601786 results about "Electrical and Electronics engineering" patented technology

The application provides a fault prediction method and apparatus, an electronic device and a storage medium. The method comprises: obtaining a vibration signal collected by a sensor installed on a target component of a target device, and cleaning and segmenting the vibration signal to obtain a target vibration signal; inputting the target vibration signal into a target anomaly judgment model to obtain an output result, and according to the output result, determining whether the target vibration signal is abnormal to obtain an anomaly judgment result; when the abnormal judgment result shows that the target vibration signal is abnormal, inputting the target vibration signal into a target fault prediction model to obtain a fault prediction result, wherein the target fault prediction model is obtained by combining an encoder of the target anomaly judgment model and a newly added full connection layer. The application solves the problem in the prior art that a faulty device cannot be timely maintained because the fault can only be monitored when the device fault is quite obvious.

Systems, methods, and apparatus are provided for automated identification of open space in a wireless communications spectrum, by identifying sources of signal emission in the spectrum by automatically detecting signals, analyzing signals, comparing signal data to historical and reference data, creating corresponding signal profiles, and determining information about the open space based upon the measured and analyzed data in near real-time.

The invention relates to the technical field of equipment fault diagnosis, and discloses an equipment fault diagnosis and prediction method based on deep learning, and the method comprises the following steps: S1, collecting multi-modal data in real time through a plurality of sensors installed on equipment; s2, preprocessing the collected data; s3, constructing a hybrid deep learning model; s4, dynamic weighted fusion is performed on the features of different modal data by using an attention mechanism, and comprehensive feature representation is generated; s5, using the marked fault data and normal data to supervise and train the model; s6, inputting equipment operation data acquired in real time into the trained model, and judging the state of the equipment; and S7, generating a potential fault early warning signal based on a prediction result of the model. A piezoelectric vibration sensor and a thermal infrared imager are arranged on a motor bearing through vibration, temperature and sound sensors, vibration waveforms, thermal imaging slices and time-frequency diagrams are synchronously captured, and composite state characteristics such as mechanical wear and temperature anomaly of equipment are comprehensively reflected.

The invention discloses a battery monomer, a battery device and a power utilization device. Each battery monomer comprises a positive pole piece, a negative pole piece, electrolyte and an isolating membrane arranged between the positive pole piece and the negative pole piece; the electrolyte comprises a solvent and an electrolyte salt, the electrolyte salt comprises lithium bis (fluorosulfonyl) imide, and based on the total mass of the electrolyte, the mass content of the lithium bis (fluorosulfonyl) imide is 1%-6%; the solvent comprises a chain carboxylic ester solvent, and the mass content of the chain carboxylic ester solvent is 5-75% based on the total mass of the electrolyte; the negative electrode plate comprises a negative electrode current collector and a negative electrode film layer arranged on at least one side of the negative electrode current collector, the negative electrode film layer comprises a negative electrode active material, and the graphitization degree of the negative electrode active material is 90-96%; the positive pole piece comprises a positive current collector and a positive film layer arranged on at least one side of the positive current collector, the positive current collector comprises aluminum foil, and the thickness of the aluminum foil is 10-16 microns.

The invention discloses an underground pipe network leakage detection method fusing big data analysis and machine learning. The underground pipe network leakage detection method comprises the step of deploying an acoustic sensor, a pressure sensor and a flow sensor at preset positions of an underground pipe network. Performing noise reduction and standardization processing on the acquired operation data, extracting frequency domain, energy and time sequence characteristics of acoustic signals to generate acoustic characteristic vectors, and calculating initial space coordinates of a leakage position based on time difference of arrival of the acoustic signals and sensor arrangement; and generating a pressure feature vector, and analyzing the spatial-temporal correlation of the flow data to generate a flow feature vector. And fusing acoustic, pressure and flow feature vectors to form a multi-dimensional feature vector, inputting the multi-dimensional feature vector and the initial space coordinates into a pre-trained cascade deep learning model, and outputting the leakage probability and the leakage position of underground pipe network leakage. And when the leakage probability exceeds a preset threshold value, triggering an alarm mechanism. According to the invention, efficient detection and accurate positioning of underground pipe network leakage are realized, and high real-time performance and positioning accuracy are achieved.

The invention relates to the technical field of the Internet of Things, and discloses a gas leakage monitoring method, device and equipment based on the Internet of Things and a storage medium, and the method comprises the steps: carrying out the data collection of a gas storage device, and obtaining an initial multi-dimensional data set; performing filtering and edge detection processing to obtain potential abnormal point data; inputting the potential abnormal point data into a mixed deep learning model for gas leakage detection to obtain initial leakage source position data and a leakage intensity value; executing multi-sensor cooperative accurate leakage positioning to obtain target leakage source position data; performing gas diffusion simulation to obtain gas concentration distribution data and risk indexes; based on the gas concentration distribution data and the risk index, dynamic reconstruction of the sensor network is carried out, an emergency response strategy and sensor network configuration information are output, and the method realizes whole-process management from leakage detection and source positioning to risk assessment and emergency response.

The invention provides an intelligent fire-fighting equipment self-inspection and fault early warning system based on an AI algorithm. The intelligent fire-fighting equipment self-inspection and fault early warning system comprises a sensing layer used for integrating a multi-source heterogeneous sensing unit; the edge layer is used for deploying intelligent preprocessing nodes; the transmission layer is used for constructing a safe and reliable transmission channel; the platform layer is used for establishing an intelligent analysis center; the application layer is used for providing intelligent decision service; and the five layers of architectures work cooperatively. According to the invention, full-dimension monitoring of fire-fighting equipment is realized through a multi-physics field cooperative sensing framework of a sensing layer, and the fault detection capability is remarkably improved. The multi-source heterogeneous sensing unit integrated in the sensing layer can capture various physical quantity information such as acoustics, vibration and thermal fields at the same time, information of different physical fields is complementarily enhanced through a cross-domain feature complementation enhancement mechanism, and more comprehensive equipment state features are obtained. In particular, the sensor self-adaptive excitation technology dynamically adjusts the excitation energy of the sensor according to the environmental interference degree, and ensures that high-quality signals can be obtained under different working conditions.

The invention discloses a battery monomer, a battery device and a power utilization device. Each battery monomer comprises a positive pole piece, a negative pole piece and an electrolyte; the lithium ion conductivity of the electrolyte is greater than or equal to 10 mS / cm; the negative electrode plate comprises a negative electrode current collector and a negative electrode film layer arranged on at least one side of the negative electrode current collector, the negative electrode film layer comprises a negative electrode active material, the negative electrode active material comprises a core part and a coating layer at least partially coating the surface of the core part, the core part comprises graphite, and the coating layer comprises graphite. In an R value cumulative distribution curve obtained by the negative electrode active material in a surface scanning mode of a laser microscopic confocal Raman spectrometer, an R value R50 with cumulative distribution of 50% is 0.15-0.50; in the obtained R values of the negative electrode active material, the number ratio of the R values smaller than or equal to 0.11 is smaller than or equal to 15%. The battery monomer provided by the invention has good dynamic performance and long cycle life.

The invention provides a circuit board fault diagnosis method and system based on artificial intelligence, and relates to the technical field of circuit board fault diagnosis, and the method comprises the steps: constructing a three-dimensional electromagnetic field simulation model of a circuit board, setting a plurality of virtual sensing probes in the three-dimensional electromagnetic field simulation model, and generating an electromagnetic field distortion distribution diagram; dividing a fault sensitive area of the circuit board based on the electromagnetic field distortion distribution diagram, outputting a performance degradation rate of each functional area of the circuit board, and generating a fault risk assessment matrix according to the performance degradation rate; performing function reconstruction on the circuit board according to the fault risk assessment matrix, establishing a dynamic fault-tolerant mechanism of the circuit board, generating a task load distribution strategy based on the dynamic fault-tolerant mechanism, and deploying the task load distribution strategy to a field programmable gate array of the circuit board. And self-repairing the circuit board by adjusting the logic structure of the field programmable gate array, verifying the repairing effect and outputting a diagnosis report.

The invention discloses a battery monomer, a battery device and a power utilization device. Each battery monomer comprises a positive pole piece, a negative pole piece and an electrolyte; the lithium ion conductivity of the electrolyte is greater than or equal to 10 mS / cm; the negative electrode plate comprises a negative electrode current collector and a negative electrode film layer arranged on at least one side of the negative electrode current collector, the negative electrode film layer comprises a negative electrode active material, the negative electrode active material comprises a core part and a coating layer at least partially coating the surface of the core part, the core part comprises graphite, and the coating layer comprises graphite. The concentration ratio (R90-R10) / R50 of an R value is less than or equal to 2.3 in an R value cumulative distribution curve obtained by the negative electrode active material in a surface scanning mode of a laser microscopic confocal Raman spectrometer.

A portable fan includes an airflow portion and a handheld portion. The airflow portion includes rotation air blades and a drive portion that is driveably connected to the rotation air blades. The drive portion is a three-phase motor that is configured to drive the rotation air blades to rotate to generate an airflow. The handheld portion is connected to the airflow portion. A power supply assembly is arranged inside the handheld portion; and the power supply assembly is electrically connected to and supply power to the three-phase motor.

The invention belongs to the technical field of electromechanical equipment operation and maintenance, and discloses an electromechanical equipment self-adaptive intelligent early warning system based on multi-source sensing data. The system is composed of a multi-source sensing module, an edge data acquisition and preprocessing module, a data cleaning and multi-dimensional feature extraction module, an equipment state dynamic modeling module, an intelligent fault prediction and trend analysis module, a self-adaptive early warning threshold generation and dynamic adjustment module, and an intelligent decision and remote cooperation module. The system is composed of a multi-source sensing module, an intelligent low-carbon operation and maintenance management and control module and a digital twin system integration and full-period mapping module, multiple sensors are deployed through the multi-source sensing module to acquire multi-dimensional data of equipment, cleaning and calibration are performed through the edge data acquisition and preprocessing module, deep processing is performed through the data cleaning and multi-dimensional feature extraction module, and multi-dimensional feature extraction is performed through the multi-source sensing module. The data integrity and accuracy are ensured; and data are quickly transmitted among the modules, so that the monitoring system can accurately present the running state of the equipment in real time.

The method can include: recording a neural state, determining a latent array, and determining an output based on the latent array. In variants, the method can function to enable a subject to use neural signals to navigate within a high-dimensional concept space to control an output (e.g., image generation, motor control, communication, etc.).

An online system trains a transformer architecture by an initialization method which allows the transformer architecture to be trained without normalization layers of learning rate warmup, resulting in significant improvements in computational efficiency for transformer architectures. Specifically, an attention block included in an encoder or a decoder of the transformer architecture generates the set of attention representations by applying a key matrix to the input key, a query matrix to the input query, a value matrix to the input value to generate an output, and applying an output matrix to the output to generate the set of attention representations. The initialization method may be performed by scaling the parameters of the value matrix and the output matrix with a factor that is inverse to a number of the set of encoders or a number of the set of decoders.

Provided are a method and a device for controlling cell change. The method may includereceiving a higher layer message including one or more candidate target cell configuration information for an L1 / L2-triggered mobility (LTM) operation; transmitting an L1 measurement result for a candidate target cell on the basis of the higher layer message; receiving a medium access control control element (MAC CE) indicating performance of an LTM operation to a target cell; and performing a cell change operation without RRC reconfiguration by applying the candidate target cell configuration information for the target cell on the basis of the MAC CE.

Various wearable health monitoring devices are described herein. Some implementations include one or more emitter chamber covers injection molded out of a first material comprising transparent glass, one or more detector chamber covers injection molded out of a second material comprising transparent glass, and a light barrier construct injection molded out of a third material over the one or more emitter chamber covers and the one or more detector chamber covers. The third material may be opaque and can comprise glass and an optically absorbing pigment. Some implementations include a circuit board, emitter(s) mounted to the circuit board and arranged within the emitter chamber cover(s), and detector(s) mounted to the circuit board and arranged within the detector chamber cover(s). The circuit board, emitter(s), detector(s), emitter chamber cover(s), and detector chamber cover(s) can form part of a sensor assembly connected to a housing of the wearable health monitoring devices.

A substrate holder includes a base configured to receive a substrate; a cover configured to mateably engage with the base, the cover defining an opening formed by inner sidewalls; and a removable insert defining a surface, the removable insert being configured to be received within the opening of the cover. The removable insert includes a gasket; a projection coupled to the gasket; and at least two insert tabs extending from opposite sides of the removable insert, each insert tab being configured to engage with at least one of the inner sidewalls forming the opening of the cover.

A wireless transmit / receive unit, WTRU, receives a plurality of positioning reference signals from a plurality of terrestrial transmission points, the positioning reference signals including at least one positioning reference signal from a first terrestrial transmission point and at least one positioning signal from a second terrestrial transmission point, on condition that at least one value based on first measurements of the plurality of positioning reference signals satisfies a condition, transmits a request to initiate, at the WTRU, positioning using positioning reference signals received from satellites, received, in response to the request, information about a set of satellites, selects at least one satellite from the set of satellites, determines a second position estimate for the WTRU based on at least one positioning reference signal received from at least one selected satellite, and sends to a network node a message comprising information indicating the second position estimate for the WTRU.

Systems, methods, and instrumentalities are disclosed herein for pre-processing for channel state information (CSI) compression in wireless system. A WTRU may receive configuration information that indicates a reference signal and a data processing model for channel state information (CSI) compression. The WTRU may determine CSI associated with a channel using the reference signal. The WTRU may determine a channel condition associated with pre-processing. The WTRU may select a pre-processing type from a plurality of pre-processing types based on the data processing model and the determined channel condition associated with pre-processing. The WTRU may pre-process the CSI associated with the channel based on the selected pre-processing type. The WTRU may generate compressed CSI by compressing the pre-processed CSI using the data processing model for CSI compression. The WTRU may send the compressed CSI to a network.

The invention discloses a wind turbine generator gearbox fault diagnosis method and system based on time-frequency feature cross complementation and multi-domain feature fusion. Collected original vibration signals are divided into a training set, a verification set and a test set; respectively utilizing FFT and CWT to obtain a one-dimensional frequency domain signal and a two-dimensional time-frequency graph of the data set; inputting the training set of the time domain signal and the frequency domain signal into a time-frequency cross attention mechanism network to obtain cross complementation characteristics of the time domain and the frequency domain; inputting the training set of the two-dimensional time-frequency graph into a two-dimensional residual CNN into which a complete attention mechanism is introduced to extract time-frequency domain features; fusing the cross complementation features of the time domain and the frequency domain and the time-frequency domain features to obtain multi-domain features, and performing fault classification by using a softmax function; and inputting test set data into the trained multi-domain feature fusion network model for testing to obtain a final fault diagnosis result. According to the method, the problem of incomplete feature extraction of deep learning fault diagnosis based on a single time domain signal and a frequency domain signal is solved, and the fault diagnosis precision is improved.

The invention relates to a battery monomer, a battery device and a power utilization device, the battery monomer comprises an electrode assembly and an electrolyte, and the electrode assembly comprises a positive pole piece and a negative pole piece; the positive pole piece comprises a positive pole current collecting part and a positive pole film layer; the positive pole film layer comprises lithium-containing phosphate with an olivine structure; the negative pole piece comprises a negative pole current collecting part and a negative pole film layer, and the negative pole film layer comprises a carbon-based material; the electrolyte comprises a carboxylic ester solvent, a first additive and fluorine-containing lithium sulfimide, and the mass content of the carboxylic ester solvent is 8%-60%; the total mass content of the first additive is 2.5%-10%, the first additive comprises 1, 3-propane sultone with the mass content larger than or equal to 0, an ethylene carbonate derivative with the mass content larger than or equal to 0 and vinylene carbonate with the mass content larger than 0, and the ethylene carbonate derivative comprises a compound shown in the formula A; the mass content of the fluorine-containing lithium sulfimide is 4%-8%. According to the invention, the rapid charging performance and the cycle performance of the battery monomer can be improved. # imgabs0 # formula A

The invention provides a photovoltaic power station photovoltaic power prediction method and system. A cloud layer motion time sequence library is constructed based on a historical cloud picture, and a nonlinear model of cloud speed and output attenuation is established. The light sensor array monitors the cloud layer thickness and the aerosol density in real time, calculates the light intensity attenuation gradient of the shadow area in combination with the model, and predicts the remaining time of the cloud cluster reaching the core area. Dividing a power prediction confidence interval according to remaining time, inputting satellite data into a multi-scale meteorological fusion architecture, and adjusting a meteorological feature extraction path of an attention mechanism based on cloud density. And fusing the surface reflectance correction value calculated by the scattering data of the light sensor to generate a short-term power prediction sequence of the sudden change cloud layer scene. And inputting the sequence into an energy management system, and outputting an active and reactive double-target scheduling instruction in combination with a grid-connected point voltage deviation and a reactive compensation parameter constrained by a power grid rule. According to the technical scheme provided by the invention, the cooperative scheduling precision of the photovoltaic power station in the cloud abrupt change scene is improved.

A system for displaying information indicative of driving conditions, to a driver, using a smart ring are disclosed. An exemplary system includes a smart ring with a ring band having a plurality of surfaces including an inner surface, an outer surface, a first side surface, and a second side surface. The system further includes a processor, configured to obtain data from a communication module within the ring band, or from one or more sensors disposed within the ring band. The obtained data are representative of information indicative of one or more driving conditions to be displayed to the driver. The smart ring also includes an electronic ink (e-ink) display disposed on at least one of the plurality of surfaces, and configured to present information indicative of the one or more driving conditions.

Methods, apparatus and systems are disclosed. In one embodiment, a method may be implemented by a first Wireless Transmit / Receive Unit (WTRU). The method may include receiving configuration information indicating a first set of RBs for performing a CSI-RS measurement, receiving an indication indicating a second set of RBs, and receiving an indication indicating that a first set of symbols or slots is not configured for a certain type of duplexing method and a second set of symbols or slots is configured for the certain type of duplexing method. The method may also include measuring a first CSI-RS in the first set of RBs in a symbol or slot in the first set of symbols or slots, measuring a second CSI-RS in a symbol or slot of the second set of symbols or slots in RBs that are in both the first set of RBs and the second set of RBs. determining a CSI based on the measurement of the first CSI-RS and the second CSI-RS, and reporting the CSI.

The invention relates to the technical field of battery management, and discloses a state monitoring and predicting method of an intelligent battery pack and related equipment. The method comprises the steps of obtaining original battery pack data and historical operation data of various preset battery pack parameters in a target intelligent battery pack, and performing signal filtering and spectral decomposition on the original battery pack data; abnormal data detection, abnormal correction, multi-mode characteristic decomposition and phase space mapping of the battery pack state are carried out on the initial battery pack characteristic data; extracting corresponding state-of-charge dynamic characteristics in the state evolution characteristics of the battery pack, and performing multilayer mapping and threshold classification on the state evolution characteristics based on historical operation data to obtain a state monitoring result; and obtaining a state transition matrix through state parameter coupling mapping and transition probability calculation, performing state evolution path calculation, and outputting a prediction result. According to the invention, correlation analysis among electrochemical parameters is realized, and reliable evaluation and accurate prediction of the state of the battery pack are enhanced.

A base station can receive, while a primary cell (PCell) and a secondary cell (SCell) are in a second power state, an uplink wake-up signal from a wireless device. In response to receiving the uplink wake-up signal, the base station can transition the PCell to a first power state and maintain the SCell in the second power state.

A smart ring charging system comprises a charging source integrated into an object, the object configured to be held by a user wearing a smart ring. The smart ring may include a ring-shaped housing and a power source disposed within or at the ring-shaped housing and configured to receive energy from the charging source while the user is wearing the smart ring and holding the object. A controller may be disposed within or at the ring-shaped housing, or at the object with the charger and configured to estimate a charging rate at which the power source receives the energy from the charging source. The system may further include one or more indicators configured to indicate the charging rate.

Pulsed electromagnetic field systems include planar microcoil arrays integrated into clothing. The planar microcoil arrays are connected to a neuromodulation controller and configured to generate an electrical current and transmit that electrical current, in accordance with a particular stimulation protocol, to each of the planar microcoil arrays.

The invention discloses a partial discharge detection method and device, and the method comprises the steps: outputting a multi-mode signal matrix after noise reduction through employing a self-adaptive noise reduction algorithm according to a multi-mode sensing signal during the operation of a generator; based on the multi-modal signal matrix, a space-time convolutional neural network is adopted to extract discharge features, meanwhile, a topological relation between signal time-frequency features and sensor space is captured, and a multi-modal feature fusion tensor is output; according to the multi-modal feature fusion tensor, a model is generated through a dynamic map, manifold learning and a particle swarm optimization algorithm are combined, and a dynamic fault map containing discharge intensity, phase and frequency point distribution characteristics is output; and based on the dynamic fault map, calculating a real-time discharge danger coefficient by using a risk prediction model, and outputting a discharge grading early warning instruction and a maintenance priority sequence. According to the embodiment of the invention, high-precision and traceable discharge detection and graded early warning can be realized.

The invention provides a curtain wall deformation condition safety detection method and device based on laser point clouds, and relates to the technical field of constructional engineering, and the method comprises the steps: 1, carrying out the coordinate system unification processing of a three-dimensional point cloud data set covering the whole surface of a curtain wall, generating a curtain wall surface digital twin model, and carrying out the coordinate system unification processing of a three-dimensional point cloud data set covering the whole surface of the curtain wall in the digital twin model; defining a first detection target point and a second detection target point according to geometrical characteristics and material joint characteristics of the curtain wall sheet; 2, according to the digital twinborn model, surface normal vector distribution characteristics are extracted, actually-measured wind pressure load distribution data and temperature field parameters are fused, a dynamic flexural deformation coupling calculation model is constructed, and global deformation parameters and local deformation parameters are output. According to the invention, the digital twinborn model is constructed through point cloud data processing, deformation and displacement parameters are extracted, the safety coefficient is evaluated, and high-precision, omnibearing and dynamic detection and safety risk early warning of the flatness of the building outer wall are realized.