Abstract: A deep learning fault diagnosis method includes the following steps: a fault diagnosis data set X is processed based on sliding window processing, to obtain a picture-like sample data set {tilde over (X)}, and obtain an attention matrix A of the picture-like sample data set {tilde over (X)}; and a 2D-CNN model is constructed to process the picture-like sample data set {tilde over (X)} to obtain a corresponding feature map F, and in the meantime, the feature map F is processed based on channel-oriented average pooling and channel-oriented maximum pooling to obtain an output P1 of the average pooling and an output P2 of the maximum pooling, and a weight matrix W is obtained based on the attention matrix A, the output P1 of the average pooling, and the output P2 of the maximum pooling, so that an output of the model is a feature map {tilde over (F)} based on an attention mechanism, where {tilde over (F)}=WF.

Abstract: Disclosed are an accelerated test data analysis method and apparatus based on a grey forecast model, a device.

Abstract: A performance degradation-based product reliability weak link evaluation method includes: acquiring a performance degradation parameter of each component of a to-be-evaluated product corresponding to each test time point; evaluating the performance degradation parameter of each component corresponding to each test time point through a fault time evaluation model, to obtain a pre-fault operating duration of each component; evaluating the pre-fault operating duration of each component through a confidence-based unreliability evaluation method, to obtain an unreliability evaluation result of each component; generating at least one component service life distribution model corresponding to each component according to the unreliability evaluation result, and selecting a corresponding target component service life distribution model; and evaluating mean time between failures corresponding to each component according to the target component service life distribution model, and selecting a reliability weak link of th

Abstract: The present disclosure discloses a method and apparatus for estimating product lifetime based on a multi-stress accelerated test, and a device. This method can be applied in the field of data processing technologies, specifically including: determining, in response to a lifetime estimation request for a target product, a target characteristic lifetime of the target product based on a target stress condition for the target product and correspondence relationships between candidate stress conditions and candidate characteristic lifetimes; and determining, based on an optimal lifetime model for the type to which the target product belongs and the target characteristic lifetime, a target average life of the target product.

Abstract: The present disclosure relates to a method and an apparatus for processing accelerated test data based on multiple performance degradation, and a device.

Abstract: The present disclosure relates to a method and an apparatus for reliability evaluation based on multiple performance degradation, a computer device, a storage medium, and a computer program product. The method includes: for each of the multiple performances of a target product, obtaining a plurality of candidate functions that the performance possibly follows, determining a target function that satisfies a preset selection condition from the plurality of candidate functions, and determining a reliability function corresponding to the performance based on the target function; determining coupling relation information between the multiple performances of the target product, and obtaining redundancy information of the multiple performances of the target product; and performing a reliability evaluation on the target product based on the coupling relation information, the redundancy information, and the reliability function of each performance.

Abstract: The present disclosure relates to a method and an apparatus for processing accelerated test data based on multiple performance degradation, and a device.

Abstract: A method for processing accelerated degradation test data based on Wiener process includes obtaining accelerated degradation test data of a to-be-tested product, selecting a target time conversion model from a predefined set of time conversion models based on the accelerated degradation test data, constructing a nonlinear Wiener degradation process based on the target time conversion model, determining a product reliability function of the to-be-tested product, and testing the reliabilities of the to-be-tested product based on the product reliability function to obtain product reliability test results of the to-be-tested products.

Abstract: Disclosed are a fault prediction method and apparatus for a power conversion device, and a power conversion system. The method includes: acquiring multiple output voltages of a detecting coil in a preset time period, wherein an electromagnetic induction is generated between the detecting coil and a switching-on circuit of a switching transistor in the power conversion device; extracting each output frequency corresponding to each output voltage of the detecting coil; predicting time when the power conversion device fails according to a change trend of each output frequency. The apparatus includes a detecting coil and a data processing device; the detecting coil is connected to the data processing device and is a closed coil; the data processing device is configured to: acquire an output voltage of the detecting coil, extract corresponding output frequency, and predict time when the power conversion device fails according to a change trend of each output frequency.

Abstract: A deep learning fault diagnosis method includes the following steps: a fault diagnosis data set X is processed based on sliding window processing, to obtain a picture-like sample data set {tilde over (X)}, and obtain an attention matrix A of the picture-like sample data set {tilde over (X)}; and a 2D-CNN model is constructed to process the picture-like sample data set {tilde over (X)} to obtain a corresponding feature map F, and in the meantime, the feature map F is processed based on channel-oriented average pooling and channel-oriented maximum pooling to obtain an output P1 of the average pooling and an output P2 of the maximum pooling, and a weight matrix W is obtained based on the attention matrix A, the output P1 of the average pooling, and the output P2 of the maximum pooling, so that an output of the model is a feature map {tilde over (F)} based on an attention mechanism, where {tilde over (F)}=WF.

Abstract: A predictive maintenance system and method for intelligent manufacturing equipment is provided. The predictive maintenance system includes a first-stage predictive maintenance module, a second-stage predictive maintenance module, and a maintenance decision module. The first-stage predictive maintenance module includes an acquisition module, a human-computer interaction module, a calculation module, and a storage module. The second-stage predictive maintenance module includes a communication module, a setting module, and a prediction module. The maintenance decision module is configured to receive a first-stage remaining service life calculated by the first-stage predictive maintenance module and a second-stage remaining service life predicted by the second-stage predictive maintenance module, and determine a predictive maintenance strategy of the intelligent manufacturing equipment according to the first-stage remaining service life and the second-stage remaining service life.

Abstract: The present application describes a path selection method and apparatus. The method may include obtaining a required latency of a service. The method may further include determining a target path for the service from m strict explicit paths based on the required latency, where a latency of the target path is less than or equal to the required latency, all the m strict explicit paths are unallocated paths, any subpath of a first strict explicit path in the m strict explicit paths exists in only the first strict explicit path, the first strict explicit path is any path in the m strict explicit paths, and m is an integer greater than or equal to 1. The present invention is applicable to the field of communications technologies and resolves at least a problem where a path computation element (PCE) cannot ensure that a path allocated to a service can meet a latency requirement of the service.

Abstract: The present application describes a path selection method and apparatus. The method may include obtaining a required latency of a service. The method may further include determining a target path for the service from m strict explicit paths based on the required latency, where a latency of the target path is less than or equal to the required latency, all the m strict explicit paths are unallocated paths, any subpath of a first strict explicit path in the m strict explicit paths exists in only the first strict explicit path, the first strict explicit path is any path in the m strict explicit paths, and m is an integer greater than or equal to 1. The present invention is applicable to the field of communications technologies and resolves at least a problem where a path computation element (PCE) cannot ensure that a path allocated to a service can meet a latency requirement of the service.

Abstract: According to the present invention, a computer is provided, which comprises a host system, an embedded subsystem, a power source, an input device control module, a first transmission interface and a second transmission interface, the input device control module being connected to the embedded subsystem through the first transmission interface, wherein the input device control module is configured to establish, in response to receipt of a first switching instruction, communication with the embedded subsystem such that the embedded subsystem is enabled to process input data from an input device and to transmit the input data obtained from the input device to the first transmission interface; and the embedded subsystem is configured to receive the input data from the first transmission interface, process the input data and perform an operation corresponding to the input data.

Abstract: A data output method and apparatus according to the present invention, which are applicable in a data processing device comprising an output unit, a computer system and an embedded system, generate a control command for enabling an establishment of a channel for outputting data when it is determined that the computer system stays in a non-operating state, establish a data transmission channel between the embedded system and the output unit based on the control command, determine data to be outputted, and transfer the data to be outputted from the embedded system to the output unit through the data transmission channel. In this way, the method and apparatus according to the present invention can ensure that a user need not wait a long time for the computer's start-up, and can carry out an operation on local data for the computer in time, which improves the user satisfaction.

Abstract: The present invention provides a computer system, a notebook computer and a method for controlling a computer system. The method comprises steps of: determining current state of the main computer subsystem; turning off the power of the embedded subsystem or enabling the embedded subsystem into a low-power state of the embedded subsystem when the main computer subsystem stays in a power-on state of the main computer subsystem; and enabling the embedded subsystem into an operating state of the embedded subsystem when the main computer subsystem stays in a low-power state or a shut-down state of the main computer subsystem. The computer system comprises: a power supply, a main computer subsystem and an embedded subsystem, wherein the main computer subsystem comprises a state determination module and a state control module for the embedded subsystem.

Abstract: Disclosed is a hybrid-system computer comprising a first system, a second system and a power supply unit, wherein the power supply unit is connected to the first system and the second system, respectively, and wherein power consumption in an operating state of the second system is lower than that in an operating state of the first system; the hybrid-system computer further comprises: a triggering unit configured for obtaining a switching command when the first system is in an operating state and the second system is in a non-operating state; and a switching unit connected to the triggering unit, the first system and the second system, respectively, and configured for receiving the switching command and controlling the first system to enter a non-operating state and the second system to enter an operating state based on the switching command.

Abstract: The present invention provides a data processing device and a method for switching states thereof. The data processing device comprises an operating system and a communication interface for communicating with another data processing device, wherein the communication interface is enabled when the operating system stays in the operating state of the operating system, and the communication interface is disabled when the operating system stays in a low-power-consumption state.

Abstract: Disclosed is a hybrid-system computer comprising a first system, a second system and a power supply unit, wherein the power supply unit is connected to the first system and the second system, respectively, and wherein power consumption in an operating state of the second system is lower than that in an operating state of the first system; the hybrid-system computer further comprises: a triggering unit configured for obtaining a switching command when the first system is in an operating state and the second system is in a non-operating state; and a switching unit connected to the triggering unit, the first system and the second system, respectively, and configured for receiving the switching command and controlling the first system to enter a non-operating state and the second system to enter an operating state based on the switching command.

Abstract: According to the present invention, a computer is provided, which comprises a host system, an embedded subsystem, a power source, an input device control module, a first transmission interface and a second transmission interface, the input device control module being connected to the embedded subsystem through the first transmission interface, wherein the input device control module is configured to establish, in response to receipt of a first switching instruction, communication with the embedded subsystem such that the embedded subsystem is enabled to process input data from an input device and to transmit the input data obtained from the input device to the first transmission interface; and the embedded subsystem is configured to receive the input data from the first transmission interface, process the input data and perform an operation corresponding to the input data.