13 results about "Model parameters" patented technology

System and method for modeling a nonlinear process. A combined model for predictive optimization or control of a nonlinear process includes a nonlinear approximator, coupled to a parameterized dynamic or static model, operable to model the nonlinear process. The nonlinear approximator receives process inputs, and generates parameters for the parameterized dynamic model. The parameterized dynamic model receives the parameters and process inputs, and generates predicted process outputs based on the parameters and process inputs, where the predicted process outputs are useable to analyze and/or control the nonlinear process. The combined model may be trained in an integrated manner, e.g., substantially concurrently, by identifying process inputs and outputs (I/O), collecting data for process I/O, determining constraints on model behavior from prior knowledge, formulating an optimization problem, executing an optimization algorithm to determine model parameters subject to the determined constraints, and verifying the compliance of the model with the constraints.

The invention relates to an SOC and SOT combined state estimation method based on a power battery electric-thermal coupling model, and belongs to the technical field of battery management. The methodcomprises the steps of selecting a to-be-measured power battery, building the electric-thermal model of the power battery, and determining parameters needed for estimating the SOC and the SOT of the power battery; under different temperatures, conducting trickling charging-discharging experiments and HPPC experiments on the measured power battery, building a database of equivalent circuit model parameters relevant to the temperature and the SOC under a charging and discharging condition, and simulating field test working conditions under different road conditions to build the database; conducting parameter identification to obtain characteristic parameters of the electric-thermal model, and obtaining the quantitative relation between the equivalent circuit model parameters and the temperature and the SOC under the charging and discharging condition. By means of the SOC and SOT combined state estimation method based on the power battery electric-thermal coupling model, the model is combined with a PF algorithm and the quantitative relation of the equivalent circuit model parameters relevant to the temperature and the SOC under the charging and discharging condition of the power battery to achieve the SOC and SOT combined state estimation of the power battery.

The present invention relates to a pedestrian detection method based on deep learning and multi-feature point fusion. The pedestrian detection method is characterized by at a training stage, firstly acquiring a pedestrian image under an application scene, marking the head and shoulder parts of the pedestrians in the image, and then using the pedestrian samples for the model training, wherein the model training comprises two steps of 1) taking the head and shoulder images of the pedestrians as the training samples, training a dichotomy model of the head and shoulder parts of the pedestrians; 2) using the model parameters obtained by the training in the step 1) to initialize partial parameters of a pedestrian detection model in a transfer learning manner. The pedestrian detection method of the present invention can overcome the problem that the pedestrians shield mutually to a certain extent, adopts a deep learning method to extract the pedestrian features, can better overcome the actual application problem that the factors, such as the pedestrian clothing, postures, backgrounds, illumination conditions, etc., change, also can effectively overcome the problems of the pedestrian multiple postures, the pedestrian multiple scales, the pedestrian mutual shielding, etc., and enables the pedestrian detection accuracy and robustness to be improved substantially.

The invention discloses an optimized design method of Gantry-type machine tool stiffness based on segmentation configuration. 3D model of Gantry-type machine is established. Parameter-driven of segmentation configuration modifies and adjust 3D parameter, then a series of 3D model as a structural template can be obtained. A sample library of Gantry-type machine tool can be formed by performance data from finite element analysis. According to the stiffness requirements of the machine tool processing, the initial plan of Gantry-type machine tool structure inputted by the design personnel is optimized based on the basic configuration and segmentation configuration. According the method, the stiffness of Gantry-type construction in early designing stage has been predicted, which provides a reference for designing high stiffness gantry-type structure and reduce the experiment cost of modification and trial production in the process of designing Gantry-type machine tool.

The invention discloses a multi-view target searching method based on a probability model. The multi-view target searching method comprises the following steps of extracting Zernike moments of initial view sets of various objects from a multi-view model library to obtain an initial feature vector set; gathering initial feature vectors of all the objects to obtain a total initial feature vector set and defining the total initial feature vector set as a multi-view feature library; randomly selecting an object from the multi-view model library and using the selected object as a query target; selecting an optional object as a comparing target; finding out an object which is similar to the query target from the multi-view model library; performing theoretical analysis to obtain a probability function based on a Gaussian model; performing sample training to obtain model parameters; calculating matching probability of the query target and the comparing target; and arraying the matching probabilities of the query target and all models in the multi-view model library in a descending order to obtain a final searching result. By the multi-view target searching method, dependence on space position information of a camera is avoided when initial views are acquired. The multi-view target searching method can be used for any multi-view target databases based on views.

The embodiment of the invention discloses a target vision model training method and device, equipment and a storage medium. The target vision model training method comprises the following steps: acquiring a first sample image and a background image; obtaining a target image according to the first sample image, and placing the target image in the background image to obtain a second sample image; inputting each sample image into a to-be-trained model, so that the to-be-trained model predicts a corresponding prediction category according to the sample image; and determining a first loss value according to the target category and the prediction category, adjusting model parameters of the to-be-trained model according to the first loss value until a preset training stopping condition is met, and taking the trained to-be-trained model as a target visual model. According to the embodiment of the invention, the problem of low model performance caused by few sample data, difficulty in sample data acquisition and the like can be solved.

The invention provides a vehicle quality evaluation method and system based on big data fusion, and relates to the technical field of data analysis and prediction algorithms. The method comprises thefollowing steps: acquiring historical data of a vehicle during running from an automobile intelligent platform; loading the historical data reported by the vehicle into a json character string in a standard format, analyzing the historical data loaded from a platform, and sorting the data reported by each vehicle in one day according to the reporting time, so that each frame of data is matched with an index expression of a monitoring index list; and after all the data of all the vehicles on the same day are processed, substituting the processed data into the scoring model to calculate the score of each vehicle, and judging the quality condition of the vehicles according to the scores of the vehicles. According to the invention, the technical problems in the prior art that the indexes of the electric vehicle are scattered and are not easy to obtain and the effective value intervals of different vehicle model parameters are not flexible enough are solved, and the working efficiency is improved.

The invention discloses an engine parameter detection method which is characterized by comprising the following steps: acquiring a plurality of engine parameters of a plurality of sorts of an airplane; obtaining a time series data set formed by each engine parameter of a single sortie; performing anomaly detection on the engine parameters of each time series data set through an anomaly detection algorithm based on a probability statistics model, and calculating an average value, a standard deviation and probability statistics model parameters of each single sortie engine parameter; for each engine parameter, constructing a support vector machine classification model through the calculated multiple groups of average values, standard deviations and probability statistics model parameters; and calculating an average value and a standard deviation of the engine parameters of the new sortie, predicting corresponding probability statistics model parameters through a support vector machine model, and obtaining abnormal data in the probability statistics model parameters of the aircraft engine of the new sortie by the probability statistics model parameters through an anomaly detection algorithm based on a probability statistics model. The method can effectively predict the health condition of the aircraft engine.