35results about How to "Reduce computing load" patented technology

This invention discloses a weak fault diagnosis method based on chaotic signals of wind turbine stator current. The diagnostic method includes: acquiring the current signal of the wind turbine stator and preprocessing the current signal, the preprocessing including row-sequence component transformation, adaptive fundamental suppression, and detrending processing; calculating a chaos index based on the preprocessed signal; calculating a health index based on the chaos index and classifying the health status according to the health index; and outputting a diagnostic result including the health index, fault type, and graded early warning signal based on the aforementioned results.

This application relates to a method, apparatus, equipment, and storage medium for optimizing decision-making in post-disaster casualty rescue. The method includes: acquiring multidimensional physiological parameters and individual environmental factors of the casualties; using an improved START classification method and fuzzy comprehensive evaluation for initial injury quantification; and using a Markov state transition model to predict the injury evolution trend, generating a dynamic priority queue. A collaborative optimization model integrating rescue order, rescue route, and rescue method is constructed, aiming to maximize the expected number of survivors. A decomposition-coordination strategy is used to jointly solve the model, generating a globally optimized rescue plan. An event-driven mechanism is used to trigger rescheduling based on collected dynamic environmental data. Rolling time-domain optimization is performed based on the predictive control of the collaborative optimization model, and incremental updates are used to replan only the local plans affected by disturbances, outputting adaptively adjusted rescue instructions. This method can effectively improve the expected number of survivors and overall rescue efficiency.

This invention provides an intelligent analysis system for photoelectric detection spectral data based on deep learning, belonging to the fields of photoelectric detection, spectral data analysis, and deep learning application technology. The system includes core units such as a spectral data acquisition unit, a preprocessing unit, a feature extraction unit, and a deep learning analysis unit, as well as auxiliary units for anomaly detection and data storage, forming a closed-loop architecture of acquisition-processing-analysis-output-optimization. It improves data quality through step-by-step preprocessing algorithms, reduces computational load by adaptively selecting key features, deeply mines spectral patterns using a model that integrates convolutional neural networks and attention mechanisms, achieves rapid scenario adaptation through transfer learning, and dynamically optimizes model parameters based on a feedback mechanism. The system solves the problems of low accuracy, poor adaptability, and long training cycles in traditional spectral analysis, achieving accurate, efficient, and intelligent spectral data analysis, and is suitable for various photoelectric detection scenarios such as qualitative and quantitative analysis of substances and environmental monitoring.

The application provides a list rendering method and device, electronic equipment, computer readable storage medium and computer program product; the method comprises the following steps: in response to a first operation for a to-be-rendered list, determining a first target object to be displayed in a viewport area of an electronic device and a second target object to be loaded outside the viewport area; calling a first coordinator located in a main execution thread, generating a first rendering instruction based on the first target object and a third target object currently displayed in the viewport area; calling a second coordinator, generating a second rendering instruction based on the second target object and a fourth target object; calling a rendering engine to obtain a current to-be-displayed view in the viewport area in response to the first rendering instruction, and calling the rendering engine to obtain a to-be-loaded view including the current to-be-displayed view in response to the second rendering instruction. Through the application, the rendering efficiency and smoothness of the list in the continuous interaction process can be improved.

The application discloses a kind of unmanned vehicle logistics directional relay network system and its coordination method, belong to intelligent logistics and unmanned vehicle application technical field, the system includes: multiple cellular airspace units, cellular airspace unit is constituted continuous grid in service area;Deployed in the center of each cellular airspace unit one micro hub, as the ground logistics node of corresponding unit;Wherein, each micro hub includes one terminal nest and at least two relay nests;Terminal nest is used to provide the storage and withdrawal interface of user goods;Each relay nest is arranged around terminal nest, and each relay nest is pre-allocated and fixedly responsible for the bidirectional goods transfer task between the unit where the micro hub is located and a particular adjacent unit;Terminal nest and each relay nest are connected by internal logistics transmission device 103.The application fundamentally simplifies scheduling and management complexity by deep coordination of cellular airspace grid, heterogeneous node division of labor, directional routing rules and high automation.

The present application belongs to the technical field of power supply and distribution. A parallel three-level inverter modulation method, system, product, medium and equipment are proposed, which equivalent double parallel three-level inverters as a whole five-level inverter, inject zero sequence components to the initial three-phase reference signal to obtain the reference signal, identify the resultant vector through rounding and remainder operation, and then adjust the reference signal according to the sum of the three-phase state of the initial resultant vector to output a five-segment switching sequence, and then decompose the equivalent five-level reference signal into two sets of three-level reference signals, allocate the reference signals by dividing the half-carrier period and compare them with the triangular carrier to obtain a three-level vector sequence combination. The present application realizes the comprehensive optimization of common-mode voltage, zero-sequence circulating current and output current ripple, avoids complex sector judgment and duty cycle calculation, and reduces the implementation complexity and computational burden.

The invention discloses a multi-terminal fidelity display adaptation method for remote ultrasonic images, which relates to the technical field of image processing, and comprises the following steps of: firstly, acquiring heterogeneous original video streams of ultrasonic instruments of different brands / models at a clinical end, and performing standardized analysis to generate basic video streams in a unified format; then obtaining characteristic parameters such as screen resolution, proportion and decoding capability of the target terminal, and calculating a non-stretching target rendering size according to the characteristic parameters; then different areas in the video are identified through ultrasonic image feature optimization, and differential zooming processing is carried out by adopting a corresponding interpolation algorithm; and finally, calculating a structural similarity index of the core diagnosis area, if the structural similarity index is lower than a threshold value, performing feedback adjustment, and transmitting a video stream with the fidelity reaching the standard to a terminal for display. According to the method, the heterogeneous video source is standardized, and regional differentiation zooming and fidelity feedback adjustment are carried out according to the terminal features, so that compatible adaptation between various types of ultrasonic instruments and various types of display terminals is realized.

The invention discloses a hydrogen fuel cell system life prediction system which comprises the following steps: a model construction module constructs an electric pile life prediction empirical model based on historical durability data of a hydrogen fuel cell system and stage characteristics of voltage attenuation of an electric pile of a hydrogen fuel cell; the life prediction module obtains a corresponding attenuation correction coefficient through a pile life prediction empirical model by utilizing historical durability data and combining with a parameter adjustment rule, obtains a pile minimum monolithic voltage attenuation curve corresponding to each reference current through the attenuation correction coefficient, and calculates a pile minimum monolithic voltage attenuation curve; and calculating to obtain a life prediction value corresponding to each reference current in the preset scene, and selecting the minimum life prediction value as a final life prediction value. By predicting the service life of the hydrogen fuel cell system, the memory occupation is reduced, and the cost is saved.

This invention discloses a robust flight control system for unmanned helicopters in complex environments based on digital twins, relating to the field of unmanned helicopter technology. It includes an environmental perception data acquisition module, an environmental field quantization module, an aerodynamic digital evolution module, a control command optimization module, and a robust control execution module. By constructing a flight threat field oriented towards wind anisotropy and opportunity constraints, a five-layer environmental risk model is established, generating dynamic flight threat density field data. Joint modeling is performed based on flight data and a reduced-order hydrodynamic model, and adaptive evolution of aerodynamic characteristics is achieved through a dynamic parameter calibration mechanism. Combining the aerodynamic model and the threat density field, a multi-objective optimization function is constructed with trajectory deviation, energy consumption, and safety constraints as objectives, and reinforcement learning is used for policy training. This invention enables adaptive, energy-saving, and safe flight control of unmanned helicopters in strong disturbance and multi-threat environments, improving the robustness of flight control in complex environments.

The application discloses an automatic meter reading device and a meter reading control method thereof, and relates to the technical field of automatic meter reading, wherein the automatic meter reading device comprises a shell, an image acquisition assembly and a shielding part. The inner side of the shell is formed with an inner cavity, and one end of the shell is formed with a mounting part. The mounting part is used for connecting a meter structure, so that the indication information of the meter structure can be displayed in the inner cavity. The image acquisition assembly comprises a camera unit and an illumination unit. The camera unit and the illumination unit are arranged in the inner cavity and correspond to the mounting part, and are used for acquiring the indication information of the meter structure. The technical scheme provided by the application can isolate the interference of unstable external light on the image acquisition process through the arrangement of the shielding part, avoid the overexposure, underexposure or ghosting problem of the collected image caused by the change of external light and environmental reflection, and does not need to repeatedly adjust the shooting parameters to reacquire the image, so that the stability of image acquisition is ensured.

The application relates to the technical field of fault diagnosis, in particular to a distributed industrial fault diagnosis system and method, which comprises edge terminals and edge servers arranged in various industrial components. The edge terminal is provided with a rapid diagnosis module, a high-level diagnosis module and a dual-mode trigger communication module. The dual-mode trigger communication module independently and in parallel controls uploading of deep feature data according to event triggering and periodic triggering conditions. The edge server is provided with a synchronous sampling module, a feature fusion module and a global diagnosis module, which are used for aligning and fusing multi-source heterogeneous data on a unified time axis, and performing system-level fault diagnosis. The application guarantees real-time response to sudden faults and continuous monitoring of system states through dual-mode triggering, realizes efficient resource utilization and accurate identification of cross-component implicit faults through a hierarchical collaborative architecture, and significantly improves the comprehensive performance of fault diagnosis of complex industrial systems.

This invention belongs to the field of next-generation information technology and discloses a safety emergency response system for chemical production equipment based on real-time data. The system includes: an anomaly analysis module: storing current and historical dynamic propagation directed graphs into a first-in-first-out (FIFO) cache queue to obtain a time-series graph sequence; performing dynamic feature calculation based on the time-series graph sequence to output the dynamic features of the edges; and performing edge-level time-series association mining based on the dynamic features of the edges to obtain a risk dynamic propagation model; and an emergency response module: extracting critical vulnerable paths based on the risk dynamic propagation model to obtain a set of equipment anomaly propagation chains; and capturing abnormal equipment based on the set of equipment anomaly propagation chains to achieve safety emergency response control for chemical production equipment. This system can intervene before a fault causes widespread impact, significantly improving the foresight of the response.

The application provides a vehicle battery full life cycle state of charge estimation method and device, through collecting the current charging and discharging working condition and actual operation data of the vehicle battery, using the particle swarm method to determine and dynamically update the discretization second-order equivalent circuit model parameters, combining the discrete state equation and the linearized observation equation, through the intelligent control adaptive extended Kalman filter algorithm start-stop and combining the ampere-hour integral method bottom-up method to determine the state of charge estimation value of the vehicle battery, solves the technical defects of poor adaptability, narrow working condition adaptation range, low estimation accuracy and error accumulation in the existing vehicle battery state of charge estimation method, realizes the high-precision real-time estimation of the state of charge of the battery in the full life cycle and full working condition, reduces the calculation load of the vehicle-mounted battery management system, and improves the algorithm practicality and landing nature.

The invention discloses an operation safety monitoring method of a wind and light energy storage platform. According to the method, operation parameters are collected and standardized in real time, and power and environment features are extracted to construct a multi-dimensional feature vector; a key feature subset is determined through dimension reduction, and a normal operation mode is established through clustering analysis; calculating the health deviation degree between the real-time state track and the clustering center, and triggering an alarm sequence; constructing a parameter interaction directed graph to reversely search and position an abnormal source; a monitoring model is updated in combination with historical abnormal logs, and the real-time abnormal risk probability is calculated through recursive filtering. According to the invention, intelligent safety monitoring and dynamic risk quantification of the wind and light energy storage system are realized, and the operation safety and the accuracy of abnormal early warning are remarkably improved.

The embodiment of the application relates to the technical field of lyocell fiber equipment, and provides a thin film evaporator fluid-thermal coupling dynamics model construction method and related devices, the method comprises the following steps: a scraper force model under multiple working conditions is established; a nonlinear normal contact force model of a thrust self-aligning roller bearing is established; a flexible body model of a main shaft and a scraper plate is established; a flexible body model of a cylinder is established; the scraper force model, the nonlinear normal contact force model, the flexible body model of the main shaft and the scraper plate and the flexible body model of the cylinder are integrated into a multi-body dynamics simulation platform to construct a thin film evaporator fluid-thermal coupling dynamics model of a complete machine, and the method can ensure key deformation precision while greatly reducing calculation load in the process of large-scale thin film evaporator dynamics modeling.

This invention relates to the field of clothing design technology, specifically to a computer-aided clothing design method and system. The method includes acquiring all operation information and original clothing parameters from user actions on the computer-aided design interface; identifying the clothing modification area and modification parameters operated by the user based on all operation information and original clothing parameters; performing regional structure analysis on the user-operated clothing modification area to obtain the modification impact area; performing a fitting simulation on the clothing modification area based on the modification impact area and modification parameters to obtain qualified simulated fitting parameters; and adjusting the user-operated clothing modification parameters based on the qualified simulated fitting parameters to obtain the clothing design parameters. The purpose of this invention is to solve the problems of inaccurate fabric simulation and system delays in existing design methods, which lead to extended clothing design time and limited designer creativity.

This application relates to a segmented transmission method for low-power industrial audio acquisition terminals. The method includes: the terminal device sending a start identifier message to a server; segmenting the acquired audio data according to preset segmentation conditions to generate multiple data segments and attaching segmentation identifier information; transmitting the data segments to the server via a cellular communication network; the server establishing a data transmission session and allocating buffer space; storing the data segments in the buffer space according to the segment sequence identifier; the terminal device sending an end identifier message; and the server performing integrity checks and merging the data segments after the checks pass to generate a complete audio data sequence. This application reduces the instantaneous power consumption on the terminal side and improves the reliability of audio data transmission through the segmented transmission mechanism.

This invention relates to the field of drone scheduling technology, and particularly to a method and system for regional route collaborative scheduling of logistics drones. The method includes: constructing a drone monitoring platform; determining whether flight interference exists based on a preset minimum interference distance, acquiring flight information of drones involved in the interference, and sending it to the corresponding drones; calculating yaw information for each drone based on the flight information and a built-in force field simulation obstacle avoidance model, and controlling the drones to fly based on the yaw information; when the distance between drones is greater than the minimum interference distance, outputting return-to-home information based on the force field simulation obstacle avoidance model, and controlling the drones to return to their flight paths. This invention provides a regional route collaborative scheduling method for logistics drones that treats each drone as an intelligent agent autonomously moving in a three-dimensional force field, decoupling complex global path planning from real-time obstacle avoidance, and greatly reducing the dimensionality and complexity of distributed computing.

This invention discloses an underwater target detection method based on dynamic channel impulse response analysis, relating to the field of underwater target detection and recognition technology based on dynamic channel impulse response analysis. The method includes the following steps: determining anomaly regions based on the difference between the instantaneous channel impulse response and the reference channel impulse response; generating a refined image of the anomaly regions by adaptively filling the pixels in the anomaly regions and adjusting the sampling step size of the anomaly regions; obtaining difference features by performing differential extraction on the channel impulse response of the refined image and the corresponding reference channel impulse response; and determining the target contour based on the difference features. This application determines the target difference features by matching the channel impulse response of the refined image with the reference channel impulse response. Based on the difference features, a reconstructed contour that is very similar to the true contour of the target can be obtained, thus highly restoring the geometric shape of the underwater target and significantly improving detection accuracy.

The application relates to a traffic flow detection method based on improved YOLOv8 and DeepSORT, which comprises the following steps: S1, acquiring a training data set; S2, obtaining initial values of hyperparameters of a target detection model; S3, after the target detection model is trained based on the training data set for multiple times, whether a first exit condition is met is judged, if yes, step S6 is executed, otherwise, step S4 is executed; S4, a Pareto Bayesian algorithm is used to update the hyperparameters to obtain candidate values of multiple groups of hyperparameters, and a genetic algorithm is further used to process the obtained candidate values of the multiple groups of hyperparameters to obtain a candidate value of a group of hyperparameters to replace the hyperparameters in the target detection model; S5, whether a second exit condition is met is judged, if yes, step S6 is executed; S6, each video frame of a to-be-detected video is detected by using the target detection model to obtain traffic flow data. Compared with the prior art, the application has the advantages of improving the detection accuracy in an unmanned aerial vehicle scene.

The application discloses a kind of dynamic self-adapting NAND Flash reading method, system, medium and equipment based on artificial intelligence, it is related to solid-state storage technical field, the method includes: S1, initiates reading request, uses default voltage to read page data, it is decoded by LDPC algorithm, constructs feature vector and is preprocessed, then it is input into neural network model that is trained in advance, voltage prediction is carried out;S2, fine sampling is carried out to predicted voltage, reconstructs accurate threshold voltage distribution, calculates log-likelihood ratio;S3, design shared bottom layer trunk network, so that neural network model has independent output branch, predicted voltage simultaneously evaluates the long-term health status of block;S4, design online transfer learning mechanism, so that neural network model uses a small amount of new data to quickly adapt to new environment.The application greatly reduces the delay and significantly saves power consumption, through early warning of bad block, data loss is prevented in the bud, and dynamic read interference suppression reduces write amplification factor to 1.26.

The present application belongs to the technical field of information recognition, and particularly relates to a media information recognition feedback method and system based on big data processing. The method analyzes and processes the to-be-recognized media information, and judges whether it is abnormal media information according to a preset abnormality judgment rule. When it is abnormal media information, the abnormal media information is directly sent to a processing end, and only normal media information is subjected to a subsequent step of constructing comparison data, so that the abnormal media information is removed in advance, and is prevented from entering a subsequent complex comparison data construction link, thereby reducing the computing load of the system to improve the overall processing efficiency, and ensuring the purity and reliability of the benchmark data used for constructing the comparison benchmark from the source.

This invention relates to a Gaussian super-resolution reconstruction method based on physically consistent sparsity and frequency awareness, comprising: performing feature extraction and saliency prediction on the spacecraft image to be processed to obtain a multi-scale deep feature tensor and a foreground saliency mask; using the foreground saliency mask to perform spatial feature modulation on the multi-scale deep feature tensor to obtain a modulated multi-scale deep feature tensor; decoding the feature vector corresponding to each spatial position of the modulated multi-scale deep feature tensor to predict the corresponding Gaussian kernel parameters; based on the foreground saliency mask, performing a physically consistent hard gating operation on the opacity of all Gaussian kernel parameters to generate a sparsified set of Gaussian kernel parameters; and based on the sparsified set of Gaussian kernel parameters, obtaining the final super-resolution result image through differentiable Gaussian sputtering. This method can obtain high-quality arbitrary-scale super-resolution reconstruction results while meeting the high-performance requirements of spaceborne edge devices.

The disclosure provides a computing system, a data processing method, equipment and a medium for high-bandwidth inference, and relates to the technical field of integrated circuits. The computing system is used for performing a decoding stage of a Transformer-based model inference, and comprises a host processor for performing a decoding stage nonlinear operator, an offload subsystem for performing at least a part of a decoding stage linear operator, and a standard high-speed interface module for transmitting an input activation vector and an output result vector between the host processor and the offload subsystem. The offload subsystem comprises a weight lock storage array for storing a weight matrix in a static residence manner, an input vector streaming interface for streamingly receiving the input activation vector, a matrix vector multiplication calculation unit for performing a matrix vector multiplication operation on the input activation vector and the weight matrix, and a result processing module for reducing or arranging the operation result to obtain the output result vector.

The application relates to a kind of based on deep learning's regional feature classification method and system of distribution network planning, belong to artificial intelligence technical field.The method includes the following steps: using unmanned aerial vehicle to collect distribution network planning area orthophoto and label to form data set;The main network of DeeplabV3+ is replaced by MobileNetV3, the global pooling operation in ASPP module is replaced by NSCT, and EMA is introduced at the end of the encoder to obtain an improved model;The model is trained based on the data set, and then the orthophoto of the region to be classified is input into the trained model to obtain a pixel-by-pixel feature classification prediction result map, wherein the improved model includes an encoder and a decoder, each part uses a specific structure and operation, such as NSCT for feature decomposition and fusion, EMA for multi-scale attention processing, and the decoder performs upsampling, splicing and other operations to output the final result, solving the limitations of manual visual interpretation of orthophoto.

The application relates to an energy storage power station intraday scheduling method based on a rule base hybrid model predictive control, wherein the method comprises the following steps: constructing a rule base considering actual operation of intraday optimization scheduling based on historical data of a target energy storage power station and scene application demand; constructing an improved particle swarm algorithm-model predictive control optimization model and generating an optimization prediction strategy fused with an adaptive mechanism; establishing an intraday scheduling hybrid optimization framework based on the rule base and the improved particle swarm algorithm-model predictive control optimization model; and generating an intraday scheduling optimization strategy based on the intraday scheduling hybrid optimization framework, the optimization prediction strategy, power deviation and operating conditions of the target energy storage power station. Thus, the problems in the prior art that the heuristic algorithm is highly dependent on initial parameter setting, is prone to falling into local optimization or divergence and non-convergence, and lacks an effective scheme for realizing rapid external feedback and internal rapid adjustment of an energy storage cluster without affecting a day-ahead planning curve are solved.

The system includes: a current sensor 14 for detecting battery state; and a battery controller 12 for estimating the battery's state of charge (SOC) based on the detected data and calculating the allowable charging and discharging current. The battery controller calculates the allowable current based on an equivalent circuit model including resistive and capacitive elements, and the battery data table correlates these elements, along with the battery state and SOC. The battery controller uses the estimated SOC as the average SOC, calculates the local SOC based on the average SOC and the charge amount of the capacitive elements, and calculates the allowable current based on the local SOC, the detected data, and the battery data table.

The present application relates to a kind of based on multi-element information fusion plug-in hybrid electric vehicle energy management method, comprising: obtaining adaptive fuzzy reasoning system model, vehicle speed sequence prediction model and SOC reference trajectory estimator;Real-time calculation current time transmission ratio, future finite time domain within the vehicle speed prediction sequence and future finite time domain within the SOC final value, based on Pontryagin minimum principle within the finite time domain rolling optimization, obtain the reference covariant variable within the time domain;If there is solution in rolling optimization, then use reference covariant variable in subsequent control domain to carry out open-loop Pontryagin minimum optimization, obtain corresponding control set, if there is no solution in rolling optimization, then execute SOC follow strategy.Compared with prior art, the present application will transmission ratio selection and torque distribution be jointly included in the category of energy management, and multi-element driving information is fused, and double-layer strategy of rolling optimization and SOC follow is proposed, which effectively improves the effect of plug-in hybrid electric vehicle energy management strategy.

The invention belongs to the technical field of live pig health detection, and discloses a live pig health detection method and system based on pixel-level activity amount, and the method comprises the steps: carrying out the data standardization and background modeling processing of an original video stream of a target pigsty, and generating a video frame sequence and a corresponding ROI mask; performing high-quality motion perception on the video frame sequence through an RAFT deep learning optical flow model to generate a dense optical flow field; calculating the instantaneous activity intensity of each pixel point based on the dense optical flow field, correcting the instantaneous activity intensity in combination with the ROI mask, and performing nonlinear time sequence accumulation on the corrected instantaneous activity intensity of each pixel point to generate an activity amount accumulation thermodynamic diagram; and based on the activity accumulation thermodynamic diagram, respectively performing group health assessment and individual abnormality positioning, and visually outputting group and individual abnormality early warning to realize live pig health detection. The invention provides a new live pig health detection normal form which is efficient in calculation, robust to shielding and capable of serving group abnormity early warning and individual accurate positioning at the same time.

The application provides a complex water system adaptive variable step length model predictive control real-time scheduling method, which comprises the following steps: constructing a canal pool integral time delay model, integral time delay model time domain verification, selecting an effective frequency domain detection / verification range, constructing a model predictive control framework, selecting different control step lengths for closed loop testing, determining an optimal control step length range, and designing an adaptive variable step length switching rule, thereby constructing an adaptive variable step length model predictive control method. According to the scheduling target and the canal pool state, the method can dynamically adjust and optimize the control step length, so as to realize the intelligent balance of the calculation efficiency and the scheduling accuracy, thereby effectively solving the problem of insufficient adaptability of the traditional fixed step length model predictive control method under complex working conditions.