882 results about "Least squares support vector machine" patented technology

The invention provides a human body behavior identification method based on an inertial sensor. The method comprises the steps of acquiring human body behavior data of testees by means of the inertial sensor, conducting sliding window segmentation on the acquired human body behavior data, conducting feature extraction on a triaxial accelerated speed subsequence and a triaxial angular speed subsequence which are obtained after sliding window segmentation, conducting feature fusion on a feature vector to form a sample set of the human body behaviors of the testees, conducting feature selection on the sample set by means of the least correlated maximum redundant algorithm and the Bayes regularization sparse polynomial logistic regression algorithm, obtaining the classification feature vectors of all human body behaviors of all the testees, obtaining a classifier model of each human body behavior by means of a fuzzy least square support vector machine, and obtaining a human body behavior identification result after the human body behavior data are tested by means of the fuzzy least square support vector machine. By means of the human body behavior identification method, self-adaptation and identification efficiency can be improved.

The invention discloses a sensor-fault diagnosing method based on the online prediction of a least-squares support-vector machine. In the method, a least-squares support-vector machine online-predicting model is established, and then the measured data of a sensor is acquired on line and used as an input sample of the least-squares support-vector machine online-predicting model to realize that the output value of the sensor at the next moment is predicted in real time as the predicting model is trained on line. Whether sensor faults occur or not is detected by comparing residual errors generated by the predicting value and the actual output value of the sensor. When the faults occur, the unary linear regression for a residual-error sequence is carried out by a least-squares method to realize the identification of the deviation and drift faults of the sensor, and furthermore, measures can be more effectively taken to carry out real-time compensation for the output of the sensor. Through the sensor-fault diagnosing method, the online fault diagnosis of the sensor can be rapidly and accurately realized, and the sensor-fault diagnosing method is particularly applicable to diagnosing the deviation faults and the drift faults of the sensor.

The invention relates to an SCR (Selective Catalytic Reduction) denitration system ammonia spraying quantity optimal control system and method based on intelligent feedforward signals. The SCR denitration system ammonia spraying quantity optimal control system based on intelligent feedforward signals is characterized in that as input parameters of a denitration system can be easily influenced by the combustion state of a boiler and for adapting to the requirement of large range of depth change of conditions for a thermal power generating unit, the SCR denitration system ammonia spraying quantity optimal control system based on intelligent feedforward signals takes the historical data of a power plant as the basis, utilizes the idea of data modeling, takes adjustable parameters at the boiler side as input and NOX concentration at the outlet of a hearth as output, utilizes a Least Squares Support Vector Machine algorithm to construct a prediction model which can be used for constructing an intelligent feedforward controller in a ammonia spraying quantity control strategy, and takes dynamic matrix control (DMC) as a main controller and PID as an auxiliary controller to construct a cascade feedback control structure; during the operating process, the intelligent feedforward controller outputs feedforward control signals in real time according to changes of the parameters at the boiler side, quickly gives a response to change of conditions of the unit, and forms an SCR system ammonia spraying quantity optimal control strategy together with feedback control, and can realize quick accurate control of the ammonia spraying quantity.

The invention discloses a combination forecast modeling method of wind farm power by using gray correlation analysis, belonging to the technical field of wind power generation modeling. In particular, the invention is related to a weighted combination forecast method of wind power based on a least square support vector machine and an error back propagation neural network. The forecast method comprises that forecasted values of wind speed and wind direction are acquired in advance from meteorological departments while real-time output power is acquired from a wind farm data acquiring system; that the forecasted values of wind speed and wind direction and the real-time output power are inputted into a data processing module for data analyzing extraction and data normalization, and then normalized data is loaded to a database server; processed data in the database server is extracted by a combination forecast algorithm server to carry out model training and power forecast, and the wind farm sends running data to the data processing module in real time to realize rolling forecasting. The method of the invention achieves the goal of combination forecast of wind farm output in a short time. The method not only maximally utilizes advantages of two algorithms but also increases forecast efficiency by saving computing resources and shortening computing time.

The invention discloses a power equipment current-carrying fault trend prediction method based ona least squares support vector machine. The method provided by the invention comprises the steps of employing historical temperature data to train an LS-SVM regression model, and employing a PSO optimization algorithm to adjust two parameters of the model, namely nucleus width sigma and punishment parameter gamma; employing a PCA algorithm and a K-means clustering algorithm to real-time analyze the temperature of equipment contacts to find contacts with abnormal temperature rising, and using the temperature value asan initial value sequence of prediction;and finally employing the regression model obtained by training to predict the temperature value of the initial value for a long term and for a short term, and analyzing the highest point the contact temperature may reach and the time when the contact temperature reaches the highest point. Through predictive analysis based on PSO-LSSVM, fault development trend of equipment contacts is actively controlled, so the time for timely measures and ensuring the safe operation of power grid is bought. The method provided by the invention can be widely used in the field of power equipment forecast alarm protection.

The invention discloses a characteristics analysis and forecast method for blast furnace molten iron silicon content. Blast furnace technological parameters in a forecast module for blast furnace molten iron silicon content are deemed as input variables; after exponential weight mobile average filtration and normalized pre-process for sample data of the input variables, the invention can use an improved dynamic separate composition analysis method for conducting characteristic extraction for the sample data of the input variables, so as to eliminate relevance between production technological parameters; a dynamic recurrence module for forecast of the blast furnace molten iron silicon content is established using the least square support vector machine arithmetic, so as to bring in a genetic arithmetic to optimize module parameters. The invention has common universality for molten iron silicon content forecast in blast furnace smelting process, so as to gain rather good forecast accuracy and improve the forecast hit ratio for blast furnace molten iron silicon content.

The invention relates to a nonlinear fault detection method based on semi-supervised manifold learning, which belongs to the field of electromechanical equipment fault diagnosis. The method comprises the following steps that (1) vibration signal data acquisition and preprocessing are performed on monitored electromechanical equipment, and hybrid-domain feature extraction is performed to obtain an initial sample set which represents an operating state of the equipment; (2) a semi-supervised Laplacian Eigenmap algorithm is adopted to perform manifold feature extraction on an equipment sample, so as to obtain essential manifold features sensitive to faults; and (3) an intelligent diagnosis model based on an LS-SVM (Least Squares-Support Vector Machine) is established in low-dimensional manifold feature space, so as to realize mode recognition and diagnosis decision to the operating state of the equipment faults. By using a semi-supervised manifold learning algorithm adopted by the invention, nonlinear geometric manifold features of a vibration signal sample can be effectively extracted, the fault category of the equipment operating state is judged, and the fault detection pertinence and accuracy are improved. The nonlinear fault detection method can be widely used for fault detection and diagnostic analysis of all kinds of mechanical equipment.

The invention relates to a soft sensing method for load parameters of a ball mill. The method is that a hardware supporting platform is used to obtain vibration signals, vibration sound signals and current signals of a ball mill cylinder to soft sense ball mill internal parameters (ratio of material to ball, pulp density and filling ratio) characterizing ball mill load. The method comprises the following steps that: the vibration, the vibration sound, the current data and the time-domain filtering of the ball mill cylinder are acquired, time frequency conversion is conducted to the vibration and the vibration sound data, kernel principal component analysis based nonlinear features of the sub band of the vibration and the vibration sound data in frequency domain are extracted, nonlinear features of the time domain current data are extracted, feature selection is conducted to the fused nonlinear feature data and a soft sensing model based on a least squares support vector machine is established. The soft sensing method of the invention has the advantages that the sensitivity is high, the sensed results are accurate, the practical value and the popularization prospect are very good, and the realization of the stability control, the optimization control, the energy saving and the consumption reduction of the grinding production process is facilitated.

The invention relates to the technical field of computer vision and pattern recognition, and provides an anti-shelter target trajectory predicting and tracking method. The method comprises the following steps of: selecting a target, initializing a Kalman parameter, and calculating a quantification histogram; reading an image, calculating the position and the size of a tracking window, correcting the central position of the target, and setting the central position of an image searching window of a next frame; predicting the position of the target by a trajectory predicting program; solving an occlusion factor; and according to a sheltered situation, selecting a Kalman filter to work, or converting to trajectory predication based on least square support vector machines, namely determining that the tracking fails if the target is not found when a determined frame number is exceeded in a predicting process; and continuing enabling an MeanShif target tracking algorithm and the Kalman filter to track and the like if the target is found. By using the method, the target which reappears after being sheltered by a large area can be tracked accurately; and the method has good real time and anti-jamming capability.

The invention provides a city short-term water consumption prediction method based on a least square support vector machine model. The method comprises the following steps that preprocessing is carried out on historical water consumption; correlation analysis is carried out; a least square support vector machine method is adopted for setting up a city short-term water consumption predicting model, and time sequence combinations of the historical water consumption with correlation coefficients larger than set values are selected to serve as a training sample set for training; the city short-term water consumption predicting model is adopted for carrying out prediction in real time; prediction errors are calculated, and if the prediction errors do not meet the prediction accuracy requirement, the city short-term water consumption predicting model is improved. According to the city short-term water consumption prediction method, preprocessing is carried out on the historical water consumption, an original change law is kept as much as possible, and therefore the prediction accuracy can be improved; as the least square support vector machine method is adopted, the problem of nonlinearity of a water supply system and the problem that an accurate model can not be set up are solved; weather data and/or holiday factors are considered comprehensively, and the prediction accuracy is improved.

The invention provides a particle swarm optimization-based least square support vector machine combined predicting method. The particle swarm optimization-based least square support vector machine combined predicting method comprises the following steps: according to data characteristics to be predicted, selecting proper single predicting models; properly combining different predicting methods; by making full use of useful information contained in the single predicting models, establishing an LSSVM (least square support vector machine) regression model; and through a PSO (particle swarm optimization), optimizing two core parameters which affect the precision of the LSSVM regression model and include a kernel function parameter g and an LSSVM regularization parameter C so as to obtain the optimal LSSVM regression model. By the method, the aims of improving the predicting precision and reducing predicting risks can be achieved; the convergence rate of the algorithm is greatly improved; and actual engineering needs can be met better.

Subsurface reservoir properties are predicted despite limited availability of well log and multiple seismic attribute data. The prediction is achieved by computer modeling with least square regression based on a support vector machine methodology. The computer modeling includes supervised computerized data training, cross-validation and kernel selection and parameter optimization of the support vector machine. An attributes selection technique based on cross-correlation is adopted to select most appropriate attributes used for the computerized training and prediction in the support vector machine

The invention discloses a combustion process multivariable control method for a CFBB (circulating fluidized bed boiler), which is realized in the following procedures: in each control period, collecting operational parameters of the boiler through data collecting equipment and storing the operational parameters in a data storage module; utilizing the history data in a memorizer to on-line identify the CARIMA model and present P step future moment predominant values such as process output variable main steam pressure, material bed temperature and flue gas oxygen content through a model on-lineparameter identification module of GPC (generalized prediction control); performing error compensation to the process future moment prediction output through an error estimation module of an LSSVM (least square support vector machine); and referring the reference trace obtained by a trace generator, performing rolling optimization in GPC for the process future moment prediction output, and calculating through the optimized algorithm to enable the process actual output to reach the set value. The method provided by the invention solves the time varying problem of the model parameter, and enables the control system to have stronger robustness.

The invention discloses a modeling method of a thermal error least squares support vector machine of a numerically-controlled machine tool. The method comprises the following steps: (1) selecting a kernel function and determining parameters; and (2) establishing a thermal error model of the machine tool according to least squares support vector machine theory. A compensating system of the invention has the advantages of simple structure and reliable application; and the modeling method of the least squares support vector machine improves the model precision and generalization capability and overcomes defects of the existing prediction methods, such as low precision, low generalization capability and the like. The modeling method has higher prediction precision when the sample size is small and even the sample data are small, thus reducing dependence on experience. Meanwhile, the method improves the self-learning ability of the system, the thermal error model obtained by training can reflect the manufacturing procedure change of the machine tool, and the method has the advantages of adaptability, low hardware requirements for the thermal error compensating system, simple structure and good reliability.

The invention relates to a license plate character recognition method based on real-time vehicle tracking and binary index classification, which comprises the following steps of: dynamically and continuously performing multi-point tracking on a vehicle in real time, and recognizing the license plate character based on a least squares support vector machine (LS-SVM) and the binary index classification. A novel license plate-extracting scheme which comprehensively adopts gray gradient, shape and posture, vision models and the like is provided in the stage of segmenting and extracting the license plate character by using the space distribution information of the license plate character. The robustness and accuracy of extracting the license plate are improved, and the real-time property is guaranteed.

The invention discloses a Kalman filtering and data driving fusion battery SOC estimation method belonging to the battery SOC estimation method technology field. The invention provides a varied variance Kalman filter least square support vector machine (VVKF LSSVM) fusion method. Based on two equations of a KF, a noise variance, which is adapted to a current system state to the greatest extent, is set during every iteration, and a problem of declined precision caused by Kalman filtering noise variance initial value relied on artificial experience setting is solved. A least square support vector machine (LS SVM) is selected as the measurement equation of the KF, and by starting from a data angle, the SOC estimation method suitable for various batteries is completed by establishing a simple sample library, and the estimation precision is improved by dynamic modeling. A part of data in an NASA lithium battery data set and a CACLE lithium battery data set is used for experimenting to prove the superiority of the VVKF by comparing with the KF, and the validity of the whole method on the lithium battery SOC estimation.

The invention relates to a wind electric power prediction method and a device thereof. The method comprises the following steps of: step one: extracting data from SCADA (Supervisory Control and Data Acquisition) relative to a numerical weather prediciton system or a power system, and carrying out smoothing processing on the extracted data; step two: determining input and output of training samples of a least squares support vector machine according to the processed data; step three: initializing relevant parameters of a smallest squares support vector machine and an improved self-adaptive particle swarm algorithm; step four: optimizing model parameters according to an optimization process; step five: acquiring a model of the smallest squares support vector machine according to the optimized parameters; and step six: carrying out prediction according to the model of the smallest squares support vector machine. According to the wind electric power prediction method disclosed by the invention, a modelling process is simple and practical, wind electric power can be rapidly and effectively predicted, and the wind electric power prediction method has an important significance on safety and stability, and scheduling and running of the electric power system, and therefore, the wind electric power prediction method has wide popularization and application values.

The invention discloses a fan gear box fault diagnosis method based on an artificial intelligence algorithm. According to the method, structure features and fault types of a fan gear box are studied, and parameter optimization is performed on least square support vector machine (LSSVM) by an artificial bee colony algorithm to be applied to fault diagnosis of the fan gear box. By means of the method, the artificial bee colony algorithm is used for optimizing the LSSVM to excellently finish the fault diagnosis of the fan gear box, the recognition rate is high, and the reliability is good.

The invention discloses a thermal process soft sensor modeling method based on least squares and support vector machine ensemble, and belongs to the technical fields of thermal process and artificial intelligence intersection. The method includes selecting auxiliary variables as an input of a model and key variables to be predicted as an output of the model, selecting running data as an initial training sample, utilizing the soft fuzzy c-means clustering (SFCM) method to divide the initial sample into sub-datasets which are overlapped and which are provided with differences, establishing individual models on each sub-dataset, and synthesizing predicted outputs of the individual models to obtain estimation of the key variable; aiming to optional new acquired sample xk, obtaining a corresponding predicted value. According to the thermal process soft sensor modeling method, the soft fuzzy C-means clustering method is adopted, predicting accuracy is improved by means of establishing integrated models, calculating of the models is easier, and calculating efficiency is improved; boundary samples are processed effectively, the process is convenient to implement, the key variable can be predicted accurately, and important significance is provided to optimized operation of the thermal process system.

The invention discloses a rock character judging method based on laser-induced breakdown spectroscopy (LIBS). According to the method, a laser-induced breakdown spectroscopy (LIBS) technology is used to establish a rock and/or rock debris element information prediction model based on a least square support vector machine; and the rock characters can be judged according to the element information prediction data of a rock and/or rock debris sample to be detected. The method has the characteristics of directness, rapidness, accuracy, and efficiency. The rock character judgment is accurate and efficient, especially for the logging rock debris powder under a high speed drilling condition, and the rock character judgment results are the same with those of drilling and coring. The invention also provides a system for the method mentioned above at the same time.

The invention relates to a method for detecting driving fatigue based on electroencephalogram. The method specifically comprises the following steps: (1) selecting characteristic quantity related to a driving fatigue state; (2) performing electroencephalogram power spectrum analysis on the driving fatigue state; (3) performing electroencephalogram sample entropy analysis on the driving fatigue state; (4) performing electroencephalogram Kc complexity analysis on the driving fatigue state; (5) using support vector machine (SVM); (6) using least squares support vector machine (LS-SVM); (7) setting model training parameters (C and g) through a particle swarm optimization (PSO) algorithm. According to the method disclosed by the invention, electroencephalograms extracted in different driving states are respectively researched from a power spectrum angle by using related methods in non-linear dynamics, so that excellent effects can be achieved in accuracy and reliability.

The invention provides an LS-SVM (Least squares support vector machine) power cell SOC (State of Charge) estimation method and system, comprising the steps of: I, obtaining a Uoc based on a power cell model and parameters through an FFRLS (Forgetting factor least squares algorithm); II, fitting a Uoc-SOC relation through the FFRLS; III, building an on-line LS-SVM SOC training model; IV, estimating an SOC initial value, and estimating an SOC through an Ah method (Ampere-hour Counting method); and V, correcting and compensating the SOC estimated through the Ah method. In the system, real-time signals of voltage and current sensors access to a microprocessor; processing modules used for executing the method are stored in a program memory, and calculate and directly display real-time SOC estimation values. The method and system can effectively compensate for fitting errors and Ah method accumulative errors, and adjust model parameters on line and in real time, and have the characteristics of fast operation speed, high traceability, and accurate estimation; according to experiments, the SOC estimation precision through the method is high, and the mean absolute error is only 1.28%.

The invention discloses a short-term power load forecast method which comprises the following steps of: 1, selecting 40 days of load data and weather data before the current moment as training sample data and forecast sample data; 2, preprocessing the sample data, and normalizing all the data to be between 0 and 1; 3, selecting parameters (gamma and sigma) as harmonic vectors, and calculating new harmonics (gamma' and sigma') by using a harmonic search algorithm; 4, calculating a target evaluation function value, and determining the harmonic vector corresponding to the maximum target evaluation function value and; 5, updating the iterative frequency k=k+1, and judging whether k belongs to NI; and 6, substituting the optimal harmonic (gamma0 and sigma0) into a least squares support vector machine model, training by the training sample, and further forecasting the load. According to the method, the load forecast precision is effectively improved.