33results about How to "Realize self-identification" patented technology

The invention discloses an intelligent garbage can capable of automatically identifying unknown garbage types and garbage sorting method. The intelligent garbage has the functions of barcode information verification, image recognition information verification, organic polymer sensor information recognition, garbage value conversion, and data uploading cloud. The garbage sorting method is simple insteps, mature in technology, and high in maneuverability, multiple methods are carried out together, the accuracy is high, moreover, the value generated by the garbage can be accumulated in a cloud account of the user through credits, the enthusiasm of people for garbage collection and recycling is improved, and the recovery utilization rate of the resources is improved.

The invention provides an online evaluation method for the capacity of a power distribution transformer. The method comprises a step of using a correlation coefficient method to realize the automaticidentification of a power distribution transformer connection group, a step of calculating Dyn11 distribution transformer short-circuit impedance and Yyn0 distribution transformer zero-sequence impedance and comparing the impedances with a standard reference value, and a step of finally obtaining a power distribution transformer evaluation capacity. According to the operating voltage data of the power distribution transformer, a correlation coefficient method is applied to realize the self-identification of the power distribution transformer connection group. Under the condition that the primary side electric quantity of the power distribution transformer cannot be obtained, the rated capacity of the power distribution transformer can be accurately evaluated by a Dyn11 distribution transformer capacity online evaluation method. Under the condition that a neutral point of a Yyn0 distribution transformer is offset, the rated capacity of the power distribution transformer can be accurately evaluated by a Yyn0 distribution transformer capacity online evaluation method.

The invention discloses an identification method for truck numbers of railway tank trucks. The method comprises the following steps: shooting grayscale images of local side surfaces of tank truck bodies by virtue of a video camera; calculating the edges of the grayscale images; positioning character zones of the edge images; carrying out binarization on grayscale images of the local side surfaces of the tank truck bodies; carrying out morphological processing on the character regions of binary images, removing isolated points, and connecting broken characters; carrying out segmentation processing on the characters, and determining the position and the range of a single character region; and inputting the segmented characters into a general character recognition engine and outputting a result. The identification method has the characteristics of low implementation cost and high automatic degree.

The invention discloses a method adopting robot for automatic recognition and additive forming of an uneven surface. The method comprises the following steps: two CCD cameras opposite in position areinstalled at the tail end of the robot, the surface of a workpiece is observed in a larger range, images are collected, defects on the surface of the workpiece are recognized and guided based on a binocular vision principle, and three-dimensional information of the defects is acquired; a controller reconstructs the three-dimensional outline of the defects, additive parameters are determined, an additive gun at the tail end of the robot is driven to reach defect positions for additive filling and repairing; after additive filling and repairing, the two CCD cameras at the tail end of the robot are driven to acquire images of the defects again; the controller reconstructs the three-dimensional contour of the defects again to determine whether the workpiece after additive filling and repairingmeets the standard, and the defects are subjected to additive filling and repairing again if the workpiece fails to meet the standard until the workpiece meets the standard. The robot has the advantages of simple structure, stable operation, high reliability and high adaptability, and can recognize the defects on the surface of the workpiece automatically and complete additive filling and repairing of the defects.

The invention provides a method and a system for transmitting voices based on the TCP in the VoIP, wherein an SIP terminal sends and receives data by means of a middleware unit. The data sending process comprises the steps of encoding a self-recognition boundary of data by the middleware unit, and sending the encoded data to an opposite-site SIP terminal through the TCP transmission. The data receiving process comprises the steps of decoding the self-recognition boundary of data received through the TCP transmission by the middleware unit, and sending the decoded data to the SIP terminal. According to the technical scheme of the invention, the TCP protocol stack is optimized, and the real-time transmission effect of voice data is improved. Meanwhile, the voice transmission is conducted based on the optimized TCP protocol to traverse a firewall. During the transmission process of voice data, the middleware unit is adopted cooperatively. Therefore, the self-recognition of the TCP data boundary is realized. The transmission effect of voice data is further improved.

The invention provides a multi-student individual segmentation and state autonomous recognition method based on deep learning, and the method comprises the steps: collecting a normal class video, carrying out the framing, and obtaining continuous frame images of a class video; segmenting out students' individuals and non-students' individuals, and marking the non-students' individuals as masks ofdifferent colors; finding a human eye feature point of each student individual through a human face feature point positioning method, calculating a human eye closure feature value of each student individual, and judging whether each student individual is in a lecture attending state at present or not; judging whether faces are detected by all the student individuals or not, and judging the class attending state grades of the student individuals; and designing the student lecture attending efficiency evaluation method in the whole class period according to whether each student is in a lecture attending state or not and whether each student is in a non-head-up state or not. The invention provides a solution for realizing the autonomous identification of the student lecture attending state and the judgment of the lecture attending efficiency, and has the advantages of high speed, high identification rate and strong environmental adaptability.

The invention discloses automatic pasting and scanning equipment of embryos bar codes. The equipment comprises a PLC, a frame, and a bar code conveying and scanning unit and a bar code pasting unit arranged on the frame; the bar code conveying and scanning unit includes a feeding mechanism, a label stripping mechanism, a bar code storage table, a scanning module, a label detecting mechanism, a collecting mechanism and a guide mechanism; the bar code pasting unit includes a rotating cylinder, an extension cylinder fixedly connected with a cylinder rod of the rotating cylinder, and a bar code picking/releasing part fixedly connected with a cylinder rod of the extension cylinder; the collecting mechanism is connected with a driving motor for driving the collecting mechanism to collect materials; and the scanning module, the label detecting mechanism, the rotating cylinder, the extension cylinder, the bar code picking/releasing part and the driving motor are electrically connected with the PLC. The equipment has the beneficial effects of possession of automatic identifying and control capacity, guarantee accurate embryos production, possession of material identifying capacity, verification of material information and possession of a control operation step.

The invention relates to a hemispherical harmonic oscillator parameter identification method. The method comprises the steps of self-excitation angular velocity application, gyroscope internal control force signal output, gyroscope error evolution model and harmonic oscillator parameter inverse solution identification model construction, single-axis forward and reverse rotation self-calibration and the like. A set of rate HRG control system simulation model with a self-excitation control module is constructed, and self-excitation angular velocity application, gyroscope error self-calibration and harmonic oscillator parameter autonomous identification under two inverse solution models can be completed. According to the method, the harmonic oscillator non-equal damping error amplitude and the main shaft deflection angle can be rapidly and autonomously identified by utilizing self-excitation in any stage of a full life cycle in a gyroscope working environment, and the method is a new method for rapidly and autonomously identifying the harmonic oscillator non-equal damping error amplitude and the main shaft deflection angle by utilizing various methods and means, such as self-excitation-based rate/rate integral HRG self-compensation (force compensation), non-equal damping error suppression and resonance mode drift error reduction. The output angular velocity/angular increment precision of the gyroscope is improved, application conditions are created, and a solution is provided.

The invention provides a parking lot management system, and the system comprises one or more cameras which are disposed above parking spaces, and are used for photographing the image frames of the corresponding parking spaces; a working unit which is used for processing the image frames shot by the one or more cameras so as to identify the occupation state of the parking space, and comprises an image acquisition module used for acquiring the image frames shot by the one or more cameras and correcting each image frame, and a processing module used for processing the image frames shot by the oneor more cameras so as to identify the occupation state of the parking space; a parking space state identification module which is used for identifying the occupation state of the corresponding parking space based on the corrected image frame; and a bottom layer communication module which is used for bottom layer information communication between the image acquisition module and the parking spacestate identification module.

The invention provides a transformer area intelligent fusion terminal and a plug-and-play access method of a low-voltage monitoring terminal, and the plug-and-play access method of the transformer area intelligent fusion terminal accessing a cloud platform comprises the following steps: the transformer area intelligent fusion terminal carries out registration confirmation on the cloud platform; a plug-and-play process is started; the cloud platform issues a preset primary equipment description file to the transformer area intelligent fusion terminal; the transformer area intelligent fusion terminal analyzes the primary equipment description file, generates an ICD file after model instantiation, and uploads the ICD file to the cloud platform; the cloud platform analyzes the ICD file and issues a corresponding CID model file; and the transformer area intelligent fusion terminal analyzes the CID model file and then performs communication and data interaction with the cloud platform. According to the method, the defects of debugging, point table configuration, software upgrading and the like when the existing transformer area intelligent fusion terminal and the low-voltage monitoring terminal are accessed to the cloud platform are overcome, the workload of field installation and maintenance is greatly reduced, and the access level of the intelligent terminal is powerfully improved.

The invention discloses a power grid monitoring alarm event identification method and device, terminal equipment and a medium. The method comprises the following steps: acquiring alarm information ofpower grid monitoring; preliminarily identifying an alarm event according to the alarm information to form preliminary identification data; preprocessing the alarm information and the preliminary identification data to form a training sample set, wherein the training sample set comprises a plurality of defined events; training the convolutional neural network model by adopting the training sampleset to form a power grid monitoring alarm event recognition model; and identifying the monitoring alarm event by adopting the power grid monitoring alarm event identification model. The efficiency andthe accuracy of identifying the power grid monitoring alarm information as the alarm event are improved; therefore, the screen monitoring capability of power grid monitoring service personnel is effectively reduced, the working efficiency of daily monitoring and accident exception handling of the service personnel is improved, and the power grid monitoring alarm information platform is enabled tobetter adapt to the development trend that the quantity of equipment fault alarm information of a power grid is increased geometrically.

The embodiment of the invention discloses a malicious resource transfer webpage identification method and device, and belongs to the field of network security. The method comprises the steps of obtaining a webpage currently accessed by a terminal; identifying whether the webpage is a resource transfer webpage, wherein the resource transfer webpage is used for online resource transfer; if the webpage is the resource transfer webpage, obtaining a malicious webpage access record of the terminal, wherein the malicious webpage access record comprises an access record corresponding to at least one malicious webpage; and if the resource transfer webpage is associated with the malicious webpage contained in the malicious webpage access record, determining the resource transfer webpage as the malicious resource transfer webpage. On the basis of the association relationship between the resource transfer webpage and the malicious webpage, self-identification of the malicious resource transfer webpage is realized, and manual report audit is not needed, so that the identification efficiency of malicious resource transfer is improved; meanwhile, the webpage accessed by each terminal can be identified in real time, and the timeliness and coverage rate of malicious resource transfer identification are improved.

The invention relates to an intelligent sensor network interface self-recognition system based on a wireless communication technology, which comprises an application master station, a gateway and a plurality of electric power sensing devices, and is characterized in that the gateway comprises an SN coding specification recognition module, a data model matching module, a self-recognition registration module, a protocol adaptation module and the like. According to the invention, the self-recognition of the network interface of the IEEE 1451 networked intelligent sensor is realized by combining the actual application requirements of electric power and utilizing the network protocol basis and hardware resources of the gateway protocol adaptation module, and the ubiquitous access of multi-type and multi-mode sensing equipment is supported. Unified access management of sensing equipment based on a service terminal can be realized at a relatively low cost and in a safer manner, and flexible deployment, upgrading and reconstruction of Internet of Things equipment in an electric power field are facilitated.

The invention discloses a service identification method and device, terminal equipment and a storage medium. The service identification method includes the steps that to-be-identified service data isacquired; identification keywords corresponding to identification elements in the to-be-identified service data are extracted according to the preset identification elements; matrixing processing is conducted on the identification keywords to obtain a to-be-identified service data matrix; a service identification model is established by using a KNN algorithm, and the service of the to-be-identified service data is determined: the Manhattan distance of the to-be-identified service data matrix and each sample data matrix in a pre-established sample database is calculated; K sample data with thesmallest Manhattan distance is adopted, and the service with the highest frequency among the K sample data is the service of to-be-identified service data. The service identification method can independently identify the service, the efficiency of service identification is improved, and the cost of the service identification is reduced.

A phase sequence identification algorithm of a distribution transformer comprises the steps of pre-processing data, calculating voltage of a distribution unit-area after three-phase calibration, taking ten groups of data, sequencing voltages of the distribution unit-area at each moment after three-phase calibration, comparing three-phase voltage of each distribution unit-area with circuit voltage,and finally determining a phase sequence condition of the distribution unit-area. The three-phase voltages of a 10kV circuit are sequenced in a descending order according to the characteristic that avoltage of a high-voltage side of the 10kV circuit and three-phase line voltage of the distribution transformer are not completely equal, the three-phase voltages of the distribution unit-area of thesame line at each moment are sequenced in the descending order, and the phase sequence condition of all distribution unit-areas of the same circuit is solved under the condition that the phase sequence of the 10kV circuit is correct. The example shows that the phase sequence condition of the distribution transformer can be accurately determined by the method, and the method is suitable for application and promotion on a large scale.

The invention provides a server intelligent identification and inspection system, which belongs to the technical field of server intelligent identification, and is used for solving the technical problems that the asset reporting workload of the existing machine room service is large and the daily inspection efficiency is low. A machine room manager uploads recorded videos or picture data to the system, models of servers in images are recognized through a model detection algorithm, and the position of each server in the machine cabinet is calculated through a position calculation method; an indicator light area of the server in the picture is detected, color information of an indicator light of the server is determined, the current state of the server is discovered, and an inspection log is formed; the server model and position identification result corresponds to the inspection result, a complete machine room equipment statistical table is formed and updated in time, and if a fault occurs, a maintainer is notified in time to maintain. The system replaces manual inspection, reduces the workload of inspection and maintenance personnel, achieves the purpose of intelligent inspection, and greatly improves the inspection efficiency and quality.

The invention discloses a fault-tolerant control method of a direct-current energy dynamic adjusting device. The method comprises the following steps: acquiring direct-current voltage, device current and normal sub-module voltage, and recording the number of normal sub-modules; calculating the sum of the voltages of the normal sub-modules and an instruction value thereof; calculating the total power and the power regulation quantity of the normal sub-modules; calculating the number of sub-modules needing to be input; and implementing a sorting voltage-sharing algorithm on the normal sub-modules to generate switching signals of the sub-modules. The control method can avoid the influence of an incomplete bypass fault module on the calculation of the number of input sub-modules, and achieves the precise control of the energy consumption power and DC voltage in a fault-tolerant state.

The invention discloses a vision enhancement method and system, a computer storage medium and intelligent glasses, a picture in front of the eyes of a user is shot through a light field camera and displayed on a display screen for the user to watch, then the position of the fixation point of the eyeballs of the user on the display picture of the display screen is tracked, and then the display picture is zoomed, the focus position of the display picture is always consistent with the position of the fixation point on the display picture so that the content concerned by the eyes of the user is always presented in front of the eyes of the user in a clearest manner, and the vision of the content concerned by the eyes of the user in the brain of the user is enhanced. Meanwhile, the outline of the object where the fixation point is located in the display picture is detected, and image enhancement is performed on the object in the display picture according to the outline of the object, so that the vision of the content concerned by the eyes of the user in the brain of the user is further enhanced. The visual perception ability of the visual impairment patient can be compensated, and the visual impairment patient can be helped to autonomously recognize the content watched by the visual impairment patient.