769results about How to "Reduce computational complexity" patented technology

The invention relates to an Internet of Vehicles multi-agent cooperative sensing method and system. The method comprises the following steps: constructing a collaborative sensing network, wherein the collaborative sensing network comprises a self-agent and a plurality of collaborative agents; acquiring and processing sensing data through the collaborative sensing network; performing feature extraction to obtain intermediate features; self-adaptive sparsification is carried out to obtain sparse features, and the sparse features are compressed and transmitted to a self-agent; performing time sequence feature enhancement on the features of all the agents at the self-agent end; fusing the features to obtain fused features; and constructing an Internet of Vehicles perception model, and realizing perception by the detection model according to the fused features. According to the method, the calculation complexity of traditional global attention is reduced from the square level to the linear level through an adaptive sparsification mechanism, the calculation overhead is remarkably reduced while the multi-agent feature interaction precision is kept, and the method is more suitable for real-time operation on the vehicle-mounted edge equipment with limited resources.

The invention relates to the technical field of intelligent traffic and Internet of Vehicles, in particular to a traffic and air pollution bidirectional coupling flow prediction method based on double-path dynamic fusion. Comprising the following steps: collecting traffic flow and air pollutant concentration data, and carrying out space-time alignment and reversible instance normalization; the data is divided into two branches, the first branch extracts time-dependent features through gated convolution and probability sparse self-attention, and the second branch obtains variable interaction features through dimension remodeling, context extraction and reversible coupling transformation; bidirectional feature interaction is carried out through cross attention, weights are dynamically generated based on channel attention, and residual connection is carried out after weighted fusion; and performing linear mapping and inverse normalization on the fused features to obtain a traffic flow predicted value. According to the method, the prediction precision and robustness in a pollution sensitive scene are remarkably improved.

The invention discloses a medical image segmentation method, system and device based on multi-attention and multi-scale fusion, and relates to the technical field of image segmentation, and the method comprises the steps: constructing an MAMF-Net model which comprises an encoder and a decoder which are in multi-layer jump connection; the encoder adopts a hybrid architecture of convolution and Transform, and is integrated with a self-adaptive expansion convolution method; the decoder integrates dual-channel attention gating and a multi-scale global channel feature enhancement method to enhance features transmitted by jump connection, and combines features extracted by the encoder to fuse and reconstruct a segmentation result; training the MAMF-Net model by adopting the historical medical image sample set to obtain a medical image segmentation model; and obtaining any medical image to be identified and inputting the medical image to the medical image segmentation model, and determining a corresponding segmentation result. The problem of insufficient fusion of global semantics and local details in medical image segmentation is solved.

The invention discloses a signal enhancement method and device in an industrial plant area, and relates to the field of wireless communication, and the method comprises the steps: firstly, obtaining complete channel state information, and guaranteeing that all decisions are based on real channel characteristics instead of theoretical assumptions; and secondly, if the complete channel state information does not meet the target QoS demand quantization parameter, maximizing a receiving signal to interference plus noise ratio and meeting the target QoS demand are taken as optimization targets, an optimization result is obtained based on channel field intensity distribution information of a preset digital twin model, and finally, the optimization result is controlled and executed to form closed-loop feedback. According to the method, optimization is carried out based on channel field intensity distribution information of a unit space in a digital twin model, and a complex problem needing to be solved by a high-dimensional iterative solution algorithm in related technologies is converted into table lookup and interpolation operation based on space coordinates, so that the calculation complexity is remarkably reduced, the time for obtaining an optimization result is greatly shortened, and the calculation efficiency is improved. Therefore, the time when the terminal is in a poor-quality signal state is greatly reduced.

The invention belongs to the related technical field of vehicle charging scheduling, and provides a vehicle charging dynamic scheduling method and system for a charging pile fault in order to solve the problem that a charging device cannot respond in time after a fault occurs, and the method comprises the following steps: monitoring the operation state of each charging pile in the execution of an initial charging scheduling scheme in real time; identifying a target vehicle set influenced by the charging pile fault; calculating an emergency priority score of each target vehicle according to the residual electric quantity and the planned departure time of the target vehicle; constructing a dynamic resource profile of the available charging pile based on the residual available power of the available charging pile, and screening a feasible candidate pile set; and according to the vehicle priority queue, reallocating available charging piles to each target vehicle in sequence by taking the minimum cost as a target, and generating a rescheduling scheme. According to the invention, charging of the vehicle at the valley point of the electricity price can be guaranteed to the greatest extent, and the reliability, economy and adaptive capability of charging are remarkably improved.

The invention discloses an oil reservoir history fitting method based on graph lasso and set smooth multi-data assimilation, and relates to the technical field of oil and gas field development. The method comprises the following steps: firstly, acquiring to-be-optimized model parameters and observation data of a target oil reservoir, constructing an observation error covariance matrix and initializing a model parameter set, performing numerical simulation by utilizing an oil reservoir numerical simulator to obtain prediction data, constructing a joint state matrix, performing dimensionless standardization processing on the joint state matrix to obtain an empirical correlation coefficient matrix, and then, performing optimization on the joint state matrix. And executing a graph lasso algorithm combined with an extended Bayesian information criterion to obtain an optimal dimensionless sparse precision matrix, extracting correlation coefficient sub-blocks required by Kalman updating from the optimal dimensionless sparse precision matrix based on a Scherr's theorem, obtaining a robust data auto-covariance matrix through a reverse reduction physical quantity outline, calculating Kalman gain in combination with an observation error covariance matrix, and calculating a Kalman filter. And the model parameter set is updated until the preset condition is met, the reservoir history fitting model parameter set is output, and the stability and precision of reservoir automatic history fitting are improved.

The invention discloses an aero-engine vibration signal generation method under extreme imbalance, and belongs to the technical field of aero-engine fault signal generation. The method comprises the following steps: acquiring an original vibration signal at a target position of the aero-engine, and performing preprocessing operation; taking the preprocessed real vibration signal as a training sample, constructing a forward noise adding process, and training the improved one-dimensional diffusion generation network to learn a reverse denoising mapping relation; and inputting random Gaussian noise into the one-dimensional diffusion generation network after training convergence, and generating a target vibration signal matched with a real vibration signal feature through a reverse diffusion denoising process. Through targeted improvement of the diffusion generation network, the problem of data imbalance is effectively relieved, the model deployment cost is reduced, the signal generation capability of the model for minority types of faults is improved, and the method is suitable for fault signal generation scenes of aero-engines under complex working conditions.

The invention discloses a low-sodium myofibrillar protein flavor prediction method and a low-sodium myofibrillar protein flavor prediction device. The method comprises the following steps: firstly, constructing a protein-flavor interaction system containing myofibrillar protein, potassium chloride, kappa-carrageenan and representative aldehyde flavor compounds; then, by means of spectroscopy, rheometer combination, an electronic tongue and the like, protein conformational change, typical aldehyde molecule binding rate and taste features are represented in a multi-dimensional mode. And establishing a random forest prediction model, taking protein conformation parameters as input, and taking a flavor binding rate and effective taste intensity as output. The model can reveal cross correlation between protein conformations and functions and identify key conformation parameters that affect flavor. And in combination with quantification and prediction capabilities of the model, a conformation-flavor relationship can be systematically analyzed, a basis is provided for optimization of a low-sodium formula, flavor is enhanced while salty taste is increased and bitter taste is inhibited, and healthy and sustainable development of low-sodium meat products is promoted.

The invention belongs to the technical field of computer software and data processing, and provides a differential upgrading method for a compressed file, which is divided into a differential stage and a reduction stage: the differential stage: decompressing an original compressed package of a starting version and an original compressed package of a target version; unifying and standardizing file permissions for the two decompressed folders, and modifying, accessing and changing timestamps; re-compressing to generate a first new compressed file and a second new compressed file with byte-level certainty; generating a first difference file based on the difference between the standardized directory structure and the content; comparing the second new compressed file with the original compressed file of the target version, performing lossless analysis on the ZIP metadata, and performing structured modeling on difference information to generate a second difference file; in the reduction stage, standardization, first differential reduction, recompression and second differential driven metadata accurate reconstruction are sequentially executed, and a result completely consistent with the byte level of the original compressed file of the target version is output. According to the method, the differential compression ratio and the restoration fidelity can be improved.

The invention relates to the technical field of three-dimensional point cloud data processing, and provides a subsidence-water-area-oriented point cloud stripe noise LTCF elimination method and system, and the method comprises the steps: obtaining point cloud data, preprocessing, filtering, and optimizing point cloud output. The filtering processing comprises the following steps: local covariance feature extraction: aiming at each target point in the preliminarily optimized point cloud obtained by preprocessing, constructing a k-nearest neighbor domain, and calculating local covariance contribution values of each target point in X, Y and Z spatial directions; compared with the prior art, the method has the following beneficial effects that the industrial pain point of a subsidence water area scene is solved, a three-direction covariance joint judgment mechanism is innovatively introduced, exclusive recognition logic is designed for specific low-elevation strip noise only containing XY-direction covariance in the subsidence water area, the lamellar strip noise which cannot be recognized completely by a traditional algorithm can be accurately captured, and the recognition accuracy of the subsidence water area scene is improved. And the problem of eliminating the point cloud core noise of the subsidence water area is solved fundamentally.

The invention discloses a micropatch bug matching quantification method, system and device based on an auto-encoder and a medium, and relates to the technical field of intelligent code analysis, and the method comprises the following steps: obtaining multi-source semantic data, carrying out analysis and unified representation processing, generating unified semantic representation with consistent dimensions, and carrying out multi-source data analysis; the method comprises the following steps: generating a low-dimensional semantic embedding vector through an unsupervised feature learning and compression process of an auto-encoder model, calculating a matching distance between a patch and a vulnerability by adopting a distance metric function, quantifying a difference degree between the patch and the vulnerability in a semantic space, and constructing a multi-dimensional matching scoring index according to the matching distance, and generating a comprehensive matching score through a weighted fusion mechanism, and sorting and screening matching results of the patches and the vulnerabilities according to the comprehensive matching score. According to the method, a three-dimensional matching evaluation system from depth semantics to surface logic is constructed, and the accuracy and reliability of micropatch and vulnerability matching are remarkably improved.

The invention discloses a wide-working-condition steam turbine system operation data correction method based on digital twinning, and relates to the technical field of steam turbine equipment digitalization, and the method comprises the steps: collecting operation data of a wide-working-condition steam turbine system in real time; constructing a digital twinborn model of the steam turbine system; performing prior covariance estimation on the operation data according to the statistical distribution condition and the design parameters; generating a Sigma point by adopting an unscented Kalman filtering algorithm, iteratively updating a state vector and a covariance in combination with a state transition equation and an observation equation, and outputting an updated known variable; performing smoothing processing on the updated known variable in a plurality of time point regions by adopting an RLOESS algorithm to obtain corrected operation data; according to the method, the real dynamic characteristics of the wide-working-condition steam turbine are approached by building the digital twinborn model, the calculation complexity of dynamic data fusion of a steam turbine system can be remarkably reduced, and the problems that the convergence speed is low and calculation is complex due to strong nonlinearity of a traditional method are solved.

The invention discloses a grid exhaustion search cross-pulse pairing method based on correlation matching, and belongs to the technical field of radio signal positioning and detection. According to the method, aiming at the problems of large cross-pulse signal pairing calculation amount and low accuracy in a multi-aircraft cooperative positioning system, efficient and accurate cross-pulse pairing is realized by establishing a cross-pulse boundary model, a symbol matching constraint mechanism and a related matching verification mechanism. The method comprises: determining upper and lower bounds of a cross-pulse according to a geometrical relationship; correcting the search range by using symbol matching; solving a candidate target solution in the limited interval by adopting grid exhaustion search; and a unique effective solution is screened through time and geometry consistency verification. The method can effectively reduce the calculation complexity, improves the cross-pulse pairing precision and uniqueness, and is suitable for a passive positioning system in a multi-target, multi-base-station and low-signal-to-noise-ratio environment. Experiments prove that the pairing time can be shortened by about 50% while high positioning precision is kept, and the method has high engineering application value.

The invention discloses a line loss prediction method and system based on integrated DBN-BP, and belongs to the technical field of power system data analysis. The method comprises the steps that firstly, a plurality of parallel DBN sub-networks are constructed, all the sub-networks adopt different activation functions, unsupervised pre-training is carried out with N antenna loss historical data and corresponding weather data as input, and high-dimensional robust features are automatically extracted; and then, taking the output of each sub-network as a feature, inputting the feature into a BP integrated network for supervised training, and finally fusing to obtain a high-precision line loss prediction value. Through the architecture of "unsupervised feature extraction + supervised integrated decision", the problems of strong dependency on annotated data and weak feature extraction ability in the prior art are effectively overcome; meanwhile, forward prediction can be simplified into efficient matrix operation through the full-connection structure of the model, the requirement for real-time dispatching of the power grid is met, excellent generalization ability is achieved, and reliable data support is provided for economical and safe operation of the power grid.

The application provides a die cutting and hot stamping equipment intelligent state monitoring and fault diagnosis system and method, and relates to the field of intelligent monitoring.The method comprises the following steps: collecting working parameters of multiple key parts of the die cutting and hot stamping equipment, constructing a time sequence collection window, slidingly collecting the working parameters, and obtaining characteristic information reflecting the equipment state; based on the characteristic information, constructing an anomaly detection model, performing anomaly detection on the equipment state, obtaining an anomaly score, and judging whether the equipment state is abnormal according to the anomaly score; for the characteristic information judged as abnormal, constructing a fault diagnosis model based on the fault type to which the characteristic information belongs, performing fault diagnosis on the equipment state, and generating a diagnosis result; and generating a comprehensive diagnosis and operation and maintenance decision report according to the diagnosis result.The application realizes comprehensive perception of the internal state of a closed host through multi-sensor collaborative monitoring and dynamic time sequence collection, breaks through the limitations of traditional monitoring, and provides accurate data basis for early fault warning and predictive maintenance.

The invention belongs to the field of wireless communication, and particularly relates to a wireless signal multi-dimensional array coding method and system based on dynamic rank optimization. The method comprises the following steps: detecting state information of a wireless channel, predicting state change of the channel by using a pre-trained deep learning model, and generating a dynamic optimization multiplier; adjusting a preset static optimization multiplier by using the dynamic optimization multiplier, constructing a target function for jointly optimizing the energy efficiency and the spectrum efficiency, and determining an optimal transmission rank by solving the target function; comparing the optimal transmission rank with the current transmission rank to determine a rank-up or rank-down operation; and reconstructing a transmission signal of the wireless channel according to a result of the rank increasing or decreasing operation. According to the method, the optimization target is dynamically adjusted by predicting the channel change, and the asymmetric ascending and descending rank algorithm is adopted, so that the adaptive transmission rank optimization in a complex time-varying channel environment is realized, and the communication performance is remarkably improved.

The present application discloses a bearing fault diagnosis method and system based on knowledge enhancement and multi-path distillation, which relates to the fields of intelligent operation and maintenance and industrial equipment health management. The method includes obtaining sensor signals and visual image data of the bearing operation; based on an asynchronous dual-channel architecture, correspondingly extracting signal features of the sensor signals and image features of the visual image data, and performing time synchronization on the signal features and the image features; using a multi-modal bottleneck Transformer module to fuse the synchronized signal features and the synchronized image features; based on a maintenance knowledge graph dynamically constructed from a bearing maintenance manual, combining a text generation model to map the fused features to a semantic space and generate a fault diagnosis report. The present application can improve the recognition accuracy, real-time performance and interpretability of diagnosis results of bearing faults.

The present application belongs to the technical field of mobile robot navigation, and particularly relates to a SLAM navigation method and system for a mobile intelligent cabinet, which comprises the following steps: acquiring a laser point cloud sequence and a grayscale image of the mobile intelligent cabinet and performing data cleaning; obtaining a geometric feature index based on the spatial jump distribution of the laser point cloud sequence; obtaining a visual texture index based on the local dispersion of the image gradient; calculating laser dynamic weight and visual dynamic weight by using the geometric feature index and the visual texture index, weighting and fusing the pose change quantity calculated by the single-line laser radar odometry and the visual odometry to obtain a fused pose quantity; and updating the global state based on the fused pose quantity and driving autonomous navigation. The present application can adjust the sensor weight in real time according to the environmental characteristics, solves the problem of positioning divergence in the long corridor of a shopping mall or a high-reflectivity environment, and improves the robustness of navigation.

The application relates to the field of optical fiber sensing, and more particularly to an event detection method, system and device for optical cable detection and a storage medium. The method comprises the following steps: inputting optical fiber data of an optical cable into a first processing unit for processing to obtain space-time features; inputting the optical fiber data into a second processing unit for processing to obtain frequency domain features; inputting the space-time features and the frequency domain features into an attention processing unit after splicing for feature enhancement to obtain enhanced features; inputting the enhanced features into a bottleneck layer processing unit for processing to obtain bottleneck features; wherein the bottleneck layer processing unit comprises at least two bottleneck layer processing subunits, and the bottleneck layer processing subunits can perform feature transformation processing on the enhanced features; and inputting the bottleneck features into a backbone network for optical fiber event detection to obtain an optical fiber event detection result corresponding to the optical fiber data. The application can improve the accuracy of optical fiber event detection in an optical cable.

A broadband voltage transformer error compensation method is proposed. First, a broadband test platform is constructed using a signal generator, power amplifier, standard voltage transformer, and high-bandwidth data acquisition system. The ratio and phase errors of the transformer at multiple frequency points are acquired through primary-side excitation and secondary-side synchronous acquisition. Based on the slope, first derivative, and second derivative characteristics of the error curve, the entire frequency band is adaptively divided into segments. Within each segment, multiple candidate models are fitted using a polynomial or exponential-linear combination model. The optimal model is selected based on the coefficient of determination, mean absolute error, and root mean square error. Ratio and phase error compensators are constructed based on the fitting functions of each segment, and error compensation is achieved using a feedforward approach. This method can significantly reduce amplitude and phase errors over a wide frequency range, improving the dynamic measurement accuracy of the voltage transformer.

This invention discloses a spline-adaptive method for eliminating power frequency interference in surface electromyography (EMG) signals, within the field of EMG signal noise reduction technology. The method includes the following steps: frequency domain input vector generation and frequency domain spline adaptive filtering; power frequency interference elimination; construction of a semi-quadratic criterion cost function and filter coefficient update; iterative update, repeating the above steps until noise reduction is complete. This spline-adaptive method for eliminating power frequency interference in EMG signals employs a robust frequency domain implementation method to construct the spline adaptive noise reduction system, exhibiting good stability, high computational efficiency, and the ability to efficiently eliminate power frequency interference.

This invention discloses a method for inverting sea surface wind speed from GNSS reflected signals based on mask perception and image-based Mamba-CNN. The method includes: performing spatiotemporal matching and interpolation processing on multi-source spaceborne GNSS-R observation data and ERA5 reanalysis data; gridding the processed observation parameters according to geographical location to obtain a multi-channel grid image and acquiring a binarized occupancy mask; inputting the multi-channel grid image and the binarized occupancy mask into a mask perception Mamba-CNN model; calibrating the grid features through a mask conditional encoder and a feature linear modulation layer, and performing spatial modeling using feature extraction blocks combining convolutional and Mamba state space paths to obtain the wind speed inversion result; aggregating the extracted features using center-perception pooling, and outputting the final sea surface wind speed inversion image through a regression network. This invention can significantly reduce computational complexity, effectively reconstruct the continuous wind field structure, and improve the inversion accuracy and robustness in high-wind-speed areas.

The invention provides a stem cell parallel reactor rotating speed measuring device, an identification method, equipment and a medium, and the method comprises the steps: capturing an edge signal outputted by a Hall sensor, and obtaining the duration of each high and low level, so as to obtain a high and low level time sequence containing rotating speed information in a plurality of periods; sorting the elements of the time sequence according to numerical values, comparing the ratio of front and rear elements with a threshold value to obtain a demarcation point of high and low level time, and calculating a threshold value of the demarcation point; comparing elements of the time sequence with a demarcation point threshold value in sequence to distinguish high level time and low level time; and calculating the rotating speed of the stirring paddle according to the time of the first high level, the time of the second high level and the time of all low levels between the two high levels. The device can be used in occasions where the space structure of a small parallel reactor is limited, and is compact in structure. The method can be used under the condition of strong interference or jitter, and the applicable rotating speed range is large.

The application relates to the technical field of deep learning and recommendation system, and particularly discloses a hybrid expert model sparse inference method and system for generative recommendation, which comprises the following steps: obtaining original input data, and obtaining an input vector through an embedding layer; obtaining hybrid expert weights through normalization and maximum value selection operation on the input vector; calculating attention-enhanced features according to the hybrid expert weights based on a hierarchical attention mechanism; inputting the input vector and the attention-enhanced features into a hybrid expert model to calculate a recommendation result; wherein, according to the attention-enhanced features, expert weights are calculated based on a parallelized gating mechanism activated by a Sigmoid activation function; the activated expert layer is selected according to the expert weights, and the input vector is used to calculate the recommendation result. The application can achieve a recommendation accuracy comparable to or even higher than that of an advanced dense model under low time overhead and low calculation complexity.

The present application relates to the field of optical interferometry, and aims at the phase distortion problem in off-axis interferometric quantitative phase imaging, and provides an interferometric microscopic phase distortion elimination method based on PACUNeXt3+ network. The method comprises the following steps: 1. using Zernike polynomials and test target pictures to simulate and generate a data set; 2. establishing and training a PACUNeXt3+ neural network model; 3. inputting the interference graph I or of the sample to be measured into the trained neural network, and outputting the background interference graph I' r corresponding to the sample without sample information; 4. using the two interference graphs I or and I' r to reconstruct the sample phase distribution φ o (x, y) without phase distortion. The present application has high precision and speed, can eliminate the secondary or high-order phase distortion in interferometric quantitative phase imaging, and has great application prospect in the field of phase imaging.

The application provides a kind of laser physical experiment ultrafast image measurement system and method based on end side coordination architecture, it is related to laser physical experiment image measurement technical field, comprising the following steps: laser target shooting generates plasma, captures the X-ray signal image of plasma, generates original data stream;Through lightweight convolutional neural network model, the original data stream is handled, and the feedback control signal for adjusting the laser parameter of the next laser is generated;Obtain the laser parameter related to each physical parameter characteristic value, adjust the laser parameter related to the physical parameter characteristic value;Store the adjustment data each time, periodically train lightweight convolutional neural network model based on adjustment data.The advantage of the application is to realize the instant, reliable experimental parameter control in the experiment process.

This invention discloses an adaptive filtering method based on the multi-kernel Nystrom method, belonging to the field of kernel adaptive filtering. The multi-kernel Nystrom method combines multiple kernel functions, which can include not only Gaussian kernels but also other different kernel functions, mapping the original data to multiple different independent feature spaces. Compared with the traditional single-kernel Nystrom method, the multi-kernel Nystrom method has better filtering accuracy and becomes less sensitive to the choice of kernel parameters. Compared with other multi-kernel adaptive filtering methods, it can significantly reduce computational complexity, time, and memory consumption. Subsequently, this invention introduces the proposed multi-kernel Nystrom method into kernel adaptive filters for the first time. Experiments show that this algorithm can achieve better filtering accuracy than current state-of-the-art kernel adaptive filtering algorithms with relatively low computational complexity.

This invention discloses a method, system, device, and storage medium for predicting oil pipe corrosion rate based on a PCA-PSO-SVR hybrid model, specifically including the following steps: S1 Collecting corrosion detection data and operating condition parameters of the oil pipe to form a dataset; S2 Preprocessing the dataset; S3 Using the PCA model to perform dimensionality reduction on the dataset and extracting the main features affecting the corrosion rate; S4 Initializing the parameters of the PSO model; S5 Optimizing the parameters of the SVR model using the PSO model; S6 Constructing a corrosion rate prediction model based on the optimized SVR model; S7 Inputting the preprocessed dataset into the corrosion rate prediction model to obtain the prediction result and complete the prediction.

This invention relates to the field of navigation and timing technology, specifically to a GNSS timing data prediction method and related equipment. The method involves acquiring Roland timing data when GNSS timing data is invalid and preprocessing it. The preprocessed data is then input into a trained single-hidden-layer extreme learning machine model. This model calculates the hidden-layer output matrix by randomly initializing the input layer weight matrix and bias vector, and solves for the output weights using regularized least squares. The model outputs a normalized GNSS timing data prediction value, which is then denormalized to obtain the final GNSS timing prediction result. This method combines the high stability of the Roland system with the efficient computational power of the extreme learning machine to achieve accurate GNSS timing data prediction. It is suitable for enhancing the resilience of positioning, navigation, and timing systems in critical infrastructure scenarios, ensuring the continuous operation of the system even when GNSS signals are interfered with or fail.