20 results about "Weighted average method" patented technology

The present application relates to the field of Bayesian networks, and discloses a social security case criminal behavior determination method, device, equipment and medium, which can construct an evidence element system and evidence structure attribute according to the characteristics of a social security case, and construct the correlation between the evidence and the behavior in the social security case. Based on the evidence element system, the evidence structure attribute and the correlation, a Bayesian evidence reasoning network of the social security case is constructed. The prior condition probability table of the Bayesian evidence reasoning network is generated based on the coordination coefficient method and the weighted average method. The evidence information obtained by investigating the scene of the social security case is input into the Bayesian evidence reasoning network, so that the Bayesian evidence reasoning network determines the target behavior information and the corresponding occurrence probability according to the prior condition probability table and the evidence information. The present application can effectively reduce the consumption of human resources of case investigators and enhance the intelligent investigation level of social security cases.

The application discloses a molten silicon liquid level estimation method based on a hybrid adaptive resampling particle filter, and comprises the following steps: firstly, processing laser spot images collected by a CCD sensor to obtain observation data of the liquid level; then, establishing a system state equation of the molten silicon liquid level according to a kinematic principle to describe the movement of the liquid level; performing state estimation on a laser centroid vertical coordinate by using a particle filter algorithm, and obtaining a new particle set by using a hybrid adaptive resampling method; after re-normalizing all particle weights, outputting an optimal estimation value; and finally, smoothing the filtered data by using a moving weighted average method, and the smoothed result is the estimation value of the molten silicon liquid level. The application solves the problem that in the prior art, the variance of Gaussian variation is too large, particles jump out of a sampling range, and it is difficult to accurately estimate a real liquid level.

The application discloses a kind of based on dual-camera width measurement's double-tower cylinder transport ovality on-line monitoring method, belong to wind power generation equipment state monitoring and intelligent operation and maintenance technical field.The method includes: after the side surface image of tower cylinder collected by camera is preprocessed, by edge extraction and least square method fitting, and further calculate the instantaneous projection pixel width;Scale factor and illumination compensation model are introduced, the actual physical width of the two sides of tower cylinder is obtained, and the weighted average method is used to obtain the short axis diameter of tower cylinder;According to the short axis diameter of tower cylinder and the ovality calculation model, the deformed long axis of ellipse is obtained, the real-time ovality of tower cylinder at present time is further calculated, and whether the real-time ovality meets the ovality upper limit requirement, the ovality change requirement and the ovality fluctuation amplitude requirement is judged, whether alarm signal is generated according to the determination result.The application method effectively solves the technical problem that tower cylinder is difficult to measure directly in double-tower cylinder parallel transport caused by tower cylinder shielding.

This invention discloses an intelligent oil pump oil quality monitoring method based on multi-source data fusion, belonging to the field of transformers. The method includes multi-source data acquisition, data processing, data fusion, result display, and long-distance data transmission: First, multi-dimensional raw data of the oil pump pipeline is collected through micro-water, pressure, and flow sensors and transmitted to a microcontroller control board; then, the raw data is denoised and filtered to obtain a standardized dataset; subsequently, a multi-source data fusion algorithm combining weighted average method and fuzzy logic is used to process the dataset, constructing an oil quality status assessment model to determine whether the oil quality has deteriorated; next, the monitoring results are visualized locally; finally, long-distance transmission of monitoring data and local-remote data synchronization are achieved. This invention improves the accuracy of oil quality monitoring through multi-parameter collaborative monitoring and data fusion, realizing local real-time display and remote real-time monitoring of oil quality status, adapting to the operational needs of transformer maintenance sites.

The application relates to the technical field of computer vision, in particular to a visual SLAM method based on 3D Gaussian spatter in a dynamic environment, a system and a readable storage medium. By performing instance segmentation on a scene image and extracting a prior dynamic mask, a potential dynamic mask is identified and fused to obtain a comprehensive dynamic mask; the comprehensive dynamic mask is optimized by using residual entropy and depth consistency, and then dynamic features are accurately removed; then, in order to balance the stability of pose tracking and the efficiency of mapping, a two-stage key frame screening strategy is constructed; on this basis, an improved 3D Gaussian spatter technology is further introduced to render and construct a scene graph; for each Gaussian ellipsoid, the volume and opacity weight are estimated, the multi-view contribution weight is calculated, the maximum weight is obtained by using a weighted average method based on the multi-view contribution weight, and pruning is performed. The application aims to solve the problem of how to reduce the computing power consumption in the 3D GS-SLAM scheme while ensuring the rendering quality.

The application discloses a kind of based on data cleaning's electric meter data repair method, device, medium and equipment, belong to electric meter repair field, the present application is by obtaining the electricity consumption data of preprocessed intelligent electric meter, environmental temperature data and user profile data, based on user geographic location information Construction undirected weighted graph, and fusion user type, electricity consumption and temperature data generate node feature vector. Coding and decoding are carried out on node feature vector using graph auto-encoder, to generate reconstructed node feature vector, and calculate reconstruction error to determine abnormal threshold. Mark abnormal user nodes accordingly, and based on graph neighbor node information, repair abnormal data using weighted average method, finally obtain repaired intelligent electric meter data, realize the efficient cleaning and repair of electric power marketing data, the present application effectively solves the problem that prior art cannot accurately and efficiently repair the abnormal data of intelligent electric meter.

The application relates to the technical field of ancient building color style migration, in particular to an ancient building color main tone determination method based on a weighted average method, which comprises the following determination steps: obtaining a digital image after digital processing of an ancient building facade image; removing non-building wall color carriers in the digital image to obtain a wall image; extracting hue values, chroma values, lightness values of each color in the wall image and area ratios of each color in the wall image, and storing the values in a database; inputting data in the database into a contrast algorithm model to solve hue contrast, chroma contrast and lightness contrast in the wall image; and selecting a color meeting selected requirements from the database as an ancient building color main tone based on the hue contrast, the chroma contrast and the lightness contrast; the application can accurately determine the main tone in ancient building colors.

The application provides an anchor rod supporting roadway surrounding rock strength estimation method and device, relates to the technical field of surrounding rock strength estimation method, and comprises the following steps: multiple monitoring sections are arranged at equal intervals along the axis of the roadway, two-dimensional data of wave velocity at the surrounding rock of each monitoring section is obtained, linear mapping is carried out according to the wave velocity value, an anchor rod monitoring area is set based on each monitoring section, and anchor rod parameters of the surrounding rock crack are obtained; a grayscale image is processed, a crack and anchor rod coupling algorithm is used to construct the surrounding rock strength coefficient of a single monitoring section; a time-dependent coupling is used to construct an anchor rod attenuation factor, the anchor rod attenuation factor is used as a correction term of the surrounding rock strength of a single monitoring section; and a spatial weighted average method is used to obtain the overall surrounding rock strength value. The crack features are automatically extracted by using a convolutional neural network, the problems of low efficiency and large error of the traditional method are solved, the anchor rod attenuation factor is dynamically corrected, the timeliness of early warning is significantly improved, and the roadway collapse risk is reduced.

The application provides a network intrusion model construction method based on meta learning, comprising the following steps: a global server constructs a plurality of client nodes based on a federated learning framework, and constructs a node detection model in each client node; the client nodes collect local multi-element heterogeneous data at a fixed time interval, generate simulated attack samples using a GAN network, and then form training data by combining the simulated attack samples and normal samples; the node detection model is iteratively trained using the training data; the node detection model after training is meta-optimized using an irrelevant meta algorithm; the global server dynamically allocates an aggregation weight to each client node, aggregates the models by a weighted average method, and generates a global detection model. The application solves the problem of class imbalance of model training samples in the prior art, which leads to insufficient detection capability of the detection model for minority class attacks and difficulty in quickly adapting to new network attacks.

The application discloses a non-contact size measurement method for permanent magnet magnetic property measurement, comprising collecting a high-contrast profile image of a permanent magnet to be measured, and pre-processing the high-contrast profile image; performing displacement compensation on the permanent magnet to be measured according to a centroid tracking algorithm to obtain optimized centroid coordinates, correcting the high-contrast profile image according to the optimized centroid coordinates, and performing adaptive edge extraction on the high-contrast profile image to obtain permanent magnet edge points; adopting a two-stage fitting strategy to perform sub-pixel straight line fitting on the permanent magnet edge points to obtain a vertical distance between fitted straight lines, performing roundness compensation on the vertical distance according to multi-angle sampling to obtain an average diameter; performing multi-height fusion on the average diameter to obtain a height average diameter, calculating an equivalent cross-sectional area by using a weighted average method, and outputting the height average diameter and the equivalent cross-sectional area as measurement results.

This paper relates to a data-driven method and apparatus for fracturing parameter optimization and production capacity prediction. The method includes acquiring historical fracturing parameters and corresponding historical production capacity data of operational wells within a target range; training multiple neural network models using these historical parameters and data, with each model fitting the relationship between the fracturing parameters and production capacity data; training an ensemble learning model for fracturing parameter optimization and production capacity prediction using a weighted average method based on the outputs of each neural network model; obtaining the optimal fracturing parameters for the target range with optimal production capacity data based on the ensemble learning model; and using these optimal parameters to perform fracturing and production on unoperated wells within the target range. The embodiments described in this specification can provide more suitable fracturing parameters, more accurately predicting oil and gas well production capacity while ensuring wellbore life.

The application discloses a network intrusion detection method and system based on deep learning, relates to the technical field of network security, and comprises the following steps: collecting network flow data by using a network packet capturing tool, constructing a space-time matrix by using a mapping matrix construction method, converting the space-time matrix into a gray image, dynamically adjusting by using a dynamic weight adjustment formula, constructing a topological complex, screening important topological features, respectively performing enhancement processing on the important topological features, fusing by using a weighted average method, and generating a fused gray image; segmenting by using a space-time mapping generation method, calculating a DTW (Dynamic Time Warping) distance by using a dynamic time warping calculation, marking a mutation point segment, calculating the evolution fitness of the mutation point segment by using an evolution fitness formula, and identifying an intrusion behavior. The neural biological signal processing technology is combined with the topological data analysis, the processability of data and the identifiable property of features are improved, the evolution fitness formula is used for analyzing the mutation point segment, and the detection precision and the adaptability of the intrusion behavior are enhanced.

This invention discloses a comprehensive analysis method and apparatus for the combustion characteristics of hydrogen-blended natural gas pipelines, relating to the fields of gas transmission and distribution and comprehensive utilization of hydrogen energy. Addressing the lack of a systematic method in existing technologies for simultaneously predicting the calorific value, Wobbe index, and combustion potential of hydrogen-blended natural gas, this invention constructs an integrated computational model encompassing thermodynamics, interchangeability, and combustion kinetics, employing a modular design: it calculates the higher and lower calorific values ​​of the mixed gas using a weighted average method, calculates the Wobbe index based on relative density and internationally accepted definitions, and innovatively quantifies combustion potential using a semi-empirical model; it also cross-compares with national standards such as GB17820, and uses multi-indicator collaborative decision-making to determine the feasibility of the proposed scheme. This invention overcomes the shortcomings of the three-dimensional comprehensive evaluation of hydrogen-blended natural gas, offering accurate calculations, strong compliance, and the ability to rapidly generate hydrogen blending ratio-combustion characteristic maps, providing technical support for the design of hydrogen-blended transportation projects, operational safety assessments, and the formulation of relevant national standards.

This invention provides a method and system for online control of machining accuracy based on multi-sensor data fusion. The method includes the acquisition and preprocessing of a multimodal heterogeneous sensor dataset; weighted fusion using a weighted average method; extraction of aggregated feature vectors and time-frequency feature vectors using Local Feature Mean Aggregation (LFMA) and Wavelet Packet Transform (WPT); the introduction of a Fisher discriminant fusion algorithm to fuse the initial feature vectors; and prediction of machining error type and magnitude using an improved Extreme Learning Machine (ELM) model. Based on the error prediction results, an adaptive control strategy is constructed to control the machine tool online. This invention employs a multimodal data acquisition network using multiple types of sensors to acquire sensor parameters in real time, including dimensions, vibration, cutting force, temperature, and tool wear. Simultaneously, through a three-level hierarchical fusion architecture of data fusion, feature fusion, and decision fusion, the accuracy of error prediction is improved, thereby ensuring the accuracy of control.

The application discloses an LED lamp bead precision current control method based on intelligent feedback and belongs to the technical field of LED display screens.The application solves the problem that the current cannot be adjusted according to the actual working state of the LED lamp bead in the prior art, thereby leading to low luminous efficiency and unstable light color of the LED display screen, accurately identifies the key correlation between variables in the working state of the LED lamp bead by calculating a dynamic correlation coefficient matrix, enhances the sensitivity of the model to key features, effectively guarantees the input data quality, and improves the precision and reliability of the LED lamp bead current control, predicts the optimal current value through a neural network model, provides a robust reference when the prediction confidence is low in combination with historical data and a random tree model, generates a final current setting value by using a weighted average method, and realizes the precision and stable control of the LED lamp bead current in cooperation with a two-stage adaptive closed-loop control mechanism, and the luminous performance and service life of the LED display screen are improved.

This invention discloses a method and system for refined cost calculation of catering dishes, belonging to the field of catering cost management technology. The method includes: establishing a recipe tree structure based on Bill of Materials (BOM) to support independent recipe management for semi-finished and finished products, achieving gram-level accuracy in dish cost accounting; performing recipe tree flattening to expand the nested structure into a detailed raw material list; establishing an intelligent unit conversion mechanism with density parameters to automatically convert purchasing units into grams of consumption; calculating real-time raw material costs using a weighted average method; executing dish synthesis to generate synthesis records; and constructing a closed-loop system covering the entire chain from restaurant ordering and backend management to financial accounting, supporting multi-cycle cost synthesis. The system includes five modules: recipe management, unit conversion, cost calculation, synthesis execution, and financial accounting. This invention solves the problems of low accuracy, large unit conversion errors, and high system coupling in existing catering cost accounting methods, achieving refined calculation of catering dish costs.

The application discloses a wind turbine blade icing blur early warning method and system, and belongs to the technical field of wind turbines. The method comprises the following steps: real-time monitoring of key factors; establishing a blade icing risk assessment model based on fuzzy logic; establishing a fuzzy inference rule table of the blade icing risk assessment model; inputting the real-time monitoring key factor data into the blade icing risk assessment model to obtain an abstract risk level; converting the abstract risk level into the membership degree of the output result; using a weighted average method to demystify the abstract risk level to obtain an accurate blade icing risk value and an accurate corresponding blade icing risk level; and issuing an early warning according to the blade icing risk level. The application solves the problems of existing wind turbine blade icing detection technology, such as response lag and high false alarm rate, and guarantees the safe operation of the wind turbine.

This invention provides a method and system for optimizing engine failure retrieval weights based on adaptive ES weights, belonging to the field of engine failure dataset retrieval and analysis technology. The method includes: S1, acquiring a preprocessed engine failure dataset and dividing and labeling it; S2, constructing an adaptive ES weight neural network model, using momentum and adaptive learning rate to improve learning and prediction efficiency; S3, training and optimizing the adaptive ES weight neural network model using the engine failure dataset; and S4, fusing and integrating the adaptive ES weight neural network model using a weighted average method to output engine failure retrieval results. This invention constructs an adaptive ES weight neural network model, dynamically learning and adjusting the ES weights of fields through an adaptive neural network, making the retrieval results more closely resemble real-world engine failure scenarios, improving retrieval accuracy, and enabling rapid acquisition of relevant engine failure data information for diagnosing the causes of engine failures.