242results about How to "Reduce the possibility of misjudgment" patented technology

The invention discloses a moving target tracking recovery method used for tracking a moving target. The method comprises the steps of: detecting the foregrounds of a current image when a tracked target is lost, obtaining foreground targets, and obtaining a pre-estimated position of the tracked target according to the lost position of the tracked target; when the tracked target is determined to be lost, matching characteristics of candidate targets with characteristics of the tracked target, and obtaining a matching value of each candidate target by means of calculation; and according to the matching values and distances to the pre-estimated position, obtaining the candidate target largest in a weight value, using the candidate target as the original tracked target, and carrying out tracking continuously. The invention further discloses a device corresponding to the method. The method and the device have the advantages that under the condition that the tracked target is lost, matching and pre-estimating are carried out according to the detected foreground target, the foreground target which is most likely to be the original tracked target is obtained, and tracking is continued, so that the tracking continuity is good.

The invention relates to a power system transient state voltage stability evaluating method based on misclassification cost classified learning, which belongs to the power system stability analyzing and evaluating field. Based on dynamic measurement datum of a synchronous phasor measuring unit, a key subsequence closely related to the power system state is extracted from a time sequence constituted of a large amount of dynamic measurement datum; by setting different misclassification costs of stable power system and unstable state, a weight coefficient is introduced into a learning sample; a decision-making tree algorithm infused with the sample weight coefficient is used to perform classified learning so as to acquire a decision-making tree model; and the decision-making tree is used for online monitoring to implement evaluation to the power system transient state voltage stable situation.

The invention relates to a method for jointly evaluating the insulation state of oil paper by using multiple statistical parameters, characterized by comprising the following steps of: using an ultra-wideband partial discharge detection system to perform partial discharge detection on the oil paper insulation in a power device; collecting and extracting the partial discharge statistical parameters of the oil paper insulation; by analyzing the change trends of seven statistical parameters, evaluating the insulation state of the oil paper insulation in the power device; and if NpSEC and Hn_Sk present a monotone increasing trend and the alfa, beta, Qmax, Hn_mean and Hqn_Kur present a monotone decreasing trend, judging that the oil paper insulation in the power device is in a deterioration state. The method can be used for forecasting the hazard degree of the partial discharge before the insulation has fault. The method can be used for preventing the insulation fault and reducing the fault possibility of the power device caused by insulation fault, has high accuracy and low dispersivity, is convenient to realize, and does not influence running of the power device.

The invention provides a method and a system for detecting the deformation of a transformer winding. The method comprises: acquiring response end voltage and exciting end voltage of the transformer winding to be detected under different frequency; calculating a transfer function module value of the transformer winding to be detected according to the response end voltage and the exciting end voltage; drawing a frequency response curve in a coordinate system according to the transfer function module value under different frequency, and drawing a frequency response curve in the coordinate system when the transformer winding is normal; pre-processing the two frequency response curves by using an erosion method to obtain curve data satisfying a preset condition, and calculating relevant coefficients of the two frequency response curves; and judging the deformation condition of the transformer winding to be detected according to the magnitude of the relevant coefficients and relevant coefficient preset values. According to the method, the two frequency response curves drawn in the coordinate system are pre-processed by using the erosion method, so that burrs are removed, interference of noise such as electromagnetic signals and the like is avoided, the accuracy of diagnosis is improved, and the probability of misjudgment is reduced.

The invention provides an auxiliary control method and device for lowering the fan load under the gust condition and a fan controller, and relates to the technical field of wind power generation. Themethod includes the steps that whether gust occurs or not is judged according to rotating speed acceleration; when gust occurs, a pitch variation rate is calculated according to pneumatic resultant moment of a fan and pneumatic features of blades; and the blades are regulated according to the pitch variation rate. The rotating speed acceleration of the fan is selected as a threshold value variablefor judging occur of gust, thresholds under different wind speeds are obtained through comprehensive calculation according to operation power, a pitch angle and other variables of the fan, and thus the possibility of missed judging and erroneous judging can be reduced to the maximum extent. Meanwhile, the variation intensity of the speed of gust is represented by air moment, and thus output of apitch angle instruction is controlled according to the air moment; time delay is reduced in the control process, reaction is more sensitive, control is more timely and effective, the pitch angle control process for involving in or exiting normal power generation is smooth, and the influence on the pitch angle in normal operation is small.

The invention belongs to the field of short text auditing, particularly relates to a short text auditing method and device fusing variant word recognition, and aims to solve the problem of how to fusea variant word recognition technology into a harmful text auditing task and realize automatic updating of a model. The method comprises the steps of constructing a configuration word bank, obtainingto-be-audited text data based on a social media platform, screening the to-be-audited text data to obtain suspicious text data, removing meaningless information, and calculating a text feature vectorand a statistical feature vector; and performing feature fusion on the text feature vectors and the statistical feature vectors, obtaining harmful texts through a trained harmful text classification model based on a support vector machine, obtaining sensitive words of the harmful texts by utilizing a preset keyword extraction algorithm, and writing the sensitive words into a configuration word bank. According to the method, the variant word recognition technology is fused into text feature and statistical feature calculation to carry out harmful text auditing tasks, automatic model updating isachieved, and the text auditing accuracy and updating speed are improved.

The invention discloses a mold detection method for an electric injection molding machine. The method comprises the steps of obtaining a residue-free rectangular standard mold image as a standard template image, removing a background region of the standard template image to obtain a mold region, normalizing the size of the standard template image to LXL, segmenting the standard template image into m sub-template images with the sizes of WXW, and extracting an eigenvalue of each sub-template image; collecting a to-be-detected mold image after mold opening, extracting an edge image of the to-be-detected mold image, and segmenting out the mold region of the image; normalizing the to-be-detected mold image to LXL, segmenting the to-be-detected mold image into m sub-images with the sizes of WXW, and extracting an eigenvalue of each sub-image; and comparing the eigenvalues of the sub-template images of the standard template image with the eigenvalues of the sub-images of the to-be-detected mold image to obtain a status of residues of the to-be-detected mold image. According to the method, the status of the residues in a mold can be quickly and accurately detected, so that the detection efficiency is improved and the automation degree of the mold processing industry is increased.

The invention provides a method for detecting indoor and outdoor scenes. The method includes: obtaining satellite positioning information about a mobile terminal by detecting a satellite positioning system; determining whether the mobile terminal is currently in an indoor environment or an outdoor environment based on a historical detection result recording situations that the mobile terminal is in an indoor or outdoor scene and the satellite positioning information. The method of the invention can improve the detection accuracy of the indoor and outdoor scenes.