Abstract: A welding process involves a fixture for holding a workpiece and a welder, or welding electrode. The fixture imposes ultrasonic vibration on the workpiece. The welder vibrates during vibration, and is operable at a first voltage for welding and a second voltage for peening. The peening may occur while the weldmetal is crystallizing. The welding process may be a process of welding two part as together, or of filling a groove or other feature, or of applying or restoring a surface, or of applying a hard facing or ceramic to a parent metal or object. The weldmetal may be the same, or substantially the same, as the parent metal, or it may be different. The different material may be a ceramic material.

Abstract: A system for improved localization of image forgery. The system generates a variational information bottleneck objective function and works with input image patches to implement an encoder-decoder architecture. The encoder-decoder architecture controls an information flow between the input image patches and a representation layer. The system utilizes information bottleneck to learn useful residual noise patterns and ignore semantic content present in each input image patch. The system trains a neural network to learn a representation indicative of a statistical fingerprint of a source camera model from each input image patch while excluding semantic content thereof. The system can determine a splicing manipulation localization by the trained neural network.

Abstract: A safety detection method for a battery module is provided in this application, which includes: obtaining a plurality of battery temperatures detected by the plurality of temperature sensors at a first moment; determining a standard battery temperature based on the plurality of battery temperatures; obtaining a second battery temperature of a first battery set at a second moment; determining a temperature change rate of first battery set based on a first battery temperature, a second battery temperature, the first moment, and the second moment; and determining that a battery in the first battery set has a liquid leakage risk when a third difference between the first battery temperature detected by the first temperature sensor at the first moment and the standard battery temperature is greater than a first temperature threshold, and the temperature change rate is greater than a temperature change rate threshold.

Abstract: The energy storage system includes battery cells, a subrack, a backplane, and a battery management system BMS. The subrack reserves a plurality of battery cell slots, the battery cells are connected to the backplane through the battery cell slots. The backplane is installed in the subrack, a first power terminal is reserved at a position corresponding to the battery cell slot on the backplane, and a plug-in power terminal is formed by a second power terminal of the battery cell together with the first power terminal. A power circuit, a sampling circuit, and an equalizer circuit are integrated into the backplane, and the power circuit, the sampling circuit, and the equalizer circuit are connected after the second power terminal is plugged and docked with the first power terminal. The BMS is connected to the backplane for managing the energy storage system.

Abstract: Computer vision systems and methods for localizing image forgery are provided. The system generates a constrained convolution via a plurality of learned rich filters. The system trains a convolutional neural network with the constrained convolution and a plurality of images of a dataset to learn a low level representation of each image among the plurality of images. The low level representation is indicative of a statistical signature of at least one source camera model of each image. The system can determine a splicing manipulation localization by the trained convolutional neural network.

Abstract: A method for operating a comprehensive three-dimensional teaching field, including: collecting, by a sensor, a depth data of a real teaching space, point cloud data of a teacher and voice data of the teacher; performing calculation and caching of an architecture for data storage, transmission and rendering of a virtual teaching space based on edge cloud; building a database model of the virtual teaching space by using a R-tree spatial index structure to realize distributed data storage; generating a virtual avatar model updating in real time by positioning and tracking an action of a user; displaying an image of the virtual teaching space on terminals of the teacher and a student through encoding, uploading, 5G rendering and decoding by using a 5G link.

Abstract: Computer vision systems and methods for localizing image forgery are provided. The system generates a constrained convolution via a plurality of learned rich filters. The system trains a convolutional neural network with the constrained convolution and a plurality of images of a dataset to learn a low level representation of each image among the plurality of images. The low level representation is indicative of a statistical signature of at least one source camera model of each image. The system can determine a splicing manipulation localization by the trained convolutional neural network.

Abstract: Machine learning (ML) systems and methods for fact extraction and claim verification are provided. The system receives a claim and retrieves a document from a dataset. The document has a first relatedness score higher than a first threshold, which indicates that ML models of the system determine that the document is most likely to be relevant to the claim. The dataset includes supporting documents and claims including a first group of claims supported by facts from more than two supporting documents and a second group of claims not supported by the supporting documents. The system selects a set of sentences from the document. The set of sentences have second relatedness scores higher than a second threshold, which indicate that the ML models determine that the set of sentences are most likely to be relevant to the claim. The system determines whether the claim includes facts from the set of sentences.

Abstract: A method for generating sense of reality of a virtual object in a teaching scene includes perception of a teaching space, generation of sense of reality of a virtual object and generation of real effect of dynamic interaction. The method is specifically performed through steps of collecting depth data of the teaching space; perceiving changes of a scene object in a field of view in real time; collecting a light intensity in the teaching scene to realize a virtual-real fused lighting effect; generating a shadow effect of the virtual object in real time by using ShadowMap; and guiding a teacher to use a multi-modal algorithm to complete a real-time interaction with the virtual object by setting interactive prompts of a sight target and a virtual hand.

Abstract: A system and method for producing a series of time-resolved magnetic resonance (MR) images is set forth. The system can perform method steps of encoding spatial information into an MRI signal by manipulating a phase of the MRI signal within an MRI system, generating and outputting a phase-encoded MRI signal over time by digitizing a plurality of time points in the MRI signal, repeating the generating and outputting step for a plurality of phase-encoded signals, each phase-encoded signal in synchrony with a trigger, producing a plurality of digitized time points, and reconstructing a series of time resolved MR images, each image of the series of MR images at one specific time point selected from the plurality of digitized time points for each phase-encoded step. Each image in the series of time-resolved MR images corresponding to a specific time point in a cyclic event.

Abstract: A method for generating a high-precision and microscopic virtual learning resource includes acquisition of high-definition specimen images, generation of a 3D model of a surface a specimen and interactive display of a microscopic virtual learning resource.

Abstract: The energy storage system includes battery cells, a subrack, a backplane, and a battery management system BMS. The subrack reserves a plurality of battery cell slots, the battery cells are connected to the backplane through the battery cell slots. The backplane is installed in the subrack, a first power terminal is reserved at a position corresponding to the battery cell slot on the backplane, and a plug-in power terminal is formed by a second power terminal of the battery cell together with the first power terminal. A power circuit, a sampling circuit, and an equalizer circuit are integrated into the backplane, and the power circuit, the sampling circuit, and the equalizer circuit are connected after the second power terminal is plugged and docked with the first power terminal. The BMS is connected to the backplane for managing the energy storage system.

Abstract: Provided is a 5G interactive distance dedicated teaching system based on holographic terminal and a working method thereof. The distance dedicated teaching system includes a data acquisition module, a data transmission module, a 5G cloud rendering module, a natural interaction module, a holographic display module and a teaching service module.

Abstract: A fusion method for movements of a teacher in a teaching scene includes normalization, motion perception and fusion of movements. According to interaction needs in an enhanced teaching scene, this application establishes a moving information collection and a conversion of moving position and range to realize the normalization of movement.

Abstract: A fusion method for movements of a teacher in a teaching scene includes normalization, motion perception and fusion of movements. According to interaction needs in an enhanced teaching scene, this application establishes a moving information collection and a conversion of moving position and range to realize the normalization of movement.

Abstract: Provided is a 5G interactive distance dedicated teaching system based on holographic terminal and a working method thereof. The distance dedicated teaching system includes a data acquisition module, a data transmission module, a 5G cloud rendering module, a natural interaction module, a holographic display module and a teaching service module.

Abstract: A battery system is provided, including a processing module and a plurality of battery modules. Each of the plurality of battery modules includes a battery management system and an electrochemical cell pack controlled by the battery management system. The processing module is configured to control the electrochemical cell pack to alternately perform a discharging or charging operation. A sum of power of battery modules other than a first battery module in the plurality of battery modules is greater than power required by a target power-supplied object, and the first battery module is any one of the plurality of battery modules. A battery management system is configured to record a target time. The processing module or the battery management system is configured to determine a state of health of the electrochemical cell pack in the first battery module based on the target time.

Abstract: A sealing device able to contain corrosive liquids includes a base body and a sealing door covering the base body. The base body defines a receiving chamber which defines an opening. The sealing door carries a protrusion and a seal ring. The protrusion corresponds in position and size to the opening to seal the receiving chamber. The protrusion is corrosion resistant and it is the protrusion which experiences sputtering and sloshing of the liquid and not the seal ring. The seal ring is sleeved on the protrusion to seal the base body and the sealing door. The present disclosure further provides a machine including the sealing device.

Abstract: A method and system for retransmitting an emergency message including receiving, at a communication device, the emergency message including a first identifier indicative of a communication type and a second identifier indicative of a type of emergency. An electronic processor of the communication device selects, for distribution of the emergency message, a plurality of communication channels and at least one communication type based on the second identifier. The electronic processor prioritizes the plurality of communication channels and the at least one communication type according to a transmission priority having a higher priority associated with at least one of the group consisting of the first identifier and the second identifier. Then, the electronic processor controls transmission of the emergency message according to the transmission priority over the plurality of communication channels and the at least one communication type.

Abstract: A particulate filtering device with a multi-layer water distribution and collection structure and a method for using the same are provided. The device includes a tank where a filtering space and a back flushing expansion space are formed. An upper water distribution pipe is arranged above the back flushing expansion space and is in communication with an ozone gas-water mixing pipe. Ozone enters the back flushing expansion space through the upper water distribution pipe and mix with water for reaction. Exhaust gas is discharged from the top of the tank. Powdered activated carbon may enter the tank through the upper water distribution pipe, and is intercepted at a space above the filtering space to form an activated carbon layer, to absorb organics dissolved in the water and catalytically decompose ozone. At least three water distribution and collection pipes are arranged on a layer basis in the filtering space.