174results about How to "Computationally efficient" patented technology

The invention relates to a structural parameter construction method for reducing vibration of a transformer. The method comprises the following steps: acquiring vibration characteristics and working condition data of the transformer; constructing a genetic algorithm model based on the objective function; candidate solution vibration performance verification based on finite element simulation; constructing a hybrid optimization strategy based on a genetic algorithm and finite element simulation; verifying and optimizing the scheme under a multi-dimensional working condition; outputting a vibration calculation result and evaluating a scheme. According to the structural parameter construction method for reducing the vibration of the transformer, the preliminary schemes are screened by applying a fast convergence genetic algorithm, and the candidate schemes are subjected to high-precision verification in combination with finite element simulation, so that the defects of a traditional vibration calculation method in the aspects of efficiency and accuracy are overcome; and the design change can be quickly responded, and the vibration performance is optimized, so that the high-standard requirements of modern power equipment on the aspects of safety and reliability are met, and powerful technical support is provided for the design and improvement of the transformer.

The invention discloses a free-form surface three-axis ball-end cutter equal approximation error finish machining tool path generation method which comprises the following steps: firstly, importing a free-form surface model to be machined, and setting data such as the radius, the line spacing, the approximation error maximum allowable value and the precision of a ball-end cutter; secondly, a group of section planes are planned according to the row spacing to intersect with the curved surface, the intersecting line serves as a cutter contact curve, and an equal-bow-height-error cutter contact iterative search method for driving cutter contact adjustment through the geometric distance is provided for the cutter contact curve on the section planes; the maximum distance between a cutter cutting envelope surface and a cutter contact track line is used as an approximation error, and an adaptive discrete method is adopted to carry out approximation error calculation; and finally, the cutter location points of the equal-bow-height-error cutter contact points serve as initial values, an equal-error cutter location point calculation method of step length self-adaptive adjustment iteration is provided, approximation errors between the cutter location points are all within an allowable range, and therefore the free-form surface three-axis ball-end cutter equal approximation error finish machining cutter path is obtained.

The invention discloses a feature classifier-based thinking chain reasoning mathematical problem solving method and system. The method comprises the following steps of: (1) acquiring a mathematical problem set, and selecting forward and reverse thinking chain examples to splice to form a new set; (2) respectively inputting the new set elements into a model for reasoning to construct a word-level reasoning path spanning tree, and selecting an attention weight matrix after pooling difference processing as node features for storage; (3) traversing all the generated reasoning path spanning trees, and screening nodes meeting requirements to construct a feature classifier training set; (4) training a feature classifier by using a support vector machine algorithm; and (5) through the trained feature classifier, participating in path selection in a pre-training language model reasoning process, and obtaining a relatively accurate reasoning process and answers. By means of the method, adjustment and control of finer granularity of the reasoning path of the pre-training language model can be achieved, accurate reasoning solving of the pre-training language model on mathematical problems is facilitated, and the generalization level of the pre-training language model is improved.

The invention relates to the technical field of voice recognition, in particular to a mixed recognition processing method and device, equipment and a medium, and the method comprises the steps: recognizing command word data based on a command word recognition model, selecting command word data with an error rate lower than a preset range, generating a corresponding phoneme embedding representation, and forming a phoneme embedding dictionary; determining a mixed recognition command word corresponding to the current command word, and generating a mixed recognition list; identifying an audio embedding sequence corresponding to the current command word; obtaining a phoneme embedding sequence of each mixed recognition command word in the mixed recognition list based on a phoneme embedding dictionary; and calculating the similarity between an audio embedding sequence and each phoneme embedding sequence to obtain an identification result. The method and the device can improve recognition accuracy and reduce mixed recognition of command words.

The invention discloses an indoor environment performance optimization design method and system for a tall and large space building based on CFD and a multi-objective optimization algorithm, and the method comprises the steps: building a parameterized analysis model through combining with a BIM model, carrying out the digital simulation analysis of an indoor light environment and energy consumption through employing Honeybee Radio and Honeybee Entry plug-ins in Rhino and Grasshopper environments, determining optimization parameters and objectives, and carrying out the optimization of the indoor environment and energy consumption. And a BIM model and an IDF file corresponding to the optimal schemes are exported, the uniformity of the indoor airflow organization is evaluated based on FFD software, and parameters of the optimal schemes are determined. Compared with a traditional indoor environment optimization method, the high and large space building indoor environment performance optimization and evaluation method is efficient, accurate and economical, and has higher accuracy, higher adaptability and wider applicability. Natural lighting, building energy consumption and indoor three-dimensional thermal comfort can be considered at the same time, and optimization of the indoor environment performance of the tall and large space building is achieved.

The invention discloses an accelerator for accelerating the reasoning process of an unstructured sparse large language model and an operation method of the accelerator. The accelerator comprises a processor module, a direct memory access module, a memory controller module, a DDR memory module, an interconnection bus module, a calculation core module and a router module. The interconnection bus module is connected with the direct memory access module, the memory controller module and the computing core module; the processor module is connected with the direct memory access module; the DDR memory module is connected with the memory controller module; the router module is connected with the computing core module and the adjacent router module; and the calculation core module obtains to-be-calculated data from the off-chip DDR memory module through the interconnection bus module. According to the method, the limit that data reuse is carried out only along a single row or a single column on a traditional systolic array is broken through, cross-row and cross-column data reuse is achieved, the pressure of hardware equipment is relieved, the positions of non-zero elements are coded through bit masks, and the calculation efficiency is improved.

The invention provides a fluid simulation data prediction and noise reduction method, system and device, and relates to the technical field of fluid simulation, and the method mainly comprises the steps: 1, constructing a simulation model; the simulation model comprises an auto-encoder, a denoising model and a decoder which are arranged in sequence; the auto-encoder is used for encoding condition input data and mapping the condition input data to a potential space to obtain characterization data; the denoising model is used for introducing noise into the representation data and converting the representation data into target data through denoising processing; the decoder is used for decoding the target data and mapping the target data to a functional space to obtain simulation result data; and step 2, inputting initial condition data of fluid dynamics into the simulation model, and outputting corresponding prediction result data. According to the scheme, the space noise reduction and output generation operation is completed in the potential space, the operation efficiency can be improved, the operation cost can be reduced, the output can be smoother, and therefore the quality and stability of the output are improved.

The invention relates to the technical field of attendance management, and discloses an electronic class board attendance system for palm vein recognition, which comprises a palm vein data acquisition module for irradiating the palm of a user through a near-infrared light source and acquiring a palm vein image; the image optimization processing module is used for performing optical modeling optimization, noise removal and quality enhancement on the acquired palm vein image; the deep learning recognition module is used for extracting palm vein features and performing identity matching; the attendance record storage module is used for storing and managing user attendance data; and the control and communication module is used for managing cooperative work of all the modules and performing data interaction with an external attendance database. Through the technical scheme of combining near-infrared illumination and the light transmission equation, the palm vein feature image is accurately extracted, the effect of optimizing palm vein contrast and detail definition is achieved, the problems of palm vein feature edge blurring and detail loss are solved, and the image processing quality is improved.

The invention discloses a scale-effect-free mine dynamic disaster fine monitoring and dynamic early warning method, which comprises the following steps of: arranging a multi-point micro-seismic monitoring network on a coal mine working face, and continuously acquiring and preprocessing micro-seismic signals; an innovative analysis positioning algorithm is adopted to accurately analyze the accurate position and time information of the micro-seismic source; in combination with signal features and positioning data, a four-dimensional joint kernel density estimation and confidence interval theory is innovatively applied, a rock burst risk assessment model is constructed, and a danger level classification standard is determined; and the system calculates risk indexes in real time and dynamically issues early warning. According to the invention, the precision, timeliness and reliability of monitoring and early warning of the dynamic disasters in the mining area are obviously improved, and key technical support is provided for safe production of a coal mine.

The invention discloses a degradation conversion rate calculation method and system based on an epoxy resin alcoholysis model, and belongs to the technical field of thermosetting epoxy resin degradation and recovery. The method comprises the following steps: pouring epoxy resin to cure and mold, carrying out an epoxy resin alcoholysis degradation experiment at different temperatures, and recording degradation conversion rates at different moments; constructing an epoxy resin geometric model, and analyzing to obtain a degradation conversion rate differential expression containing reaction rate constants and geometric parameters; solving the differential equation to obtain a reaction rate constant, and fitting by using an Arrhenius formula to obtain degradation activation energy; analyzing a transesterification process of the epoxy resin and the alcohol solvent and a diffusion process of the alcohol solvent in the epoxy resin, and establishing a degradation conversion rate expression which does not contain geometric dimension parameters; and substituting degradation reaction activation energy, and fitting to determine a degradation conversion rate expression which does not contain geometric dimension parameters. The invention aims to provide a reference for the degradation process analysis of the large-size epoxy resin with a complex shape.

The invention discloses a Chiplet-based matrix chain multiplication accelerator and an acceleration method. The matrix chain multiplication accelerator comprises a first matrix multiplication module, a first external memory interface and a nonlinear processing module, and a second matrix multiplication module and a second external memory interface which are connected with each other through Chiplet. The method comprises the following steps: acquiring operator data of a Transform network and preprocessing the operator data to obtain a matrix chain data stream; based on the matrix chain data stream, performing initialization processing on a matrix chain multiplication accelerator to obtain an initialized matrix chain multiplication accelerator; and inputting the matrix chain data stream into the initialized matrix chain multiplication accelerator for matrix multiplication operation to obtain attention matrix data. According to the embodiment of the invention, the utilization rate of the processing element can be improved, so that the memory access times and the data transmission delay are reduced, and the calculation efficiency is improved. The method can be widely applied to the technical field of computer hardware acceleration.

The invention discloses a medium metasurface reverse optimization method based on a space coupling mode theory, and relates to the field of optics, and the method comprises the following steps: building a cut-off waveguide array based on a metasurface, calculating a guided mode and a propagation constant of each waveguide according to the cut-off waveguide array, and coupling adjacent waveguides through a coupling matrix, a waveguide array is obtained; an input light field is coupled into a waveguide array, propagation of light in waveguides is simulated based on a spatial coupling mode theory model, and near-field intensity distribution is converted into far-field intensity distribution by using a Rayleigh-Sommerfeld diffraction theory; and calculating the difference between the target intensity and the far-field intensity through a loss function, evaluating the effect of the current metasurface design, and gradually adjusting the geometric parameters of the waveguide unit through an optimization algorithm. According to the method, the problems of efficient modeling and optimization in metasurface design are solved through the space coupling mode theoretical model.

The invention provides an image enhancement system and method and a medium. The system comprises (N-1) row cache FIFO (First In First Out) which are connected in series, N row cache registers, a Demosaic module, a G component cache FIFO and a G component cache register. According to the invention, by reasonably controlling the read-write of the row cache FIFO and the register, at least five pixel points are output all the time under the condition that any number of pixel data is transmitted for each row of image data of each clock, so that the calculation requirement of the Demosaic algorithm is met. Under the condition of balancing and optimizing the combinational logic series to be executed in each clock period and the occupation of the total register, in the pipeline design of the Demosaic algorithm, the finiteness of hardware internal resources and the time sequence convergence problem of high clock frequency are fully considered, and by combining the combinational logic series optimization and the pipeline series optimization, the time sequence convergence problem of the high clock frequency is fully solved. In this way, better occupation of various resources of the FPGA is achieved, and efficient calculation is achieved. Based on the calculation strategy provided by the invention, the image enhancement process is finally realized, and the high-quality color display image is obtained.

The invention provides a parking visual positioning method and system based on parking space semantic information and a vehicle-mounted terminal.The method comprises the steps that an aerial view image of a vehicle in a parking environment and a global parking space semantic map are obtained, and the global parking space semantic map is constructed according to the parking environment; inputting the aerial view image into a parking space detection model for parking space detection, and obtaining first parking space semantic information under an image coordinate system; according to the relative position relation between the vehicle and the parking space in the aerial view image, global coordinate conversion is carried out on the first parking space semantic information, second parking space semantic information under a global coordinate system is obtained, and the global coordinate system is constructed based on the parking environment; and matching the second parking space semantic information with the global parking space semantic map, and determining the position of the vehicle in the parking environment. Parking visual positioning is carried out based on the corresponding parking space semantic information of the vehicle in the current parking environment, the position of the vehicle in the parking environment can be accurately determined, and the accuracy of vehicle positioning during parking is improved.

The invention relates to the technical field of electric power fault detection, and discloses a fault monitoring system and method based on an electric power acquisition terminal, and the method comprises the steps: constructing a non-linear relation between the power consumption and the temperature through analyzing the historical power consumption data of a user and the weather temperature; the method comprises the following steps: dividing a user electricity consumption day into a plurality of time periods, and setting a time interval threshold value; and in each time period, data are acquired through the electric power and temperature acquisition devices, an electric quantity and temperature scatter diagram is constructed, and nonlinear data fitting is carried out. Thirdly, the similarity between the temperature nonlinear relational expressions of different time periods is calculated, the time periods are divided into sets, and a temperature retrieval set is established; and searching a corresponding electric quantity relation set by matching the temperature nonlinear relational expression of the user in the current time period, and judging whether electric power fluctuation and fault exist or not according to the priority ranking and the relation similarity.

The invention discloses a method and device for detecting the center position in a laser spot image, and the method comprises the steps: obtaining a laser spot image which is a fuzzy circle / circular ring light spot, and solving the center-of-gravity coordinate of the fuzzy circle / circular ring light spot as an initial center position; calculating radial distances from the initial circle center position along a plurality of different directions of the fuzzy circle / circular ring light spot, and calculating an average value of the radial distances in the different directions as an average radius; based on the average radius, utilizing a least square method to fit a new circle center position; and taking the new circle center position as an initial circle center position, repeating iterative calculation until the difference between the current fitting new circle center position and the previous fitting new circle center position is smaller than a preset threshold value, and determining the current fitting new circle center position as a final circle center position. The method is more accurate in circle center position detection and higher in calculation speed.

The invention provides a rail transit environment vibration directional control method and system using a wedge-shaped tree array. According to the method, ground surface vertical vibration caused by passing of a train beside a certain ballast track is calculated by constructing a semi-analytical three-dimensional dynamic response model, simulation of the tree vibration reduction measure effect is achieved by coupling the wedge-shaped tree array into the model, and the tree vibration reduction measure effect is achieved by adjusting parameters of the wedge-shaped tree array. The wedge-shaped tree array with the expected vibration reduction effect is obtained, and then design parameters of wedge-shaped tree array vibration reduction measures are obtained. The wedge-shaped tree array is arranged between a track structure and a target vibration control area, and the selection and arrangement mode of tree characteristics such as tree species, tree height and tree diameter can be optimally designed according to a target vibration reduction frequency band and an expected vibration reduction effect. The invention overcomes the limitation of the traditional vibration isolation technology on cost and implementation, provides a wedge-shaped tree array vibration reduction measure which is low in cost and easy to arrange and meets the environmental protection requirement, and has good popularization and application potential.

The invention relates to a water resource pressure assessment method integrating social economy and climate change. Relates to the technical field of drought basin water resource pressure assessment. The method comprises the following steps: acquiring a historical value and a predicted value of social economic data, and correcting the predicted value of the social economic data to obtain a corrected predicted value; calculating the potential evapotranspiration of the drainage basin in different scenes based on the meteorological data of the historical scenes and the corrected future climate mode data; calculating a future drainage basin water resource quantity based on a correlation between drainage basin rainfall and the water resource quantity; according to the variation trend of the drainage basin drought index in the historical scene and the future scene, drought intensity characteristics are extracted; constructing a drainage basin water resource pressure index calculation formula; and according to the calculated water resource pressure index of the water resource area, standardization is carried out to obtain a standardization index, and according to the standardization index, the water resource pressure change trend of different scene areas is evaluated. According to the method, the quantization and evaluation problem of the drainage basin water resource pressure under the complex condition is solved.

The invention provides a lightweight large model operation method based on end-side deployment. The lightweight large model operation method comprises the following steps: acquiring equipment operation data and storing a model file in a mixed precision format according to quantization precision supported by terminal equipment; determining a mixing precision quantification strategy and carrying out strategy analysis on the equipment operation data; a Key-Value cache file obtained through model reasoning in the historical dialogue is reserved; calculating a semantic embedding vector of the second user request, calculating a cosine similarity between the semantic embedding vector and the first V vector, and judging whether the second user request has a similar intention or not according to a calculation result; and if yes, performing incremental reasoning on the second user request by multiplexing the Key-Value cache file. By monitoring the state of the terminal equipment in real time, dynamically adjusting the quantization level, multiplexing the cache data of the semantic related requests and merging batch request reasoning, the effects of balancing the energy consumption and performance of the terminal equipment, reducing repeated calculation and improving the service time of the equipment and the user experience are achieved.

The invention relates to the technical field of civil engineering, and particularly discloses a railway tunnel high-performance active support system design method considering a space-time effect, which comprises the following steps: S1, establishing a tunnel early-strength and high-strength sprayed concrete layer calculation model; s2, determining calculation parameters required by the sprayed layer calculation model according to the tunnel early-high-strength sprayed concrete layer calculation model; s3, influence factors of surrounding rock deformation pressure borne by the tunnel early-strength and high-strength sprayed concrete layer are determined; s4, establishing a surrounding rock deformation pressure calculation method of the tunnel early-strength and high-strength sprayed concrete layer considering the surrounding rock level; and S5, establishing a surrounding rock deformation pressure calculation method of the tunnel early-strength and high-strength sprayed concrete layer considering the rock mass quality index. By adopting the railway tunnel high-performance active support system design method considering the space-time effect, the safety of the tunnel early-strength and high-strength sprayed concrete layer under different time, geological conditions, construction levels and support design parameters can be simply, quickly and accurately calculated.

The invention provides a neural network hardware implementation method and system based on an incomplete specified function, and the method comprises the steps: carrying out the quantification of the input data and weight of a neural network, and obtaining a position index of a non-zero weight; traversing the training set, and obtaining a plurality of data sets related to the non-zero weight according to the position index of the non-zero weight based on an incomplete specified function; performing logic minimization on the basis of the plurality of data sets, generating a Boolean logic expression based on an incomplete specified function, and determining a flash memory logic array scale and internal port connection lines according to a cube of the Boolean logic expression and logic variables in the Boolean logic expression; the flash memory logic array is constructed according to the scale of the flash memory logic array and the internal port connecting line, and a peripheral circuit of the flash memory logic array is constructed, and the peripheral circuit is mainly used for processing output data of the flash memory logic array. According to the invention, power consumption and time delay in a neural network hardware implementation process are reduced.

The invention discloses a small target detection method and system, the method is specially designed for server-side processing of image acquisition of an unmanned aerial vehicle, the unmanned aerial vehicle is only responsible for image acquisition and transmission, and all image processing and target detection are completed on a server. According to the method, intrusion identification of people and vehicles and early detection of petroleum leakage are divided into two independent modules: for intrusion identification of people and vehicles, an improved YOLOv8 network is adopted; for early detection of petroleum leakage, a ResNeXt network is selected for processing. According to the technical scheme, the small target detection effect in the unmanned aerial vehicle image can be improved, the calculation resources of the model cannot be obviously increased by introducing the module, and the detection performance and the calculation resources can be better balanced; moreover, an effective solution is provided for the current situation that the petroleum leakage detection technology is deficient in the desert environment, the technical blank in the field is filled, and the accuracy of desert petroleum leakage detection is improved.

The invention discloses a blast hole parameter adaptive tunnel smooth surface effect prediction method, which comprises the steps of constructing a smooth surface effect prediction model based on a graph neural network; predicting rock mass displacement data by using the smooth surface effect prediction model; and calculating a tunnel smooth surface effect in combination with a prediction result of the rock mass displacement data. According to the method, the adaptive blast hole parameter smooth surface effect rapid prediction model based on the depth map neural network is constructed, smooth surface blasting data are comprehensively extracted by using the map neural network, the accuracy of a deep learning-based calculation method is improved, and the method has important theoretical significance and application value for tunnel blasting construction.

The invention discloses an intelligent visual rating device and method for fabric appearance flatness. The method comprises the following steps: S1, acquiring a fabric image; s2, preprocessing the fabric image; s3, camera calibration and image correction; s4, feature extraction and matching; s5, stereo matching and depth estimation; s6, performing three-dimensional reconstruction; s7, grading the appearance flatness of the fabric; the objective rating method for automatically processing the fabric depth image difference is constructed on the basis of quickly reconstructing the fabric appearance form based on a machine vision technology, so that the fabric flatness detection efficiency and accuracy are improved, and a more reliable and objective basis is provided for fabric quality evaluation.

The invention provides a method and system for improving bid evaluation accuracy, and relates to the technical field of bid evaluation, and the method comprises the steps: bid file data preprocessing including data cleaning and feature selection, bid insensitive learning model building and fusion, and real-time fusion model performance evaluation including fairness constraint, cross validation and bid detection. Updating according to an evaluation result, substituting the feature information to calculate a bid evaluation score, adding an expert review mechanism to adjust the score, and archiving a final bid evaluation score; according to the method, the labor cost is reduced through a rule calculation engine, the scoring accuracy and generalization ability are improved through data cleaning and other technologies, expert review and fairness constraint are introduced to guarantee fairness, review traceability is guaranteed through an archiving result, project decision is supported, and the bid evaluation accuracy is improved through multiple innovation strategies.

The invention provides an underwater robot environment sensing method and device based on a feature propagator. The method comprises the following steps: acquiring a binocular image acquired by an underwater robot and a pre-established deep neural network; the binocular images are corrected, the corrected binocular images are respectively input into a feature extractor of the network, feature maps under different scales are obtained, and a feature pyramid is formed; and performing cost body construction, cost body aggregation and parallax regression based on each feature pyramid by using a cost aggregator. And initializing a multi-stage convolution gating cycle unit in the iterative optimizer based on the original cost body and the aggregated cost body by a feature propagator. And optimizing parallax prediction based on a multi-level convolution gating circulation unit initialized by the feature propagator until a parallax prediction value reaches a convergence condition, and obtaining a final parallax map. Internal and external parameters of the binocular camera are obtained, a scene depth map and a three-dimensional point cloud of the underwater environment are calculated based on the internal and external parameters and the disparity map, and robust and efficient underwater environment perception is achieved.

The invention belongs to the technical field of wireless communication, and discloses a fluid antenna assisted communication, perception and calculation integrated (ISCC) method, which comprises the following steps of: unloading communication and perception tasks of a terminal to a mobile edge calculation (MEC) server at a base station end, and constructing an efficient ISCC system by utilizing the strong calculation capability of the server; a fluid antenna is integrated to a base station end, a fluid antenna assisted ISCC system is provided, and a fluid antenna assisted communication and perception model is established; the time delay of communication and sensing tasks is calculated, a time delay optimization problem is constructed, and the total time delay of the system is minimized by optimizing the position of a fluid antenna. According to the method, the flexibility of the fluid antenna is fully utilized, and the position of the antenna at the base station end is dynamically adjusted, so that the channel condition is adapted and optimized, and efficient and low-delay communication, sensing and calculation between the terminal and the base station are realized.

The invention relates to the technical field of particle deposition and semiconductor anti-radiation analysis, and discloses an alpha particle energy deposition calculation method based on a Monte Carlo particle transport simulation tool, which sequentially comprises the steps of material and particle source setting, energy deposition score indicator use, single particle event statistics, soft error rate calculation and output and data analysis. By adopting the method and the device, the requirements of field experiments are greatly reduced, and the time and the cost required by the experiments are saved. Moreover, through the simulation method, designers can more efficiently calculate the energy deposition of the alpha particles in the semiconductor device and obtain the soft error rate of the alpha particles, and radiation hardening design of the semiconductor device can be carried out according to the data, so that the radiation resistance and reliability of the device are improved.