196results about How to "Save computing resources" patented technology

The application provides a low-grade oil reservoir water injection development effect evaluation method, comprising the following steps: S1, collecting core scale limit oil displacement efficiency data; S2, collecting well pattern controlled reserve degree data; S3, calculating sweep efficiency of the low-grade water drive oil reservoir; S4, correcting the sweep efficiency according to the changes of reservoir physical property parameters caused by near-well pollution and reservoir energy decline; and S5, calculating the reference recovery rate and evaluating the development effect. The application can effectively avoid collecting and arranging a large number of cumbersome production dynamic data, fully utilize the flow characteristics and dynamic physical property parameter evolution of the low-grade oil reservoir, accurately evaluate the development effect of the low-grade oil reservoir, and be beneficial to efficient development of the low-grade oil reservoir.

The invention relates to the technical field of data processing and state monitoring, and discloses an intelligent ring main unit fault real-time diagnosis method and system, and the method comprises the steps: constructing a fault feature over-complete dictionary; collecting and preprocessing high-frequency operation data streams of the ring main unit in real time; carrying out online sparse decomposition and manifold mapping based on the dictionary, and converting a high-dimensional signal into a low-dimensional sparse coefficient and manifold features; and a lightweight classification model is used for rapid reasoning, and fault early warning and data uploading are triggered when abnormity is detected. The system comprises a data acquisition module, a preprocessing unit, an edge computing engine, an intelligent diagnosis module and a communication gateway. According to the method, depth dimension reduction and feature enhancement are realized through a manifold sparse coding technology, the bandwidth pressure and the calculation overhead are reduced on the premise of ensuring the fault feature integrity, and the real-time performance and the accuracy of diagnosis are improved.

The invention discloses a high-precision coordinate calculation method based on Matlab, and belongs to the field of coordinate calculation technology and data processing, and the method comprises the steps: firstly, obtaining the combination of all points and vectors through a specific combination generation function, and then initializing a result vector; aiming at each combination, calculating intersection point coordinates and parameters by virtue of an accurate geometric intersection point calculation function, storing the intersection point coordinates and parameters in a result vector, and distributing the intersection point coordinates and parameters to a working area according to a rule by virtue of a working area assignment function; then, a midpoint coordinate matrix is obtained by applying a midpoint calculation function based on the coordinates of the intersection points, the distance between the points is calculated, a clustering center is determined by adopting a clustering algorithm, points of an intersection point concentrated area are screened out according to distance characteristics in a cluster, and finally, high-precision coordinates are calculated through a weighted average calculation function in combination with priori knowledge and weights. According to the method, the coordinate calculation precision can be effectively improved, good noise immunity is achieved, priori knowledge can be fully fused, and the method is suitable for numerous fields with high coordinate precision requirements.

This application relates to the field of integrated circuit design technology, and in particular to a hardware-software integrated border texture sampling system. This system implements border texture sampling through a hardware-software integration approach, supports user-defined sampling colors, and pre-stores a target texture lookup table on the software side, providing the hardware side with the target index value for the customized color. The hardware side only needs to perform target offset mapping and target address calculation to directly read the target texture data from the cache based on the target address, eliminating the need for format conversion after obtaining the texture data, thus saving hardware computing resources. Furthermore, the target texture lookup table contains texture data in multiple data formats, so the hardware side does not need to always obtain large-bit-width texture data and then convert it, but can directly obtain the texture data with the required bit width, thereby reducing the memory access bandwidth on the hardware side and improving border texture sampling efficiency.

The invention discloses a wind generating set risk early warning method, device and equipment in sand storm weather and a storage medium, and relates to the technical field of wind power generation, and the wind generating set risk early warning method in sand storm weather at least comprises the following steps: collecting multi-source meteorological data in a target area, judging whether a preset sand storm early warning condition is triggered or not according to the multi-source meteorological data; in response to the condition of triggering sand storm early warning, simulating the motion condition of sand and dust according to the multi-source meteorological data and the digital elevation model of the target area, and predicting to obtain sand and dust settlement distribution information in the target area; determining at least one to-be-protected generator set according to a preset wind generating set distribution diagram and the sand and dust sedimentation distribution information; and executing a protection control strategy on the to-be-protected generator set according to the multi-source meteorological data and the sand and dust settlement distribution information. The protection effect on the wind generating set in the sand storm weather is improved, and power generation output is guaranteed.

The application relates to the field of phased array antennas, and discloses a subarray-level anti-interference implementation method based on a planar phased array, which can quickly and accurately perform null processing on multiple interference signals at the subarray level when the planar phased array performs digital beam forming, thereby effectively receiving the expected signals while suppressing the interference. The implementation scheme is as follows: the planar phased array is arranged, and the center position coordinates of each subarray and the array element position coordinates are stored; the target information features are extracted by using a fast capture technology to determine the spatial target positions of the expected signals and the interference signals; a subarray-level constraint matrix C and a constraint vector f required for anti-interference are constructed; the optimal weight values are solved in the unit of the subarray; and a directional diagram is scanned. The anti-interference implementation method based on the planar phased array can be implemented at the subarray level, does not need to know the expected signals and calculate the covariance matrix of the received signals, saves the calculation resources, and can conveniently and quickly perform null processing on the positions of all the interference signals in the directional diagram.

The invention discloses a full-process visual monitoring and intelligent management method for a glass bracket production line, and relates to the technical field of industrial quality control, and the method comprises the steps: carrying out the continuous image collection of all stations of the glass bracket production line through an image collection unit, and constructing a full-process image data sequence; detecting the size of the glass bracket by using the qualified glass bracket size image database, and judging whether the size is abnormal or not; further performing defect detection on the glass bracket with the normal size, and determining whether an abnormal defect exists or not through pixel value difference analysis; and finally, summarizing the glass brackets with abnormal sizes or defects and related information thereof, and generating a visual quality report, so as to quickly position problems and optimize the production process. The comprehensive monitoring and intelligent management of the glass bracket production process are realized, and the production efficiency and the product quality are improved.

The application discloses a kind of battery core temperature online estimation and prediction method, system, equipment and storage medium based on mixed TSDM-AMBO-GRU, applied to lithium ion battery core temperature estimation and prediction field, comprising: obtaining battery operating data, and utilizing TSDM to create synthesis of battery operating data, as training set with battery operating data together;Training set is input to BO-GRU-AM framework, and the battery core temperature prediction model based on BO-GRU-AM is obtained by training;Input test set to battery core temperature prediction model, and obtain battery core temperature prediction result.The application not only can effectively overcome the problem caused by uneven distribution of temperature sensors and limited data in lithium ion battery system, and can realize real-time, efficient and accurate battery core temperature prediction under various temperatures and complex conditions, provide reliable fault warning and real-time monitoring support for BMS in practical application.

The application discloses a laser vision real-time weld seam tracking method based on a lightweight target detection network, and the method comprises the following steps: before welding, an industrial camera collects an initial weld seam image and transmits the initial weld seam image to an embedded industrial computer, pixel coordinate values of initial weld seam feature points are acquired, and a starting position of the weld seam is obtained; a lightweight target neural network is constructed; during welding, the industrial camera continuously collects weld seam images and sends the weld seam images to the embedded industrial computer, pixel coordinate values of weld seam feature points in the weld seam images are extracted by using the lightweight target neural network; a welding position to be reached by a robot is obtained through the pixel coordinate values of the weld seam feature points; a difference between the welding position of the robot and a current position of the robot is calculated, and a deviation value is sent to a control cabinet, so that the welding gun of the robot is controlled to automatically track and move along the weld seam. The weld seam image is detected by using the lightweight target neural network, and the problem that the real-time rate of the existing weld seam tracking method is not high on a resource-limited device is solved.

The present application belongs to the technical field of internet of things device monitoring, and particularly relates to a kind of internet of things device survival state real-time monitoring method and system, comprising: monitoring each internet of things device to receive the heartbeat signal periodically sent by internet of things device;According to the heartbeat signal periodically sent by internet of things device and the device type of internet of things device, the survival state of internet of things device is determined;When the survival state of internet of things device is abnormal, reconnect internet of things device.The technical scheme provided by the present application not only realizes the use of less computing resources, monitors more device states, reduces the cost of purchasing servers;It can also automatically realize the monitoring and state reconnection of state, reduce personnel operation, greatly improve the maintenance efficiency, and reduce the maintenance cost.

This invention provides a target detection method, apparatus, electronic device, and storage medium. The method includes: acquiring echo data received by a vehicle-mounted radar; performing a Fast Fourier Transform (FFT) on the echo data to obtain range-Doppler two-dimensional data; and performing detection processing on the range-Doppler two-dimensional data according to a preset pre-detection tracking model to obtain a target detection result. The preset pre-detection tracking model includes at least a particle filter-based pre-detection tracking model. The preset pre-detection tracking model employs a first preset likelihood ratio function, which includes a background noise amplitude term and a sum term of the target's amplitude and the background noise amplitude. Using this invention can reduce the computational resources consumed by particle filter-based pre-detection tracking algorithms for target detection, thereby reducing its computational cost.

The invention discloses a cleaning method and device, a cleaning robot and a readable storage medium, and the method comprises the steps: obtaining a single-frame image, carrying out the recognition of the single-frame image based on a preset deep learning algorithm, and obtaining an initial behavior recognition result; based on a multi-frame image fusion judgment strategy, performing fusion judgment on the initial behavior recognition result corresponding to each single-frame image to obtain a first behavior recognition result; if the first behavior recognition result is abnormal recognition, accumulating each single-frame image, performing time sequence behavior recognition on multiple frames of images obtained by accumulation according to a time sequence behavior recognition algorithm, and determining a second behavior recognition result; determining a target behavior recognition result based on the first behavior recognition result and the second behavior recognition result; the target behavior recognition result is used for determining a target cleaning strategy so as to perform cleaning processing. By adopting the method, the cleaning efficiency is improved.

This invention provides a perception fusion arbitration method and system based on vehicle-to-everything (V2X) communication. The method includes: acquiring a ground truth model of the perception system for the road environment and meteorological information; acquiring perception information and data quality parameters from each sensor in the vehicle-mounted perception system; retrieving the influence coefficients of each sensor corresponding to the meteorological information and calculating the perception quality score of each sensor based on the data quality parameters to determine the optimal sensor; selecting candidate arbitration ratios from a pre-set perception fusion arbitration ratio case library; performing simulated fusion calculations on the perception information; comparing the matching degree of each fusion result with the ground truth model of the perception system to determine the optimal arbitration ratio; and sending the result to the vehicle controller. This invention achieves adaptive output of the optimal vehicle-mounted sensor fusion weight ratio according to the specific meteorological environment, significantly reducing the perception misidentification rate in adverse environments such as rain, snow, fog, and sandstorms, ensuring the perception prediction accuracy of the autonomous driving system in all weather conditions.

The application discloses a Spike-BP on-chip learning method and system based on a Ca-LIF neuron model and a processor, wherein a trainable linear leakage parameter and a positive and negative double-channel pulse transmitter mechanism based on calcium gating are adopted; for the Ca-LIF neuron model, a linear leakage operation can be realized only by subtraction, complex leakage compensation operations can be avoided when a gradient matrix is solved, hardware implementation complexity is reduced, a large amount of calculation resources of subsequent hardware design is saved, and the performance of pulse neural network training is improved.

The invention provides an image rendering method and device, a storage medium and electronic equipment, and relates to the technical field of image processing, and the image rendering method comprises the steps: obtaining graphic elements of a to-be-rendered target image and attribute information of the graphic elements through a central processing unit; and sending a rendering instruction to the coprocessor through the central processing unit, so that the coprocessor renders the target image according to the graphic element and the attribute information in response to the rendering instruction. The computing process of the central processing unit is shared through the coprocessor, the load of the central processing unit can be reduced, and computing resources used by the central processing unit during image rendering are saved.

The application discloses an event reporting method, a setting device, a target device and a system based on MCTP, and the method comprises the following steps: the setting device sends a setting event message with the MCTP message type code being 0x77 to the target device, the message at least containing an event label, a data length and an event condition described by a formatted string key-value pair; the target device receives and stores the event condition; when the event condition is met, the target device actively sends a reporting event message with the code being 0x77 to the setting device. By using the event notification mechanism, the setting device does not need to poll frequently, the monitoring condition is configured on the target device by one time setting, the target device actively reports when the condition is met, repeated information transmission is avoided, the MCTP bus communication flow is greatly reduced, and the system load is reduced; meanwhile, the key information and the change information can be sent in real time, the information updating delay problem caused by reducing the polling frequency is solved, and the balance between the system load and the real-time response is realized.

The invention provides a traffic signal lamp redundancy identification system and method based on red light narrowband filtering, and belongs to the technical field of intelligent driving environment perception. The system is characterized in that a main processing module processes a color image based on a YOLOv8n model and a lightweight convolutional neural network, and outputs a first recognition result and the confidence of the first recognition result; when the confidence coefficient is lower than a threshold value, a redundancy identification module is started, a narrow-band image obtained by an auxiliary imaging module is analyzed, whether a strong red light signal emitted by a traffic signal red light exists or not is judged through self-adaptive threshold value segmentation, morphological processing and feature analysis, and a second identification result is generated; and the decision fusion module fuses the two paths of results to generate a final control instruction. According to the invention, through physical spectrum filtering and double-path information fusion, interference of ambient light such as sunset and the like is effectively overcome, and the robustness and safety of an automatic driving system in recognizing traffic lights under complex illumination, especially red light, are remarkably improved.

The invention relates to the technical field of augmented reality and computer vision processing, in particular to an augmented reality art display system, which comprises an environment perception processing center used for calling multi-dimensional environment sensing data, obtaining environment illumination features and scene semantic features, performing coupling processing on the environment illumination features and the scene semantic features, and obtaining a scene image; obtaining photometric semantic coupling data; when photometric semantic coupling data is generated, the imbalance prediction unit is used for obtaining an aesthetic imbalance index; the intention constraint unit is used for obtaining a conventional rendering signal or a reconstructed rendering signal; when a reconstruction rendering signal is generated, the reconstruction rendering unit is used for performing visual consistency synthesis on the obtained compensation model and a real video stream to obtain an augmented reality display image; according to the method, the technical problem caused by neglecting environment interference is effectively solved, and quantitative evaluation of environmental aesthetics quality is supported from a data bottom layer.

Embodiments of the present disclosure disclose an obstacle distance information generation method, device, equipment and computer readable medium. A specific implementation of the method comprises: acquiring a current time road image; performing obstacle detection on the current time road image to generate current time obstacle detection information, wherein the current time obstacle detection information comprises: obstacle type information, an obstacle detection bounding box equation set and an obstacle detection bounding box vertex coordinate set; in response to determining that the horizontal coordinate values of each obstacle detection bounding box vertex coordinate in the obstacle detection bounding box vertex coordinate set are all greater than the horizontal coordinate value of a preset camera optical center imaging point coordinate, generating a first target obstacle key point coordinate set based on the obstacle detection bounding box vertex coordinate set; and generating obstacle distance information based on the first target obstacle key point coordinate set and the obstacle type information. The implementation can generate obstacle distance information efficiently.

The chain system fixed-point resampling method belongs to the technical field of rotating machinery signal processing, and aims to solve the problems that the time domain signal regularity of a single chain link is poor, the dynamics characteristics of the whole system are difficult to directly reflect, and the frequency domain feature extraction cannot be performed. The method comprises the following steps: extracting original data of discrete motion units from multi-body dynamics simulation results; at the preset data monitoring point position of the system, the nearest discrete motion unit is searched as a monitoring unit in real time by calculation; according to the data type, one of a direct method, a synthetic method and an average method is adopted to process the original data of the monitoring unit, and feature data representing the dynamics state of the fixed position are generated; and finally, the feature data are written into a file in time sequence. The time sequence data of the fixed position are collected through the fixed-point resampling method, and the problems that the data is strong in contingency, poor in regularity, and difficult to perform in-depth frequency domain and statistical analysis due to tracking a single motion unit are solved.

Embodiments of the present application relate to a kind of processing method and system for lane line identification based on image, the method comprises: receiving first image;According to preset image size, the size of first image is adjusted to obtain corresponding second image;Second image is input into preset lane line prediction model to carry out lane line instance and attribute identification processing to obtain corresponding third image.Through the end-to-end lane line prediction model provided in the present application, the identification efficiency can be improved, and system algorithm power resource is saved.

The invention relates to a spatial position instruction fine tuning method based on a multi-modal large language model, and the method comprises the following steps: S1, converting a spatial position reasoning data set into a visual instruction format through employing a dialogue template, and obtaining a visual spatial position reasoning data set; s2, acquiring a large language model InternVL as a multi-modal large language model, performing pre-training on the general data set to obtain a pre-training model, reasoning the data set based on the visual spatial position, adjusting parameters of the pre-training model by adopting a low-rank adaptation method to obtain a trained large language model, and outputting a description corresponding to a spatial task by the large language model; and S3, introducing a text-based large language model, and optimizing the description corresponding to the space task based on the large language model. Compared with the prior art, the method has the advantages that the ability of the multi-modal large language model in understanding and generating context rich description is fully utilized, and the ability of the model in generating accurate and detailed description is enhanced.

The invention relates to the technical field of railway engineering reliability analysis, and particularly discloses a seamless track key influence factor identification method considering multi-source uncertainty, and the method comprises the steps: firstly, constructing an initial factor library and a parameter set based on field and literature data; secondly, a Latin hypercube sampling (LHS) technology is adopted to generate samples in an uncertain parameter space, and an input-response data set is obtained through parametric simulation; secondly, training a high-precision efficient proxy model based on simulation data to replace an original physical model; and finally, implementing Monte Carlo simulation (MCS) based on the agent model, and completing system probability reliability evaluation and global sensitivity analysis. According to the method, the influence of multiple parameters and the coupling effect thereof on the service performance of the seamless track can be evaluated simultaneously in single simulation, the analysis efficiency is remarkably improved, and the method is suitable for reliability analysis and optimization design of the seamless track in a complex environment.

This invention discloses a method for optimizing the design of complex equipment based on a hybrid adaptive sampling surrogate model. This method divides the design space into several Voronoi polygons controlled by sample points. Three indices—leave-one-out error, local nonlinearity, and polygon region size—are used to evaluate the importance of each sample point region. An entropy-weighted distance method is used to select the most suitable sensitive region for adding points. A learning function based on error estimation is then combined to determine new sampling points. This iterative update constructs a high-precision surrogate model, establishing a mapping relationship between design parameters and optimization objectives, thereby solving the design optimization problem. This invention innovatively proposes a multi-index adaptive weight allocation method to select sensitive sample regions and proposes a novel learning function to determine the location of added points. This method can construct a high-precision surrogate model using fewer sample points and can be used for the optimization design of complex equipment, including but not limited to tunnel boring machines.

The application discloses an NVH simulation analysis method and system of an axial flux motor, and relates to the technical field of motor NVH simulation.The method provided by the application comprises the following steps: a three-dimensional finite element model of the axial flux motor is established; a three-dimensional electromagnetic model comprising at least one periodic structural unit is established; first node electromagnetic excitation of a first stator on the periodic structural unit is extracted based on the three-dimensional electromagnetic model; complete electromagnetic excitation covering the first stator and a second stator is generated and loaded to the three-dimensional finite element model by performing spatial transformation on the first node electromagnetic excitation, including a rotation replication operation based on circumferential periodicity and a symmetric mapping operation based on double-stator symmetry; and finally, coupling calculation is performed to obtain NVH response parameters.The application significantly improves the accuracy of simulation analysis by using an accurate excitation loading mode, and provides a reliable basis for the optimization of the NVH performance of the motor.

The invention relates to the technical field of equipment monitoring and control, and discloses a power take-off wheel real-time energy consumption monitoring method and system and a storage medium. The method comprises the following steps: synchronously acquiring a torque value and a rotating speed value to construct a sampling data record; torque fluctuation gradient setting sampling frequency is calculated, and whether the sampling frequency is switched or not is judged based on the fluctuation gradient change rate and the hysteresis band; calculating instantaneous power and accumulated energy consumption, establishing a power baseline, and generating an energy consumption abnormal event when the deviation degree exceeds a preset number of times; and according to the deviation degree and the duration, determining an alarm level and executing corresponding alarm. According to the invention, the real-time performance of energy consumption monitoring and the utilization efficiency of edge computing resources are improved.

The application discloses a multi-target authentication method based on secret sharing. The system applied by the method comprises at least one client and a server, and the client and the server are in communication connection; each client has a unique id, and an id of each client and corresponding secret fragment information mapping relationship table are stored in the server; the method comprises a predefined secret fragment allocation strategy flow and a protocol authentication flow. The application is efficient, safe and capable of multi-target authentication, and can guarantee that a receiver authenticates a sender when data is exchanged each time, and can ensure data confidentiality and authenticity; the multi-target batch authentication processing is performed by referring to the secret sharing mode, and the server overhead is reduced to guarantee communication efficiency.

The application provides a virtual clothing search method and device, electronic equipment, computer readable storage medium and computer program product, including: displaying an artificial intelligence search control, the artificial intelligence search control is used for inputting a search instruction to the artificial intelligence, the search instruction describes the virtual clothing of a virtual role that needs to be searched, and indicates the artificial intelligence to search at least one virtual clothing that meets the description;In response to the search instruction input based on the artificial intelligence search control, display at least one target virtual clothing searched by the artificial intelligence. In this way, the accuracy and hardware resource utilization rate when searching for virtual clothing can be improved.

This disclosure proposes a video processing method, apparatus, computer device, and storage medium. The method includes: decomposing a video to obtain multiple video segments; determining multiple action event information corresponding to each of the multiple video segments; determining a target video segment from the multiple video segments based on the action event information; identifying object description information from the target video segment; and determining whether a target action event has occurred in the scene described by the video based on the object description information. Because the video is first decomposed, and a target video segment is determined based on the decomposed video segments, and target action events in the scene are identified and judged around the target video segment, the method achieves rapid identification and judgment of target action events around the target video segment, effectively reducing the computational resources consumed in target action event identification and judgment, and improving the identification and judgment effect of target action events.

The application relates to the technical field of artificial intelligence speech recognition, in particular to a customer service call center ASR intelligent speech transcription system and method, the intelligent speech transcription system comprises a data input module, a domain knowledge enhancement module, a dialogue level context perception engine, a self-adaptive real-time transcription scheduler and an application output module; through a three-layer context modeling architecture, in combination with a domain language model enhancement technology based on a knowledge graph, and a double-track parallel processing mechanism of front desk real-time display and background automatic correction, while maintaining low response delay, the professional field vocabulary recognition accuracy is effectively improved, and only a small amount of parameter adjustment or rule configuration is needed to complete the rapid migration adaptation of cross-industry scenes, and the core technical problems of multi-round dialogue context loss, difficulty in recognizing domain professional vocabulary, difficulty in balancing real-time transcription accuracy and delay, and difficulty in quickly adapting different business scenarios are solved.