16results about How to "Real-time judgment" patented technology

The invention discloses a rapid diagnosis method for potassium nutrition of sweet potatoes, which comprises the following steps: measuring potassium concentrations of inverted 5 petioles and positive 1 petioles, calculating a difference value, fitting by taking a horizontal coordinate as a petiole concentration difference and a vertical coordinate as a relative yield, and constructing a regression equation 1 of the petiole potassium concentration difference and the relative yield; according to the regression equation 1, taking the corresponding petiole potassium concentration when the relative yield is maximum as the critical concentration of plant potassium nutrition diagnosis; performing correlation analysis on the plant potassium absorption amount and the petiole potassium concentration difference value to obtain a regression equation 2; comparing the measured value with the critical value petiole potassium concentration, determining the topdressing coefficient, and calculating the topdressing amount in the period. The diagnosis method can timely and accurately judge the potassium nutrition condition of the sweet potato plants, provides a basis for subsequent accurate application amount of sweet potato potash fertilizer, and can improve the yield and quality of sweet potatoes.

The automatic compensating and avoiding device of the construction hoist comprises a mounting bracket, a hoist body is arranged on the mounting bracket, and the hoist body is connected with the mounting bracket in a matched mode; a traction device is arranged on the mounting bracket and is fixedly connected with the elevator body; a plurality of wind direction and wind speed detection sensors are arranged outside the mounting bracket; the elevator body is provided with a data analysis processor which is electrically connected with the wind direction detection sensor and is used for analyzing and processing detection data; a driving controller is arranged on one side of the data analysis processor, the driving controller is electrically connected with the data analysis processor, the driving controller is electrically connected with the traction device and the anti-falling safety device, and whether an output result analyzed by the data analysis processor belongs to a non-Gaussian turbulence excitation state or not is judged through the controller. And if yes, the operation state of the construction hoist is adjusted through the traction device and the anti-falling safety device. The invention aims to solve the problem of safe operation of the construction hoist during buffeting under the excitation of canyon wind non-Gaussian turbulent flow.

The invention provides an underground rescue equipment positioning and navigation method and system, and electronic equipment, and the method comprises the steps: collecting the surrounding image data of rescue equipment through a depth camera disposed on the rescue equipment, processing the collected data, and carrying out the passable channel judgment according to a preset judgment rule; and formulating an advancing route and an advancing rule based on the judgment result, in the advancing process of the rescue equipment, acquiring distance data between the rescue equipment and the channel in real time by utilizing a laser radar arranged on the rescue equipment, and meanwhile, acquiring inclination angle data of the rescue equipment by utilizing a strapdown inertial navigation module arranged on the rescue equipment. The trafficability of the rescue equipment in the channel is judged in real time according to the distance data, and whether the posture of the rescue equipment is within a safe range or not is judged according to the obtained inclination angle data. When complex terrains such as obstacles are encountered, real-time and efficient channel judgment is achieved, efficient obstacle breaking is conducted when the obstacles cannot avoid, and irregular and even dynamic obstacles cannot be avoided.

The present application relates to the technical field of tool positioning, and discloses a tool positioning management and control system and early warning method based on RFID and video fusion, which comprises the following steps: establishing an association mapping of RFID tag unique code and tool unique identification and constructing a tool information file; configuring an electronic fence based on a management and control area space model, collecting RFID tag signals to perform area attribution inference, generating an RFID side position state and performing first stage state determination; obtaining a monitoring video stream that is spatially registered with the electronic fence space range, performing tool target detection, tool category confirmation and cross-frame target tracking on the video picture to obtain a video side tool existence state; and fusing the RFID side position state and the video side tool existence state to perform second stage determination, and starting a hierarchical early warning strategy to output alarm information according to the determination. The present application reduces the false judgment and missed judgment caused by single sensing.

A logo detection method is disclosed. According to the grayscale image of the current display screen, the pixel brightness of each feature point of at least two groups of feature points is obtained, and according to the pixel brightness of each feature point and its corresponding preset brightness value interval, whether the feature point is a standard feature point is determined, and according to the number of standard feature points and the total number of the at least two groups of feature points, whether the current display screen displays a target logo is determined. The detection and judgment steps of the logo detection method of the present invention are simple and effective, and can quickly and in real time determine whether the current display screen has an effective display of the target logo.

The application discloses a kind of multi-channel sensing fusion systems for exposure stress judgment, it is related to sensing fusion technical field, for solving the problem of insufficient accuracy of stress exposure state judgment, by the monitoring equipment corresponding to the working individual, the respiratory rhythm, the heart beat interval, the skin electricity response and the action trajectory such as multi-dimensional physiological and behavioral parameters in the working process are continuously collected, the multi-channel stress state observation basis is constructed, the feature extraction and abnormal discrimination of each channel data are carried out, the state mode is classified modeling using pattern recognition method, combined with cross-channel consistency analysis and causal order constraint, the abnormal response is comprehensively evaluated, when the evaluation result meets the preset stress exposure determination condition, combined with action trajectory characteristics, the stress exposure grade of working individual is graded determination, and according to the determination result, continuous monitoring or event record and information upload operation is selected, realize the automation, real-time judgment of stress exposure state.

The invention discloses a front and rear combined lamp fault reminding method and device, a storage medium and a vehicle, and relates to the technical field of automobile body electronic control, and the method comprises the steps: monitoring function state signals fed back by front and rear combined lamps based on a set lamp state feedback period in a vehicle starting state; in response to a continuous first number of lamp state feedback periods, the function state signals fed back by the front and rear combined lamps are not received, and a first lamp which does not feed back the function state signals is determined in the front and rear combined lamps; and reminding a user that the first lamp breaks down. According to the mode, a complex detection mechanism does not need to be additionally arranged, the function state signal fed back in the working process of the lamp is directly used as a basis, the advantages of being fast in response, low in cost and high in reliability are achieved, a user, especially a driver, can notice the lamp fault phenomenon, and the driver can conveniently conduct safe driving.

The invention discloses an indoor and outdoor integrated inspection method based on an omni-directional mobile aerial robot. The method comprises the following steps: controlling the omni-directional mobile aerial robot to fly to a predetermined entrance of a target building along a preset outdoor navigation path; acquiring a predetermined entrance image and laser radar point cloud data, and determining a six-degree-of-freedom motion track passing through the entrance; generating a six-degree-of-freedom motion control instruction for obstacle avoidance control according to the real-time scanning data of the laser radar and the displacement track of the image feature point; determining attitude adjustment parameters of the aerial robot according to a matching result of the two-dimensional feature point set, the equipment three-dimensional structure feature library and the laser radar point cloud subset; and controlling the omni-directional mobile aerial robot to return to the outdoor starting point according to the task execution sequence, the path pose information and the return initial pose data, and uploading inspection data. According to the invention, high autonomy and comprehensive reliability of the inspection process are realized in a complex building environment, and the overall performance and the application range of the unmanned building inspection system are significantly improved.

This invention provides an AI-based intelligent recognition method for determining chips in difficult-to-machine materials, belonging to the field of intelligent machining technology. First, cutting images are acquired to construct a chip morphology image dataset. The images in the chip morphology image dataset are preprocessed to extract geometric feature parameters of each chip region, constructing a multi-dimensional feature vector F. Using the original chip image as the main input and the multi-dimensional geometric feature vector F as the auxiliary feature input, the chip morphology recognition model is input, outputting the chip morphology type and its corresponding confidence score. Based on the chip morphology type recognition result, it is mapped to an online assessment of the machining state and surface quality, obtaining the machining state assessment result. This achieves high-precision automatic recognition of chip morphology and real-time determination of machining state.

The application discloses a kind of GNSS interference detection methods based on navigation receiver, comprising: obtaining the original observation information of navigation receiver and the elevation angle information of each satellite output;Set an observation window, in the observation window, the number of satellites tracked is counted for each frequency point of each GNSS system, and the mean value of the number of visible satellites is recorded;For each frequency point of each GNSS system, the carrier-to-noise ratio of each satellite is counted, and the maximum value and the mean value are recorded;The standard deviation of the pseudo-range of each satellite is counted, and the mean value is recorded;At the current observation time, for each frequency point of each GNSS system, the new observation quantity is compared with the statistical value to judge whether interference occurs, and the disturbed frequency point and the interference type are reported;The application solves the problem that the sensitivity of traditional monitoring receiver is insufficient and GNSS interference cannot be effectively detected.

This disclosure relates to the technical field of automotive brake testing, and discloses a method, device, and system for health monitoring of electromechanical braking systems. The method includes: acquiring, during a braking test of the electromechanical braking system, the ideal clamping force value, the actual clamping force value, spatial magnetic field distribution data generated by the hub motor, and mechanical vibration signal data of the braking components; determining a clamping force influence function based on the difference between the ideal and actual clamping force values; determining a magnetic field difference value based on the spatial magnetic field distribution data; fusing the clamping force influence function, the magnetic field difference value, and the mechanical vibration signal data to obtain a comprehensive degradation index; comparing the comprehensive degradation index with a pre-acquired comprehensive health evaluation threshold, and determining the health monitoring result of the electromechanical braking system based on the comparison result. This method can achieve real-time determination of the health status of the electromechanical braking system during operation.

The invention discloses a nuclear power unit autonomous operation decision method and device, and the method comprises the steps: collecting the equipment state information and equipment performance information of a nuclear power unit in real time through a PHM tool in the operation process of the unit, and if the equipment state is changed or the equipment performance is reduced, determining that the nuclear power unit is an autonomous operation decision; if so, analyzing a related accident sequence of the equipment by using a simulation technology to determine a sequence result; according to the sequence consequence obtained by simulation analysis, updating a PSA model of the nuclear power unit to carry out risk assessment, obtaining a risk value, and judging whether the risk value is in a risk yellow area; if so, establishing an alternative scheme set; analyzing the alternative scheme set by using a deterministic theory analysis method to determine a first scheme set; according to the first scheme set, a probability theory analysis method is used for analysis, and a second scheme set is formed; and for the second scheme set, based on the deterministic theory safety index, the probability theory safety index, the economic index and weighting, comprehensive decision making is carried out, and an optimal scheme is obtained.

The invention relates to a deep learning algorithm-based method for detecting a missed gluing behavior of screw glue. The method comprises the following steps of: 1, preprocessing a real-time video of a screw glue gluing station; step 2, performing algorithm identification based on a deep learning algorithm on the preprocessed real-time video in a single-frame and single-frame manner so as to identify categories and positions of three objects including a screw glue box, a hand and a screw glue stick in a screw glue coating station; step 3, performing joint judgment on multi-frame recognition results of algorithm recognition so as to switch among a non-gluing state, a to-be-gluing state and a gluing state of a screw glue gluing station, and performing judgment processing on conditions of each state; and step 4, performing corresponding processing according to whether the screw glue coating omission behavior exists or not output in the step 3: if the screw glue coating omission behavior exists in the screw glue coating station, indicating an alarm device to give an alarm, and recording the time of the current frame of the real-time video.

The application discloses a near-bit array ultrasonic velocity imaging logging device and method, relates to the technical field of logging, and comprises a drill collar sub, a logging acoustic system and a booster plate. The logging acoustic system comprises a focused transmitting probe and an array receiver. A sound insulation groove is arranged on the drill collar sub between the focused transmitting probe and the array receiver. Ultrasonic waves excited by the focused ultrasonic probe are refracted in the stratum at the well wall to generate sliding longitudinal and transverse waves through the fluid in the well, and are received by the array receiver through the fluid in the well. The first wave received by the array receiver is the sliding longitudinal wave of the stratum. The application can measure the stratum velocity near the drill bit in real time, accurately determine the position of the drill bit, timely adjust the well trajectory, reduce the risk of out-of-zone, and increase the reservoir drilling rate.

This invention discloses an active acoustic motion sickness suppression system and method for electric vehicles based on multimodal information fusion. The system includes a signal acquisition module, a data processing and motion sickness level recognition module, an acoustic signal generation module, and an onboard sound device. The signal acquisition module collects vehicle motion parameters and occupant physiological state data. The data processing and motion sickness level recognition module fuses and analyzes the raw EEG signals and vehicle motion parameters, outputting a motion sickness level judgment result. The acoustic signal generation module uses an order synthesis algorithm to enhance the corresponding parameters of specific order harmonics, amplifying the synthesized audio signal as an acoustic intervention signal. The onboard sound device receives the acoustic intervention signal and plays the intervention sound. This invention achieves accurate judgment of motion sickness and can dynamically generate highly correlated acoustic intervention signals based on the unique vehicle motion parameters of electric vehicles, compensating for auditory information gaps and achieving a motion sickness suppression effect.

This invention provides a method for determining the initiation of fractures in low-maturity shale heated by supercritical carbon dioxide, belonging to the technical field of low-maturity shale. This invention obtains multi-field coupling parameters by integrating conventional well logging, core experiments, and formation testing data. It then calibrates key coefficients through high-temperature mechanical experiments, hydrocarbon generation pressurization experiments, pyrolysis kinetic experiments, and supercritical carbon dioxide immersion experiments. These parameters are substituted into the multi-field coupling fracture initiation pressure formula to calculate the fracture initiation pressure at each moment. The input to the physical constraint graph attention recursive network outputs corrected fracture initiation pressure and safety margin. When the safety margin is lower than the warning threshold, a two-step approximation method is used to predict the fracture initiation time and adjust the construction parameters. This solves the technical problem of being unable to accurately determine the fracture initiation time of low-maturity shale heated by supercritical carbon dioxide under multi-field coupling conditions in real time.