Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

13results about How to "Realize automatic discrimination" patented technology

Intelligent anti-blocking system, method and device for gas distribution plate of fluidized bed roaster

The invention relates to the technical field of fluidized bed roamers, in particular to an intelligent anti-blocking system, method and device for a gas distribution plate of a fluidized bed roaster. Installing two groups of nozzle arrays on the side wall of the fluidized bed roaster, and adjusting the spraying direction of nozzles to be aligned with the small hole area of the distribution plate; high-precision temperature and pressure sensors are installed at the edge and corner blockage high-incidence area of the distribution plate, real-time and continuous monitoring of temperature-pressure data is achieved, and key supporting data are provided for system diagnosis and control. An integrated programmable logic controller system is introduced, when a sensor captures signals indicating that small holes are possibly blocked, such as abnormal temperature drop or obvious pressure rise, a PLC immediately judges the existence and position of blockage and triggers a preset blockage clearing program, a nozzle is driven to spray high-pressure pulse airflow, and blockages are efficiently cleared. The system has the characteristics of intelligence, automation, high efficiency and the like, can prevent the problem of blockage of the gas distribution plate of the fluidized bed roaster, and ensures high efficiency and stability of equipment operation.
Owner:KUNMING UNIV OF SCI & TECH

A method and device for automatically constructing an evaluation operation template

The present invention proposes a method and device for automatically constructing an evaluation operation template to improve the efficiency and accuracy of evaluating computer security. It is used to solve the problem that manual verification and operation configuration of computer system security in the prior art require a lot of time and energy, and the efficiency is often very low. At the same time, it solves the technical problem that experience and methods cannot be reused and the verification efficiency is low. The present invention proposes a method for automatically constructing an evaluation operation template. By automatically constructing an evaluation operation template, the test results are objectively classified, counted and analyzed. When the evaluation template itself can realize automatic judgment, or the evaluation template that can realize automatic judgment after manual correction is added to the template library, the existing experience can be used to improve the efficiency and accuracy of computer system evaluation, and automatic construction and detection can be realized.
Owner:GUANGDONG SOUTHERN INFORMATION SECURITY RES INST

A method, system and storage medium for chronic low back pain surface electromyography discrimination based on fourier analysis neural network

ActiveCN121400850BdiscriminatingRealize automatic discriminationBiological modelsSensors
This invention provides a method, system, and storage medium for discriminating surface electromyography (EMG) signals in chronic low back pain based on a Fourier analysis neural network. First, a dataset is acquired, containing several EMG signals and their corresponding ground truth labels. The EMG signals are preprocessed to obtain preprocessed EMG signals. These preprocessed EMG signals are then input into a constructed Fourier analysis-based neural network to obtain a predicted label for each EMG signal. A loss function is constructed based on the ground truth labels and predicted labels, and the Fourier analysis-based neural network is trained to obtain a trained Fourier analysis-based neural network. The EMG signal to be detected is then input into the trained Fourier analysis-based neural network to obtain the corresponding predicted label. This invention, by constructing and training a Fourier analysis-based neural network, aims to extract discriminative latent periodic features, achieving automated discrimination of abnormal patterns in EMG signals of chronic low back pain, thus achieving more robust, generalizable, and efficient discrimination.
Owner:GUANGDONG UNIV OF TECH

Portable breather valve online detection system and method

The invention discloses a portable breather valve online detection system and method. The system comprises a signal acquisition module, a valve response monitoring module, a feature point identification module, a performance parameter evaluation module and a detection state output module. Signal quality is improved through continuous segment stability detection, a synchronous sudden change area is identified in dynamic data, a sudden change characteristic sampling point group is extracted, a traffic ratio threshold judgment mechanism is combined to realize accurate identification of an emergency state, and a rate change extreme point is compared with a fluctuation difference, a trigger node is calibrated, and a characteristic pairing value is extracted. A plurality of groups of flow pressure pairing sequences are formed in a test round and are compared with a standard interval to generate a compliance result, whether the inspiration and expiration state reaches the standard or not is automatically judged, and detection period label information and response state records with traceability are formed by performing unified archiving and identification processing on each detection period state. The recognition efficiency of abnormal opening and closing of the breather valve, the response speed of state feedback and the recording integrity of a detection result are improved.
Owner:CNOOC INSPECTION TECH CO LTD

A method and system for determining load power factor angle distribution interval

ActiveCN113985120BRealize automatic discriminationPower measurement by current/voltageFast algorithmPower factor
This invention provides a method and system for determining the distribution range of load power factor angle, belonging to the field of electricity metering technology. It mainly includes the following steps: acquiring continuous load records of active and reactive power for phases A and C; calculating power projection characteristic values ​​(hereinafter referred to as characteristic values) based on phase-by-phase power; determining the mathematical partition to which the loads of phases A and C belong; and converting this into a distribution range for determining the power factor angle of the loads of phases A and C. This invention utilizes the daily active and reactive power data curves of phases A and C from the metering device in an automated meter reading system. Based on the principle of power projection of current in the voltage direction, it achieves automated determination of the distribution range of the user's load power factor angle, providing rapid algorithmic support for the automated determination of miswiring in electricity metering devices.
Owner:JIANGSU FRONTIER ELECTRIC TECH

A method for online dynamic monitoring of magnetic field strength

PendingCN122386204AAvoid random inspection blind spotsGet rid of the space constraints of wired cabling
This invention discloses an online dynamic monitoring method for magnetic field strength, belonging to the field of industrial non-destructive testing. The method includes: setting 8, 16, and 32 monitoring points at the end face, inner wall, shaft hole, and abrupt geometric changes, respectively, based on the workpiece's maximum size: less than 100 mm, 100 mm to 500 mm, and greater than 500 mm; deploying sensor nodes integrating Hall elements and wireless transmission modules at these points to collect magnetic field signals, encapsulate them into data frames, and wirelessly transmit them; receiving the data wirelessly and transmitting it to a host computer via a USB-to-serial converter, where it is digitally filtered and displayed in real time; comparing the magnetic field values ​​at each point with a safety threshold, triggering an alarm when the threshold is exceeded, and continuously receiving data until the magnetic field values ​​at all points are below the threshold. This invention achieves multi-point wireless online dynamic monitoring and closed-loop control, improving the comprehensiveness and real-time performance of the detection.
Owner:SHENYANG RES INST OF FOUNDRY

A method for initial screening of onychomycosis based on improved residual network

ActiveCN114820545BRealize automatic discriminationImage analysisCharacter and pattern recognitionAmygdalaFeature extraction
The present invention discloses a method for primary screening of onychomycosis based on an improved residual network, comprising the following steps: preparing an onychomycosis image dataset; inputting the image dataset into a feature extractor to extract features; integrating the features by a classifier; and calculating the difference between the current value and the true value. The present invention uses a feature extractor based on a lightweight attention mechanism to extract relevant features, inputs them into an improved classifier for classification, and uses a regularization loss function to normalize the output prediction of the network. The effective features in the onychomycosis image are learned and identified through forward and back propagation mechanisms to achieve automatic discrimination of the primary screening classification of onychomycosis.
Owner:TIANJIN UNIV

Composite material damage imaging method based on time-space cross-correlation of ultrasonic guided wave field

The invention relates to the technical field of nondestructive testing, and provides a composite material damage imaging method based on time-space cross correlation of an ultrasonic guided wave field, which comprises the following steps: S1, acquiring a wave field signal of a detected plate; s2, narrow-band signal extraction is carried out on the wave field signal; s3, filtering the wave field signal after the narrow-band signal extraction; s4, moving the wave field signals to obtain wave field signal cross-correlation characteristics; and S5, obtaining a damage imaging result by using a convex hull algorithm. According to the method, the difference coefficient between the wave field signals is creatively extracted to serve as a damage positioning basis, a new thought is provided for a feature extraction algorithm based on the time-frequency domain, automatic judgment of composite material layering damage positioning is achieved, and the method is sensitive to damage to the surface and the interior of a structure.
Owner:BEIHANG UNIV

A method for automatically determining a protection section limit point and a turnout lock

The application discloses a kind of methods for automatically judging protection section limit point and turnout locking, it is to the laser survey data of trackside equipment collected to carry out processing, screen out the approachable signal with protection section limit point, identify its protection section limit point, and judge limit point type, then establish protection section limit point judgment model, carry out real-time difference comparison and update, judge whether protection section limit point meets design requirement;Again, turnout and warning post are analyzed, identify the axle counter near it, calculate the distance between each train after the direction of sliding and the axle counter near it, then establish turnout locking state judgment model, carry out real-time difference comparison and update, judge whether turnout locking state meets design requirement;Finally, obtain the judgment result.According to the application, only according to the collected laser survey data, the automatic update of protection section limit point and turnout locking state can be carried out, and whether it meets the design requirement is automatically judged.
Owner:卡斯柯信号(成都)有限公司

Optical cable identity recognition and illegal access detection method and system for smart grid

ActiveCN121690618BRealize automatic discriminationRealize the structureCircuit arrangementsUser identity/authority verificationSmart grid communicationIdentity recognition
The application is suitable for the technical field of communication and power safety monitoring, and provides a kind of optical cable identity recognition and illegal access detection method and system for smart grid, the method comprises the following steps: real-time acquisition vibration signal, when the amplitude of vibration signal is greater than the preset amplitude threshold, and its energy is greater than the energy threshold calculated based on dynamic baseline energy, it is determined as effective disturbance event;In response to effective disturbance event or according to the preset inspection plan, visible light image and infrared thermal image of target optical cable node are synchronously collected;Visible light image and infrared thermal image are spliced to form a fusion image;The fusion image is input into the lightweight target detection network, and the target detection result is output;According to the target detection result, the actual identity information of the current optical cable is extracted, and whether the actual identity information of the optical cable is legal and whether there is illegal access behavior is determined.The application provides a new generation of verifiable, traceable and closed-loop protection capability for the physical layer security of smart grid communication.
Owner:INFORMATION & COMMNUNICATION BRANCH STATE GRID JIANGXI ELECTRIC POWER CO

Distribution network protection setting value automatic checking method based on adaptive matching

The invention relates to a distribution network protection constant value automatic checking method based on adaptive matching. The method comprises the following steps: step 1, establishing a constant value checking rule system; 2, determining the role of a distribution network protection switch; step 3, according to the distribution network protection switch role determined in the step 2, the distribution network protection switch adaptively matches a constant value checking scheme, and a constant value checking rule of each segment of current protection in the constant value checking rule system in the step 1 corresponding to the constant value checking scheme is obtained; step 4, automatically calculating a check value by the distribution network protection switch based on the check rule of the constant value of each section of current protection obtained in the step 3; and 5, based on the check value obtained in the step 4, judging a constant value check result. According to the distribution network protection switch role and the topological structure, the corresponding constant value checking scheme and the constant value checking position are adaptively matched to carry out constant value automatic checking.
Owner:ELECTRIC POWER SCI & RES INST OF STATE GRID TIANJIN ELECTRIC POWER CO +2

A low-carbon intelligent one-way freeze-thaw cycle test system

The present invention discloses a low-carbon intelligent one-way freeze-thaw cycle test system, comprising: a semiconductor temperature controller, the semiconductor temperature controller is fixed on the top of the test piece; the semiconductor temperature controller comprises: a semiconductor refrigeration plate, the semiconductor refrigeration plate is fixed on an aluminum plate, the aluminum plate is arranged on the top of the test piece; the surface of the semiconductor refrigeration plate in contact with the aluminum plate is a working surface, and the other surface is a heat exchange surface, and a heat exchange device is installed on the heat exchange surface of the semiconductor refrigeration plate. A control system, the control system is used to control the semiconductor temperature controller to heat / cool the test piece, and control the semiconductor temperature controller to heat and cool the test piece. The cycle process and the number of cycles. One output end of the control system is connected to a first switch module arranged on the connection line between a DC power supply and the semiconductor refrigeration plate; the other output end of the control system is connected to a second switch module arranged on the connection line between the first switch module and the DC power supply. The test results accurately reflect the performance of the material in a real freeze-thaw cycle.
Owner:HARBIN INST OF TECH

A method, device and system for automatically determining the maintenance quality of packaging equipment based on deep learning

The present invention provides a method, device and system for automatically distinguishing the maintenance quality of a wrapping device based on deep learning. The method respectively constructs a recognition model for identifying maintenance parts and a detection model for detecting dirt in maintenance parts. The recognition model adopts a ResNet50 network model embedded with an SE module to improve the accuracy of recognition. The detection model adopts a Faster R-CNN model, adds an RPN network, generates candidate frames based on an Anchor mechanism, integrates feature extraction, candidate frame selection, frame regression and classification into one network, and effectively improves detection accuracy and efficiency. Combined with the information of maintenance part recognition and the results of dirt detection, the automatic distinction of maintenance quality can be achieved, and the accuracy of distinction can be improved.
Owner:HUBEI CHINA TOBACCO INDUSTRY CO LTD