108results about How to "Remove outliers" patented technology

Systems and methods are disclosed for controlling and diagnosing the health of a motorized system. The systems may comprise a diagnostics system and a controller, wherein the diagnostics system employs a neural network, an expert system, and / or a data fusion component in order to assess the health of the motorized system according to one or more attributes associated therewith. The controller may operate the motorized system in accordance with a setpoint and / or a diagnostics signal from the diagnostics system. Also disclosed are methodologies for controlling and diagnosing the health of a motorized system, comprising operating a motor in the motorized system in a controlled fashion, and diagnosing the health of the motorized system according to a measured attribute associated with the motorized system, wherein the motor may be operated according to a setpoint and / or the diagnostics signal.

A system and method is provided for monitoring the operating condition of a pump by evaluating fault data encoded in the instantaneous current of the motor driving the pump. The data is converted to a frequency spectrum which is analyzed to create a fault signature having fault attributes relating to various fault conditions associated with the pump. The fault signature is then input to a neural network that operates in conjunction with a preprocessing and post processing module to perform decisions and output those decisions to a user interface. A stand alone module is also provided that includes an adaptive preprocessing module, a one-shot unsupervised neural network and a fuzzy based expert system to provide a decision making module that operates with limited human supervision.

A system and method is provided for monitoring the operating condition of a pump by evaluating fault data encoded in the instantaneous current of the motor driving the pump. The data is converted to a frequency spectrum which is analyzed to create a fault signature having fault attributes relating to various fault conditions associated with the pump. The fault signature is then input to a neural network that operates in conjunction with a preprocessing and post processing module to perform decisions and output those decisions to a user interface. A stand alone module is also provided that includes an adaptive preprocessing module, a one-shot unsupervised neural network and a fuzzy based expert system to provide a decision making module that operates with limited human supervision.

Ultrasound sound-speed tomography requires accurate picks of time-of-flights (TOFs) of transmitted ultrasound signals, however, manual picking on large datasets is time-consuming. An improved automatic TOF picker is taught based on the Akaike Information Criterion (AIC) and multi-model inference (model averaging), based on the calculated AIC values, to improve the accuracy of TOF picks. The automatic TOF picker of the present invention can accurately pick TOFs in the presence of random noise with average absolute amplitude of up to 80% of the maximum absolute synthetic signal amplitude. The inventive method is applied to clinical ultrasound breast data, and compared with manual picks and amplitude threshold picking. Test results indicate that the inventive TOF picker is much less sensitive to data signal-to-noise ratios (SNRs), and performs more consistently for different datasets in relation to manual picking. The technique provides noticeably improved image reconstruction accuracy.

The invention discloses a density and closeness clustering based user moving behavior determination method and belongs to the field of data businesses. The method comprises: introducing a time window, performing time window division on a moving sequence of a user, and dividing the continuous moving sequence into a plurality of window sequences discrete in time; according to a definition of a moving locus, mining out a plurality of moving loci of the user from the window sequences; according to a definition of a characteristic locus set, performing division on the moving loci, including similar loci in a same characteristic locus set, and removing noise data; and according to a definition of a characteristic locus, selecting corresponding central loci as characteristic loci from the characteristic locus set, and finally determining a moving behavior of the user. The method can be applied to practical mobile communication data, so that the randomness and abnormal points of moving of the user can be eliminated; and the determined moving behavior of the user can serve as an input of a position service based position module and also can serve as an input of a mobile recommendation system, so that personalized services can be provided.

The invention relates to an unmanned vehicle positioning algorithm based on a three-dimensional laser radar. The unmanned vehicle positioning algorithm includes the following steps: 1. extracting road edge feature points from a single frame of laser point cloud data, and according to a vehicle kinematic model, converting multiple frames of detected road edge feature point coordinates into a current vehicle coordinate system; 2. utilizing a Beam model method to extract the outlines of the multiple frames of road edge feature points; and 3. matching the road edge outline extracted in the Step 2 with high-precision map data, calculating lateral, longitudinal and course angle deviations of a current vehicle as observation values, and inputting the observation values into Kalman filters to perform vehicle pose estimation. Long-time long-distance stable positioning of the vehicle can be guaranteed. The method is applicable to various laser sensors, and can also obtain relatively high positioning accuracy. Abnormal points can be effectively removed, so that map matching is more accurate, and positioning accuracy is higher.

An automatic milking device for milking a dairy animal, comprising a control device and a weighing floor with weight sensors for supplying weight signals, and with a filter for filtering the weight signals into a filtered signal indicative of the position of the centre of gravity of the dairy animal, wherein the control device is configured for controlling the milking by the automatic milking device on the basis of the weight signal filtered by the filter. The control device is arranged for controlling the automatic milking device on the basis of the unfiltered weight signal after the milking has been finished. As a result thereof, it is possible to respond more quickly to movements of the dairy animal, without the filter having a delaying effect.

Embodiments of the invention relate to a method for minimizing the influence of disturbing signals during calculation of shape elements from coordinate points. An aim of the embodiments of the invention is to exclude the coordinates which are not to be locally assigned to the desired shaped element from the calculation of the shaped element. Said aim is achieved by combining compensation methods for calculating the desired type of shaped element with recognition methods for the same type of shaped element and using the recognition methods for filtering the coordinate points that are relevant for calculating the shaped element out of all input coordinate points.

A method and system are provided for automatic calibration of a video camera by providing automatic perspective calculation. A calibration object detector is arranged to detect a calibration object in video data representing a scene observed by a video camera, and arranged to gather object data for the detected calibration object at a multiplicity of positions, such as three or more positions. The calibration object detector can include an automatic moving object detector and / or a static object detector. An automatic plane calculator is in communication with the calibration object detector and arranged to calculate the perspective of the camera based on gathered object data for at least one calibration object at a multiplicity of positions. The automation provided can enhance the operation of video analytics systems and reduce errors that can be introduced when an unskilled operator manually enters parameters on which the perspective is estimated.

The invention provides an ultrasonic color Doppler image post-processing method, which comprises the following steps of 1) setting a blood parameter estimation module in an ultrasonic color Doppler imaging system; 2) correspondingly receiving a blood flow variance signal and a blood flow velocity signal by a blood flow signal processing module; 3) setting a parameter pre-processing module in the ultrasonic color Doppler imaging system; 4) comparing and judging whether a signal is a blood flow signal or not by the parameter pre-processing module; 5) setting a spatial processing module for processing an image. Based on the above method, the generation of anomalous points is lowered maximally.

The invention provides an aircraft digital twinning situation deduction and risk assessment method in a complex meteorological environment, and belongs to the technical field of data processing, the aircraft digital twinning situation deduction and risk assessment method in the complex meteorological environment comprises the following steps: collecting and processing weather data covering parameters such as wind direction and wind speed; obtaining aircraft performance parameters and building a database; and inputting and analyzing the flight plan. By establishing a three-dimensional deduction model including dynamics, weather influence and environment models, aircraft situations under different weathers are deduced, and flight safety, performance and task risks are evaluated. The method has the advantages that weather factors are comprehensively and accurately analyzed, and influences are quantified through data acquisition and processing and a meteorological model; the system is suitable for various aircrafts, can integrate navigation and control systems, and realizes remote monitoring management; risk assessment is scientific and reliable, multiple factors are integrated, powerful support is provided for flight decision making, and aircraft safety and task success rate in complex weather are effectively improved.

The invention relates to an output power prediction method for photovoltaic generating devices; the method comprises: predicting by using a physical model prediction, and a neural network prediction of environmental factors and a rolling a neural network prediction; setting the physical model prediction as P0, the neural network prediction of the environmental factors as P1, the rolling a neural network prediction as P2, and final power prediction output value as p; if P1 is more than P0 and P2 is more than P0, P is equal to P0; if the P1 is more than P0 that is more than P2, P is equal to P2; if the P2 is more than P0 that is more than P1, P is equal to P1; if P1 is less than P0 and P2 is less than P0, P is equal to (P1+P2) / 2. According to the output power prediction method for photovoltaic generating devices provided by the invention, relatively complex mathematic relation is changed to be simple and reasonable mathematic relation, thus being beneficial to applying to actual engineering, improving predicting speed, reducing predicting difficulty, and being capable of significantly improving accuracy of prediction value of photovoltaic module output power, controlling error range and eliminating outlier.

The invention discloses a multi-millimeter-wave radar cooperative positioning and tracking method. The problem that in the prior art, a virtual target is generated due to the multipath phenomenon is solved. The method comprises the following steps: S1, installing a multi-millimeter-wave radar cooperative positioning and tracking system, and setting a plurality of radars with overlapped beam ranges in a positioning scene; S2, according to a multi-radar coordinate system parameter calibration algorithm, obtaining a rotation angle and a translation matrix of each radar coordinate and an absolute coordinate system; S3, mapping the point cloud information detected by the radar to the absolute coordinate system based on the rotation angles and translation matrixes of the radar coordinate system and the absolute coordinate system; and S4, calculating trajectory information according to the distance between the point cloud information detected by the radar and the predicted trajectory point. Through matching of points and tracks, isolated points generated by multipath and disturbance can be eliminated to a certain extent.

The present invention provides a foundation cloud form identification method based on multiscale structure characteristics. The method has the following concrete steps of (1) utilizing a foundation infrared cloud measurement instrument to obtain images, screening the images in the artificial contrast and artificial correction manners, selecting the typical samples to combine into a typical sample base as a training standard set, wherein the rest is used as a test sample set; (2) decomposing the training standard set and the test sample set by a layering method to obtain a multiscale image of each cloud picture; (3) extracting the multiscale structure characteristics of the cloud pictures; (4) by a support vector machine classifier and according to the final character representation of the training foundation cloud picture samples in the training standard set and the final character representation of the test foundation cloud pictures in the test sample set, classifying the test foundation cloud pictures to obtain a classification result of the test foundation cloud pictures, and optimizing the parameters of a support vector machine according to the classification result.

Embodiments of the present invention provide systems, apparatuses, methods, and computer program products for forecasting the future headcount of an organization by generating, validating and displaying models of the headcount of an organization or division thereof over time. In some embodiments, at least three different models are generated using stored historical headcount information, including a linear regression model, a multivariate model using macroeconomic variables, and an autoregressive moving average model. In some embodiments, for each of the foregoing types, multiple models are generated and the best model of each type is selected for use in forecasting headcount according to predetermined evaluation criteria.

The invention discloses a distribution network multi-parameter data fusion fault positioning method and system, and the method and system achieve the omnibearing monitoring of a power distribution network fault through the collection of multiple types of data, such as electrical signals, video images, meteorological information and environmental parameters. Compared with a traditional fault positioning method of a single information source, the system can reflect the fault condition more truly, and the positioning accuracy and reliability are remarkably improved. Machine learning or a deep learning model is utilized to analyze fusion data, fault types and positions are automatically identified, intelligent diagnosis is realized, manual intervention is reduced, the operation and maintenance cost is reduced, and the processing efficiency and accuracy are improved. The real-time data acquisition and transmission technology guarantees the system to monitor in real time and rapidly alarm potential faults. According to the method, historical data and an expert knowledge base are combined, fault causes are deeply analyzed, accurate information and maintenance suggestions are provided for maintenance personnel, operation and maintenance decisions are optimized, and the maintenance efficiency and quality are enhanced. The system provides an efficient and intelligent solution for distribution network fault positioning.

The present invention provides a normal distribution H threshold-based purple soil image segmentation and extraction method. The method comprises the following steps that: S1, a color image containinga purple soil region is converted into the image I of an HSV color space; S2, a threshold for segmenting the image I is determined, and the image I is divided, and a binary image II can be obtained;S3, the boundary of the binary image II is identified, so that a binary image III is obtained; S4, the boundary of the purple soil region in the binary image III is extracted, and the binary image V of the extracted boundary is obtained; S5, a closed region segmented out from the boundary in the binary image III is filled, so that a binary image IV can be obtained; and S6, the Hadamard product ofthe binary image IV and the color image containing the purple soil region is obtained. According to the method of the invention, a fact that the soil region of the purple soil color image has a good aggregation characteristic in the H component of the HSV color space, and a fact that the H component of the purple soil image is in approximate normal distribution are considered, the segmentation threshold of the H component is obtained, and the soil region is quickly and accurately segmented from a background region completely.

The invention relates to the technical field of data processing, and discloses an ocean current simulation method and system based on a three-dimensional temperature-salinity value. The method comprises the following steps: carrying out line calculation and adaptive mesh refinement processing on a three-dimensional temperature and salt field simulation model to obtain a model operation scheme; performing three-dimensional visualization processing on the three-dimensional temperature and salt field initial data set and the model operation scheme to obtain dynamic three-dimensional temperature and salt field visualization data, and analyzing the dynamic three-dimensional temperature and salt field visualization data to obtain three-dimensional structure data and evolution process data of the key ocean phenomenon; performing data assimilation processing on the multi-source real-time observation data, the three-dimensional structure data and the evolution process data to obtain a fusion data set; and performing ocean current prediction calculation on the fused data set to obtain a three-dimensional ocean current prediction field, and performing uncertainty quantitative analysis on the three-dimensional ocean current prediction field to obtain ocean current simulation probability distribution data. According to the invention, the accuracy and timeliness of ocean current simulation based on the three-dimensional temperature-salinity value are improved.

The invention relates to the technical field of data processing and optimization, in particular to a liquid crystal display screen display optimization method and system. The method comprises the following steps: acquiring display data of a liquid crystal display screen by using a sensor to obtain the display data of the liquid crystal display screen; preprocessing the display data of the liquid crystal display screen to obtain standard display data of the liquid crystal display screen; performing multi-dimensional feature recognition on the display data of the standard liquid crystal display screen to obtain multi-dimensional display feature data; performing key display information extraction on the multi-dimensional display feature data to obtain key display information; according to the invention, through a data processing technology, an image identification technology and an intelligent regulation and control technology, a specific environment condition is analyzed so as to obtain an abnormal display condition of the liquid crystal display screen caused by environmental influence; and dynamic display optimization adjustment is carried out on abnormal display conditions of the liquid crystal display screen, so that the display effect of the liquid crystal display screen is improved.

A method for monitoring a reference half cell, which forms with a measuring half cell a potentiometric measuring point for determining and / or monitoring an ion concentration of a medium. The ion concentration of the mediums determined on the basis of at least one measurement signal determined in a measuring circuit, between the measuring half cell and the reference half cell. According to the invention, the measuring point is operated intermittently in an operating mode and in a test mode, wherein, in the operating mode, the ion concentration is measured and wherein, in the test mode, the proper functioning of the reference half cell is checked.

The invention provides a distributed photovoltaic output power estimation method, and the method comprises the steps: installing a load sensor and a photovoltaic output sensor at an access point, and collecting original data including load data and photovoltaic output data in real time; processing the collected original data; carrying out time synchronization on the load data and the photovoltaic output data; key features are extracted from the cleaned original data, and photovoltaic output is predicted through a time sequence analysis model; inputting load data and photovoltaic output data which are acquired in real time into the trained time sequence analysis model; the time sequence analysis model performs real-time operation according to the load data and the photovoltaic output data, and estimates the photovoltaic output power at the current moment; and based on the estimated photovoltaic output power and the real-time load data, the intelligent coordination controller performs dynamic adjustment, so that the photovoltaic output is matched with the load power. According to the invention, efficient estimation and optimal control of photovoltaic output are realized.

The invention discloses a measurement method for improving distributed spatial resolution of an OFDR (Optical Frequency Domain Reflectometer) system. The method comprises the following steps of firstly, converting a traditional one-dimensional cross-correlation processing result signal into a two-dimensional image signal, denoising an image through a Gaussian filtering denoising algorithm on the basis of the two-dimensional image, and then carrying out next operation on the processed image to obtain a two-dimensional image; and finally, a high-spatial-resolution result being obtained. According to the OFDR sensing system based on the Gaussian filtering and denoising algorithm, the spatial resolution of a measurement system can be improved, so the OFDR sensing system has greater advantages and wider application in the high-precision monitoring fields such as space flight and aviation, machinery equipment and the like.

The invention relates to the technical field of automobile exhaust pollution, in particular to a sensor-based automobile exhaust networking analysis system, which comprises a data acquisition module, a data processing and fusion module, an analysis and prediction module, an intelligent decision module, a data storage module and a user interaction module, the data processing and fusion module is used for processing the received pollutant component data, the data storage module is used for storing the pollutant component data, the analysis and prediction module is used for analyzing the pollutant component data in real time and predicting the tail gas emission trend, and the intelligent decision module is used for generating optimized vehicle operation parameters and providing maintenance suggestions. And the user interaction module provides a visual interaction interface and displays the tail gas emission data, the analysis result and the decision suggestion of the vehicle in real time. According to the automobile exhaust monitoring system, the technical problems existing in an existing automobile exhaust monitoring system are effectively solved, and the accuracy and reliability of data are remarkably improved.

The invention relates to the technical field of power distribution cabinet control, in particular to an electrical power distribution cabinet and a control method thereof. The method comprises the following steps: acquiring multi-dimensional data of the power distribution cabinet; performing data preprocessing on the multi-dimensional data of the power distribution cabinet to generate a power distribution cabinet preprocessing data set; performing contribution degree sorting on the preprocessed data set of the power distribution cabinet to generate contribution degree sorting data of the power distribution cabinet; constructing an electric cabinet model according to the contribution degree sorting data of the power distribution cabinet, and generating an electric cabinet power consumption prediction model; acquiring real-time power distribution cabinet data; performing power distribution cabinet power utilization prediction on the real-time power distribution cabinet data based on the power utilization cabinet power utilization prediction model to generate a power distribution cabinet prediction result; therefore, by comprehensively integrating the multi-dimensional data of the power distribution cabinet, intelligent prediction and optimal scheduling are performed, the problems of low prediction precision, non-uniform resource distribution, response lag and the like in traditional power distribution cabinet management are solved, and the operation efficiency and the resource utilization rate of the electrical power distribution cabinet are improved.

A semiconductor device manufacture method has the steps of: (a) forming a semiconductor device structure in a chip and alignment marks, respectively in a semiconductor wafer; (b) forming a workpiece layer above the semiconductor wafer; (c) exposing the alignment marks; (d) coating an electron beam resist film on the workpiece layer; (e) scanning the alignment marks with an electron beam to obtain plural position information on the alignment marks and obtaining differences between the plural position information; (f) removing abnormal values of position information in accordance with the difference between the plural position information; and (g) performing an electron beam exposure in accordance with plural position information of the alignment marks with the abnormal value being removed. An alignment mark detection precision can be improved in electron beam exposure.

The invention discloses a hardware and software cooperation method for measuring cloud layer height and thickness. The method comprises the following steps: automatic emission and automatic collection of a high speed laser pulse train are realized, and collected discrete data are stored in an FPGA and then processed via an embedded processor. According to the hardware and software cooperation method, the high speed FPGA is used for pulse emission and data collection, speed higher than that of other hardware systems can be realized, and off-chip resources can be saved. According to the hardware and software cooperation method, a curvature segmentation and wavelet filtering method is adopted and is greater than a single value calculating method in terms of real-time performance, flexibility and measuring precision. Compared with the prior art, a high speed FPGA-based cloud layer height and thickness measuring instrument is advantaged by high speed, strong processing performance, monolithic integration, no need for redundant peripheral chips, capability of making it convenient to make an SOPC and realize chunked transplant, application to continuous, wireless and remote measurement, and wide application to the various fields such as meteorology, civilian use, transportation and the like.

The invention relates to the technical field of nursing information management, and particularly discloses a cancer patient home pain management decision-making system based on a patient report outcome, which is used for solving the challenges of uneven data quality, slow update feedback speed, large and diverse data volume and the like in pain management of cancer patients in a home environment. The system comprises an intelligent sensing and data aggregation module, a cloud server, a distributed computing and data processing module, an intelligent decision support module and a user interaction feedback module. Noise and abnormal values can be removed through dynamic data cleaning and data standardization, data consistency is ensured through multi-source data fusion, real-time data is analyzed through large-scale data analysis and an LSTM model, future pain states and risks of cancer patients are predicted, personalized management suggestions are generated, and the efficiency and effect of home pain management are improved.

The invention discloses an extensible water pump digital twinborn body construction method, and particularly relates to the field of digital twinborn, and the method comprises the steps: S1, constructing a physical model, S2, collecting water pump performance data, S3, preprocessing the water pump performance data, S4, constructing a water pump digital twinborn model, S5, applying the water pump digital twinborn model, and S6, optimizing a water pump digital twinborn body. The water pump digital twinborn model is constructed according to multiple dimensions of water pump flow data, water pump pressure data and water pump operation data, the model is continuously improved according to the actual operation condition of the water pump, the expandability of the water pump digital twinborn body is achieved, the water pump digital twinborn model can also conduct safety monitoring on a water resource allocation project, and the water resource allocation project safety is improved. And different running conditions of the water pump are judged, and different response results are made, so that the engineering safety is further improved.

A method for predicting a trajectory of a target vehicle in an environment of a vehicle. The method includes the steps of a) capturing states of the target vehicle, capturing states of further vehicle objects in the environment of the vehicle and capturing road markings by a camera-based capture device; b) preprocessing the data obtained in step a), wherein outliers are removed and missing states are calculated; c) calculating an estimated trajectory by a physical model on the basis of the data preprocessed in step b); d) calculating a driver-behavior-based trajectory on the basis of the data preprocessed in step b); and e) combining the trajectories calculated in steps c) and d) to form a predicted trajectory of the target vehicle.