304 results about "Scatter plot" patented technology

The invention relates to the technical field of printed circuit board manufacturing and quality detection, in particular to a PCB forming detection method based on a hole site scatter diagram and SPC analysis, and the method comprises the steps: collecting the actual hole site data of a PCB substrate through an optical scanner or a laser measurement device, generating a scatter diagram containing coordinates, aperture and tolerance, and carrying out the detection of the hole site scatter diagram; an abnormal region is identified by using an improved density clustering algorithm; performing multi-dimensional analysis on the scatter diagram based on an SPC model, extracting characteristic parameters such as hole site density deviation, constructing a dynamic control limit, and calculating a CPK to judge a processing state; and when the CPK is lower than a threshold value, optimization instructions such as drilling path correction and drill bit wear compensation are generated and fed back to the equipment through the anti-saturation fuzzy PID controller to realize closed-loop control. According to the method, the hole site machining quality can be accurately detected, the machining parameters are adaptively adjusted, and the PCB forming precision and the production stability are effectively improved.

The invention discloses a visual gas leakage detection system and method based on a laser spectrum, and relates to the technical field of gas detection visualization. According to the visual gas leakage detection system and method based on the laser spectrum, the method comprises the following steps that 1, gas monitoring data are collected and preprocessed; 2, extracting a characteristic spectrum from the gas monitoring data, obtaining a gas spectrum reduction value, and separating an overlapped absorption spectrum; 3, estimating the diffusion trajectory of the gas, and calculating a gas diffusion coefficient estimation value and a diffusion rate estimation value; outputting a gas concentration estimated value; 4, gas leakage source points are calculated, gas mass tracking is carried out, and different gas leakage sources are separated; and 5, generating a scatter diagram to display gas concentrations at different positions, and marking the position of a leakage source. The problem that a complex multi-gas environment cannot be recognized due to the fact that homogeneity and heterogeneity possibly exist in the same environment due to leakage of different types of gases in the prior art is solved.

A multi-target vital sign monitoring method based on a millimeter-wave radar comprises the following steps: sending out a linear frequency modulation electromagnetic wave signal through the millimeter-wave radar, and constructing a three-dimensional data matrix according to a reflected signal of the linear frequency modulation electromagnetic wave signal; fourier transform and data processing are carried out on different dimensions of the data matrix to obtain distance, speed and angle information of a target and make a three-dimensional point cloud data set; clustering the generated point cloud data to obtain related information of a plurality of targets, and generating a two-dimensional motion state scatter diagram based on the clustered information; inputting the scatter diagram into a motion state classifier network model for motion state recognition; signals of the target in the motion intermission period are extracted, and the respiration rate and the heartbeat rate of the target are monitored. The method has the characteristics of good privacy protection, low time delay, non-contact property and the like, and multi-target vital signs can be monitored.

The invention belongs to the technical field of geotechnical engineering testing and site investigation, and provides a shear wave velocity estimation method based on a piezocone penetration test, which can accurately and conveniently estimate the shear wave velocity. The method specifically comprises the following steps of S1, carrying out a pore pressure static sounding test on a plurality of drill holes in a site, and obtaining pore pressure static sounding basic parameters and shear wave velocity of each drill hole tested in the depth direction, S2, interpreting derived parameters according to the pore pressure static sounding basic parameters, S3, carrying out soil layer division, soil type identification and soil body type judgment, and S4, carrying out soil layer classification, soil type identification and soil body type judgment. S4, selecting data tested by the same soil body type as an analysis object, performing fitting analysis on the scatter diagrams of the cone tip resistance and the shear wave velocity of the piezocone penetration test to obtain a fitting formula, and S5, obtaining normalized cone tip resistance and normalized shear wave velocity based on the cone tip resistance and the shear wave velocity, substituting the normalized cone tip resistance and the normalized shear wave velocity into the fitting formula in the step S4, and introducing a soil classification index to obtain a soil classification result. And obtaining a calculation expression of the optimal estimation shear wave.

A method and apparatus for identifying an outlier of a wind power curve, a device, and a storage medium, which relate to the technical field of wind power data anomaly identification, and are used to solve the technical problem of relatively poor results identifying anomalous data in high-density clustered wind power data. The present invention comprises: acquiring wind power raw data; normalizing the wind power raw data, to obtain normalized data; generating a scatter plot by using the normalized data; identifying the scatter plot, to obtain dispersed noise points; removing the dispersed noise points from the scatter plot, to obtain preliminary denoised data; generating a fitting standard power curve of the preliminary denoised data; calculating a mean standard deviation of wind speed on the basis of the preliminary denoised data; and determining an outlier on the basis of the mean standard deviation of wind speed and the fitting standard power curve.

Disclosed are various techniques for generating image specific global tone curves and residual gain maps based on multiple images. A gain map is generated based on a comparison of a first image to a second image. A gain map scatter plot is constructed based on the gain map values and channel values of either the first image or the second image. An image specific global tone curve is determined by curve fitting to the gain map scatter plot. A residual gain map is generated based on a comparison of the gain map to a reconstructed gain map derived from the image specific global tone curve. An approximation of the second image can be constructed using the image specific global tone curve and the first image. A replica of the second image can be constructed using the image specific global tone curve, the residual gain map, and the first image.

The invention relates to the technical field of process parameter adjustment, in particular to an intelligent maintenance and management platform for process data of an intelligent manufacturing production line. The platform comprises a raw material attribute data processing module used for acquiring an attribute feature vector of each sample in history, one raw material being a sample, and further acquiring a material attribute difference; the process deviation analysis module is used for acquiring a process deviation value of the two processed samples; the process parameter analysis module is used for acquiring the process parameter difference weight of one process parameter of the two samples, and then establishing a scatter diagram; the conjoint analysis module is used for analyzing the scatter diagram to obtain the quality influence stability of one technological parameter and further obtain the influence degree of the technological parameter; and the process parameter adjusting module is used for updating the reference value according to the influence weight and the reference value of each process parameter of the current sample to obtain the optimal process parameter combination of the current sample. According to the invention, the quality of a processed product can be improved.

The invention relates to the technical field of power load monitoring, in particular to a ring main unit with an overload fault monitoring and circuit breaking function. Obtaining a load filtering time sequence according to the instantaneous fluctuation characteristics of the load time sequence; constructing a load feature vector according to the load filtering time sequence; constructing a temperature feature vector according to the temperature time sequence; obtaining a temperature difference degree and a date cluster according to the temperature feature vector; obtaining a load difference degree according to the load feature vector; constructing a difference scatter diagram and a load difference prediction model according to the temperature difference degree and the load difference degree corresponding to the date cluster; and obtaining a difference degree weight according to the scattered point distribution characteristics and training a load difference prediction model. Obtaining a load prediction difference degree according to the temperature feature vector of the preset current time period; obtaining a deviation index according to the load prediction difference degree, the actual load difference degree and the model prediction error characteristics; and the load state is monitored according to the change characteristics of the deviation index, so that the load monitoring accuracy is improved.

The present invention relates to the technical field of natural language processing, and specifically to a visual patent search method based on a pre-trained language model. In a patent keyword search scenario, the present invention extracts keywords and represents word vectors from patent texts based on the pre-trained language model, reduces the dimensionality of patent features returned by the search, and visually displays the search results in the form of a scatter plot. Compared with search results displayed in a list form, the method is more intuitive and provides richer search information such as the degree of similarity between patents and patent clustering.

The invention discloses a large-scale wind turbine generator blade root bolt vibration displacement monitoring method, which comprises the following steps: through blade root bolt connection integral monitoring, converting a bolt vibration condition into flange gap displacement identification, and obtaining a flange gap displacement value; extracting displacement peak-to-peak value data; processing a flange gap displacement value according to the rotating speed information of the generator set, and removing data when the wind turbine generator set stops rotating and the rotating speed is less than 5r / min; drawing a rotating speed-displacement peak-to-peak value scatter diagram in combination with the rotating speed information of the unit; removing abnormal values for the rotation speed-displacement peak-to-peak value scatter diagram through a quartile method, and setting an effective early warning line; and when the flange gap displacement peak-to-peak value is continuously above the early warning line within the preset time range, an alarm is triggered immediately. According to the invention, blade root bolt vibration monitoring can be simplified and converted into flange gap displacement monitoring of the whole connection, intelligent identification of the healthy service state of the blade root bolt of the large-scale wind turbine generator is realized, and the manual inspection cost is reduced.

The invention provides a unit operation data processing method for temperature fault early warning of large components of a wind turbine generator. The method comprises the steps of drawing a wind speed and power scatter diagram according to operation data of a wind turbine generator, dividing a plurality of different types of abnormal temperature points in the wind speed and power scatter diagram, and removing the different types of abnormal temperature points by adopting a plurality of different methods to obtain cleaned data samples; each piece of data of the cleaned data sample comprises a power value and a plurality of feature parameters, calculating each feature parameter by adopting at least two different feature extraction methods to obtain a correlation degree value, and retaining the corresponding feature parameter or deleting the corresponding feature parameter according to each correlation degree value, the reserved characteristic parameters and the power values form a training sample, and the training sample is used for training a temperature prediction model. According to the method, the cleaning efficiency and effect can be improved, and feature parameters with higher relevancy can be screened out.

The invention discloses an AI intelligent coal blending method based on deep learning, relates to the technical field of intelligent coal blending, and solves the technical problems of low efficiency in feature association recognition and screening and poor model architecture scene adaptability. The Pearson coefficient is used for linear features, the mutual information method is used for hierarchical redundancy elimination for nonlinear features, the limitation of traditional single statistic feature screening is avoided, hidden association is generated and mined through composite features, feature dimensions are more simplified, association with coal blending targets is more direct, the model training efficiency and prediction precision are effectively improved, and the method is suitable for large-scale popularization and application. Models are customized for different scenes, compared with an existing method that a single model adapts to a full scene, precise coverage of lightweight-dynamic-complex scenes is achieved, and the applicability and optimization effect of coal blending schemes under different scenes are greatly improved.

The invention relates to a characteristic interval fitting and modeling method for breakdown voltage between GIS (Gas Insulated Switchgear) disconnecting switches, which is characterized in that on the basis of an actually measured scatter diagram of breakdown voltage, optimal distribution fitting is carried out on the scatter diagram, the distribution interval is predicted, and upper and lower boundary curves are calculated, so that subsequent modeling is facilitated. On the basis of an original simulation model, randomness of breakdown voltage is introduced to be combined with a reignition arc module to form a new model, and the new model is combined with an arc quenching module, a switch control module and an arc resistance module to form a new GIS disconnecting switch dynamic reignition arc simulation model. According to the invention, simulation of switch gap arc reignition randomness and extinguishing phenomenon is realized, and then the peak value distribution condition and the maximum peak value of the VFTO are analyzed. According to the method, the simulation precision is improved, the influence of the switching operation on the VFTO can be evaluated more accurately, and the reliability analysis of an electrical system is enhanced.

The invention discloses a wheat seed viability nondestructive testing method and system based on a near-infrared hyperspectral imaging technology. According to the method, near-infrared hyperspectral image data (the wavelength range is 936-1720 nm) of wheat seeds are collected, standardized preprocessing is carried out, and viability prediction is carried out through a constructed seed spectrum converter (SST) deep learning model. The SST model combines a convolutional neural network (CNN) and a self-attention mechanism, can effectively extract local and global features of spectral data, and enhances the training stability and generalization ability of the model through residual connection and layer normalization. Model hyper-parameters are optimized through a scatter diagram and a box plot, optimal configuration is determined through a grid search method or a Bayesian optimization method, and the accuracy and stability of the model are ensured. In addition, the detection accuracy of the model on unknown varieties is evaluated through a cyclic cross validation method, and the final accuracy rate reaches 85.53% or above. Experimental results show that the method can complete detection within several seconds, does not damage the physical structure of the seeds, is suitable for non-destructive detection of the vitality of various wheat varieties, and meets the requirements of the modern seed industry for rapid, non-destructive and high-throughput detection.

The present invention relates to the field of medical diagnosis technology, and discloses a flow cytometer cell scatter plot classification method based on deep learning, which uses a flow cytometer to collect cell features of multiple samples, and classifies and enhances the samples to obtain multiple label samples; inputs the input tensor in the training set into the classification model for training, and optimizes the classification model based on a loss function containing a regular term; inputs the test set into the optimized classification model for classification calculation, obtains the classification accuracy, and completes the classification; solves the problem of inaccurate classification of flow cytometers when facing overlapping features of different types of cells. It has strong generalization ability, robustness, and the ability to handle abnormal samples, and has high classification accuracy for cell classification.

The invention provides an annotation grading avoiding arrangement method and system for a two-dimensional drawing. The method comprises the steps that S1, two-dimensional CAD drawing data to be processed are acquired; s2, constructing a scatter diagram, fitting a picture cutting path according to the scatter diagram, and executing picture cutting to generate a picture frame; s3, executing mirror image partitioning in the picture frame range according to the gravity center of the pipeline object; and S4, performing offset avoidance arrangement on the labels based on a hierarchical avoidance arrangement strategy. According to the scheme, automatic avoiding and reasonable arrangement of the labels can be achieved in the design of the two-dimensional drawing with dense labels, the problem of overlapping of the labels in complex layout is effectively solved, uniform distribution of the labels in the drawing frame is further achieved, the overall readability and attractiveness of the drawing are remarkably improved, and the practicability of the drawing is improved. And meanwhile, the automation degree and efficiency of labeling arrangement are greatly improved.

The present application provides a rapid evaluation method and system for generator vibration data of a wind turbine generator set. The method comprises: step 1, acquiring current-day operation data of a wind turbine generator set under test, wherein the current-day operation data comprises a time label, an operation power and a generator vibration signal; step 2, constructing a two-dimensional plane scatter plot on the basis of the current-day operation data; and step 3, combining the obtained two-dimensional plane scatter plot with a preset regression function, and evaluating the vibration state of said wind turbine generator set. The present application utilizes a lossless compression method to process data, so that the current-day vibration state of a generator can be accurately evaluated.

A detection device extracts a plurality of range profiles from a radar signal detected during a time period from a target; determines obtain magnitude variance data defined with respect to a plurality of magnitude components corresponding to a target index in the plurality of range profiles, phase variance data defined with respect to a plurality of phase components corresponding to the target index, scatter plot data defined with respect to a plurality of In-phase Quadrature (IQ) components corresponding to the target index, and spectrogram data defined with respect to the target index and a plurality of adjacent indices adjacent to the target index; and inputs the magnitude variance data, the phase variance data, the scatter plot data, and the spectrogram data into an Artificial Intelligence (AI) model to detect a type of the target.

The invention belongs to the field of coal mine tunnel intelligent detection, and provides a coal mine tunnel deformation detection method and system based on point cloud, and the technical scheme is as follows: carrying out feature registration, section registration and tunnel overall alignment on reference and target three-dimensional point cloud data; projecting the registered reference three-dimensional point cloud data and target three-dimensional point cloud data to a two-dimensional plane to obtain a two-dimensional scatter diagram; extracting boundary points of a roadway based on the two-dimensional scatter diagram; fitting a boundary line of the whole roadway based on the boundary points of the roadway; calculating a roadway trend curve; extracting a point cloud section contour corresponding to each position and calculating the local width of a bounding box to obtain a minimum bounding box; and emitting rays to the roadway based on the minimum bounding box, searching points on the registered target point cloud and points or adjacent points on the datum point cloud data through which the rays penetrate, calculating the distance between the two points, and calculating the deformation of the to-be-detected point based on the calculated distance. And stable operation in a complex roadway environment can be realized.

Systems and methods for detecting anomalies in aviation data communication systems (e.g., air traffic control surveillance systems), include a processor receiving device status information. A variational autoencoder receives and optimizes the device status information and determines whether it qualifies as an anomaly. Optimized device status information is compared to either non-anomalous or anomalous device status data in a latent space of the variational autoencoder. The latent space preferably includes an n-D point scatter plot and hidden vector values. The processor optimizes the device status information by generating a plurality of probabilistic models of the device status information and determining which of the plurality of models is optimal. A game theoretic optimization is applied to the plurality of models, and the best model is used to generate the n-D point scatter plot in latent space. An image gradient sobel edge detector preprocesses the device status information prior to optimization.

The invention discloses a method for predicting single well recoverable reserves through wellhead pressure decline. The method comprises the steps that production dynamic data such as wellhead pressure (oil pressure or casing pressure), daily gas production and accumulated gas production of a tight sandstone gas production well are collected; by taking the accumulated gas production rate data as a horizontal coordinate and the wellhead pressure data as a vertical coordinate, displaying and constructing a scatter diagram in a logarithmic coordinate form; fitting scatter data in the graph according to an index curve to obtain a regression relational expression; wherein the accumulated gas production rate under the corresponding waste pressure can be obtained by substituting the wellhead pressure into the waste pressure value, namely the recoverable reserves of the production well under the corresponding waste pressure. The method provides a quantitative basis for the evaluation of the tight sandstone gas production well.

[Problem] To provide a high-precision diagnostic system that uses multi-item simultaneous measurement data, classifies known mutations and unknown mutations with high precision, analyzes and visualizes classified results, and then visually displays a basis for a conclusion. [Solution] A high-precision determination system 1 comprises: an acquisition unit that acquires at least multi-item simultaneous measurement data for an unknown sample and multi-item simultaneous measurement data for a known sample; a classifying unit that analyzes and quantifies similarity between the acquired multi-item simultaneous measurement data for the unknown sample and multi-item simultaneous measurement data for the known sample, classifies an unknown sample having a different trend than a known sample, and generates classification data; a determination unit that performs dimensional compression of the generated classification data to generate a two-dimensional scatter plot as determination data; a storage unit that stores at least the unknown multi-item simultaneous measurement data, the known multi-item simultaneous measurement data, the classification data, and the determination data; and a provision unit that provides at least the stored various types of data.

The present application relates to the technical field of combustion state monitoring, and discloses a visual analysis method and device for combustion simulation, which comprises the following steps: under different initial conditions of combustion simulation, generating multiple sets of time sequence flow images for each combustion simulation example; encoding each frame of image in each set of time sequence flow images to obtain corresponding multiple high-dimensional embedding vectors; generating a scatter plot after dimension reduction of the multiple high-dimensional embedding vectors after dimension reduction clustering, and generating multiple time sequence trajectories for each combustion simulation example based on the scatter plot after dimension reduction; searching for a similar time sequence trajectory most similar to a specified time sequence trajectory within a preset convergence radius, and analyzing combustion convergence and stability.The present application makes full use of the correlation and similarity between data, can accurately identify similar combustion evolution modes, helps experts more accurately grasp key characteristics such as stability and oscillation in the combustion process, deeply reveals the combustion law, and improves the precision of ramjet combustion simulation.

The present invention discloses a microalgae density measurement method and system based on an illumination light source and image analysis. The microalgae density measurement method comprises: preprocessing a collected image by an information processing terminal, including operations of unifying the image size and separating RGB channels; calculating and optimizing a scatter plot of nonlinear changes of various clarity calculation-related factors, comprehensive clarity, RGB channel color difference, and comprehensive color difference indicators under conditions of microalgae solutions with different densities, and a nonlinear fitting curve thereof; optimizing the nonlinear fitting curve to improve the correlation between the scatter points and the fitted curve and the smoothness of the curve, taking into account the advantages of the optimal intervals of each algorithm and reducing local anomalies; and performing nonlinear fitting on a scatter plot obtained by testing the optimized comprehensive clarity under conditions of different microalgae densities. The present invention obtains the characteristics of comprehensive color difference and comprehensive clarity through fitting and modeling, and can accurately distinguish the different characteristics of images of microalgae solutions with different densities.

The invention relates to a computer-implemented method for optically characterizing a textile fiber structure. A plurality of pieces of information on the color at different locations of the textile fiber structure are detected by an optical sensor system. The detected color information is transmitted to a computer (107) and is entered into a color space (2) in the form of a scatter plot (31) by the computer. A frequency density distribution (4) of the scatter plot (31) is determined, and the frequency density distribution (4) is numerically specified. The invention allows a change in the material of the textile fiber structure to be ascertained and optimizes the elimination of foreign materials from the textile fiber structure.

This makes it easier to recognize the correspondence between selected plot points in a scatter plot and the data corresponding to those selected points. [Solution] The processor of the information processing device 1 displays a scatter plot on the display unit 20 in which multiple plot points are plotted based on the input data. When the processor of the information processing device 1 receives an input data display operation to display the input data on the display unit 20, in which case the first data in the input data corresponding to the first plot point is displayed in a display manner that allows it to be identified from other data in the input data.

In virtual assistant platforms that provide access to a plurality of plug-ins, plug-in selection based on comparisons between high-dimensional embeddings of user prompts and high-dimensional embeddings of the example prompts contained in plug-in definitions can cause “collisions”—that is, selection of the wrong plug-ins—if the plug-in-definitions of the intended and erroneously selected plug-ins are too similar. Debugging such collisions or avoiding them in the first place can be aided by visualizing the example prompts of multiple plug-ins, optionally along with the user prompts, in a scatter plot based on mappings of the high-dimensional embeddings onto lower-dimensional vector representations, and analyzing changes in the scatter plot responsive to modifications of the plug-in definitions.

The application discloses a helicopter flexible beam actual load substitution analysis method, comprising the following steps: considering that the flexible beam root actual measured load data is effective in the initial flight test, using the effective time period corresponding to the effective flight test data of the flexible beam root actual measured load, performing spectrum analysis on the flexible beam root profile actual measured load and the airfoil section profile actual measured load on the same piece of tail rotor blade at preset interval time in the effective time period of the effective flight test data, so as to obtain the amplitude of the flexible beam root profile actual measured load and the airfoil section profile actual measured load corresponding to the tail rotor rotating speed frequency respectively; combining the amplitude of each time point in the effective time period to form two groups of data columns; a scatter plot of the two groups of data columns can be drawn, a plurality of correlation formulas of the two groups of data columns are obtained through linear fitting, the correlation formula with the optimal correlation between the airfoil section profile actual measured load and the flexible beam root profile actual measured load on the same piece of tail rotor blade is selected as the basis for calculating the flexible beam root profile actual measured load, and the flexible beam root profile actual measured load in the whole flight process can be obtained based on the airfoil section profile actual measured load of the tail rotor blade.

This invention relates to the field of power management and anomaly detection technology, specifically to a method and system for detecting anomalies in multi-port charging power supplies based on current analysis. It is applied to a charging system containing multiple load power supply buses and several branch switching transistors. The method includes: extracting and sampling AC ripple current from the total current signal of the multiple load power supply buses and each branch; performing delay mapping on the AC ripple current to construct a multi-dimensional phase space matrix and calculate a Poincaré cross-section scatter plot; calculating the current topological information entropy based on the scatter distribution probability and comparing it with the baseline information entropy to generate an information entropy residual; comparing the information entropy residual with a safety manifold boundary threshold range, determining a charging anomaly when it exceeds the threshold, outputting a hardware interrupt signal to control the state of the corresponding branch switching transistor, and generating a diagnostic report containing physical feature parameters extracted based on the multi-dimensional phase space matrix. This invention enables early identification of anomalies in multi-port charging systems and rapid hardware-level response.

The invention discloses intelligent analysis of seepage data of a small reservoir based on rainfall characteristics, which comprises the following steps of: generating corresponding characteristics for seepage pressure data, rainfall capacity and reservoir water level through characteristic construction, and normalizing the data by adopting a Robust Scaler method; a long-short-term memory network model and a random forest model based on historical rainfall are constructed, and model parameters are adjusted and optimized in combination with Bayesian optimization and a grid search technology; systematically analyzing the real water level of the piezometric tube, filtering the potential influence of the water level of the reservoir on the water level of the piezometric tube, comparing the influence of the rainfall in the cumulative time period and the historical rainfall on the water level of the piezometric tube, and drawing a scatter diagram between the two by using a visual tool. The method is particularly suitable for intelligent analysis of seepage data of a small reservoir, and the intelligent level of reservoir safety monitoring and management can be improved.