a camera mounted on the seat; a lens holder mounted on the seat and rotatable relative to the seat; a transparent lens mounted on the lens holder and arranged opposite to the camera; and a driving assembly connected with the lens holder to drive the lens holder to rotate relative to the base.

Abstract: The present disclosure discloses a rolling ring shrink fitting tool for rotary equipment, including a lifting frame; a movement slot is formed in a bottom surface of a top of the lifting frame; an output end of a first motor is connected with a main gear; guide rollers are embedded in a lifting seat through bearings; shrink fitting plates are two semicircular structures; lifting lugs are welded on outer sides of the shrink fitting plates; tooth rings are arranged outside the shrink fitting plates; stop rods are fixed on inner walls of the tooth rings; supporting screw rods are embedded at sunken positions on inner walls of the shrink fitting plates through bearings.

Abstract: The present disclosure discloses a rolling ring shrink fitting tool for rotary equipment, including a lifting frame; a movement slot is formed in a bottom surface of a top of the lifting frame; an output end of a first motor is connected with a main gear; guide rollers are embedded in a lifting seat through bearings; shrink fitting plates are two semicircular structures; lifting lugs are welded on outer sides of the shrink fitting plates; tooth rings are arranged outside the shrink fitting plates; stop rods are fixed on inner walls of the tooth rings; supporting screw rods are embedded at sunken positions on inner walls of the shrink fitting plates through bearings.

Abstract: This application provides a packet forwarding method and a related apparatus. The method may include: A first device receives a first packet sent by a second device in a second cycle; and the first device determines a target cycle corresponding to the first packet based on cycle modification information corresponding to the first packet and a cycle mapping relationship, and forwards the first packet in the target cycle corresponding to the first packet.

Abstract: A ground fault directionality detection method, a ground fault directionality detection device and a computer-readable storage medium for a small current grounding system are disclosed. The ground fault directionality detection method comprises sampling at least a part of a current signal to obtain a numerical matrix; providing the numerical matrix as an input to a ground fault directionality detection neural network; calculating a label vector corresponding to the numerical matrix by the ground fault directionality detection neural network, wherein the label vector indicates whether the current signal is an upstream fault current signal or a downstream fault current signal; receiving a ground fault confirmation signal by the ground fault directionality detection neural network; and outputting the label vector by the ground fault directionality detection neural network when the ground fault confirmation signal indicates that the current signal is a ground fault current signal.

Abstract: An inrush current detection method, an inrush current detection device and a computer-readable storage medium for a transformer are disclosed. The inrush current detection method includes sampling at least a part of a current signal of the transformer to obtain a numerical matrix; providing the numerical matrix as an input to an inrush current detection neural network; and calculating and outputting a label vector corresponding to the numerical matrix by the inrush current detection neural network, wherein the label vector indicates whether the current signal is an inrush current.

Abstract: A communication terminal includes an upper flip cover and a lower flip cover rotatably connected to each other. The upper flip cover is provided with a metal plate. The lower flip cover is provided with a system motherboard. The system motherboard is connected to the metal plate.

Abstract: A split air cabin ventilation system for construction of tunnel inclined shafts, including a first air cabin and a second air cabin which are both in a hollow closed structure with an air inlet end and an air outlet end respectively at both sides. The two air outlet ends are arranged away from each other. An end of the split air cabin is provided with an air inlet, and the other end is provided with an air outlet. The air inlet is connected to an air source, and the air outlet is connected to the air inlet ends of the first and second air cabins, respectively. The air inlet end of the first air cabin is connected to another air source.

Abstract: The present application relates to tunnel monitoring and measuring, more particularly, to a quick fixing device for measuring a tunnel peripheral convergence and an application method thereof. A right-angle steel sheet includes a first steel sheet and a second steel sheet which are vertically fixed with each other. The fastener vertically penetrates the first steel sheet, and an explosive powder loading portion on a rear end of the fastener is arranged at a side of the second steel sheet. The reinforcing steel sheet is respectively connected to the first steel sheet and the second steel sheet as a reinforcing bar. A through hole is provided on the reinforcing spacer, through which the reinforcing spacer is sleeved on the fastener. The reinforcing spacer is arranged between the explosive powder loading portion on the rear end of the fastener and the first steel sheet.

Abstract: A mixing nozzle includes a first connector, a second connector, a first channel and a second channel, where a first end of the first channel is connected to the first connector, and a second end of the first channel is provided with a spraying opening in communication with the first channel; a first end of the second channel is connected to the second connector, and a second end of the second channel is in through connection with the first channel; the first connector is configured to introduce a first fluid into the first channel, and the second connector is configured to introduce a second fluid into the second channel; and a length of the second channel is less than a length of the first channel.

Abstract: An inrush current detection method, an inrush current detection device and a computer-readable storage medium for a transformer are disclosed. The inrush current detection method includes sampling at least a part of a current signal of the transformer to obtain a numerical matrix; providing the numerical matrix as an input to an inrush current detection neural network; and calculating and outputting a label vector corresponding to the numerical matrix by the inrush current detection neural network, wherein the label vector indicates whether the current signal is an inrush current.

Abstract: A ground fault directionality detection method, a ground fault directionality detection device and a computer-readable storage medium for a small current grounding system are disclosed. The ground fault directionality detection method comprises sampling at least a part of a current signal to obtain a numerical matrix; providing the numerical matrix as an input to a ground fault directionality detection neural network; calculating a label vector corresponding to the numerical matrix by the ground fault directionality detection neural network, wherein the label vector indicates whether the current signal is an upstream fault current signal or a downstream fault current signal; receiving a ground fault confirmation signal by the ground fault directionality detection neural network; and outputting the label vector by the ground fault directionality detection neural network when the ground fault confirmation signal indicates that the current signal is a ground fault current signal.

Abstract: The present invention relates to a compound having a benzo seven-membered ring structure, and a preparation method therefor, and use thereof. The compound has a structure as represented by formula (I). Provided is use of the compound having the structure and prepared with the preparation method of the present invention, enantiomers, diastereomers, racemates and mixtures thereof of the compound, as well as chemically acceptable salts, crystalline hydrates and solvent mixtures of the compound and the enantiomers, diastereomers, racemates and mixtures thereof of the compound in the preparation of drugs for treating BET Bromodomain BRD4 activity or expression level related diseases.

Abstract: An imaging device for a vehicle and a vehicle are disclosed. The imaging device includes: a casing, a camera, a wiping member, and a drive device. The casing includes a casing body and a transparent cover disposed to the casing body, and the transparent cover is rotatable relative to the casing body. The camera is disposed in the casing and configured to obtain image information outside the transparent cover through the transparent cover. The wiping member is disposed to the casing and is stationary relative to the camera. The drive device is connected with the transparent cover and configured to drive the transparent cover to rotate to enable the wiping member to wipe an outer surface of the transparent cover.

Abstract: A photographing device for a vehicle and relates to the field of automatic driving technology is disclosed. The specific solution is that the photographing device includes a seat; a camera mounted on the seat; a lens holder mounted on the seat and rotatable relative to the seat; a transparent lens mounted on the lens holder and arranged opposite to the camera; and a driving assembly connected with the lens holder to drive the lens holder to rotate relative to the base.

Abstract: A lidar base, a lidar device and an autonomous vehicle are provided, and relate to the technical field of automatic driving. Wherein, the lidar base includes: a seat body for installing a lidar assembly; a cover plate arranged on the seat body, and a diversion gap being defined between the cover plate and the base body, wherein an air outlet of the diversion gap is arranged toward the lidar assembly.

Abstract: A system is provided that includes a server having a first engine, a second engine, a search word warehouse, and a purchasing engine. The first engine (i) maps topics to product features of products using a topic hotness method which computes a hotness degree of a product on a topic from (a) product identifiers, (b) product features, (c) customer comments, and (d) topics with relevant key words, and (ii) builds a model providing a relevance degree of a topic to a product feature. The model is built based on the hotness degree. The second engine extracts remarkable topics based on product features using a method applied to the relevance degree of the topic to the product feature to identify remarkable topics for each product. The search word warehouse stores the remarkable topics for each product. The purchasing engine conducts purchases of products identified in searches using the remarkable topics.

Abstract: A split air cabin ventilation system for construction of tunnel inclined shafts, including a first air cabin and a second air cabin which are both in a hollow closed structure with an air inlet end and an air outlet end respectively at both sides. The two air outlet ends are arranged away from each other. An end of the split air cabin is provided with an air inlet, and the other end is provided with an air outlet. The air inlet is connected to an air source, and the air outlet is connected to the air inlet ends of the first and second air cabins, respectively. The air inlet end of the first air cabin is connected to another air source.

Abstract: Certain aspects and features relate to a system that monitors for kick and lost circulation in the riser string of an offshore drilling rig. The system compensates for annulus outflow fluctuation induced by wave (heave) motion in order to reduce false alarms, resulting in fewer drilling operation disruptions. The system includes a sensor or sensors disposable with respect to a drilling rig subject to rig motion. A processor receives a real-time position signal indicative of the rig motion from the sensor and applies a state observer to the position signal to determine annular flow parameters. The system models an annular flow for the wellbore to produce a modeled flow signal that reflects a position of the drilling rig relative to influx flow. The system uses the modeled flow to determine kick-loss-alarm parameters that take into account the heave motion.