26results about How to "Increase computing speed" patented technology

The present application relates to a kind of lake reservoir type chlorophyll concentration prediction method, device and medium, method includes the following steps: obtaining the water quality, water dynamics and weather of the online automatic monitoring data of lake reservoir including forecast point and upstream point;The online automatic monitoring data is preprocessed, and the data after processing is obtained;The data after processing is carried out feature extraction to obtain the water quality feature and water dynamics index feature of forecast point and upstream point, and construct cumulative illumination feature;Upstream water quality feature, water dynamics index feature and illumination feature are input into the fusion prediction model pre-trained, to obtain upstream transport chlorophyll prediction result and time series influence chlorophyll prediction result, using error reciprocal method upstream transport chlorophyll prediction result and time series influence chlorophyll prediction result are fused;The chlorophyll prediction result obtained by fusion is output.Compared with prior art, the present application has the advantages of high accuracy, strong stability and the like.

This invention discloses a partial discharge (PD) signal denoising method based on image information entropy and multivariate variational mode decomposition (MMD). The method involves converting the noisy signal into a grayscale image, calculating the image information entropy, and optimizing the number of modes K in the MMD by combining Pearson correlation coefficient and execution efficiency to determine the optimal value. The noisy PD signal is then decomposed. The kurtosis value of each intrinsic mode component is calculated, and the nature of the mode component is determined based on a threshold, classifying it as either a dominant PD component or a noise component. A mathematical statistical method using the 3σ criterion is employed to filter out normally distributed white noise. The reconstructed signal is then denoised using an improved wavelet thresholding method to obtain the denoised PD signal. This denoising method accurately reduces noise in noisy PD signals, achieving good noise suppression and restoring the waveform characteristics of the PD signal while maintaining high execution efficiency.

The application provides a micro-service message scheduling method, device, electronic equipment and storage medium. The method comprises the following steps: based on request information corresponding to each logical operation of a monomer service, a packaged single message body in a single logical operation unit is determined, and the single message body is added to a RabbitMQ message queue; based on message bodies corresponding to different logical operations in the RabbitMQ message queue, a required micro-service cluster is determined; and based on pre-configuration information of a zookeeper center, an optimal micro-service provider in the micro-service cluster is determined as an optimal micro-service scheduling scheme of the single logical operation according to an optimal rule. The micro-service message scheduling method provided by the application greatly accelerates the program operation speed and response time by decoupling the business logic through RabbitMQ, and the introduction of the zookeeper can centrally register and manage multiple distributed services, so that the system resources can be used more.

The water-fat separation method, system and terminal for magnetic resonance imaging of the present application obtain the corresponding water-fat separation result according to the echo complex image data through the water-fat separation model based on the deep learning and the traditional model segmentation combination. The present application optimizes the precision of the field map extraction, improves the stability and calculation speed of the water-fat separation, at the same time, retains the constraint force of the traditional algorithm on the output result, and maximizes the consistency of the output result and the original signal.

The invention discloses a carbon emission calculation method and system based on building main material equivalent, belongs to the technical field of carbon emission calculation, and solves the problems that an existing carbon emission calculation method is high in data requirement, low in calculation speed and insufficient in applicability. By analyzing historical project data, screening out key principal materials and constructing an algorithm model between consumption and total carbon emission, 'less data and high precision 'rapid calculation is realized, indirect carbon emission generated by building material production, transportation and construction is mapped to the key principal materials through weights, a whole-process carbon emission equivalent evaluation system is established, and the evaluation accuracy is improved. And the whole-process carbon emission can be output in a one-stop manner by inputting the consumption. The model output is an interpretable regression equation with a clear coefficient weight, a transparent decision basis is provided, and in addition, the key main materials are pre-determined through an algorithm, so that a new project can directly utilize the use amount of the existing key main materials in the project cost process to carry out carbon emission quick calculation.

This invention discloses a method for detecting internal leakage in hydraulic cylinders and its application in TBM support shoe hydraulic cylinders, comprising the following steps: S1, acquiring stroke data of the hydraulic cylinder within a predetermined time t1; S2, cleaning and segmenting the acquired hydraulic cylinder stroke data; S3, acquiring and filtering pressure data of the hydraulic cylinder in each specified time period; S4, performing wavelet decomposition and reconstruction on each group of filtered pressure data; S5, calculating the proportion of the energy of each order of high-frequency reconstructed signal in the total energy of the original pressure signal to determine whether internal leakage has occurred in the hydraulic cylinder. This invention completes the detection of internal leakage in TBM support shoe hydraulic cylinders using only pressure and stroke data, without the need to establish a complex physical model based on the geometric parameters of the TBM support shoe hydraulic cylinder, thus improving calculation speed and detection efficiency.

The application discloses a substation equipment identification method and system based on an improved point pair feature matching algorithm, and comprises the following steps: obtaining original point cloud data of equipment in a substation, performing mean value processing on point clouds in a grid by using a grid downsampling method to obtain new point cloud data; wherein the size of the grid is automatically adjusted according to the number of the original point cloud data; performing key point screening on the new point cloud data, randomly selecting a reference point from the extracted key points, and respectively forming point pair features of the reference point and other points in the scene; matching the point pair features with pre-stored equipment model point pair features in a hash table to obtain matched point pair features, and identifying substation equipment based on the matched point pair features. By optimizing and screening the key points, the application reduces invalid points and redundant points, thereby improving the calculation speed and matching accuracy, and finally accelerating the substation equipment identification speed.

The invention relates to a rectangular coordinate-to-polar coordinate conversion method and device based on an LUT and CORDIC hybrid architecture. The method comprises the following steps: S1, sector folding preprocessing; s2, performing coarse rotation iteration; s3, generating a dynamic address; s4, a compression lookup table is queried; and S5, data compensation and reconstruction. According to the method, a small amount of CORDIC iteration is introduced to rotate the input vector to a very small angle range, so that the input space required to be covered by a subsequent lookup table is greatly compressed; meanwhile, the bit width and the address depth of a storage value in the LUT are remarkably reduced by combining module value residual storage and a dynamic truncation technology, so that the storage resources of the LUT are greatly reduced on the premise of ensuring the precision, and the hardware implementation cost is lower.

The application provides an artificial intelligence-based molecular processing method and device, electronic equipment, computer readable storage medium and computer program product; the method comprises: performing state sampling processing on a first state random distribution corresponding to a first time and a second time to obtain a first state at the first time and a second state at the second time; determining a plurality of third times from a first time period composed of the first time and the second time, and performing encoding processing on the first state and the second state to obtain a first encoding of the first state and a second encoding of the second state; generating a second state random distribution of the third time, performing random state sampling processing on the second state random distribution to obtain a third encoding of the third time; and performing decoding processing on the third encoding of the third time and the third encoding of the historical third time to obtain a third state at the third time. Through the application, the calculation speed and accuracy of the molecular state can be improved.

The invention discloses a material microstructure interactive efficient three-dimensional reconstruction method, and relates to the technical field of material microstructure analysis and three-dimensional reconstruction, and the method comprises the steps: completing the selection of a target microstructure on a material microscopic image based on the prompt segmentation capability of SAM2; tracking a target microstructure in a material microstructure series section by using a memory mechanism of SAM2, and performing tracking optimization by modifying a memory code of a segmentation mask; introducing a tracking constraint condition of a morphological change trend of the microstructure between adjacent layers, and combining a bidirectional tracking strategy to obtain a corresponding relationship between target microstructure layers; and on the basis, a contour surface extraction algorithm is adopted to generate a corresponding three-dimensional structure model. According to the method, continuous tracking and high-quality three-dimensional reconstruction of the complex material microstructure can be achieved without retraining the model, and the method has the advantages of being high in universality, low in interaction cost and high in reconstruction stability and is suitable for three-dimensional representation and analysis of the material microstructure.

The invention discloses a traffic signal control method based on a generalized TUC and a maximum pressure strategy of cv data, and the method comprises the steps: taking a #-shaped road network as a control region, carrying out the traffic signal control periodically, and carrying out the traffic signal control of all intersections in the control region through employing the maximum pressure strategy in a first period; starting from a second period, determining a supersaturated intersection based on video data collected by cv equipment arranged at each intersection and each entrance in the control area in the previous period, and determining an associated intersection of the supersaturated intersection; then, traffic signal control is carried out on all the supersaturated intersections and the associated intersections thereof by adopting a TUC strategy by adopting the associated intersections of all the supersaturated intersections in the current period, and traffic signal control is carried out on other intersections by adopting a maximum pressure strategy; the method has the advantages of being high in calculation speed, high in real-time performance, high in control performance under the supersaturated traffic condition and high in control precision.

The application discloses a kind of based on genetic algorithm's convolutional neural network feature map selection method, it is related to genetic algorithm technical field.The based on genetic algorithm's convolutional neural network feature map selection method, when the fitness value of individual in population is greater than the precision value of original classification network srcNet, and the number of 0 in the binary encoding of this individual meets the demand of user, that is, the number of discarded feature map meets the demand of user, stop iteration, can be through the advantage of genetic algorithm, that is, global search and parallel computing capacity, different feature map is evaluated and selected, according to the setting of population size, select and keep the individual of higher fitness, to maintain the elite of population, to facilitate selection optimal feature map combination, improve the speed and accuracy of model;Genetic algorithm can also consider the importance of different feature map, so as to weigh when selecting feature map, reduce the redundancy between feature map, improve model generalization ability.

This application discloses an adaptive optimization method and system for thermal coupling parameters of automotive backlight panels, relating to the field of parameter simulation optimization technology. The specific implementation scheme is as follows: A full-envelope operating condition script is compiled; a thermal model and thermal coupling parameter set are imported; thermal simulations are automatically run in batches sequentially using the full-envelope operating condition script; raw datasets for each operating condition segment are collected; risky operating condition segments are screened; thermal coupling parameter perturbation groups are applied to each risky operating condition segment; high-risk operating condition segments are identified; parameter inversion is performed on each high-risk operating condition segment; and the thermal coupling parameter update strategy for each high-risk operating condition segment is determined, along with the optimal thermal coupling parameter version. This invention can improve the prediction accuracy of the thermal model under complex or extreme operating conditions, thereby avoiding problems such as underestimated junction temperature peaks, distorted hotspot locations, and drifting temperature rise rates. This provides a scientific and reliable data basis for the structural design, safety margin setting, and temperature control strategy optimization of automotive backlight panel radiators.

The invention discloses a vector information sensing system and method, and the system comprises at least one group of sensing units, the output end of each group of sensing units is sequentially connected with a group of storage units and a group of calculation units, and each sensing unit comprises a scalar signal distribution input end, a horizontal vector output end and a vertical vector output end. The storage unit comprises a horizontal vector information storage subunit and a vertical vector information storage subunit which are respectively used for carrying out in-situ storage on horizontal vector signals and vertical vector signals to form two storage states, and the calculation unit comprises a horizontal vector information processing subunit and a vertical vector information processing subunit which are respectively used for carrying out in-situ storage on the horizontal vector signals and the vertical vector signals to form two storage states. The storage states of the horizontal vector signal and the vertical vector signal are respectively subjected to weighted calculation and summarized at an output end to obtain a calculation result, and the calculation result is used for classification or discrimination. According to the method, the problems of low calculation efficiency, high data redundancy and the like in the processing process of distribution of scalar signals such as images and the like are solved on the hardware level.

A current-mode circuit, comprising: at least one switch unit, each switch unit comprising a field-effect transistor connected at its source terminal in series with an impedance and configured to carry a given current, wherein for each switch unit or for at least one of the switch units the impedance is a variable impedance; and an adjustment circuit configured, for each switch unit or for said at least one of the switch units, to adjust an impedance of the variable impedance to calibrate a predetermined property of the switch unit which is dependent on the field-effect transistor.

Embodiments of the present application disclose a clock frequency division method, a circuit and a storage medium. The scheme can select a clock source on a microcontroller chip to determine an oscillator clock signal, input the oscillator clock signal to a pre-frequency divider to output a pre-divided system clock signal, input the pre-divided system clock signal to a post-frequency divider to output a plurality of non-overlapping quadrature clock signals, and divide an instruction period into a plurality of clock periods according to the plurality of non-overlapping quadrature clock signals. The scheme provided by the embodiments of the present application can support 4T mode and 2T mode by dividing the system clock, and can improve the CPU operation speed and peripheral device working speed of the microcontroller chip.

The disclosure provides a fuel cell life migration prediction method, comprising the following steps: S1, constructing a source domain fuel cell life prediction model; S2, training the source domain fuel cell life prediction model using fuel cell degradation data to obtain a trained source domain fuel cell life prediction model; S3, extracting bottom layer feature data and middle layer feature data of the trained source domain fuel cell life prediction model; S4, constructing a target domain fuel cell life prediction model based on the bottom layer feature data and the middle layer feature data; S5, training the target domain fuel cell life prediction model according to fuel cell life prediction original training data; in the training process, keeping the bottom layer feature data unchanged and fine-tuning the middle layer feature data; obtaining a trained target domain fuel cell life prediction model; S6, inputting fuel cell life prediction original data into the trained target domain fuel cell life prediction model to obtain a prediction result.

The application provides a server, a server component and a server cluster. The server is electrically connected with a switching module. The server comprises a controller, a chip module and a signal processing module. The chip module, the signal processing module and the switching module are electrically connected in sequence. The controller is electrically connected with the switching module and the signal processing module respectively. The controller is configured to acquire the type of the switching module, configure the signal processing module according to the type of the switching module, and enable the chip module to communicate with the switching module through the signal processing module. Thus, the signal transmission mode between the chip module and the switching module is not locked, and the same server mainboard can be adapted to different types of chip modules, which is beneficial to saving the development cost of the server mainboard and facilitating the maintenance and production of the server mainboard.

This invention discloses a method for calculating the equivalent model of the radar cross-section of a large ship target, comprising the following steps: establishing a three-dimensional geometric model of the large ship target; establishing a virtual electromagnetic wave incident aperture surface approaching infinity based on the target geometry, and discretizing the aperture surface to obtain individual ray tubes; tracking the reflection direction of each ray tube on the target surface until the ray leaves the target surface; calculating the scattering field of each ray tube in the receiving direction, and superimposing the scattering fields of all ray tubes to obtain the total scattering field of the target; plotting the horizontal cross-section and vertical gain diagram of the ship target based on the calculated target radar scattering gain at typical horizontal azimuth and vertical elevation angles; and calculating the radar cross-section of the ship target when detected by radar equipment in different directions based on the target radar scattering gain diagram using interpolation formulas. This invention improves the calculation accuracy and speed of scattering of large ship targets, and is helpful for the stealth assessment of large ship targets.

The application discloses a kind of slope and river channel confluence coupling parallel computing method and related device, method includes: the cumulative confluence area of each cell is calculated based on the flow direction relationship between each cell to identify slope cell and river channel cell;Based on the flow direction relationship between each cell, simulate the slope confluence movement of study area, and calculate the hydrological flow data of each slope cell and river channel cell in parallel;Simulate the river channel confluence movement of study area, according to the hydrological flow data, calculate the inflow data of each river channel cell at the current time step in parallel;According to inflow data, update the water storage of each river channel cell at the next time step in parallel based on linear storage confluence method;Based on water storage, update the outflow data of each river channel cell at the next time step in parallel.The application realizes the coupling simulation of slope and river channel confluence;Through linear storage, the water quantity of each cell is updated, and the river channel confluence does not need sequential iteration, so as to realize the synchronous update of whole watershed cell.

This application discloses a method, product, medium, and device for handwritten digit recognition based on a quantum neural network, relating to the field of quantum computing technology. The method includes: acquiring image data of handwritten digits; inputting the image data into a quantum neural network; and outputting the handwritten digit recognition result. The quantum neural network is determined using a quantum optimization algorithm with the aim of minimizing the cross-entropy loss function. The quantum neural network includes an input layer, a quantum layer, an activation layer, and an output layer connected sequentially. The input layer is equipped with a multi-qubit controlled Ry gate. The input layer is used to convert the image data into a quantum image, obtaining an image information qubit sequence. This application can fully utilize the quantum superposition property and parallel computing characteristics of the quantum neural network, thereby effectively improving the efficiency and accuracy of handwritten digit recognition.

The application discloses a lithium ion battery state of charge estimation method based on an Informer, which comprises the following steps: collecting battery sample data, constructing an Informer network model, processing the battery sample data by using the Informer network model, and obtaining a state of charge estimation value of the lithium ion battery. The Informer network model used in the application reduces the point product calculation of the attention mechanism and improves the encoder-decoder architecture, thereby reducing the calculation complexity and spatial complexity, improving the model training and calculation speed, and to some extent, solving the cumulative error problem existing in the recurrent neural network, achieving higher SOC estimation accuracy, showing superiority in MAE and RMSE error indicators, and better solving the estimation difficulty under low temperature conditions and the problem of insufficient temperature expansion capability. The application is widely applied in the technical field of batteries.

The invention discloses a Snesim modeling-oriented search tree mixed query acceleration optimization method and device, and the method comprises the steps: obtaining a training image and a data template, constructing a search tree based on a Snesim method, constructing a reverse auxiliary retrieval structure to establish a mapping relation between a data event attribute value and a search tree node, and obtaining a data event attribute value; the simulation progress is used as a strategy switching index, a reverse query strategy is adopted in the initial simulation stage with the progress smaller than a preset threshold value, and redundancy of search tree traversal is reduced; and switching back to the efficient traditional forward query strategy in the simulation middle and later periods of which the progress is greater than or equal to the preset threshold value. According to the method, the evolution process of condition data from sparse to dense can be dynamically adapted, the search and query time is remarkably shortened, the calculation efficiency and speed of Snesim modeling are greatly improved on the premise of ensuring the reproducibility of geologic structure features, and an effective optimization scheme is provided for large-scale geologic modeling.

This application belongs to the field of hydraulic systems, and specifically relates to a rapid calculation and application method for spatiotemporally distributed pulsating pressure in hydraulic pipelines. It assumes that the pressure value is the same at all locations on the inner wall of the hydraulic pipeline cross-section, and the cross-sectional pressure is controlled only by the distance from the intersection of the cross-section and the pipeline control spline to the pipeline inlet. The control points belonging to the pipe wall nodes are obtained, and a spatiotemporal distribution function of the pipe wall pressure is established based on the coordinates of the discrete control points and the spatiotemporal distribution of the pulsating pressure. The transient response of the pipeline is calculated based on the spatiotemporal distribution function of the pipe wall pressure, yielding the pipeline's time-domain response. Utilizing the spatiotemporal distribution characteristics of hydraulic pulsations, the spatiotemporally related pressure distribution along the pipeline streamline direction is calculated, and then rapidly applied to the pipeline finite element model. This method omits the unsteady CFD calculation of the flow within the pipeline and allows for rapid application of a spatiotemporally coupled pressure load field to the pipeline finite element model, improving the computational efficiency and iteration speed of the initial design phase of aircraft pipelines.

The invention belongs to the technical field of integrated energy system planning, and particularly relates to a power grid control method and system. The power grid control method provided by the invention comprises the following steps: setting constraint conditions of new energy power generation, adjustable power load, electrolytic hydrogen production and energy storage; predicting safety parameters through load flow calculation; determining a target function, and constructing a corresponding relation between a penalty function and an out-of-limit value of the safety parameter; carrying out optimization solution on the solution variable through an intelligent algorithm to obtain an optimal variable for realizing the target function, and executing the optimal variable; and judging whether safety parameters are out of limit or not in real time in the execution process. The hydrogen capacity of electrolytic hydrogen production, the energy storage capacity constraint of the energy storage device and the power grid safety constraint are fully considered, and the safety stability of the hydrogen production device, the adjustable power load and the electrochemical energy storage device and the economical efficiency of system operation are guaranteed through the hydrogen, the adjustable power load, the capacity constraint of electrochemical energy storage and the power flow constraint.

The application relates to a semantic segmentation and stereo matching method and framework based on multi-task joint learning, which comprises the following steps: acquiring stereo image pair information, wherein the stereo image pair information comprises a left image and a right image; based on the left image and the right image, shared features are extracted by using a joint encoder, and a preliminary disparity map is obtained by calculating a disparity; based on the shared features, the preliminary disparity map is updated by updating the disparity, so that a refined disparity map is obtained, wherein the refined disparity map is a stereo matching result; the shared features are converted to a semantic space, and feature fusion is performed with the refined disparity map, so that fused features are obtained; and based on a densely connected skip connection decoder, the fused features are decoded, so that a semantic segmentation result is obtained. Compared with the prior art, the application has the advantages of improving real-time performance, low data requirement and the like.