41results about How to "Remove outliers" patented technology

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.

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 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 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.

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 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.

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.

The invention provides an OFDR large strain measurement method under high spatial resolution, and the method comprises the steps: converting a conventional one-dimensional cross-correlation processing result signal corresponding to each position on an optical fiber into a two-dimensional image signal in the strain measurement of an OFDR system; on the basis of a two-dimensional image, performing denoising processing on the image through a total variation denoising algorithm or a wavelet denoising algorithm, performing next operation on the processed image, and finally obtaining a large strain measurement result under high spatial resolution. The method has the advantages that the OFDR sensing system based on wavelet denoising algorithm performs denoising on the two-dimensional image information, the spatial resolution of the system can be improved, abnormal values of large strain measurement results can be effectively removed, the measurement accuracy is improved, and large strain measurement under the high spatial resolution is achieved.

The invention discloses a bridge health monitoring method and system for signal adaptive decomposition and recognition, which is applied to the technical field of bridge structure detection, and comprises the following steps: S1, collecting response signals of a bridge structure under the working conditions that a train does not get on a bridge and gets on the bridge; S2, performing regularity analysis on the signal by adopting a graphic method in an EDA analysis method; S3, adopting a Pauta method to remove abnormal values in the response signals; S4, adopting a trinomial least square method to eliminate trend terms and burrs in the actually measured response signals; S5, based on an AEMD algorithm, performing signal adaptive decomposition and automatic recombination on the response signal; and S6, on the basis of a DATA-SSI method, carrying out modal parameter identification on the recombined signal, and monitoring the health state of the bridge structure in real time. The system can quickly output a detection result; according to the method, trend terms and burrs in the response signals can be removed, abnormal factors in the response signals can be eliminated, and the accuracy of monitoring the health state of the bridge structure is improved.

The invention provides a crystallizer copper plate quality optimization method and system based on heat conduction performance evaluation, and relates to the technical field of data processing, and the method comprises the steps: obtaining the parameter information of a crystallizer copper plate; according to the crystallizer copper plate parameter information, partition processing is conducted on the crystallizer copper plate, and multiple block parameters are obtained; obtaining a heat-conducting property parameter set of the crystallizer copper plate through the plurality of block parameters; first temperature information is obtained through application scene parameter information of the crystallizer copper plate; performing partition processing to obtain a first temperature information set; determining a heat-conducting property parameter test set; evaluating the heat-conducting property parameter set to obtain a heat-conducting property evaluation result; and correspondingly optimizing the quality of the crystallizer copper plate. The technical problem that the surface and internal quality of the continuous casting blank can be affected by poor heat conductivity or too fast heat conductivity is solved, and the technical effects that the heat conductivity is reasonably evaluated, the quality of the crystallizer copper plate is optimized according to the heat conductivity requirement, and then the quality of the casting blank is improved are achieved.