9results about How to "Low computing resource requirements" patented technology

The invention belongs to the technical field of rocket launching, and particularly relates to a rocket fairing noise reduction method and device and a storage medium. The method comprises the following steps: acquiring a noise signal; performing spectral analysis on the acquired noise signal by adopting fast Fourier transform to obtain a frequency domain signal, the frequency domain signal comprising amplitude and phase information under different frequency components; setting a boundary of each frequency band, extracting feature information of each frequency band, and extracting noise components of each frequency band according to the feature information of each frequency band; the noise reduction strategy of each frequency band is optimized through an artificial bee colony algorithm, and the optimal frequency and amplitude of the anti-phase sound waves of each frequency band are obtained; and according to the output of the artificial bee colony algorithm, anti-phase sound waves are generated, and active noise reduction is carried out on the fairing. According to the method, the overall noise reduction performance of the fairing can be improved, the response speed is high, the requirement for computing resources is low, and the method is suitable for scenes with strict requirements for time and resources in rocket launching scenes.

The invention provides a fire alarm prediction method and device based on a high-order Markov chain. The method provided by the invention comprises the following steps: converting a subsequence in historical state sequence data of the fire-fighting equipment into data to form a first state sequence of the fire-fighting equipment; determining a state space based on the first state sequence of the fire-fighting equipment; determining the order of a high-order Markov chain model based on the length of the historical state sequence data, and constructing the high-order Markov chain model based on the order and the state transition probability matrix; solving the target function under the constraint condition based on a linear programming solver to obtain model parameters of a Markov chain model, and obtaining an optimized Markov chain model based on a solving result; and predicting a fire alarm state in the first time period based on the high-order Markov chain model. According to the fire alarm prediction method and device based on the high-order Markov chain provided by the invention, rapid analysis of a fuzzy system state is realized through short-term data so as to predict a short-term fire risk.

The embodiment of the invention provides a real-time cross-lens multi-target tracking method for multiple fixed lenses, a storage medium and electronic equipment, and relates to the technical field of target tracking, and the method comprises the steps: projecting a plurality of target center positions between cameras into a same position coordinate system through employing a pre-calculated projection transformation matrix between every two cameras; and then multi-target pairwise matching with the minimum cost is carried out by using a bipartite graph matching algorithm, the same ID is allocated to the two matched targets, and the unique ID is reallocated to the unmatched targets, so that multi-target tracking is realized. According to the method and the device, target features do not need to be calculated, the requirement on calculation resources is relatively low, multi-target tracking can be realized only by utilizing the projection transformation relationship between the cameras, and the method and the device can be migrated to any scene.

The present invention provides a virtual laser radar system and method based on mutual early warning of wind turbines, including: a wind farm deployment data module, which obtains the front and back relationship of wind turbines arranged at intervals in the main wind direction in the wind farm; a wind speed transfer characteristic module, which obtains the transfer characteristic of the wind speed in the main wind direction in the area where the wind farm is located; a wind farm operation data module, which obtains the actual operation data of the wind farm; and a neural network module, which captures the wind speed relationship between wind turbines according to the front and back relationship of wind turbines arranged at intervals in the main wind direction in the wind farm, the transfer characteristic of the wind speed in the main wind direction, and the wind farm operation data, so as to replace the physical laser radar to predict gusts.

The present application relates to a vehicle re-identification method, apparatus, computer equipment and storage medium. In the re-identification method, firstly, the vehicle appearance is used to perform a rough match from a query library to obtain a candidate vehicle, and then a multi-frame three-dimensional point cloud is used to obtain the side profile features of the vehicle, and a fine match is performed in combination with the image features of the vehicle to obtain a target vehicle from the candidate vehicles. The method utilizes multi-dimensional information during fine matching, and the scheme can obtain a more precise and accurate re-identification result based on the increase of limited data processing.

The invention belongs to the technical field of power electronic system control, and particularly relates to a bridge arm energy balance control method of a modular multi-level converter, which comprises the following steps: generating a direct current bus current reference value for representing the direct current side energy regulation requirement of the modular multi-level converter; in combination with the energy state of each bridge leg, generating a bridge leg current reference value corresponding to each bridge leg by using a bridge leg current reference value distribution strategy; generating mutually independent bridge leg common-mode voltage modulation signals of the bridge legs; based on a common-mode modulation signal energy rectification distribution strategy, performing energy rectification type distribution in the bridge legs, and generating common-mode voltage modulation signals corresponding to the upper bridge arm and the lower bridge arm; the differential mode voltage modulation signals are combined with differential mode voltage modulation signals generated by alternating current side control to generate bridge arm voltage modulation signals corresponding to the bridge arms; trigger pulses of all sub-modules in the bridge arm of the modular multilevel converter are generated through a modulation method, and controlled adjustment of the energy of the bridge arm is achieved.

A chlorophyll visualization method and system based on hyperspectral ensemble learning belongs to the field of instrumentation technology. The method involves measuring chlorophyll physicochemical indices from modeled one-dimensional spectral data and augmenting the data with Gaussian noise and distortion. The data is then divided into a modeling set and a prediction set in a 7:3 ratio, ensuring the modeling set includes the prediction set. The divided modeling set is used to train and optimize XGBOOST, PLS, and RIDGE models respectively, yielding three optimal models. These models are then weighted and merged to obtain an ensemble model. After iterative optimization, the optimal weighted ensemble model is obtained. The spectral data of the region of interest (ROI) of the hyperspectral data to be measured is input into the optimal weighted ensemble model for prediction, and the predicted results and corresponding spatial locations are saved. Chlorophyll information is overlaid on the corresponding chlorophyll pixels in the three-dimensional image of the hyperspectral data to be measured, and a heatmap is generated. This method exhibits strong generalization ability and achieves high accuracy even with small sample sizes.

The invention relates to a weight and overload prediction method for a distribution transformer. The method comprises the following steps: acquiring historical power load data of daily preset interval time in a target area; decomposing the historical power load data according to a preset STL time sequence decomposition algorithm to obtain a plurality of sequence components; performing feature extraction on the sequence component to obtain a sequence feature component; predicting a future sequence value corresponding to the sequence feature component according to a preset prediction model to obtain power load prediction data; performing accuracy evaluation on the power load prediction data according to a preset evaluation model to obtain a sample prediction load; calculating a sample load rate according to the sample plate prediction load; and performing heavy overload judgment on the sample load rate according to a preset heavy overload judgment threshold. According to the technical scheme, the distribution transformer weight and overload prediction method and device have the advantages of being reliable in prediction precision, simple, easy to implement, good in model interpretability and the like, and can be well applied to power load data.

The invention discloses a method and system for converting an Excel file to a complex structure table image, and the method comprises the steps: obtaining image data, carrying out the feature extraction of the image data through a first backbone network, and obtaining feature information; performing first transformation on the feature information to obtain first feature information, and inputting the first feature information to a first branch to obtain positioning information; inputting the first feature information to a second branch based on the positioning information to obtain a first sequence; replacing the first sequence according to the positioning information and the first sequence to obtain a first code; and the first code is converted by utilizing a first tool to obtain the Excel file, and the Excel file has better performance for table images with complex structures.